Method for diagnosing a component by means of acoustic emission
Patent Information
- Application Number
- EP2023701160
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2022-01-28
- Filing Date
- 2023-01-20
- Publication Date
- 2024-12-04
AI Technical Summary
Existing methods for diagnosing valves in pipelines using acoustic emission testing are insufficiently accurate and reliable, as they primarily rely on radial sensor arrangements that fail to distinguish noise sources effectively, leading to incomplete and inaccurate assessments.
The method employs multiple acoustic emission sensors positioned at different points along the pipeline to capture distinct acoustic emission signals, analyzing differences in intensity and frequency to differentiate between component-related noise and background noise, enabling a more precise and reliable diagnosis by considering signals from various positions along the flow path.
This approach allows for a more accurate and reliable diagnosis of valve conditions, including leakage and cavitation, by distinguishing noise sources and reducing interference from background noise, thereby enhancing the reliability of pipeline component assessments.
Smart Images

Figure 1.1
Abstract
Description
[0001] Method for diagnosing a component using acoustic emission
[0002] Technical area
[0003] The invention relates to a method for diagnosing a component, in particular a valve, by means of acoustic emission testing. The component is installed in a pipeline designed to conduct a fluid along a flow path in a flow direction. The invention also relates to a computer program product for implementing this method. Furthermore, the invention relates to a method for diagnosing a component, in particular a valve, by means of acoustic emission testing. The component is installed in a pipeline designed to conduct a fluid along a flow path in a flow direction. The method also relates to an arrangement for implementing this method.
[0004] State of the art
[0005] Methods, computer program products, and arrangements belonging to the technical field mentioned above are known. For example, WO 2014 / 105839 A1 from Score Group PLC describes a method for acoustically determining the leakage rate of a valve, wherein acoustic emission sensors are arranged radially around the valve to detect acoustic emission signals caused by the valve leakage. The leakage rate is determined and thus the diagnosis of the respective valve is created by evaluating the acoustic emission signals detected by the acoustic emission sensors using a computer program product.
[0006] The disadvantage of these known methods, computer program products and arrangements is that they only allow the creation of an insufficiently accurate and insufficiently reliable diagnosis or an insufficiently accurate and insufficiently reliable diagnosis of the valve.
[0007] Description of the invention
[0008] The object of the invention is to provide a method belonging to the aforementioned technical field for diagnosing a component, in particular a valve, which component is installed in a pipeline designed to conduct a fluid along a flow path in a flow direction, using acoustic emission testing. This method enables a more precise and reliable diagnosis of the component. Furthermore, the object of the invention is to provide a computer program product for implementing this method, which enables a more precise and reliable diagnosis of the component.Furthermore, it is the object of the invention to provide a method for diagnosing a component, in particular a valve, which component is installed in a pipeline, which pipeline is designed to guide a fluid along a flow path in a flow direction, by means of acoustic emission testing and to provide an arrangement for carrying out the method for diagnosing the component, in particular a valve, by means of acoustic emission testing, which enables a more precise and reliable diagnosis of the valve.
[0009] The solution to the problem is defined by the features of claim 1. According to the invention, the diagnosis of the component is created taking into account a first acoustic emission sensor signal and a second acoustic emission sensor signal, wherein a distinguishing feature between the first acoustic emission sensor signal and the second acoustic emission sensor signal is also taken into account for creating the diagnosis, wherein the first acoustic emission sensor signal has been output by one of at least one acoustic emission sensor, wherein a first acoustic emission signal has been detected by the respective one of at least one acoustic emission sensor at a first position on the pipeline, in particular outside the pipeline, wherein the first acoustic emission sensor signal output by the respective one of at least one acoustic emission sensor corresponds to the detected first acoustic emission signal,wherein the first position, viewed in the flow direction, is located at a height of the component installed in the pipeline, wherein the second acoustic emission sensor signal has been output by one of the at least one acoustic emission sensors, wherein a second acoustic emission signal has been detected by the respective one of at least one acoustic emission sensors at a second position on the pipeline, in particular outside the pipeline, wherein the second acoustic emission sensor signal output by the respective one of at least one acoustic emission sensors corresponds to the detected second acoustic emission signal, wherein the second position is located on the pipeline, in particular outside the pipeline, at a distance from the first position in the flow direction or against the flow direction from the first position.
[0010] Preferably, a computer program product is designed to carry out the method according to the invention for creating a diagnosis of a component. Preferably, the computer program product comprises instructions which, when the program is executed by a computer, cause the computer to carry out the method according to the invention. Preferably, a diagnostic unit for creating a diagnosis of a component using the method for creating a diagnosis of a component is designed to create the diagnosis of the component using the method for creating a diagnosis of a component. Particularly preferably, the diagnostic unit is a computer unit on which the computer program product for carrying out the method for creating a diagnosis of a component is installed.
[0011] According to the invention, the component is installed in a pipeline, which pipeline is designed to conduct a fluid along a flow path in a flow direction. The component can be, for example, a pipe section, a connector for connecting pipe sections, a valve or a condensate separator. Since a condensate separator has at least one valve, the method can also be used to create a diagnosis of the at least one valve of the condensate separator. The pipeline can contain various components such as pipe sections, connectors for connecting pipe sections, valves, condensate separators and pipe sections with sensors and can be composed of these components. However, the pipeline can also contain further components. As already mentioned, the pipeline is designed to conduct a fluid along a flow path in a flow direction.The fluid can be a liquid, a gas, or a mixture of a liquid and a gas, such as water vapor. Furthermore, the flow path is preferably the path along which the fluid is conveyed in the pipeline. This means that the flow path is preferably determined by the course of the pipeline.
[0012] Since the component being diagnosed is installed in a pipeline, the acoustic emission test is performed on the assembled pipeline. This has the advantage of enabling a non-invasive diagnosis of the component while the pipeline is in full operation. This is particularly advantageous in production plants that use pipelines for production. In such production plants, the present invention can thus be used to create a diagnosis for the pipeline components.
[0013] The diagnosis of the component preferably includes determining a condition of the respective component. In a preferred variant, the diagnosis of a component includes determining whether or not the respective component has a leak. In a preferred variation thereof, the diagnosis of a component also includes determining a leakage rate of the respective component. However, the diagnosis may also not include determining the leakage rate. In a further preferred variant, the diagnosis of a component includes determining whether or not cavitation occurs in the component. In a variation thereof, the diagnosis of a component also includes determining a cavitation rate of the respective component. However, the diagnosis may also not include determining the cavitation rate.
[0014] According to the invention, a distinguishing feature between the first acoustic emission sensor signal and the second acoustic emission sensor signal is taken into account for making the diagnosis.
[0015] The distinguishing feature can, for example, be a difference in the intensity averaged for the two detected acoustic emission signals over a predetermined frequency range. Since the acoustic emission sensor signals correspond to the respective detected acoustic emission signal, the intensity of the first acoustic emission sensor signal averaged over the predetermined frequency range can, for example, be greater than the intensity of the second acoustic emission sensor signal averaged over the predetermined frequency range. The predetermined frequency range can, for example, be a subrange of the frequency range detected by at least one acoustic emission sensor or cover the entire frequency range detected by the respective acoustic emission sensor.
[0016] As already mentioned, the second acoustic emission sensor signal is output by one of the at least one acoustic emission sensors. The second acoustic emission sensor signal can be output by the same acoustic emission sensor with which the first acoustic emission signal is detected at the first position on the pipeline, or the second acoustic emission sensor signal can be output by a different acoustic emission sensor.
[0017] According to the invention, the diagnosis of the component is thus carried out taking into account a distinguishing feature between at least two acoustic emission sensor signals, which correspond to acoustic emission signals recorded at different positions along the flow path on the pipeline, one of which (the first position) is located at a height of the component installed in the pipeline, as seen in the flow direction. This has the advantage that noises caused by the condition of the component can be at least partially distinguished from noises inherent in the pipeline caused by other sources, such as the fluid, thus enabling a more precise and reliable diagnosis of the component.
[0018] Advantageously, the diagnosis of the component is created taking into account a third acoustic emission sensor signal, wherein the third acoustic emission sensor signal has been output by one of the at least one acoustic emission sensors, wherein a third acoustic emission signal has been detected by the respective at least one acoustic emission sensor at a third position on the pipeline, in particular on the outside of the pipeline, wherein the third acoustic emission sensor signal output by the respective at least one acoustic emission sensor corresponds to the detected third acoustic emission signal. This has the advantage of enabling the creation of an even more precise and reliable diagnosis.It is irrelevant whether the acoustic emission sensor with which the third acoustic emission sensor signal was output is the same acoustic emission sensor with which the first acoustic emission signal was detected at the first position on the pipeline and / or the same acoustic emission sensor with which the second acoustic emission signal was detected at the second position on the pipeline, or can be a different acoustic emission sensor.
[0019] Preferably, the third position, viewed along the flow path, is located on a different side of the first position than the second position is located from the first position, whereby the first position, viewed along the flow path, is located between the second position and the third position, wherein a distinguishing feature between the first acoustic emission sensor signal and the third acoustic emission sensor signal is taken into account for establishing the diagnosis. This has the advantage that both noise in the detected acoustic emission signals whose source lies beyond the second position, viewed from the first position, and noise beyond noise whose source lies beyond the third position, viewed from the first position, can be identified as noise.Accordingly, the evaluation of the acoustic emission sensor signals can be adjusted so that the identified noises are correctly treated as such. This enables a more precise diagnosis of the component.
[0020] In a preferred variant, the third position, viewed along the flow path, is located on a different side of the second position than the first position is located from the second position, whereby the second position, viewed along the flow path, is located between the first position and the third position. A distinguishing feature between the first acoustic emission sensor signal or the second acoustic emission sensor signal and the third acoustic emission sensor signal is taken into account for the purpose of establishing the diagnosis. This has the advantage that noise in the detected acoustic emission signals, the source of which lies beyond the third position, viewed from the first position, can be better quantified, thus enabling a more precise diagnosis of the component.Preferably, the diagnosis of the component is created taking into account a fourth acoustic emission sensor signal, wherein the fourth acoustic emission sensor signal has been output by one of the at least one acoustic emission sensors, wherein a fourth acoustic emission signal has been detected by the respective at least one acoustic emission sensor at a fourth position on the pipeline, in particular on the outside of the pipeline, wherein the fourth acoustic emission sensor signal output by the respective at least one acoustic emission sensor corresponds to the detected fourth acoustic emission signal. This has the advantage of enabling the creation of an even more precise and reliable diagnosis.The acoustic emission sensor from which the fourth acoustic emission sensor signal has been output can be the same acoustic emission sensor with which the first acoustic emission signal was detected at the first position on the pipeline, and / or the same acoustic emission sensor with which the second acoustic emission signal was detected at the second position on the pipeline, and / or the same acoustic emission sensor with which the third acoustic emission signal was detected at the third position on the pipeline, or can be a different acoustic emission sensor therefrom.
[0021] Preferably, the fourth position is located on a different side of the third position along the flow path than the first position is located from the third position, whereby the third position is located between the first position and the fourth position along the flow path, wherein a distinguishing feature between the first acoustic emission sensor signal or the third acoustic emission sensor signal and the fourth acoustic emission sensor signal is taken into account for establishing the diagnosis.
[0022] If, in addition, the third position, viewed along the flow path, is located on a different side of the first position than the second position is located from the first position, whereby the first position, viewed along the flow path, is located between the second position and the third position, wherein a distinguishing feature between the first acoustic emission sensor signal and the third acoustic emission sensor signal is taken into account for the purpose of establishing the diagnosis, this has the advantage that noise in the recorded acoustic emission signals, the source of which lies beyond the fourth position, viewed from the first position, can be better quantified, thereby enabling a more precise diagnosis of the component.
[0023] If, on the other hand, the third position, viewed along the flow path, is located on a different side of the second position than the first position is from the second position, whereby the second position, viewed along the flow path, is located between the first position and the third position, wherein a distinguishing feature between the first acoustic emission sensor signal or the second acoustic emission sensor signal and the third acoustic emission sensor signal is taken into account for the purpose of establishing the diagnosis, this has the advantage that noise in the recorded acoustic emission signals whose source lies beyond the fourth position, viewed from the first position, can be quantified even better than noise whose source lies beyond the third position, viewed from the first position, thereby enabling an even more precise diagnosis of the component.
[0024] Preferably, the diagnosis of the component is created taking into account a fifth acoustic emission sensor signal, wherein the fifth acoustic emission sensor signal has been output by one of the at least one acoustic emission sensors, wherein a fifth acoustic emission signal has been detected by the respective at least one acoustic emission sensor at a fifth position on the pipeline, in particular on the outside of the pipeline, wherein the fifth acoustic emission sensor signal output by the respective at least one acoustic emission sensor corresponds to the detected fifth acoustic emission signal. This has the advantage of enabling the creation of an even more precise and reliable diagnosis.The acoustic emission sensor from which the fifth acoustic emission sensor signal has been output can be the same acoustic emission sensor with which the first acoustic emission signal was detected at the first position on the pipeline, and / or the same acoustic emission sensor with which the second acoustic emission signal was detected at the second position on the pipeline, and / or the same.
[0025] Acoustic emission sensor with which the third acoustic emission signal was detected at the third position on the pipeline, and / or the same acoustic emission sensor with which the fourth acoustic emission signal was detected at the fourth position on the pipeline, or can be a different acoustic emission sensor.
[0026] Preferably, the fifth position, viewed along the flow path, is located on a different side of the first position than the third position is located from the first position, whereby the first position, viewed along the flow path, is located between the third position and the fifth position, whereby the second position, viewed along the flow path, is located on a different side of the second position than the third position is located from the second position, whereby the second position, viewed along the flow path, is located between the third position and the fifth position, wherein a distinguishing feature between the first acoustic emission sensor signal or the second acoustic emission sensor signal and the fifth acoustic emission sensor signal is taken into account for establishing the diagnosis.
[0027] If, in addition, the third position, viewed along the flow path, is on a different side of the first position than the second position is from the first position, whereby the first position, viewed along the flow path, is located between the second position and the third position, wherein a distinguishing feature between the first acoustic emission sensor signal and the third acoustic emission sensor signal is taken into account for the purpose of creating the diagnosis, this has the advantage that both noise in the recorded acoustic emission signals whose source lies beyond the fourth position as viewed from the first position, and noise in the recorded acoustic emission signals whose source lies beyond the fifth position as viewed from the first position, can be better quantified, thereby enabling a significantly more precise diagnosis of the component.
[0028] If, however, the third position, viewed along the flow path, is located on a different side from the second position than the first position is from the second position, whereby the second position, viewed along the flow path, is located between the first position and the third position, wherein a distinguishing feature between the first acoustic emission sensor signal or the second acoustic emission sensor signal and the third acoustic emission sensor signal is taken into account for the purpose of making the diagnosis, this has the advantage that, on the one hand, noise in the recorded acoustic emission signals whose source lies beyond the fourth position, viewed from the first position, can be quantified even better than noise whose source lies beyond the third position, viewed from the first position, and, on the other hand, that noise in the recorded acoustic emission signals,whose source lies beyond the fifth position from the first position can be better quantified, thus enabling a more precise diagnosis of the component.
[0029] As an alternative to these variants, it is also possible to record only four acoustic emission signals, only three acoustic emission signals, or only two acoustic emission signals. Accordingly, in these variants, only the first, second, third, and fourth acoustic emission sensor signals, only the first, second, and third acoustic emission sensor signals, or only the first and second acoustic emission sensor signals are taken into account for creating the diagnosis.
[0030] Advantageously, the acoustic emission sensor signals are electronic signals which are output by the respective acoustic emission sensor detecting the respective acoustic emission signal and which reproduce the respective detected acoustic emission signal in a time-resolved or frequency-resolved manner and thus correspond to the respective detected acoustic emission signal. The acoustic emission sensor signals can be analog or digital electrical signals. Regardless of whether the acoustic emission sensor signals are analog or digital electrical signals, time-resolved preferably means an amplitude, the absolute value of the amplitude or intensity (i.e., the squared absolute value of the amplitude) which corresponds to the respective time-resolved detected acoustic emission signal, while frequency-resolved preferably means the Fourier transform of the time-resolved detected acoustic emission signal or the acoustic emission signal in the frequency domain.
[0031] Advantageously, the acoustic emission signals detected by the at least one acoustic emission sensor, in particular by each of the at least one acoustic emission sensors, in particular the first acoustic emission signal, the second acoustic emission signal, and, if the third acoustic emission signal is or has been detected, also the third acoustic emission signal; if the fourth acoustic emission signal is or has been detected, also the fourth acoustic emission signal; and, if the fifth acoustic emission signal is or has been detected, also the fifth acoustic emission signal, are detected over a frequency range. Advantageously, the frequency range is the range from approximately 1 kHz to approximately 1 MHz, preferably from 1 kHz to 1 MHz, particularly preferably from 25 kHz to 500 kHz, very particularly preferably from 25 kHz to 300 kHz.Preferably, the acoustic emission signals emitted by the respective acoustic emission sensor also cover this frequency range, in particular from approximately 1 kHz to approximately 1 MHz, or from 1 kHz to 1 MHz, or from 25 kHz to 500 kHz, or from 25 kHz to 300 kHz.
[0032] Because defective components, especially leaking valves, generate acoustic emission signals in this frequency range, the vibrations caused by the defect or leakage, while many noises or background noises within the audible range are not included in the acoustic emission signals, the acoustic emission signals required for component diagnosis can be captured even in a noisy environment, such as a factory production hall.
[0033] In a variant thereof, the sound emission signals detected by the at least one sound emission sensor, in particular by each of the at least one sound emission sensors, in particular the first sound emission signal, the second sound emission signal and, if the third sound emission signal is detected or has been detected, also the third sound emission signal, if the fourth sound emission signal is detected or has been detected, also the fourth sound emission signal, and, if the fifth sound emission signal is detected or has been detected, also the fifth sound emission signal, can be detected over a frequency range which is not from approximately 1 kHz to approximately 1 MHz, or from 1 kHz to 1 MHz, or from 25 kHz to 500 kHz, or from 25 kHz to 300 kHz. The acoustic emission signals emitted by the respective acoustic emission sensor may also have a frequency range other than from approximately 1 kHz to approximately 1 MHz, or from 1 kHz to 1 MHz, orfrom 25 kHz to 500 kHz, or from 25 kHz to 300 kHz. Preferably, at each of the positions, the respective acoustic emission signal is recorded continuously with the respective one of the at least one acoustic emission sensor for a period of at least 1 s, particularly preferably at least 2 s. This has the advantage that an analysis of the acoustic emission sensor signals, in particular a frequency-dependent analysis of the acoustic emission sensor signals, enables a more reliable result. Preferably, at each of the positions, the respective acoustic emission signal is recorded continuously with the respective one of the at least one acoustic emission sensor for a period of at most 20 s, particularly preferably at most 10 s, most preferably at most 5 s. This has the advantage that the recording of the acoustic emission signals requires only a short time.Preferably, at each of the positions, the respective acoustic emission signal is detected by the respective one of the at least one acoustic emission sensor continuously for a period of time from 1 s to 20 s or 1 s to 10 s, particularly preferably from 2 s to 10 s, most particularly preferably from 2 s to 5 s.
[0034] Alternatively, it is also possible for the respective acoustic emission signal to be recorded at each of the positions with the respective one of the at least one acoustic emission sensor continuously for a period of less than 1 s or more than 20 s.
[0035] To create the component diagnosis, the acoustic emission sensor signals are advantageously filtered with a prefilter. The prefilter comprises a prefilter criterion. The prefiltered acoustic emission sensor signals are used as acoustic emission sensor signals for further processing of the acoustic emission sensor signals to create the component diagnosis. It is irrelevant whether this prefiltering takes place in the acoustic emission sensor with which the respective acoustic emission signal is detected, and the respective acoustic emission sensor already outputs the acoustic emission sensor signal as a prefiltered acoustic emission sensor signal of the detected acoustic emission signal, or whether the acoustic emission sensor signal output by the respective acoustic emission sensor is prefiltered.
[0036] Preferably, pre-filtering includes the time-resolved reproduction of the respective detected acoustic emission signal by the respective acoustic emission sensor signal and the division of the respective time-resolved acoustic emission sensor signal into sections. Preferably, for pre-filtering, at least one characteristic of the respective acoustic emission sensor signal is subsequently determined for each of the sections of the respective acoustic emission sensor signal, wherein the pre-filter criterion is applied to the values of the at least one characteristic determined for the various sections, and one or more sections of the respective acoustic emission sensor signal are selected based on the pre-filter criterion, and the selected section(s) are used as the respective pre-filtered acoustic emission sensor signal to create the diagnosis of the component.
[0037] Preferably, the respective time-resolved acoustic emission sensor signal is divided into at least 10 sections, particularly preferably into at least 20 sections. Preferably, the respective time-resolved acoustic emission sensor signal is divided into a maximum of 1,000 sections. In variants of this, however, the respective time-resolved acoustic emission sensor signal is divided into fewer than 10 sections or more than 1,000 sections.
[0038] Preferably, the sections each correspond to a time duration of at least 10 ms, more preferably at least 20 ms, most preferably at least 50 ms, and most preferably at least 100 ms, of the respective detected acoustic emission signal. Preferably, the sections each correspond to a time duration of at most 30 s, at most 20 s, at most 10 s, or at most 2 s of the respective detected acoustic emission signal. However, the sections can also correspond to a time duration of more than 30 s or less than 10 ms of the respective detected acoustic emission signal.
[0039] Preferably, one of the at least one key figure is a root mean square (RMS Abschnitt ) of the respective acoustic emission sensor signal within the respective section. Preferably, the root mean square (RMS Abschn itt) according to the formula
[0040] RMS Abschnitt = calculated, where m is the number of data points in the respective
[0041] section of the respective acoustic emission sensor signal and Wj is the value of the j-th data point in the respective section of the respective acoustic emission sensor signal.
[0042] Preferably, the at least one key figure is exactly one key figure. Regardless of whether the key figure is the root mean square (RMS Abschnitt) or not, the pre-filter criterion is preferably the median value of the values of this precisely one key figure determined for the sections of the respective acoustic emission sensor signal. Accordingly, the section of the respective acoustic emission sensor signal is preferably used as the respective pre-filtered acoustic emission sensor signal whose value of the key figure is closest to the median value of the values of this key figure determined for the sections of the respective acoustic emission sensor signal. If there is an odd number of sections of the respective acoustic emission sensor signal, the section of the respective acoustic emission sensor signal is thus used as the respective pre-filtered acoustic emission sensor signal whose value of the key figure is the median value of the values determined for the sections of the respective acoustic emission sensor signal.If the value of the characteristic number for several sections of the respective acoustic emission sensor signal is equal to the median value, one or more of these sections can be used as the respective pre-filtered acoustic emission sensor signal. However, if the respective acoustic emission sensor signal has an even number of sections, at least one of those sections of the respective acoustic emission sensor signal whose value of the characteristic number is the median or whose value is, as appropriate, the lower median or upper median is used as the respective pre-filtered acoustic emission sensor signal.
[0043] By filtering the acoustic emission sensor signals with a pre-filter to create the component diagnosis, where the pre-filter criterion is the median value of the values determined for the sections of the respective acoustic emission sensor signal of exactly one characteristic, the advantage is achieved that outliers in the measured values in the respective acquired acoustic emission signals can be eliminated. Accordingly, the pre-filtered acoustic emission sensor signals used contain more reliable information about the component's condition, thus making the creation of the component diagnosis more reliable.
[0044] However, it is also possible to apply a different pre-filter criterion to the values of at least one key figure determined for the various sections. For example, the mean can be used instead of the median. Furthermore, it is also possible to use a key figure other than the root mean square (RMS).Abschnit t) of the respective acoustic emission sensor signal within the respective section. For example, the sum of the points of the respective acoustic emission sensor signal within the respective section can also be used as a key figure.
[0045] As an alternative to these variants, there is also the possibility of dispensing with pre-filtering, i.e. the acoustic emission sensor signals are not filtered with a pre-filter to create the diagnosis of the component.
[0046] Advantageously, for the purpose of creating the diagnosis of the component, for each acoustic emission sensor signal, i.e. for the first acoustic emission sensor signal, the second acoustic emission sensor signal, if applicable the third acoustic emission sensor signal, if applicable the fourth acoustic emission sensor signal and if applicable the fifth acoustic emission sensor signal, a coupling strength of the respective one of the at least one acoustic emission sensor at the respective position on the pipeline, in particular outside on the pipeline, i.e. at the first position, at the second position, if applicable at the third position, if applicable at the fourth position or if applicable at the fifth position, is taken into account when detecting the respective acoustic emission signal, to which acoustic emission signal the respective acoustic emission sensor signal corresponds.This has the advantage that differences in the intensity of the acoustic emission sensor signals caused by different coupling strengths can be taken into account for determining the diagnosis of the component, whereby the diagnosis of the component can be determined with increased precision.
[0047] For this purpose, the respective acoustic emission sensor is preferably positioned at the respective position on the pipeline, in particular outside the pipeline, i.e. at the first position, at the second position, optionally at the third position, optionally at the fourth position or optionally at the fifth position, before the respective acoustic emission sensor of the at least two acoustic emission sensors with which the respective acoustic emission signal has been detected at the respective position on the pipeline, in particular outside the pipeline, and an acoustic coupling of the respective acoustic emission sensor to the pipeline is checked. At least two acoustic emission sensors are preferably used for this purpose.In this case, in addition to the respective one of the at least two acoustic emission sensors being positioned at the respective position on the pipeline, in particular on the outside of the pipeline, a further one of the at least two acoustic emission sensors is preferably positioned at a position on the pipeline adjacent to the respective position, in particular on the outside of the pipeline, after which the test sound signal is output by the further one of the at least two acoustic emission sensors, while the test sound signal is detected by the acoustic emission sensor whose acoustic coupling to the pipeline has been checked. On the basis of the test sound signal detected by the respective acoustic emission sensor, a reception strength and thus a coupling strength of the test sound signal detected by the respective acoustic emission sensor is then preferably determined. If the determined reception strength orIf the coupling strength was below a specified minimum strength, the respective acoustic emission sensor is preferably repositioned at the respective position and its acoustic coupling to the pipeline is checked until the determined reception strength or coupling strength corresponds to at least the specified minimum strength. Advantageously, only when the reception strength or coupling strength determined for the respective acoustic emission sensor at the respective position corresponds to at least the specified minimum strength is the respective acoustic emission signal detected by the respective acoustic emission sensor and the respective acoustic emission sensor signal corresponding to the detected acoustic emission signal is output by the respective acoustic emission sensor. This has the advantage of ensuring that the acoustic emission signals have been detected sufficiently well.
[0048] Alternatively, there is also the possibility that the acoustic coupling of the acoustic emission sensor with which the respective acoustic emission signal was recorded was not checked.
[0049] Advantageously, the physical state of the fluid and / or the fluid's medium are taken into account when creating the component diagnosis. This has the advantage that characteristics in the acoustic emission signals caused by the physical state of the fluid or by the fluid's medium can be taken into account for the component diagnosis. The medium can be water or air, for example, or a mixture of air and water vapor. However, the medium can also be something other than water or air. For example, the medium can be oil or natural gas. Likewise, the medium can also be a mixture of different chemicals, such as pharmaceuticals.
[0050] Alternatively, it is also possible that neither the aggregate state of the fluid nor the medium of the fluid is taken into account when creating the diagnosis of the component.
[0051] Advantageously, the temperature and / or viscosity of the fluid are also taken into account when creating the component diagnosis. This has the advantage that characteristics in the acoustic emission signals caused by the temperature or viscosity of the fluid can be taken into account for the component diagnosis.
[0052] Alternatively, it is also possible that neither the temperature nor the viscosity of the fluid are taken into account when creating the diagnosis of the component.
[0053] To create the diagnosis of the component, a pressure difference, in particular a pressure drop, in the pipeline across the component installed in the pipeline is preferably taken into account. The pressure difference in the pipeline across the component installed in the pipeline is preferably a difference between a pressure at which the fluid is at a first point in the pipeline, viewed from the component along the flow path opposite to the flow direction, directly adjacent to the component, and a pressure at which the fluid is at a second point in the pipeline, viewed from the component along the flow path in the flow direction, directly adjacent to the component. If the component is a valve, the pressure difference is preferably a pressure drop, viewed in the flow direction.If, however, the component is a pump, the pressure difference in the flow direction can also be a pressure increase. The pressure difference is preferably determined by a pressure measurement at the first point and a pressure measurement at the second point, with the difference between the two pressure measurements being the pressure difference. Taking the pressure difference, particularly the pressure drop, in the pipeline across the component installed in the pipeline into account when creating the component diagnosis has the advantage that characteristics in the acoustic emission signals caused by different flow velocities of the fluid can also be taken into account.
[0054] Regardless of whether the pressure difference, in particular the pressure drop, in the pipeline across the component installed in the pipeline is taken into account when creating the diagnosis of the component or not, the pressure under which the fluid is at a point in the pipeline, viewed from the component along the flow path against the flow direction, directly adjacent to the component, can also be taken into account.
[0055] Advantageously, the component type is taken into account when creating the component diagnosis. If the component is a valve, the valve type is also taken into account. As explained above, the component can be, for example, a pipe section, a connector for connecting pipe sections, a valve, or a condensate separator. Accordingly, the component type is preferably a pipe section, a connector for connecting pipe sections, a valve, or a condensate separator. This has the advantage of enabling a component-type-dependent diagnosis of the component, thus enabling a more reliable diagnosis because component-type-dependent characteristics can be taken into account in the acoustic emission signals.
[0056] Preferably, a size of the component, in particular an inner diameter, is also taken into account for creating the diagnosis of the component, wherein, if the component is a valve, a nominal diameter of the valve is taken into account as the size of the component.
[0057] As an alternative to these variants, it is also possible that neither the size of the component nor the component type is taken into account when creating the diagnosis of the component.
[0058] If, as described above, the acoustic emission sensor signals are filtered with a pre-filter to create the component diagnosis, wherein the pre-filter comprises a pre-filter criterion, then, as already mentioned, the pre-filtered acoustic emission sensor signals are preferably used as the acoustic emission sensor signals for further processing of the acoustic emission sensor signals to create the component diagnosis. Therefore, when reference is made below to the use of the acquired acoustic emission signals, the use of the acoustic emission sensor signals, a calculation based on the acquired acoustic emission signals, or a calculation based on the acoustic emission sensor signals, this preferably refers to the respective pre-filtered acoustic emission sensor signal. This means, in the variant described below as preferred, where a Fast Fourier Transformation is calculated from each of the recorded acoustic emission signals to create the diagnosis of the component, for example, the Fast Fourier Transformation is preferably calculated from the pre-filtered acoustic emission sensor signal to create the diagnosis of the component, after which this Fast Fourier Transformation is subsequently used to create the diagnosis of the component.
[0059] Preferably, a Fast Fourier Transformation is calculated from each of the acquired acoustic emission signals to create the component diagnosis. It is irrelevant whether the Fast Fourier Transformation is calculated in the acoustic emission sensor with which the respective acoustic emission signal is acquired, and the respective acoustic emission sensor outputs the acoustic emission sensor signal as a Fast Fourier Transformation of the acquired acoustic emission signal, or whether the Fast Fourier Transformation is calculated from the respective acoustic emission sensor signal.Irrespective of this, the Fast Fourier Transformation has the advantage that, for the diagnosis of the component, one or more sub-ranges of the frequency range over which the acoustic emission signals are recorded can be evaluated separately by evaluating the desired sub-range of the Fast Fourier Transformation of the acoustic emission sensor signal corresponding to the respective acoustic emission signal or by evaluating the desired sub-ranges of the Fast Fourier Transformation of the acoustic emission sensor signal corresponding to the respective acoustic emission signal.
[0060] Alternatively, it is also possible that no Fast Fourier Transformation is calculated for each of the acquired acoustic emission signals to create the component diagnosis. This could be the case, for example, if the component diagnosis is created using an evaluation method based on supervised machine learning.
[0061] To create a diagnosis for the component, the acoustic emission sensor signals are preferably evaluated over a sub-range of the frequency range over which the acoustic emission signals are recorded. This has the advantage that the most suitable sub-range for evaluation can be selected depending on the situation.
[0062] If a state of aggregation of the fluid and / or a medium of the fluid is taken into account for creating the diagnosis of the component and the medium is steam, in particular steam composed of a mixture of air and water, the sub-range is preferably from approximately 200 kHz to approximately 250 kHz, particularly preferably from 200 kHz to 250 kHz. However, the sub-range can also be selected to be higher and be from approximately 250 kHz to approximately 300 kHz, in particular from 250 kHz to 300 kHz. However, the sub-range can also be selected to be even higher and be, for example, from approximately 300 kHz to approximately 350 kHz, in particular from 300 kHz to 350 kHz.
[0063] If, for the purpose of diagnosing the component, a state of aggregation of the fluid and / or a medium of the fluid is taken into account, wherein the medium is not vapor, in particular if the state of aggregation of the fluid is either gaseous or liquid or if the medium is either a gas or a liquid, the sub-range is preferably from approximately 25 kHz to approximately 50 kHz, particularly preferably from 25 kHz to 50 kHz. The sub-range can also be selected to be higher and to be from approximately 50 kHz to approximately 100 kHz, in particular from 50 kHz to 100 kHz. However, the sub-range can also be selected to be even higher and to be, for example, from approximately 100 kHz to approximately 150 kHz, in particular from 100 kHz to 150 kHz.
[0064] However, when the medium of the fluid is water, the partial range is preferably from about 20 kHz to about 400 kHz, particularly preferably from 20 kHz to 400 kHz.
[0065] To create the component diagnosis, the acoustic emission sensor signals are advantageously evaluated across the sub-range of the frequency range over which the acoustic emission signals are recorded, by determining at least one characteristic value of the respective acoustic emission sensor signal for this sub-range. The at least one characteristic value of the respective acoustic emission sensor signal can be determined for the entire sub-range or for one or more sections of the sub-range, such as sections of the sub-range. Irrespective of this, determining at least one characteristic value for the sub-range of the respective acoustic emission sensor signal has the advantage that, based on the characteristic values, the various acoustic emission sensor signals can be easily compared with one another.In a preferred variant, in order to create the diagnosis of the component, the acoustic emission sensor signals are evaluated over the sub-range of the frequency range over which the acoustic emission signals are recorded, by determining at least one characteristic number of the respective acoustic emission sensor signal for the entire sub-range.
[0066] Preferably, one of the at least one characteristic number is a root mean square (RMS) of the respective acoustic emission sensor signal within the sub-range. Preferably, the root mean square (RMS) is calculated according to the formula RMS = , where n is the number of data points in the Fast Fourier Transform in the sub-domain and f is the value of the i-th data point in the Fast Fourier Transform in the sub-domain.
[0067] Preferably, the at least one characteristic number is at least two characteristic numbers, wherein one of these at least two characteristic numbers is the maximum amplitude of the respective acoustic emission sensor signal within the sub-area and one of these at least two characteristic numbers is an average amplitude of the respective acoustic emission sensor signal.
[0068] Alternatively, it is also possible for the at least two key figures to be different key figures. It is also possible for the at least one key figure to be just one key figure.
[0069] Preferably, a difference between the at least one characteristic number determined for the sub-range of one of the acoustic emission sensor signals and the at least one characteristic number determined for the sub-range of the other of the acoustic emission sensor signals is used as a distinguishing feature between one of the acoustic emission sensor signals and another of the acoustic emission sensor signals. This means that, advantageously, a difference between the at least one characteristic number determined for the sub-range of the first acoustic emission sensor signal and the at least one characteristic number determined for the sub-range of the second acoustic emission sensor signal is used to create the diagnosis as a distinguishing feature between the first acoustic emission sensor signal and the second acoustic emission sensor signal.If a distinguishing feature between the first acoustic emission sensor signal and the third acoustic emission sensor signal is taken into account for creating the diagnosis, a difference between the at least one characteristic number determined for the partial range of the first acoustic emission sensor signal and the at least one characteristic number determined for the partial range of the third acoustic emission sensor signal is preferably used as a distinguishing feature between the first acoustic emission sensor signal and the third acoustic emission sensor signal for creating the diagnosis.If a distinguishing feature between the second acoustic emission sensor signal and the third acoustic emission sensor signal is taken into account for creating the diagnosis, a difference between the at least one characteristic number determined for the partial range of the second acoustic emission sensor signal and the at least one characteristic number determined for the partial range of the third acoustic emission sensor signal is preferably used as a distinguishing feature between the second acoustic emission sensor signal and the third acoustic emission sensor signal for creating the diagnosis.If a distinguishing feature between the first acoustic emission sensor signal and the fourth acoustic emission sensor signal is taken into account for creating the diagnosis, a difference between the at least one characteristic number determined for the partial range of the first acoustic emission sensor signal and the at least one characteristic number determined for the partial range of the fourth acoustic emission sensor signal is preferably used as a distinguishing feature between the first acoustic emission sensor signal and the fourth acoustic emission sensor signal for creating the diagnosis.If a distinguishing feature between the third acoustic emission sensor signal and the fourth acoustic emission sensor signal is taken into account for creating the diagnosis, a difference between the at least one characteristic number determined for the partial range of the third acoustic emission sensor signal and the at least one characteristic number determined for the partial range of the fourth acoustic emission sensor signal is preferably used as a distinguishing feature between the third acoustic emission sensor signal and the fourth acoustic emission sensor signal for creating the diagnosis.If a distinguishing feature between the first acoustic emission sensor signal and the fifth acoustic emission sensor signal is taken into account for creating the diagnosis, a difference between the at least one characteristic number determined for the partial range of the first acoustic emission sensor signal and the at least one characteristic number determined for the partial range of the fifth acoustic emission sensor signal is preferably used as a distinguishing feature between the first acoustic emission sensor signal and the fifth acoustic emission sensor signal for creating the diagnosis.If a distinguishing feature between the second acoustic emission sensor signal and the fifth acoustic emission sensor signal is taken into account for creating the diagnosis, a difference between the at least one characteristic number determined for the partial range of the second acoustic emission sensor signal and the at least one characteristic number determined for the partial range of the fifth acoustic emission sensor signal is preferably used as a distinguishing feature between the second acoustic emission sensor signal and the fifth acoustic emission sensor signal for creating the diagnosis.
[0070] As an alternative to these variants, it is also possible to use a differentiating feature between one of the acoustic emission sensor signals and another acoustic emission sensor signal than a difference between the at least one key figure determined for the sub-range of one of the acoustic emission sensor signals and the at least one key figure determined for the sub-range of the other of the acoustic emission sensor signals. For example, the key figures can also be used independently. This can be the case, for example, if the component diagnosis is created using an evaluation method based on supervised machine learning.
[0071] Preferably, the diagnosis of the component is created taking into account the first acoustic emission sensor signal and at least two further acoustic emission sensor signals, i.e. based on the first acoustic emission sensor signal and at least two of the above-mentioned second acoustic emission sensor signal, the above-mentioned third acoustic emission sensor signal, the above-mentioned fourth acoustic emission sensor signal and the above-mentioned fifth acoustic emission sensor signal, wherein the first position, viewed along the flow path, is located between the two positions at which two of the at least two further acoustic emission signals have been detected, wherein, if for one of the at least one characteristic number, in particular the root mean square (RMS) of the respective acoustic emission sensor signal within the sub-area or the average amplitude of the respective acoustic emission sensor signal within the sub-area,a condition is met according to which one of the at least one characteristic number determined for the sub-range of the first acoustic emission sensor signal has a value which lies between the value of the one of the at least one characteristic number determined for the sub-range of one of the two of the at least two further acoustic emission sensor signals and the value of the one of the at least one characteristic number determined for the sub-range of the other of the two of the at least two further acoustic emission sensor signals, the sub-range within the frequency range over which the acoustic emission signals are recorded is shifted to higher frequencies, and for the purpose of creating the diagnosis of the component, the acoustic emission sensor signals are evaluated over the shifted sub-range of the frequency range over which the acoustic emission signals are recorded,by determining at least one characteristic value of the respective acoustic emission sensor signal for this shifted sub-area.
[0072] This means that the evaluation previously described for the partial range is repeated for the shifted partial range. Thus, the evaluation previously described for the partial range, with subsequent shifting of the partial range and repeated evaluation for the shifted partial range, can be repeated multiple times, so that ultimately the partial range is shifted multiple times until the condition whereby the value of the respective key figure determined for the partial range of the first acoustic emission sensor signal lies between the values of the respective key figure determined for the partial range for the two of the at least two further acoustic emission signals, the partial range within the frequency range over which the acoustic emission signals are recorded, is no longer met, and the last obtained partial range is used for further evaluation to create the diagnosis.
[0073] This approach has the advantage that noise caused by sources located away from the first position and thus away from the component for which the diagnosis is being created can be masked out, as a sub-area is searched for in which the noise is not present in the recorded acoustic emission sensor signals or at least plays only a minor role. Accordingly, this enables the creation of a more precise diagnosis of the component.
[0074] With this approach, it is irrelevant whether the shifted sub-range is located completely outside or above the previously used sub-range, or whether the shifted sub-range partially overlaps with the previously used sub-range. The latter is the case, for example, if the sub-range is only slightly shifted to higher frequencies, e.g., if the sub-range extends beyond 25 kHz and the lower and upper limits of the sub-range are only shifted upwards by 5 kHz.
[0075] If a state of aggregation of the fluid and / or a medium of the fluid is taken into account for creating the diagnosis of the component and the medium is steam, in particular steam composed of a mixture of air and water, the sub-range on which the described evaluation is carried out is preferably from approximately 200 kHz to approximately 250 kHz, particularly preferably from 200 kHz to 250 kHz, while the shifted sub-range is from approximately 250 kHz to approximately 300 kHz, in particular from 250 kHz to 300 kHz, or from approximately 300 kHz to approximately 350 kHz, in particular from 300 kHz to 350 kHz. If, however, the sub-range on which the described evaluation is carried out is from approximately 250 kHz to approximately 300 kHz, particularly preferably from 250 kHz to 300 kHz, the shifted sub-range is preferably from approximately 300 kHz to approximately 350 kHz, in particular from 300 kHz to 350 kHz.In the latter case, the sub-range from about 250 kHz to about 300 kHz, particularly preferably from 250 kHz to 300 kHz, on which the described evaluation is carried out, may already be a shifted sub-range. That is, the evaluation described above for the sub-range with subsequent shifting of the sub-range and repeated evaluation for the shifted sub-range can be repeated several times, so that ultimately the sub-range is shifted several times until the condition according to which the value of the respective key figure which was determined for the respective sub-range of the first acoustic emission sensor signal lies between the values of the respective key figure which were determined for the respective sub-range for the two of the at least two further acoustic emission signals, the respective sub-range within the frequency range over which the acoustic emission signals are recorded, is no longer met and the last obtained sub-range is used for further evaluation to create the diagnosis.
[0076] If, for the purpose of creating the diagnosis of the component, a state of aggregation of the fluid and / or a medium of the fluid is taken into account, wherein the medium is not vapor, in particular if the state of aggregation of the fluid is either gaseous or liquid or if the medium is either a gas or a liquid, the sub-range is preferably from approximately 25 kHz to approximately 50 kHz, particularly preferably from 25 kHz to 50 kHz, while the shifted sub-range is from approximately 50 kHz to approximately 100 kHz, in particular from 50 kHz to 100 kHz, or from approximately 100 kHz to approximately 150 kHz, in particular from 100 kHz to 150 kHz. If, however, the sub-range on which the described evaluation is carried out is from approximately 50 kHz to approximately 100 kHz, particularly preferably from 50 kHz to 100 kHz, the shifted sub-range is preferably from approximately 100 kHz to approximately 150 kHz, in particular from 100 kHz to 150 kHz.In the latter case, the sub-range from about 50 kHz to about 100 kHz, particularly preferably from 50 kHz to 100 kHz, on which the described evaluation is carried out, may already be a shifted sub-range.
[0077] Alternatively, there is also the possibility that the sub-area is not moved as described above.
[0078] Advantageously, the diagnosis of the component is created taking into account the first acoustic emission sensor signal and at least one further acoustic emission sensor signal, i.e. based on the first acoustic emission sensor signal and at least one of the above-mentioned second acoustic emission sensor signal, the above-mentioned third acoustic emission sensor signal, the above-mentioned fourth acoustic emission sensor signal and the above-mentioned fifth acoustic emission sensor signal, wherein, if for one of the at least one characteristic number, in particular the root mean square (RMS) of the respective acoustic emission sensor signal within the sub-range or the average amplitude of the respective acoustic emission sensor signal within the sub-range, a condition is met, according to which the one of the at least one characteristic number determined for the sub-range of the first acoustic emission sensor signal has a value,which value is at least one limit value greater than the value of one of the at least one characteristic number determined for the sub-range of the at least one further acoustic emission sensor signal, as a diagnosis of the component, the component is diagnosed as defective.
[0079] Thus, a difference between the at least one characteristic number determined for the sub-range of the first acoustic emission sensor signal and the at least one characteristic number determined for the sub-range of the at least one further acoustic emission sensor signal is used as a distinguishing feature between the first acoustic emission sensor signal and at least one further acoustic emission sensor signal, and is taken into account when creating the diagnosis of the component. This has the advantage of enabling a reliable diagnosis of the component.
[0080] If the diagnosis of the component is made taking into account the first acoustic emission sensor signal and at least two further acoustic emission sensor signals, i.e. based on the first acoustic emission sensor signal and at least two of the above-mentioned second acoustic emission sensor signal, the above-mentioned third acoustic emission sensor signal, the above-mentioned fourth acoustic emission sensor signal and the above-mentioned fifth acoustic emission sensor signal, wherein the first position, viewed along the flow path, is located between the two positions at which two of the at least two further acoustic emission signals have been detected, then, as a diagnosis of the component, the component is preferably only diagnosed as defective if for one of the at least one characteristic number,in particular the root mean square (RMS) of the respective acoustic emission sensor signal within the sub-range or the average amplitude of the respective acoustic emission sensor signal within the sub-range, the condition is met according to which the one of the at least one characteristic number determined for the sub-range of the first acoustic emission sensor signal has a value which is at least the limit value greater than the value of the one of the at least one characteristic number determined for the sub-range of one of the two of the at least two further acoustic emission sensor signals and at least the limit value greater than the value of the one of the at least one characteristic number determined for the sub-range of the other of the two of the at least two further acoustic emission sensor signals. This procedure has the advantage that by moving away from the first position and thus away from the component for which the diagnosis is being made,Noise caused by arranged sources can be masked out, as it is ensured that no such noise is present in the recorded acoustic emission sensor signals, or at least plays only a minor role. Accordingly, this enables a more precise and reliable diagnosis of the component.
[0081] Advantageously, for the purpose of creating the diagnosis of the component, the component is only diagnosed as defective if for each of the additional acoustic emission sensor signals recorded in addition to the first acoustic emission sensor signal, iethe second acoustic emission sensor signal, optionally the third acoustic emission sensor signal, optionally the fourth acoustic emission sensor signal and optionally the fifth acoustic emission sensor signal, for one of the at least one characteristic number, in particular the root mean square (RMS) of the respective acoustic emission sensor signal within the sub-range or the average amplitude of the respective acoustic emission sensor signal within the sub-range, the condition is met according to which the one of the at least one characteristic number determined for the sub-range of the first acoustic emission sensor signal has a value which value is at least the limit value greater than the value of the one of the at least one characteristic number determined for the sub-range of the respective one of the further acoustic emission sensor signals additionally detected in addition to the first acoustic emission sensor signal.This approach has the advantage of masking out noises caused by sources located away from the first position and thus away from the component for which the diagnosis is being created, as it ensures that such noises are absent from the recorded acoustic emission sensor signals or at least play only a minor role. Accordingly, this enables the creation of a more precise and reliable diagnosis of the component.
[0082] If the component is a valve and the acoustic emission signals were recorded with the valve closed, a leak in the valve, i.e., the valve is diagnosed as leaking, is preferably diagnosed if the component is diagnosed as defective. In a preferred variant, the leakage rate of the valve is determined depending on how much the value of the respective characteristic number determined for the partial range of the first acoustic emission sensor signal is greater than the value of the respective characteristic number determined for the partial range of at least one of the other acoustic emission sensor signals.In particular, a greater leakage rate is preferably determined the greater the value of the respective characteristic number determined for the partial range of the first acoustic emission sensor signal is greater than the value of the respective characteristic number determined for the partial range of the at least one further acoustic emission sensor signal.
[0083] As an alternative to these variants, it is also possible that the acoustic emission sensor signals are not evaluated over a partial range of the frequency range over which the acoustic emission signals are recorded in order to create the diagnosis of the component, but that the acoustic emission sensor signals are evaluated over the entire frequency range over which the acoustic emission signals are recorded in order to create the diagnosis of the component.
[0084] Preferably, in order to create the diagnosis of the component, the acoustic emission sensor signals are evaluated by determining a value of the at least one characteristic number for at least two mutually offset range sections, particularly preferably at least ten mutually offset range sections, very particularly preferably at least twenty mutually offset range sections, of the frequency range of the respective acoustic emission sensor signal, over which frequency range the respective acoustic emission signal is detected. If, in order to create the diagnosis of the component, as explained above, the acoustic emission sensor signals are evaluated over a sub-range of the frequency range, over which frequency range the acoustic emission signals are detected, by determining at least one characteristic number of the respective acoustic emission sensor signal for this sub-range, then the at least two or at least ten orAt least twenty mutually offset range sections of the frequency range are preferably included in the sub-range. Accordingly, to create the diagnosis of the component, the acoustic emission sensor signals are preferably evaluated by determining a value of the at least one characteristic number for at least two mutually offset range sections, particularly preferably at least ten mutually offset range sections, very particularly preferably at least twenty mutually offset range sections, of the sub-range of the frequency range of the respective acoustic emission sensor signal, over which frequency range the respective acoustic emission signal is detected.
[0085] Regardless of whether the at least two, at least ten, or at least twenty mutually offset range sections of the frequency range are included in the subrange or not, this has the advantage that, based on the values of the at least one characteristic number for the various range sections, a more reliable determination of differences between the various acoustic emission sensor signals is possible, thereby enabling a more reliable diagnosis of the component. It is irrelevant whether the at least two, at least ten, or at least twenty mutually offset range sections are disjoint or partially overlapping.
[0086] Particularly preferably, the at least two, at least ten, or at least twenty mutually offset region sections all have the same width. In a variant, however, the at least two, at least ten, or at least twenty mutually offset region sections can also have different widths.
[0087] Particularly preferably, the closest of the at least two or at least ten or at least twenty mutually offset area sections are each offset by the same offset from one another. In a variant, however, the closest of the at least two or at least ten or at least twenty mutually offset area sections can also be offset by a different offset from one another. If the medium is water, the area sections preferably have a width in the range from 10 kHz to 25 kHz. In a preferred variant, the closest of the at least two or at least ten or at least twenty mutually offset area sections are each offset from one another by an offset, which offset is in the range from 1 kHz to 10 kHz, particularly preferably in the range from 2 kHz to 5 kHz.However, the range sections can also have a width that does not lie within the range of 10 kHz to 25 kHz. The offset between the closest range sections can also be less than 1 kHz or greater than 25 kHz.
[0088] Advantageously, the diagnosis of the component is created taking into account the first acoustic emission sensor signal and at least two further acoustic emission sensor signals, wherein the first position, viewed along the flow path, is located between the two positions at which two of the at least two further acoustic emission signals were detected. Preferably, the diagnosis is made either based on one of the at least one key figure for each of the at least two or at least ten orat least twenty area sections are classified in that the respective area section is classified as belonging to a first class if and only if a condition is met for one of the at least one characteristic number, according to which the one of the at least one characteristic number determined for the respective area section of the first acoustic emission sensor signal has a value which is at least one classification limit value greater than the value determined for the respective area section of one of the two of the at least two further acoustic emission sensor signals and at least the classification limit value greater than the value determined for the respective area section of the other of the two of the at least two further acoustic emission sensor signals, or wherein on the basis of the one of the at least one characteristic number for each of the at least two or at least ten orat least twenty range sections are classified in that the respective range section is classified as belonging to the first class if and only if a condition is met for one of the at least one characteristic number, according to which the one of the at least one characteristic number determined for the respective range section of the first acoustic emission sensor signal has a value which is at least the classification limit value smaller than the value determined for the respective range section of one of the two of the at least two further acoustic emission sensor signals and at least the classification limit value smaller than the value determined for the respective range section of the other of the two of the at least two further acoustic emission sensor signals.
[0089] This classification of certain area sections as belonging to the first class has the advantage that, based on the number or proportion of the area sections belonging to the first class, a more reliable determination of the differences between the first acoustic emission sensor signal and the two of the at least two further acoustic emission sensor signals is enabled. Since the first position, viewed along the flow path, is located between the two positions at which the two of the at least two further acoustic emission signals were recorded, noise caused by sources arranged away from the first position and thus away from the component for which the diagnosis is being created can be particularly efficiently masked out, since only area sections in which the noise is not present in the recorded acoustic emission signals or at least plays only a minor role are classified as belonging to the first class.Accordingly, this enables a more reliable diagnosis of the component to be made.
[0090] Preferably, the respective range section is classified as belonging to the first class if a difference between the value of the characteristic number determined for the respective range section of the first acoustic emission sensor signal and the values of the characteristic number determined for the respective range section of the two of the at least two further acoustic emission sensor signals indicates a defective component.Depending on the definition of one of the at least one characteristic number, a value of the characteristic number determined for the respective range section of the first acoustic emission sensor signal which is at least the classification limit value greater than the values of the characteristic number determined for the respective range section of the two of the at least two further acoustic emission sensor signals indicates a defective component, or a value of the characteristic number determined for the respective range section of the first acoustic emission sensor signal which is at least the classification limit value smaller than the values of the characteristic number determined for the respective range section of the two of the at least two further acoustic emission sensor signals indicates a defective component. If one of the at least one characteristic number, for example, as already mentioned, is the root mean square (RMS). BereiC h Ssection) of the respective acoustic emission sensor signal within the respective range section, whereby this root mean square (RMS Bereichsabschnitt ) according to the formula RMS Bereichsabschnitt = is calculated, where p is the number
[0091] data points in the range section and f is the value of the i-th data point in the range section, then the respective range section is preferably classified as belonging to the first class if the value of the root mean square RM S range section determined for the respective range section of the first acoustic emission sensor signal is at least the classification limit value greater than the value of the root mean square RMS determined for the respective range section of the two of the at least two further acoustic emission sensor signals Ber calibration section-
[0092] In all of these variants, the classification threshold can be a constant value. However, in all of these variants, the classification threshold can also be a relative value. For example, the classification threshold can be a percentage of the value of one of the at least one characteristic number, which value is determined for the respective range section for the respective one of the at least two additional acoustic emission sensor signals and is compared for classification purposes with the value of one of the at least one characteristic number determined for the respective range section of the first acoustic emission sensor signal. The percentage can be, for example, 10%, 15%, 20%, or 25%.
[0093] If, for the purpose of creating the component diagnosis, a pressure difference, in particular a pressure drop, in the pipeline across the component installed in the pipeline is taken into account, the classification limit value is selected, for example, depending on the pressure difference. If, for example, the pressure difference in the pipeline across the component installed in the pipeline is less than 0.5 bar, the classification limit value is preferably 15% of the value of one of the at least one key figure, which value is determined for the respective range section for the respective one of the at least two further acoustic emission sensor signals and is compared for classification with the value of one of the at least one key figure determined for the respective range section of the first acoustic emission sensor signal. If, on the other hand, for example, the pressure difference in the pipeline across the component installed in the pipeline is 0.5 bar or more, the classification limit value is preferably 25% of the value of one of the at least one characteristic number, which value is determined for the respective range section for the respective one of the two of the at least two further acoustic emission sensor signals and is compared for the classification with the value of one of the at least one characteristic number determined for the respective range section of the first acoustic emission sensor signal.
[0094] Preferably, if a proportion of the at least two, at least ten, or at least twenty range sections has been classified as belonging to the first class, which proportion is greater than a proportion threshold, the component is diagnosed as defective. However, if fewer than the proportion threshold of the at least two, at least ten, or at least twenty range sections have been classified as belonging to the first class, the valve is diagnosed as non-defective and thus intact. This has the advantage of enabling a very reliable diagnosis of the component.
[0095] Preferably, the proportion limit is at least 2% of the at least two or at least ten or at least twenty range sections, particularly preferably at least 3% of the at least two or at least ten or at least twenty range sections, and very particularly preferably at least 5% of the at least two or at least ten or at least twenty range sections. In a variant, however, the second proportion limit can also be less than 2% of the at least two or at least ten or at least twenty range sections.
[0096] Advantageously, the diagnosis of the component is created using an evaluation method based on supervised machine learning. This has the advantage that, with increasing training data, a more reliable and precise diagnosis of the component is easily achieved. Supervised machine learning is preferably achieved by training an algorithm with training data. The training data preferably includes data acquired on a test bench. The training data can, for example, have been acquired using the arrangement described below. However, the training data can also include data acquired on one or more pipelines, indicating which pipelines a component is installed in, for which component a diagnosis was created using the method according to the invention.However, the diagnosis of the component is preferably subsequently verified, for example by removing and examining the component, so that the condition of the test component or component to which the respective acoustic emission sensor signals belong is known and thus information on the diagnosis of the component associated with the respective acoustic emission sensor signals is included in the training data.
[0097] The test stand preferably comprises a test pipeline with a test component, in particular a test valve, installed therein. The test pipeline is preferably structurally similar to pipelines for which the diagnosis is to be made for a component installed therein using the method according to the invention, while the test component is preferably structurally similar, particularly preferably identical, to the component for which the diagnosis is to be made using the method according to the invention. For example, the test component can be a valve of the same type as the valve for which the diagnosis is to be made using the method according to the invention.
[0098] The training data advantageously comprises a plurality of training data sets, each training data set preferably containing a first training acoustic emission sensor signal and a second training acoustic emission sensor signal, as well as optionally a third training acoustic emission sensor signal, optionally a fourth training acoustic emission sensor signal, and optionally a fifth training acoustic emission sensor signal. These training acoustic emission sensor signals are preferably output by the at least one acoustic emission sensor and correspond to the acoustic emission signal detected by the respective one of the at least one acoustic emission sensor at the first position, second position, third position, fourth position, or fifth position, in particular on the outside of the test pipeline or pipe.In the case of training data acquired on one or more pipelines when using the method according to the invention, the respective training acoustic emission sensor signal is preferably the respective acoustic emission sensor signal, whereas in the case of training data acquired on the test bench, the respective training acoustic emission sensor signal preferably corresponds to the acoustic emission signal acquired at the respective position on the test pipeline, in particular on the outside of the test pipeline. This means that the training acoustic emission sensor signals acquired on the test bench are preferably recorded analogously to how the acoustic emission sensor signals were recorded on the pipeline, in particular on the outside of the pipeline, as described above.
[0099] Preferably, the training acoustic emission sensor signals are frequency-resolved in the frequency domain, and the resulting Fast Fourier transformation is used for supervised machine learning. If the acoustic emission sensor signals or training acoustic emission sensor signals are output in a time-resolved manner by at least one acoustic emission sensor, a Fast Fourier transformation is preferably calculated from each time-resolved training acoustic emission sensor signal, with the resulting Fast Fourier transformation being used for supervised machine learning. Preferably, the frequency-resolved training acoustic emission sensor signals or the Fast Fourier transformations are smoothed before being used for supervised machine learning. For this purpose, they can be convolved with a Gaussian curve, for example.
[0100] Preferably, each training data set further contains the state of the test component or component to which the training acoustic emission sensor signals of the respective training data set belong, and thus information on the diagnosis of the test component or component associated with the training acoustic emission sensor signals of the respective training data set. With the information on the diagnosis of the test component or component associated with the training acoustic emission sensor signals of the respective training data set, the test data contains a classification of the training acoustic emission sensor signals.
[0101] If the respective training data set was recorded on the test bench and the test component used is a leaking test valve, the respective training data set preferably also includes the leakage rate of the test valve determined on the test bench.
[0102] If the respective training data set has been recorded on the test bench, each training data set preferably contains for each training acoustic emission sensor signal, ie for the first training acoustic emission sensor signal, the second training acoustic emission sensor signal, optionally the third training acoustic emission sensor signal, optionally the fourth training acoustic emission sensor signal and optionally the fifth training acoustic emission sensor signal, a coupling strength of the respective one of the at least one acoustic emission sensor at the respective position on the test pipeline, in particular outside on the test pipeline, ie at the first position, at the second position, optionally at the third position, optionally at the fourth position or optionally at the fifth position, when detecting the respective acoustic emission signal, to which acoustic emission signal the respective training acoustic emission sensor signal corresponds.
[0103] For this purpose, the respective acoustic emission sensor is preferably positioned at the respective position on the test pipeline, in particular outside the test pipeline, i.e. at the first position, at the second position, optionally at the third position, optionally at the fourth position or optionally at the fifth position, before the respective acoustic emission sensor of the at least two acoustic emission sensors with which the respective acoustic emission signal has been detected at the respective position on the test pipeline, in particular outside the test pipeline, and an acoustic coupling of the respective acoustic emission sensor to the test pipeline is checked. At least two acoustic emission sensors are preferably used for this purpose.In this case, in addition to the respective one of the at least two acoustic emission sensors being positioned at the respective position on the test pipeline, in particular on the outside of the test pipeline, a further one of the at least two acoustic emission sensors is preferably positioned at a position on the test pipeline adjacent to the respective position, in particular on the outside of the test pipeline, after which the test sound signal is output by the further one of the at least two acoustic emission sensors, while the test sound signal is detected by the acoustic emission sensor whose acoustic coupling to the test pipeline has been checked. Based on the test sound signal detected by the respective acoustic emission sensor, a reception strength and thus a coupling strength of the test sound signal detected by the respective acoustic emission sensor is then preferably determined. If the determined reception strength orIf the coupling strength was below a specified minimum strength, the respective acoustic emission sensor was preferably repositioned at the respective position and its acoustic coupling to the test pipeline was checked until the determined reception strength or coupling strength corresponded to at least the specified minimum strength. Advantageously, only when the reception strength or coupling strength determined for the respective acoustic emission sensor at the respective position corresponded to at least the specified minimum strength was the respective acoustic emission sensor recorded the respective acoustic emission signal, and the respective acoustic emission sensor output the training acoustic emission sensor signal corresponding to the respective recorded acoustic emission signal.
[0104] Preferably, each training data set also contains information on the state of aggregation of the fluid and / or the medium of the fluid to which the training acoustic emission sensor signals of the respective training data set belong.
[0105] Preferably, each training data set also contains information on a pressure difference, in particular pressure drop, in the test pipeline or pipeline, via which the test component or component installed in the test pipeline or pipeline is taken into account.
[0106] In this case, the pressure difference in the test pipeline or pipeline across the test component or component installed in the test pipeline or pipeline is preferably a difference between a pressure under which the fluid is at a first point in the test pipeline or pipeline, viewed from the test component or component along the flow path opposite to the flow direction, directly adjacent to the test component or component, and a pressure under which the fluid is at a second point in the test pipeline or pipeline, viewed from the test component or component along the flow path in the flow direction, directly adjacent to the test component or component. If the test component or component is a test valve or valve, the pressure difference is preferably a pressure drop seen in the flow direction. If the test component or componentHowever, if the component is a pump, the pressure difference in the flow direction can also be a pressure increase. The pressure difference is preferably determined by a pressure measurement at the first point and a pressure measurement at the second point, with the difference between the two pressure measurements being the pressure difference.
[0107] Advantageously, each training data set also includes information about the test component or component, wherein, if the test component or component is a test valve or valve, the information includes information about the valve type.
[0108] Advantageously, each training data set also contains information on a size of the test component or component, in particular an inner diameter, wherein the information, if the test component or component is a valve or test valve, contains information on a nominal diameter of the valve or test valve as the size of the test component or component.
[0109] Preferably, in the training data sets, the training acoustic emission sensor signals are evaluated over a sub-range of the frequency range over which the training acoustic emission signals are acquired, as described above for the acoustic emission sensor signals, by determining at least one characteristic value of the respective acoustic emission sensor signal for this sub-range, with the resulting value of the characteristic value being used as part of the respective training data set. The sub-range can be shifted according to the conditions described above.
[0110] Advantageously, the training data comprises at least 40 training data sets, preferably at least 100 training data sets, particularly preferably at least 500 training data sets. The training data preferably contains at least 40 training data sets for each state of the test component or component. Particularly preferably, the training data for each test component or component contains at least 40 training data sets for each state. Very particularly preferably, the training data for each test component or component contains at least 40 training data sets for each state, each for each medium.
[0111] As mentioned above, supervised machine learning is preferably achieved by training an algorithm with training data. This algorithm is preferably based on a random forest approach or a custom-designed neural network approach. Alternatively, the algorithm can also be based on another approach.
[0112] According to the invention, the method described above for creating a diagnosis of a component is used in a method for diagnosing a component. This is a method for diagnosing a component, in particular a valve, by means of acoustic emission testing, which component is installed in a pipeline, which pipeline is designed to conduct a fluid along a flow path in a flow direction. In this case, the first acoustic emission signal is detected by one of at least one acoustic emission sensor at a first position on the pipeline, in particular on the outside of the pipeline, and the first acoustic emission signal is detected by the at least one acoustic emission sensor with which the first acoustic emission signal is detected at the first position on the pipeline, in particular on the outside of the pipeline.the first acoustic emission sensor signal corresponding to the detected first acoustic emission signal is output. Furthermore, the second acoustic emission signal is detected by one of the at least one acoustic emission sensors at a second position on the pipeline, in particular on the outside of the pipeline, and the second acoustic emission sensor signal corresponding to the second acoustic emission signal is output by the one of the at least one acoustic emission sensors with which the second acoustic emission signal is detected at the second position on the pipeline, in particular on the outside of the pipeline. The first acoustic emission sensor signal is transmitted to a diagnostic module connected to the one of the at least one acoustic emission sensor with which the first acoustic emission signal was detected, for creating the diagnosis of the component, and the second acoustic emission sensor signal is transmitted to the one connected to the one of the at least one acoustic emission sensor,with which the second acoustic emission signal has been detected, is transmitted to the diagnostic module for creating the diagnosis of the component and, by means of the diagnostic module, taking into account the first acoustic emission sensor signal and the second acoustic emission sensor signal, the diagnosis of the component is created using the method according to the invention for creating a diagnosis of a component described above.
[0113] The acoustic emission sensor by means of which the second acoustic emission signal is detected at a second position on the pipeline, in particular on the outside of the pipeline, can be the same acoustic emission sensor with which the first acoustic emission signal is detected at the first position on the pipeline or can be a different acoustic emission sensor.
[0114] Preferably, the diagnostic module is formed by the computer program product described above for carrying out the method for creating a diagnosis of a component using the method for creating a diagnosis of a component.
[0115] Advantageously, the third sound emission signal is detected by one of the at least one sound emission sensors at the third position on the pipeline, in particular on the outside of the pipeline, and the third sound emission sensor signal corresponding to the third sound emission signal is output by the at least one sound emission sensor with which the third sound emission signal is detected at the third position on the pipeline, in particular on the outside of the pipeline, wherein the third sound emission sensor signal is transmitted to the diagnostic module connected to the at least one sound emission sensor with which the third sound emission signal was detected, for creating the diagnosis of the component, and the diagnostic module is used to create the diagnosis of the component with additional consideration of the third sound emission sensor signal using the method for creating a diagnosis of a component.
[0116] Preferably, the fourth sound emission signal is detected by one of the at least one sound emission sensors at the fourth position on the pipeline, in particular on the outside of the pipeline, and the fourth sound emission sensor signal corresponding to the fourth sound emission signal is output by the at least one sound emission sensor with which the fourth sound emission signal is detected at the fourth position on the pipeline, in particular on the outside of the pipeline, wherein the fourth sound emission sensor signal is transmitted to the diagnostic module connected to the at least one sound emission sensor with which the fourth sound emission signal was detected, for creating the diagnosis of the component, and the diagnostic module is used to create the diagnosis of the component with additional consideration of the fourth sound emission sensor signal using the method according to the invention for creating a diagnosis of a component.Preferably, the fifth sound emission signal is detected by one of the at least one sound emission sensors at the fifth position on the pipeline, in particular on the outside of the pipeline, and the fifth sound emission sensor signal corresponding to the fifth sound emission signal is output by the at least one sound emission sensor with which the fifth sound emission signal is detected at the fifth position on the pipeline, in particular on the outside of the pipeline, wherein the fifth sound emission sensor signal is transmitted to the diagnostic module connected to the at least one sound emission sensor with which the fifth sound emission signal was detected, for creating the diagnosis of the component, and the diagnosis of the component is created by means of the diagnostic module with additional consideration of the fifth sound emission sensor signal using the method according to the invention for creating a diagnosis of a component.
[0117] If the component is a valve, then at least one acoustic emission sensor preferably detects the first acoustic emission signal and the second acoustic emission signal and optionally the third acoustic emission signal, optionally the fourth acoustic emission signal and optionally the fifth acoustic emission signal when the valve is closed.
[0118] Advantageously, the at least one acoustic emission sensor comprises at least two acoustic emission sensors. Advantageously, a test acoustic signal can be output by at least one of the at least two acoustic emission sensors, in particular within the frequency range over which the acoustic emission signals are detected by the at least two acoustic emission sensors. In a particularly preferred variant, the test acoustic signal has a frequency corresponding to a natural frequency of the at least two acoustic emission sensors. In one variant, the test acoustic signal comprises only the frequency corresponding to the natural frequency of the at least two acoustic emission sensors.Regardless of whether the test sound signal has a frequency that corresponds to the natural frequency of the at least two acoustic emission sensors or not, in a further particularly preferred variant, the test sound signal has a frequency spectrum that extends across the entire frequency range over which the acoustic emission signals are detected by the at least two acoustic emission sensors. The frequency spectrum can be a continuous or a discrete frequency spectrum.
[0119] Advantageously, at the respective position on the pipeline, in particular outside on the pipeline, ie at the first position, at the second position, optionally at the third position, optionally at the fourth position or optionally at the fifth position, before the respective sound emission sensor of the at least two sound emission sensors with which the respective sound emission signal is detected at the respective position on the pipeline, in particular outside on the pipeline, is positioned at the respective position on the pipeline, in particular outside on the pipeline, and an acoustic coupling of the respective sound emission sensor to the pipeline is checked.For this purpose, in addition to the respective acoustic emission sensor being positioned at the respective position on the pipeline, in particular on the outside of the pipeline, a further one of the at least two acoustic emission sensors is preferably positioned at a position on the pipeline adjacent to the respective position, in particular on the outside of the pipeline, after which the test sound signal is output by the further one of the at least two acoustic emission sensors, while the test sound signal is detected by the acoustic emission sensor whose acoustic coupling to the pipeline is being checked. Based on the test sound signal detected by the respective acoustic emission sensor, a reception strength and thus a coupling strength of the test sound signal detected by the respective acoustic emission sensor is then preferably determined. If the determined reception strength orthe coupling strength is below a predetermined minimum strength, the respective acoustic emission sensor is preferably repositioned at the respective position and its acoustic coupling to the pipeline is checked until the determined reception strength or coupling strength corresponds at least to the predetermined minimum strength. Advantageously, only when the reception strength or coupling strength determined for the respective acoustic emission sensor at the respective position corresponds at least to the predetermined minimum strength is the respective acoustic emission signal detected by the respective acoustic emission sensor and the respective acoustic emission sensor signal corresponding to the detected acoustic emission signal is output by the respective acoustic emission sensor. The reception strength or coupling strength can be a scalar value or can be a frequency-dependent function. That is,In the latter case, the reception strength can have a different value for each frequency in the test sound signal. As an alternative to these variants with at least two acoustic emission sensors, however, the at least one acoustic emission sensor is a single acoustic emission sensor.
[0120] According to the invention, an arrangement for carrying out the method for diagnosing a component, in particular a valve, by means of acoustic emission testing, which component is installed in a pipeline, which pipeline is designed to conduct a fluid along a flow path in a flow direction, comprises at least one acoustic emission sensor for detecting a first acoustic emission signal at a first position on a pipeline, in particular outside the pipeline, and outputting a first acoustic emission sensor signal, wherein the first acoustic emission sensor signal corresponds to the detected first acoustic emission signal, for detecting a second acoustic emission signal at a second position on the pipeline, in particular outside the pipeline, and outputting a second acoustic emission sensor signal, wherein the second acoustic emission sensor signal corresponds to the detected second acoustic emission signal,optionally a third acoustic emission signal at a third position on the pipeline, in particular outside the pipeline, and outputting a third acoustic emission sensor signal, wherein the third acoustic emission sensor signal corresponds to the detected third acoustic emission signal, optionally a fourth acoustic emission signal at a fourth position on the pipeline, in particular outside the pipeline, and outputting a third acoustic emission sensor signal, wherein the fourth acoustic emission sensor signal corresponds to the detected fourth acoustic emission signal, optionally a fifth acoustic emission signal at a fifth position on the pipeline, in particular outside the pipeline, and outputting a fifth acoustic emission sensor signal, wherein the fifth acoustic emission sensor signal corresponds to the detected fifth acoustic emission signal,and a diagnostic unit with the diagnostic module for creating the diagnosis of the component taking into account the first acoustic emission sensor signal and the second acoustic emission sensor signal, the diagnosis of the component with the method according to the invention, wherein the diagnostic unit is connected to the diagnostic module for receiving the first acoustic emission sensor signal with that of the at least one acoustic emission sensor with which the first acoustic emission signal is to be detected, and for receiving the second acoustic emission sensor signal with that of the at least one acoustic emission sensor with which the second acoustic emission signal is to be detected, and optionally for receiving the third acoustic emission sensor signal with that of the at least one acoustic emission sensor with which the third acoustic emission signal is to be detected,optionally connected to receive the fourth acoustic emission sensor signal with that of the at least one acoustic emission sensor with which the fourth acoustic emission signal is to be detected, and optionally connected to receive the fifth acoustic emission sensor signal with that of the at least one acoustic emission sensor with which the fifth acoustic emission signal is to be detected.
[0121] If, in the method for creating the diagnosis of a component as described above, the acoustic emission sensor signals are prefiltered with a prefilter, the diagnostic module preferably comprises a prefilter module for prefiltering the acoustic emission sensor signals. In one variant, however, the prefilter module can also be designed separately from the diagnostic module. Thus, the arrangement can include the prefilter module, but the prefilter module is not part of the diagnostic module.
[0122] As an alternative to these variants, there is also the possibility that the arrangement is designed without the pre-filter module.
[0123] The diagnostic unit can, for example, be a smartphone on which the diagnostic module is installed in the form of a computer program product. This has the advantage that the diagnostic unit can be easily brought to the location of the component for which the diagnosis is to be made. However, the diagnostic unit can also be another computer unit, such as a personal computer, on which the diagnostic module is installed in the form of a computer program product. However, the diagnostic unit can also be formed by multiple computers and thus, for example, by a cloud on which the diagnostic module is installed in the form of a computer program product.
[0124] Preferably, the at least one acoustic emission sensor comprises a magnet for attaching the at least one acoustic emission sensor to the pipeline, in particular on the outside of the pipeline, and for holding the at least one acoustic emission sensor to the pipeline. This has the advantage that the at least one acoustic emission sensor can be attached to the pipeline, in particular on the outside of the pipeline, in a simple manner and with a reproducible force. Alternatively, however, it is also possible for the at least one acoustic emission sensor not to have a magnet for attaching the at least one acoustic emission sensor to the pipeline and for holding the at least one acoustic emission sensor to the pipeline. Thus, for example, the at least one acoustic emission sensor can simply be attached to the pipeline and held in place by hand.
[0125] The arrangement preferably comprises at least two acoustic emission sensors. This has the advantage that the coupling strength of the acoustic emission sensors can be determined simply and reliably, as described above, and used for diagnosing the component. Alternatively, however, the arrangement can also comprise only one acoustic emission sensor.
[0126] Further advantageous embodiments and combinations of features of the invention emerge from the following detailed description and the entirety of the patent claims.
[0127] Short description of the drawings
[0128] The drawings used to explain the embodiment show: Fig. 1 a simplified schematic representation of an arrangement for
[0129] Carrying out a method according to the invention for diagnosing a component, in particular a valve, by means of acoustic emission testing, which component is installed in a pipeline, which pipeline is designed to guide a fluid along a flow path in a flow direction,
[0130] Fig. 2 Curves of a first acoustic emission sensor signal, a second
[0131] Acoustic emission sensor signal and a third acoustic emission sensor signal over the frequency range from 25 kHz to 350 kHz of a first measurement for creating a diagnosis of a valve,
[0132] Fig. 3 Curves of the first acoustic emission sensor signal, the second acoustic emission sensor signal and the third acoustic emission sensor signal over the frequency range from 25 kHz to 350 kHz of a second measurement for creating a diagnosis of the valve,
[0133] Fig. 4 Curves of the first acoustic emission sensor signal, the second acoustic emission sensor signal and the third acoustic emission sensor signal over the frequency range from 25 kHz to 350 kHz of a third measurement for creating a diagnosis of the valve,
[0134] Fig. 5 Curves of the first acoustic emission sensor signal, the second acoustic emission sensor signal and the third acoustic emission sensor signal over the frequency range from 25 kHz to 350 kHz of a fourth measurement for creating a diagnosis of another valve,
[0135] Fig. 6 Curves of the first acoustic emission sensor signal, the second acoustic emission sensor signal and the third acoustic emission sensor signal over the frequency range from 25 kHz to 350 kHz of a fifth measurement for creating a diagnosis of another valve,
[0136] Fig. 7 is a simplified schematic representation of another pipeline which is designed to conduct a fluid along a flow path in a flow path direction and in which a valve is installed as a component, on which valve the method according to the invention for diagnosing a component or valve by means of acoustic emission testing can be carried out,
[0137] Fig. 8 is an illustration of how the method according to the invention can be used to
[0138] Acoustic emission signals can be reproduced and pre-filtered in a time-resolved manner by the respective acoustic emission sensor signal, whereby the respective time-resolved acoustic emission sensor signal is divided into sections for pre-filtering,
[0139] Fig. 9 shows an acoustic emission sensor signal shown in the frequency domain to illustrate the further processing of the pre-filtered acoustic emission sensor signals by evaluating the respective pre-filtered acoustic emission sensor signal in different range sections of the respective pre-filtered acoustic emission sensor signal,
[0140] Fig. 10 shows three pre-filtered acoustic emission sensor signals to illustrate how the diagnosis of the valve can be created taking into account the first acoustic emission sensor signal, the second acoustic emission sensor signal and the third acoustic emission sensor signal using the method according to the invention, by first obtaining an intermediate result by classifying the range sections of the acoustic emission sensor signals based on determined values of the respective root mean square, and
[0141] Fig. 1 1 is a graph of the determined root mean square values for the different range sections of the three acoustic emission sensor signals to illustrate the further procedure for establishing the diagnosis of the valve.
[0142] In principle, identical parts are provided with identical reference numerals in the figures. Ways of carrying out the invention
[0143] Figure 1 shows a simplified schematic representation of an arrangement 1 for carrying out a method according to the invention for diagnosing a component 100, in particular a valve, by means of acoustic emission testing. The component 100 is installed in a pipeline 200, which pipeline 200 is designed to conduct a fluid along a flow path in a flow direction 201. The arrangement 1 comprises two acoustic emission sensors 2.1, 2.2 for detecting acoustic emission signals in a frequency range from 25 kHz to 350 kHz and outputting acoustic emission sensor signals which each correspond to the respective detected acoustic emission signal. In variants, it is also possible for the two acoustic emission sensors 2.1, 2.2 the respective acoustic emission signal cannot be detected over the previously specified frequency range of 25 kHz to 350 kHz, but over a frequency range of approximately 1 kHz to approximately 1 MHz, from 1 kHz to 1 MHz, 25 kHz to 500 kHz, or from 25 kHz to 300 kHz. The acoustic emission signals emitted by the respective acoustic emission sensor also cover the frequency range corresponding to the respective variant, from approximately 1 kHz to approximately 1 MHz, from 1 kHz to 1 MHz, or from 25 kHz to 500 kHz, or from 25 kHz to 350 kHz, or from 25 kHz to 300 kHz.
[0144] The two acoustic emission sensors 2.1, 2.2 each have a magnet for attaching at least one of the respective acoustic emission sensors 2.1, 2.2 to the outside of the pipeline 200 and for securing the respective acoustic emission sensors 2.1, 2.2 to the pipeline 200. Both acoustic emission sensors 2.1, 2.2 can also output a test sound signal at 50 kHz, which is a natural frequency of the acoustic emission sensors 2.1, 2.2. However, the test sound signal can also have one or more frequencies other than 50 kHz. For example, the test sound signal can be in the range from 1 kHz to 1 MHz, in the range from 20 kHz to 500 kHz, or in the range from 50 kHz to 200 kHz.
[0145] The arrangement 1 thus comprises at least one acoustic emission sensor 2.1, 2.2 for detecting a first acoustic emission signal at a first position 51 on the pipeline 200 and outputting a first acoustic emission sensor signal, wherein the first acoustic emission sensor signal corresponds to the detected first acoustic emission signal, for detecting a second acoustic emission signal at a second position 52 on the pipeline 200 and outputting a second acoustic emission sensor signal, wherein the second acoustic emission sensor signal corresponds to the detected second acoustic emission signal, for detecting a third acoustic emission signal at a third position 53 on the pipeline 200 and outputting a third acoustic emission sensor signal, wherein the third acoustic emission sensor signal corresponds to the detected third acoustic emission signal,for detecting a fourth acoustic emission signal at a fourth position 54 on the pipeline 200 and outputting a fourth acoustic emission sensor signal, wherein the fourth acoustic emission sensor signal corresponds to the detected fourth acoustic emission signal, and for detecting a fifth acoustic emission signal at a fifth position 55 on the pipeline 200 and outputting a fifth acoustic emission sensor signal, wherein the fifth acoustic emission sensor signal corresponds to the detected fifth acoustic emission signal. Furthermore, the arrangement 1 comprises a diagnostic unit 3 with the diagnostic module 4 for creating the diagnosis of the component 100, taking into account the first acoustic emission sensor signal and the second acoustic emission sensor signal, using the method according to the invention for creating a diagnosis of the component 100. The diagnostic unit 3 is connected to the diagnostic module 4 with the acoustic emission sensors 2.1, 2.2 in order to detect the signals transmitted by the acoustic emission sensors 2.1,2.2. Thus, the diagnostic unit 3 is connected to the diagnostic module 4 for receiving the first acoustic emission sensor signal to that of the at least one acoustic emission sensor 2.1, 2.2, with which the first acoustic emission signal is to be detected; for receiving the second acoustic emission sensor signal, it is connected to that of the at least one acoustic emission sensor 2.1, 2.2, with which the second acoustic emission signal is to be detected; for receiving the third acoustic emission sensor signal, it is connected to that of the at least one acoustic emission sensor 2.1, 2.2, with which the third acoustic emission signal is to be detected; for receiving the fourth acoustic emission sensor signal, it is connected to that of the at least one acoustic emission sensor 2.1, 2.2, with which the fourth acoustic emission signal is to be detected.and for receiving the fifth acoustic emission sensor signal, it is connected to that of the at least one acoustic emission sensor 2.1, 2.2 with which the fifth acoustic emission signal is to be detected. In one embodiment, the diagnostic module 4 comprises a pre-filter module 6 for pre-filtering the acoustic emission sensor signals. In one variant, the arrangement 1 comprises the pre-filter module 6, but the pre-filter module is not part of the diagnostic module. In an alternative to these variants, however, the arrangement can also be designed without the pre-filter module.
[0146] In the present exemplary embodiment, the diagnostic unit 3 is a smartphone on which the diagnostic module 4 is installed in the form of a computer program product 5. In a variant thereof, however, the diagnostic unit 3 is formed by another computer unit, such as a personal computer, on which the diagnostic module 4 is installed in the form of a computer program product 5. However, the diagnostic unit 3 can also be formed by multiple computers and thus, for example, by a cloud on which the diagnostic module 4 is installed in the form of a computer program product 5.
[0147] If the inventive method for diagnosing a component 100, in particular a valve, by means of acoustic emission testing is carried out with the arrangement 1, in one embodiment the first acoustic emission signal is detected by one of the acoustic emission sensors 2.1, 2.2 at the first position 51 on the outside of the pipeline 200, and the first acoustic emission sensor signal corresponding to the detected first acoustic emission signal is output by that of the at least one acoustic emission sensors 2.1, 2.2 with which the first acoustic emission signal is detected at the first position 51 on the pipeline 200. Furthermore, the second acoustic emission signal is detected by one of the at least one acoustic emission sensors 2.1, 2.2 at the second position 52 on the outside of the pipeline 200, and the second acoustic emission signal is output by that of the at least one acoustic emission sensor 2.1, 2.2.2, with which the second acoustic emission signal is detected at the second position 52 on the pipeline 200, the second acoustic emission sensor signal corresponding to the second acoustic emission signal is output. Furthermore, the third acoustic emission signal is detected by one of the at least one acoustic emission sensors 2.1, 2.2 at the third position 53 outside on the pipeline 200, and the third acoustic emission sensor signal corresponding to the third acoustic emission signal is output by that of the at least one acoustic emission sensor 2.1, 2.2, with which the third acoustic emission signal is detected at the third position 53 on the pipeline 200, the third acoustic emission sensor signal is output. Furthermore, the fourth acoustic emission signal is detected by one of the at least one acoustic emission sensors 2.1, 2.2 at the fourth position 54 outside on the pipeline 200, and the fourth acoustic emission signal is output by that of the at least one acoustic emission sensor 2.1, 2.2, with which the fourth acoustic emission signal is detected at the fourth position 54 on the pipeline 200, the fourth acoustic emission sensor signal corresponding to the fourth acoustic emission signal is output. Furthermore, the fifth acoustic emission signal is detected by one of the at least one acoustic emission sensors 2.1, 2.2 at the fifth position 55 outside the pipeline 200, and the fifth acoustic emission sensor signal corresponding to the fifth acoustic emission signal is output by that of the at least one acoustic emission sensor 2.1, 2.2 with which the fifth acoustic emission signal is detected at the fifth position 55 on the pipeline 200.
[0148] Before the respective acoustic emission signal is detected at each of the positions 51, 52, 53, 54, 55 with the respective one of the at least one acoustic emission sensors 2.1, 2.2, the respective acoustic emission sensor 2.1, 2.2 is positioned at the respective position 51, 52, 53, 54, 55 outside on the pipeline 200 with that acoustic emission sensor 2.1, 2.2 with which the respective acoustic emission signal is detected at the respective position 51, 52, 53, 54, 55 outside on the pipeline 200, and an acoustic coupling of the respective acoustic emission sensor 2.1, 2.2 to the pipeline 200 is checked. For this purpose, in addition to the respective acoustic emission sensor 2.1, 2.2 being positioned at the respective position 51, 52, 53, 54, 55 outside on the pipeline 200, the other acoustic emission sensor 2.2, 2.1 is positioned at a position adjacent to the respective position 51, 52, 53, 54, 55 on the outside of the pipeline 200, after which the test sound signal is output by the other acoustic emission sensor 2.2, 2.1, while the test sound signal is detected by the acoustic emission sensor 2.1, 2.2 whose acoustic coupling to the pipeline 200 is being checked. Based on the test sound signal detected by the respective acoustic emission sensor 2.1, 2.2, a reception strength and thus a coupling strength of the test sound signal detected by the respective acoustic emission sensor 2.1, 2.2 is subsequently determined. If the determined reception strength or the coupling strength is below a predetermined minimum strength, the respective acoustic emission sensor 2.1, 2.2 is repositioned at the respective position 51, 52, 53, 54, 55 and its acoustic coupling to the pipeline 200 is checked until the determined reception strength orCoupling strength corresponds at least to the predetermined minimum strength. Only when the reception strength or coupling strength determined for the respective acoustic emission sensor 2.1, 2.2 at the respective position 51, 52, 53, 54, 55 corresponds at least to the predetermined minimum strength is the respective acoustic emission signal detected by the respective acoustic emission sensor 2.1, 2.2 and the acoustic emission sensor signal corresponding to the respective detected acoustic emission signal is output by the respective acoustic emission sensor 2.1, 2.2. In the present exemplary embodiment, the reception strength or coupling strength is a scalar value. In a variant, the reception strength or coupling strength can also be a frequency-dependent function. This means that the reception strength can have a different value for each frequency in the test sound signal. Irrespective of this, the coupling strength is taken into account in each case for creating the diagnosis of the component 100.
[0149] If the respective acoustic emission sensor 2.1 , 2.2 is used to
[0150] Acoustic emission signal at the respective positions 51, 52, 53, 54, 55 is recorded and from the respective acoustic emission sensor 2.1, 2.2 the respective recorded
[0151] If a sound emission sensor signal corresponding to the sound emission signal is output, the respective sound emission signal is detected with the respective one of the at least one sound emission sensor 2.1, 2.2 continuously for a period of 2 s.
[0152] The output acoustic emission sensor signals are each determined by the diagnostic module 4 and the diagnostic module 4 is used to create the diagnosis of the component 100 using the method according to the invention for creating a diagnosis of a component, in particular a valve, by means of acoustic emission testing, which component is installed in the pipeline, which pipeline is designed to guide a fluid along a flow path in a flow direction.
[0153] In the present embodiment, the second position 52 is located on the pipeline 200 at a distance from the first position 51 in the flow direction. Furthermore, the third position 53 is located on a different side from the first position 51 than the second position 52 is from the first position 51, so that the first position 51 is located between the second position 52 and the third position 53 as viewed along the flow path.In addition, the fourth position 54 is located on a different side of the third position 53 than the first position 51 is located on the third position 53, so that the third position 53 is located between the first position 51 and the fourth position 54 as viewed along the flow path. In addition, the fifth position 55 is located on a different side of the first position 51 than the third position 53 is located on the first position 51, so that the first position 51 is located between the third position 53 and the fifth position 55 as viewed along the flow path.In addition, viewed along the river path, the fifth position 55 is located on a different side from the second position 52 than the third position 53 is located from the second position 52, whereby the second position 52 is located between the third position 53 and the fifth position 55 viewed along the river path.
[0154] To create the diagnosis of component 100, the first acoustic emission sensor signal, the second acoustic emission sensor signal, the third acoustic emission sensor signal, the fourth acoustic emission sensor signal, and the fifth acoustic emission sensor signal are taken into account. In one variant, however, only the first acoustic emission sensor signal, the second acoustic emission sensor signal, the third acoustic emission sensor signal, and the fourth acoustic emission sensor signal are taken into account to create the diagnosis of component 100. In another variant, however, only the first acoustic emission sensor signal, the second acoustic emission sensor signal, and the third acoustic emission sensor signal are taken into account to create the diagnosis of component 100. In another variant, however, only the first acoustic emission sensor signal and the second acoustic emission sensor signal are taken into account to create the diagnosis of component 100.
[0155] The method according to the invention for creating a diagnosis of a component is explained below in conjunction with the further figures. As an exemplary embodiment, a variant is explained in which only the first acoustic emission signal at the first position 51 on the outside of the pipeline 200, the second acoustic emission signal at the second position 52 on the outside of the pipeline 200, and the third acoustic emission signal at the third position 53 on the outside of the pipeline 200 have been recorded. Therefore, in this exemplary embodiment, only the first acoustic emission sensor signal, the second
[0156] Acoustic emission sensor signal and the third acoustic emission sensor signal are taken into account. The fourth acoustic emission sensor signal explained above and the fifth
[0157] Acoustic emission sensor signals, however, are not taken into account because they were not recorded at all.
[0158] Figure 2 shows curves of the first acoustic emission sensor signal, the second acoustic emission sensor signal, and the third acoustic emission sensor signal over the frequency range from 25 kHz to 350 kHz, which correspond to the first acoustic emission signal detected at the first position 51, the second acoustic emission signal detected at the second position 52, and the acoustic emission signal detected at the third position 53, respectively. The pipeline 200 had an inner diameter of 25 mm, and the installed component 100 was a valve, more precisely a ball valve with an inner diameter of 25 mm. The fluid in the pipe 200 was liquid water and was above the valve, ie viewed from the valve against the flow direction 201, under a pressure of 40 bar, while below the valve, ie viewed from the valve in the flow direction, atmospheric pressure, ie a pressure of 1 bar, prevailed.Thus, there was a pressure drop of 39 bar across the valve. The closed valve was intact, meaning it was leak-tight.
[0159] The curves shown in Figure 2 are the continuous root mean square according to the formula RMS = f(t) 2 dt the Fast Fourier Transformation of the respective acoustic emission sensor signal, where t2— each corresponds to the width of a bin in the curve, whereby the acoustic emission sensor signals are each corrected with the coupling strength of the acoustic emission sensor 2.1, 2.2 with which the respective acoustic emission signal was recorded, so that they are comparable with one another. As can be seen from Figure 2, the curves of the three acoustic emission sensor signals have very similar profiles. This already indicates, from a visual assessment of the curves, that the component 100 is intact or the valve is tight and that no or only minor interference noises from sources outside the area from the second position 52 to the third position 53 in the pipeline 200 were recorded.Since the pipeline 200 on which the measurements shown were taken was a test pipeline, the valve could also be directly checked for leaks and it could be ensured that these acoustic emission sensor signals originate from the pipeline with a leak-tight valve.
[0160] Figure 3 shows the curves of the first acoustic emission sensor signal, the second acoustic emission sensor signal, and the third acoustic emission sensor signal, analogous to the curves shown in Figure 2. However, in Figure 3, for the same pipeline, the closed ball valve exhibited a leakage rate of 0.16 l / min at a water pressure of 40 bar. As can be seen, the curve of the first acoustic emission sensor signal, which was recorded at the first position 51 near the valve, exhibits the highest RMS values almost throughout, while the curve of the second acoustic emission sensor signal, which was recorded at the second position 52 from the first position 51 in the flow direction, exhibits a very similar curve to the curve of the first acoustic emission sensor signal below 200 kHz and slightly lower RMS values than the curve of the first acoustic emission sensor signal above 200 kHz.The curve of the third acoustic emission sensor signal, which was recorded from the first position 51 against the flow direction at the third position 53, exhibits almost consistently lower RMS values than the curves of the first and second acoustic emission sensor signals. This indicates a leak in the valve.
[0161] Figure 4 shows the curves of the first acoustic emission sensor signal, the second acoustic emission sensor signal, and the third acoustic emission sensor signal, analogous to the curves shown in Figures 2 and 3. However, in Figure 4, the fluid was a gas at a pressure of 32 bar and the closed ball valve exhibited a leak with a leakage rate of 0.18 l / min. Here, the different curve shapes are primarily evident in the sub-range from 50 kHz to 180 kHz, while the curves outside this sub-range are largely similar.Within the sub-range, the curve of the first acoustic emission sensor signal, recorded at the first position 51 near the valve, exhibits the highest RMS values almost consistently, while the curve of the second acoustic emission sensor signal, recorded from the first position 51 in the flow direction at the second position 52, exhibits lower RMS values than the curve of the first acoustic emission sensor signal. The curve of the third acoustic emission sensor signal, recorded from the first position 51 against the flow direction at the third position 53, exhibits consistently lower RMS values than the curves of the first and second acoustic emission sensor signals. This indicates a leak in the valve.
[0162] It should be noted, however, that the curves in Figure 4 also show these different curves, albeit to a significantly lesser extent, in the sub-ranges from 220 kHz to 250 kHz and from 270 kHz to 300 kHz, which indicate a leak in the valve. Thus, in the example shown in Figure 4, the sub-range from 50 kHz to 180 kHz is primarily suitable for evaluating the acoustic emission sensor signals for diagnosing the valve. If this sub-range is overlaid with noise, one or both sub-ranges from 220 kHz to 250 kHz or from 270 kHz to 300 kHz can be used for the evaluation. How this is achieved within the framework of the inventive method for creating a diagnosis of a component is described below:
[0163] Figure 5 again shows RMS curves of the first acoustic emission sensor signal, the second acoustic emission sensor signal, and the third acoustic emission sensor signal. In Figure 5, the fluid was water at a pressure above the valve of 5 bar, and the pipeline 200 had an inner diameter of 25 mm, but the valve was a globe valve with a valve diameter of 25 mm. Unlike the previous examples, the acoustic emission signals were recorded here on a pipeline 200 in a production facility. Therefore, the exact leakage rate could not be determined. However, it was known, and could be determined using the method according to the invention, that the valve had a large leak. It was determined that, viewed from the valve in the flow direction 201, a source of strong noise with a frequency of approximately 10 kHz was present behind the second position 52.
[0164] Since the fluid was liquid water at room temperature, the component 100 or valve was a straight-through valve and the pressure drop across the valve was 4 bar, a frequency of 25 kHz to 50 kHz was selected for the diagnosis in a first step, in which the root mean square (RMS) of the corrected Fast Fourier Transformation was calculated as a key figure for each of the acoustic emission sensor signals corrected according to the coupling strength according to the formula RMS = Subsequently, the values of the characteristic number determined for each sub-range of the three acoustic emission sensor signals were compared with each other. Since the characteristic number determined for the sub-range of the first acoustic emission sensor signal had a value that lay between the value determined for the sub-range of the second acoustic emission sensor signal and that for the sub-range of the third acoustic emission sensor signal, it was determined that a source of noise in this sub-range was emitting noise that was hindering the diagnosis of the valve. Therefore, the sub-range was shifted to higher frequencies, more precisely to the sub-range from 100 kHz to 150 kHz.Subsequently, in a second step, the root mean square (RMS) of the corrected Fast Fourier Transformation signals was calculated as a key figure in this shifted sub-area for each of the acoustic emission sensor signals corrected for the coupling strength using the formula RMS = . The key figure determined for this shifted sub-range of the first acoustic emission sensor signal had a value which was not between the value determined for the shifted sub-range of the second acoustic emission sensor signal and the value determined for the shifted sub-range of the third acoustic emission sensor signal, it was determined that only minimal or no interference was detected in this sub-range, which would hinder the creation of a diagnosis for the valve. Rather, since the key figure determined for the shifted sub-range of the first acoustic emission sensor signal had a value which was at least one limit value greater than the key figure value determined for the sub-range of the second and third acoustic emission sensor signals, the component was diagnosed as defective and the valve as leaking.
[0165] Figure 6 again shows RMS curves of the first acoustic emission sensor signal, the second acoustic emission sensor signal, and the third acoustic emission sensor signal. In Figure 5, the fluid was water vapor at a pressure above the valve of 7 bar, and the pipeline 200 had an inner diameter of 150 mm, but the valve was a globe valve with a valve diameter of 150 mm. Here, too, the acoustic emission signals were recorded on a pipeline 200 in a production facility. Therefore, the exact leakage rate could not be determined. However, it was known, and could be determined using the method according to the invention, that the valve had a small leak. It is evident from the curves shown that, viewed from the valve in the flow direction 201, a source of noise with a frequency of approximately 30 kHz to approximately 160 kHz was present behind the second position 52.
[0166] The procedure for creating the diagnosis was very similar to that already described in connection with Figure 5. However, since the fluid was steam, the sub-range from 200 kHz to 250 kHz was used in the first step. The RMS value was determined for this and the determined values for the various acoustic emission sensor signals were compared. Since the characteristic value determined for the sub-range of the first acoustic emission sensor signal had a value that was not between the value determined for the sub-range of the second acoustic emission sensor signal and that for the sub-range of the third acoustic emission sensor signal, it was possible to ensure that only minimal or no interference was detected in this sub-range, which would have hindered the creation of the valve diagnosis.In addition, since the characteristic value determined for the shifted sub-range of the first acoustic emission sensor signal had a value that was precisely the limit value greater than the value of the characteristic value determined for the sub-range of the second and third acoustic emission sensor signals, the component was diagnosed as defective and the valve as leaking, although it was also determined that the leak was very small. Apart from the rule-based procedure described above, the method according to the invention for creating a diagnosis of a component can also be used to create the diagnosis of the component using a different rule-based procedure. An example of such a different rule-based procedure is illustrated and described below with reference to Figures 7 to 11.
[0167] Shows a simplified schematic representation of a pipeline 1200 configured to conduct a fluid along a flow path in a flow path direction 1201. In the present example, the fluid is water in the liquid state. In variations, however, the fluid can also be water, steam, or any other fluid.
[0168] A valve 1000 is installed as a component in the pipeline 1200, on which component the inventive method for diagnosing a component or valve 1000 can be carried out by means of acoustic emission testing with the arrangement 1 shown in Figure 1. Thus, in this exemplary embodiment, the at least one acoustic emission sensor 2.1, 2.2 of the arrangement 1 for detecting a first acoustic emission signal at a first position 151 on the pipeline 1200 and outputting a first acoustic emission sensor signal, wherein the first acoustic emission sensor signal corresponds to the detected first acoustic emission signal, for detecting a second acoustic emission signal at a second position 152 on the pipeline 1200 and outputting a second acoustic emission sensor signal, wherein the second acoustic emission sensor signal corresponds to the detected second acoustic emission signal, and for detecting a third acoustic emission signal at a third position 153 on the pipeline 1200 and outputting a third acoustic emission sensor signal, wherein the third acoustic emission sensor signal corresponds to the detected third acoustic emission signal.Accordingly, the diagnostic unit 3 with the diagnostic module 4 is used to create the diagnosis of the valve 1000, taking into account the first acoustic emission sensor signal and the second acoustic emission sensor signal and the third acoustic emission sensor signal, using the method according to the invention for creating a diagnosis of the valve 1000. When carrying out this variant of the method according to the invention for diagnosing the valve 1000 by means of acoustic emission testing, the first acoustic emission signal is detected by one of the acoustic emission sensors 2.1, 2.2 at the first position 151 on the outside of the pipeline 1200, and the first acoustic emission sensor signal corresponding to the detected first acoustic emission signal is output by that of the at least one acoustic emission sensor 2.1, 2.2 with which the first acoustic emission signal is detected at the first position 151 on the pipeline 1200. Furthermore, one of the at least one acoustic emission sensors 2.1, 2.2, the second acoustic emission signal is detected at the second position 152 on the outside of the pipeline 1200, and the second acoustic emission sensor signal corresponding to the second acoustic emission signal is output by the sensor of the at least one acoustic emission sensor 2.1, 2.2, with which the second acoustic emission signal is detected at the second position 152 on the pipeline 1200. Furthermore, the third acoustic emission signal is detected by one of the at least one acoustic emission sensors 2.1, 2.2 at the third position 153 on the outside of the pipeline 1200, and the third acoustic emission sensor signal corresponding to the third acoustic emission signal is output by the sensor of the at least one acoustic emission sensor 2.1, 2.2, with which the third acoustic emission signal is detected at the third position 153 on the pipeline 1200.
[0169] In Figure 7, the first acoustic emission sensor signal, the second acoustic emission sensor signal, and the third acoustic emission sensor signal are symbolically represented in the rectangle in the lower part of the figure. The arrows shown in Figure 7 from the pipeline 1200 to the acoustic emission sensor signals illustrate where on the pipeline 1200, or at which of the first position 151, second position 152, and third position 153 the respective acoustic emission sensor signal was detected.
[0170] In the present exemplary embodiment, the first position 151, viewed in the flow direction 1201, is at a height of the valve 1000 installed in the pipeline 1200. Furthermore, the second position 152 is located on the pipeline 1200 at a distance from the first position 151 in the flow direction. Furthermore, viewed along the flow path, the third position 153 is located on a different side of the first position 151 than the second position 152 is located from the first position 151, whereby the first position 151, viewed along the flow path, is located between the second position 152 and the third position 153. Before the respective acoustic emission signal is compared with the respective one of the at least one acoustic emission sensors 2.1, 2.2 is detected, as already in connection with Figure 1 at the respective position 151, 152, 153 outside on the pipeline 1200 with that acoustic emission sensor 2.1, 2.2 with which the respective acoustic emission signal is detected at the respective position 151, 152, 153 outside on the pipeline 1200, the respective acoustic emission sensor 2.1, 2.2 is positioned at the respective position 151, 152, 153 outside on the pipeline 1200 and an acoustic coupling of the respective acoustic emission sensor 2.1, 2.2 to the pipeline 1200 is checked.
[0171] If the respective acoustic emission signal at the respective positions 151, 152, 153 is detected by the respective acoustic emission sensor 2.1, 2.2 and the acoustic emission sensor signal corresponding to the respective detected acoustic emission signal is output by the respective acoustic emission sensor 2.1, 2.2, the respective acoustic emission signal is detected by the respective one of the at least one acoustic emission sensor 2.1, 2.2 continuously for a period of 2 s. The output acoustic emission sensor signals are each determined by the diagnostic unit 3 with the diagnostic module 4, and the diagnostic module 4 is used to create the diagnosis of the valve 1000 using the inventive method for creating a diagnosis of the valve 1000.
[0172] As illustrated in Figure 8, in order to create the diagnosis of the valve 1000, the acoustic emission sensor signals 105 are filtered with a pre-filter, wherein the pre-filter comprises a pre-filter criterion, wherein in order to create the diagnosis of the valve 1000, the pre-filtered acoustic emission sensor signals are used as acoustic emission sensor signals for the further processing of the acoustic emission sensor signals.
[0173] As shown in Figure 8, pre-filtering involves the time-resolved reproduction of the respective acquired acoustic emission signal by the respective acoustic emission sensor signal 105 and the subdivision of the respective time-resolved acoustic emission sensor signal 105 into sections 106.1, ..., 106.20. As already mentioned, in the present example, the acoustic emission sensor signals 105 each correspond to an acoustic emission signal continuously acquired for a period of 2 s. The respective time-resolved acoustic emission sensor signal 105 is divided into 20 sections 106.1, ..., 106.20. Each section 106.1, 106.20 thus corresponds to 100 ms of continuously acquired acoustic emission signal.
[0174] For pre-filtering, a characteristic number of the respective acoustic emission sensor signal 105 is then determined for each of the sections 106.1, 106.20 of the respective acoustic emission sensor signal 105, wherein the pre-filter criterion is applied to the values of the at least one characteristic number determined for the various sections 106.1, ..., 106.20, and a section 106.1, ..., 106.20 of the respective acoustic emission sensor signal 105 is selected based on the pre-filter criterion, and the selected section 106.1, ..., 106.20 is used as the respective pre-filtered acoustic emission sensor signal 105 to create the diagnosis of the valve 1000. This pre-filtering is performed by a pre-filter module 6, which is a component of the diagnostic module 4 of the arrangement 1 shown in Figure 1.
[0175] In this example, the key figure is the root mean square (RMS Abschnitt) of the respective acoustic emission sensor signal 105 within the respective section 106.1, ..., 106.20. The root mean square (RMS Abschn itt) according to the formula RMS Abschnitt = calculated, where m is the number of data points in the respective section 106.1 , ..., 106.20 of the respective acoustic emission sensor signal 105 and Wj is the value of the j-th data point in the respective section 106.1, ..., 106.20 of the respective
[0176] acoustic emission sensor signal 105. In Figure 8, these values of the root mean square (RMS Abschnitt ) are symbolically represented as rectangles labeled "RMS".
[0177] Furthermore, in the present example, the pre-filter criterion is the median value of the values of the characteristic number or the root mean square (RMS) determined for the sections 106.1, ..., 106.20 of the respective acoustic emission sensor signal 105. Abschnitt)- Accordingly, that section 106.1, ..., 106.20 of the respective acoustic emission sensor signal 105 is used as the respective pre-filtered acoustic emission sensor signal whose value of the root mean square (RMS Absch nitt) the median value of the root mean square (RMS) values determined for sections 106.1, ..., 106.20 of the respective acoustic emission sensor signal 105 Abschnitt ) is closest to the original value. Since in the present example the respective acoustic emission sensor signal 105 is divided into an even number of sections 106.1 , ..., 106.20 one of those sections 106.1 , 106.20 of the respective
[0178] Acoustic emission sensor signal 105 is used as the respective pre-filtered acoustic emission sensor signal, the value of which of the root mean square (RMS Abschn itt) is the median or whose value is the lower median or upper median, as appropriate.
[0179] If one of the acoustic emission sensor signals for the different sections 106.1, ..., 106.20 shows excessive differences in the value of the root mean square (RMS Absch nitt) is detected, the corresponding acoustic emission sensor signal can be recorded at the respective first position 151, second position 152, and third position 153. For this purpose, the arrangement 1 can, for example, directly prompt the user to record the respective acoustic emission sensor signal again.
[0180] Furthermore, in the method, an acoustic emission sensor signal can also be recorded at different positions in the flow direction 1201 at the level of the valve 1000 installed in the pipeline 1200. Subsequently, these acoustic emission sensor signals can be pre-filtered as described above, wherein the acoustic emission sensor signal which has the largest value of the root mean square (RMS) is used as the first acoustic emission sensor signal. Absch This acoustic emission sensor signal can thus be used as the first acoustic emission signal detected at the first position 151, viewed in the flow direction 1201, at the level of the valve 1000 installed in the pipeline 1200. This procedure ensures that the first acoustic emission sensor signal used for the further method contains the clearest signal from the valve.
[0181] To further diagnose valve 1000, a Fast Fourier Transformation is calculated from each of the acquired acoustic emission signals. This means that in this case, to diagnose valve 1000, the Fast Fourier Transformation is calculated from the pre-filtered acoustic emission sensor signal, after which this Fast Fourier Transformation is used to diagnose the component. The acoustic emission sensor signals are further evaluated across a sub-range of the frequency range over which the acoustic emission signals are acquired. Since the fluid medium in this case is water in the liquid state, this sub-range is from 20 kHz to 400 kHz.
[0182] Figure 9 shows the Fast Fourier Transformation of one of the pre-filtered acoustic emission sensor signals. This means that Figure 9 illustrates the further processing of an acoustic emission sensor signal based on an acoustic emission sensor signal shown in the frequency domain. As illustrated in Figure 9, the acoustic emission sensor signals are evaluated to create the diagnosis of the valve 1000 by determining a value of a characteristic number for each of 181 mutually offset range sections 107 of the sub-range 108. The range sections 107 each have a width of 20 kHz and are offset by 2 kHz from one another. The characteristic number is the root mean square.
[0183] (RMSß erejC which is calculated according to the formula RMS range section where p is the number of data points in the range segment and f is the value of the i-th data point in the range segment.
[0184] As illustrated in Figure 10, the diagnosis of valve 1000 is created taking into account the first acoustic emission sensor signal, the second acoustic emission sensor signal, and the third acoustic emission sensor signal. For this purpose, the Fast Fourier Transformation of the pre-filtered first acoustic emission sensor signal is shown in Figure 10 as "M2," while the Fast Fourier Transformation of the pre-filtered second acoustic emission sensor signal is shown as "M3," and the Fast Fourier Transformation of the pre-filtered third acoustic emission sensor signal is shown as "M1."
[0185] Thus, the diagnosis of the valve 1000 is created taking into account the first acoustic emission sensor signal as well as two further acoustic emission sensor signals. The first position 151, at which the first acoustic emission signal was recorded by one of the acoustic emission sensors 2.1, 2.2 on the pipeline 1200, is located along the flow path between the two positions 152, 153, at which the two further acoustic emission signals were recorded. To create the diagnosis, the root mean square (RMS B ebereichsabschnitt) as a key figure for each of the 181 range sections 107, a classification is made by classifying the respective range section 107 as belonging to a first class if and only if for the root mean square (RMS BereiC h S section) the condition is met according to which the root mean square (RMS BereiC h Ssection) for the respective range section 107 of the first acoustic emission sensor signal has a value that is at least one classification limit greater than the value determined for the respective range section 107 of one of the two further acoustic emission sensor signals and at least the classification limit greater than the value determined for the respective range section 107 of the other of the two further acoustic emission sensor signals. This procedure is referred to in Figure 10 as "Algorithm A," which leads to an intermediate result referred to as the "Intermediate Result."
[0186] When performing this classification of the range sections 107, the classification threshold can be a constant value. However, in the present example, the classification threshold is a relative value. More precisely, the classification threshold is a percentage of the root mean square (RMS) value. BereiChs section), which value is determined for the respective range section 107 for the respective of the two further acoustic emission sensor signals and for the classification with the value of the root mean square (RMS) determined for the respective range section 107 of the first acoustic emission sensor signal BereiC h S section). The classification limit is selected depending on the pressure difference in the pipe 1 200 across the valve 1000 installed in the pipe 1 200. If the pressure difference in the pipe 1 200 across the valve 1000 installed in the pipe is less than 0.5 bar, the classification limit is 15% of the value of the root mean square (RMS Bereichsabschnitt), which value is determined for the respective range section 107 for the respective of the two further acoustic emission sensor signals and for the classification with the value of the root mean square (RMS) determined for the respective range section 107 of the first acoustic emission sensor signal BereiC h S section). However, if the pressure difference in the pipe 1 200 across the valve 1000 installed in the pipe 1 200 is 0.5 bar or more, the classification limit is 25% of the root mean square (RMS) value BereiC hs section), which value is determined for the respective range section for the respective of the two further acoustic emission sensor signals and for the classification with the value of the root mean square (RMS) determined for the respective range section 107 of the first acoustic emission sensor signal BBy selecting the classification limit value in this way depending on the pressure difference in the pipe 1200 across the valve 1000 installed in the pipe 1200, it is taken into account that a larger pressure difference generally results in a larger noise level in the recorded acoustic emission signals. This larger noise level leads to larger statistical fluctuations in the recorded acoustic emission signals for a given state of the valve 1000, which also results in the determined value of the root mean square (RMS Bereichsabschnit t) exhibits statistically larger deviations. These statistically larger deviations can be accounted for by using the larger classification limit for a larger pressure difference in the pipeline.
[0187] Figure 1 1 shows a graph of the determined values of the root mean square (RMS Brange section) for the various range sections 107 of the three acoustic emission sensor signals to illustrate the further method for creating the diagnosis of the valve 1000. The horizontal axis is symbolically designated as "frequency," since the values for the various range sections 107 are arranged along the horizontal axis according to the respective frequency range of the respective range section. The values of the root mean square (RMS) determined for the respective range section 107 of the third acoustic emission sensor signal Bereichsabschnitt ) are each shown as circles ("RMS M 1"). The values of the root mean square (RMS BereiC h S section) are each shown as squares ("RMS M2"). The values of the root mean square (RMSB e r egg Ch section) are each shown as triangles ("RMS M3"). For those range sections 107 that were classified as belonging to the first class, a black horizontal bar is indicated below the values of the respective range section 107. For those range sections 107 that were not classified as belonging to the first class, a gray horizontal bar is indicated below the values of the respective range section 107. As illustrated at the bottom of Figure 11, the proportion of the range sections that are considered to belong to the first class is subsequently examined to create the diagnosis of the valve 1000.
[0188] 107 of the total number of area sections is 107.
[0189] More precisely, the valve 1000 is diagnosed as defective if a proportion of the 181 range sections 107 has been classified as belonging to the first class, which proportion is greater than a proportion threshold. In the present exemplary embodiment, this proportion threshold is 3% of the 181 range sections 107. Thus, if 3% or more of the 181 range sections 107 have been classified as belonging to the first class, the valve 1000 is diagnosed as defective. If, however, less than the proportion threshold of 3% of the 181 range sections 107 have been classified as belonging to the first class, the valve 1000 is diagnosed as non-defective and thus intact. However, this proportion threshold can also be selected differently. For example, the share limit may be at least 2% of area sections 107 or at least 5% of area sections 107.
[0190] With the procedure described above, the respective range section 107 is classified as belonging to the first class if and only if the difference of the value of the root mean square (RMS) determined for the respective range section 107 of the first acoustic emission sensor signal BereiC h S section) to the values of the root mean square (RMS) determined for the respective section 107 of the two other acoustic emission sensor signals BereiC h Ssection) indicates a defective component. Since the first position 151, at which the first acoustic emission signal was detected by one of the acoustic emission sensors 2.1, 2.2 on the pipeline 1 200, is located between the two positions 152, 153, viewed along the flow path, at which the two further acoustic emission signals were detected, disturbing noises caused by sources arranged away from the first position 151 and thus away from the valve 100 for which the diagnosis is being made can be particularly efficiently masked out, since only area sections 107 are classified as belonging to the first class, in which the disturbing noises are not present in the detected acoustic emission signals or at least play only a minor role.By diagnosing the valve 1000 as defective when the proportion of area sections 107 classified as belonging to the first class is greater than the proportion limit, it is also achieved that when creating the diagnosis of the valve 1000, the degree to which the acoustic emission sensor signals indicate a leaky valve 1000 is taken into account, regardless of the frequency at which the indications occur. This allows, on the one hand, various types of leaks in the valve 1000 to be detected, which can cause signatures at different frequencies in the acoustic emission sensor signals. On the other hand, frequency ranges in which noise occurs caused by sources located away from the first position 151 and thus away from the valve 100 can be masked out. This enables a very reliable diagnosis of the valve 1000.
[0191] Apart from the rule-based procedures described above, in the method according to the invention for creating a diagnosis of a component, the diagnosis of the component can also be created by an evaluation method supported by supervised machine learning, as explained below.
[0192] Supervised machine learning is achieved by training an algorithm with training data. The training data comprises training data sets, wherein each training data set represents a test measurement on a pipeline 200 and, in addition to the respective acoustic emission sensor signals belonging to the test measurement, which correspond to the acoustic emission signals respectively recorded on the pipeline 200, also contains the condition of the component, which condition is to be diagnosed for the respective test measurement. If the component is a valve, the condition of the valve to be diagnosed can be binary and have the value "tight" or the value "leaky". However, the condition of the valve to be diagnosed can also contain the leakage rate of the valve if the valve exhibited a leak during the respective test measurement.The training data sets can, for example, be the measurements shown in Figures 2 to 6, whereby the respective training data set can also include further information such as the previously mentioned information on the fluid, pressure, the pipeline 200, the component 100, but also on the coupling strengths of the acoustic emission sensors 2.1, 2.2 when recording the respective acoustic emission signals. In particular, the acoustic emission signals recorded on a test bench, as shown in Figures 2, 3 and 4, can be used, since the condition of the component or the leakage rate of the valve can be precisely determined there and included in the respective training data set. However, measurements that were recorded on pipelines 200 in production plants, such as the measurements shown in Figures 5 and 6, can also be used as training data sets.Furthermore, for each training data set, the previously described determined values of a key figure for the previously described sub-areas can also be included in the respective training data set. In this case, these values of the respective key figure for the respective sub-area must ultimately be determined when implementing the method and also transmitted to the algorithm for evaluation for the diagnosis of the component 100. However, it is also possible for the acoustic emission sensor signals to be transmitted to the algorithm for evaluation for the diagnosis of the component 100 only after the correction for the coupling strength or even without the correction for the coupling strength. This meansIt is possible to transmit the acoustic emission sensor signals to the algorithm in a time-resolved or frequency-resolved manner as a Fast Fourier Transformation, possibly as described above in connection with Figure 2, as a continuous square mean for evaluation for the diagnosis of component 100. However, the algorithm should have been previously trained with training data available in the same form.
[0193] In a first example, a random forest approach was used as a supervised machine learning algorithm. The random forest approach is a meta-estimator that fits a series of decision tree classifiers to different subsamples of the dataset and uses averaging to improve prediction accuracy and control overfitting. The number of random trees was set to 100, and the maximum depth was not restricted. The minimum number of samples required to split an internal node was left at the default value of 2.
[0194] To train the algorithm, training data sets were used, which were collected on a test rig with a test pipeline containing a test valve, as described in Figures 2 to 4. The training data included twice as many training data sets for a leaking test valve as for a tight test valve. When training the algorithm, care was taken to ensure that at least 40 training data sets were available for each class to ensure that the trained algorithm could accurately diagnose both leaking and tight valves.
[0195] Each training data set contained the first training acoustic emission sensor signal, the second training acoustic emission sensor signal, and the third training acoustic emission sensor signal, the respective coupling strength of the respective acoustic emission sensor when detecting the respective corresponding acoustic emission signal, the valve type of the test valve, information on whether the valve was tight or leaking, and information on whether the fluid was water, steam, or air. The training data sets also included information on the pressure drop across the test valve and the root mean square (RMS) determined for sub-ranges of the respective test acoustic emission sensor signal. The previously described sub-ranges from the detected frequency range were selected as sub-ranges depending on whether the fluid was water, steam, gas, or air.
[0196] The test acoustic emission sensor signals each had a length of 2 16data points. The test acoustic emission sensor signals were corrected for the respective coupling strength, and a Hanning window was applied before the Fast Fourier Transform was calculated from the test acoustic emission sensor signals. The Fast Fourier Transform was then smoothed with a Gaussian filter with a width of 100 data points, and the result was converted to a logarithmic (dB) scale. These logarithmic intensity curves, as well as the pressure drop across the test valve and the root mean square (RMS) determined for the sub-ranges of the respective test acoustic emission sensor signals, were scaled to a specified value range for all training data sets to obtain comparable magnitudes.
[0197] The classification model was run a total of 100 times, and the best result was selected. The selection was based on the classification model's ability to exceed an initially specified minimum rating for accuracy, precision, true positives, true negatives, and false negatives. The selected best classification model was then used to implement the method according to the invention.
[0198] As a result, using the Random Forest approach as an algorithm for supervised machine learning with the method according to the invention, the diagnosis of a valve, i.e. whether the valve was tight or leaking, could be correctly established with an accuracy of over 90%, with a precision of over 90% and a hit rate of over 90%.
[0199] In a second embodiment, a custom-designed neural network approach was used as a supervised machine learning algorithm. With a custom-designed neural network, a window is moved over the signal and relevant features are identified at different levels (from low to high). These features are identified automatically, without any prior knowledge of which features these ultimately are. The custom-designed neural network approach makes it possible to maintain interrelationships between the features. The final architecture in this embodiment consisted of three convolutional layers for pattern extraction, followed by three dense decision layers. A binary cross-entropy was chosen as the loss function, since the model ultimately solves the binary question or answer.The binary classification task was to determine whether the valve was leaking or not. To optimize the learning rate and improve the result, a LookAhead mechanism was also used, as this makes the model less sensitive to suboptimal hyperparameters and thus reduces the need for extensive hyperparameter tuning. The LookAhead mechanism was used in combination with RectifiedAdam, which was the most powerful optimizer for the model.
[0200] In the second embodiment using the custom-designed neural network approach, similar training data was used to train the algorithm as in the first embodiment using the random forest approach. However, in the second embodiment using the custom-designed neural network approach, the Fast Fourier Transformation of the training acoustic emission sensor signals was smoothed three times in succession using a Gaussian filter with a width of 100 data points, and the result was then quadratically distorted along the x-axis to enhance the more significant features at lower frequencies.
[0201] As a result, using the custom-designed neural network approach as an algorithm for supervised machine learning with the method according to the invention, the diagnosis of a valve, i.e. whether the valve was tight or leaking, could be correctly established with an accuracy of over 90%, with a precision of over 90% and a hit rate of over 90%.
[0202] The invention is not limited to the exemplary embodiments explained above. If, in the method for creating a diagnosis of a component, the diagnosis of the component is created using an evaluation method based on supervised machine learning, other features not previously described can also be used to train the algorithm. For example, the kurtosis of the acoustic emission sensor signals can be used as a feature. Furthermore, the skewness of the acoustic emission sensor signals can be used as a feature. The energy of the acoustic emission sensor signals, which energy is the area under the curve of the square of the absolute value of the respective acoustic emission sensor signal, can also be used as a feature. The standard deviation of the acoustic emission sensor signals can also be used as a feature.Furthermore, the histograms of the voltages output by the respective acoustic emission sensor, which correspond to the output acoustic emission sensor signals, can be used as a feature. Zero crossings of the acoustic emission sensor signals can also be prevented as an indicator of the signal noise present in the respective acoustic emission sensor signal. Furthermore, the spectral centers of gravity of the acoustic emission sensor signals can be used as a feature. The spectral centers indicate the location of the center of mass of the respective acoustic emission sensor signal. It is calculated as a weighted average of the frequencies present in the respective acoustic emission sensor signal, with the weights being formed by the values of the Fast Fourier Transformation at the respective frequencies. Furthermore, the ratio of the signal to noise can also be used as a feature.Furthermore, additive white Gaussian noise can be added to the acoustic emission sensor signals in the training data to prevent overfitting of the model.
[0203] In summary, a method belonging to the technical field mentioned above for diagnosing a component, in particular a valve, which component is installed in a pipeline designed to conduct a fluid along a flow path in a flow direction, is created using acoustic emission testing. This method enables a more precise and reliable diagnosis of the component. Furthermore, a computer program product for implementing this method is to be created, which enables a more precise and reliable diagnosis of the component.Furthermore, a method for diagnosing a component, in particular a valve, which component is installed in a pipeline, which pipeline is designed to guide a fluid along a flow path in a flow direction, by means of acoustic emission testing is to be created and an arrangement for carrying out the method for diagnosing the component, in particular a valve, by means of acoustic emission testing is to be created, which enables a more precise and reliable diagnosis of the valve.
Claims
Patent claims 1. A method for creating a diagnosis of a component (100), in particular a valve (1000), by means of acoustic emission testing, which component (100) is installed in a pipeline (200, 1200), which pipeline (200, 1200) is designed for guiding a fluid along a flow path in a flow direction (201, 1201), wherein the diagnosis of the component (100) is created taking into account a first acoustic emission sensor signal and a second acoustic emission sensor signal, wherein a distinguishing feature between the first acoustic emission sensor signal and the second acoustic emission sensor signal is taken into account for creating the diagnosis, a) wherein the first acoustic emission sensor signal was output by one of at least one acoustic emission sensor (2.1, 2.2), wherein the respective signal from the at least one acoustic emission sensor (2.1, 2.2) is used to determine the type of acoustic emission sensor used in the diagnosis.2) a first acoustic emission signal has been detected at a first position (51) on the pipeline, wherein the first acoustic emission sensor signal output by the respective at least one acoustic emission sensor (2.1, 2.2) corresponds to the detected first acoustic emission signal, wherein the first position (51, 151) is located at a level of the component (100, 1000) installed in the pipeline (200, 1200) when viewed in the flow direction (201, 1201), b) wherein the second acoustic emission sensor signal has been output by one of the at least one acoustic emission sensors (2.1, 2.2), wherein a second acoustic emission signal has been detected by the respective at least one acoustic emission sensor (2.1, 2.2) at a second position (52, 152) on the pipeline (200, 1200), wherein the signal output by the respective at least one Acoustic emission sensor (2.1, 2.2) the second acoustic emission sensor signal output corresponds to the detected second acoustic emission signal, wherein the second position (52, 152) is located on the pipeline (200, 1200) spaced apart from the first position (51, 151) in the direction of flow (201, 1201) or against the direction of flow (201, 1201) from the first position (51, 151).
2. The method according to claim 1, characterized in that the diagnosis of the component (100) is made taking into account a third acoustic emission sensor signal, wherein the third acoustic emission sensor signal has been output by one of the at least one acoustic emission sensor (2.1, 2.2), wherein a third acoustic emission signal has been detected by the respective at least one acoustic emission sensor (2.1, 2.2) at a third position (53, 153) on the pipeline (200, 1200), wherein the third acoustic emission sensor signal output by the respective at least one acoustic emission sensor (2.1, 2.2) corresponds to the detected third acoustic emission signal.
3. The method according to claim 2, characterized in that, viewed along the flow path, the third position (53, 153) is located on a different side from the first position (51, 151) than the second position (52, 152) is located from the first position (51, 151), whereby, viewed along the flow path, the first position (51, 151) is located between the second position (52, 152) and the third position (53, 153), wherein a distinguishing feature between the first acoustic emission sensor signal and the third acoustic emission sensor signal is taken into account for creating the diagnosis.
4. The method according to one of claims 1 to 3, characterized in that the sound emission signals detected by the at least one sound emission sensor (2.1 , 2.2), in particular by each of the at least one sound emission sensor (2.1, 2.2), are detected over a frequency range, in particular from about 1 kHz to about 1 MHz, preferably from 1 kHz to 1 MHz, particularly preferably from 25 kHz to 500 kHz, most preferably from 25 kHz to 300 kHz.
5. The method according to one of claims 1 to 4, characterized in that, for creating the diagnosis of the component, the sound emission sensor signals are filtered with a pre-filter, wherein the pre-filter comprises a pre-filter criterion, wherein, for creating the diagnosis of the component, the pre-filtered sound emission sensor signals are used as sound emission sensor signals for further processing of the sound emission sensor signals. The method according to any one of claims 1 to 5, characterized in that the state of matter of the fluid and / or the medium of the fluid is taken into account for the diagnosis of the component (100). The method according to any one of claims 1 to 6, characterized in that a pressure difference, in particular a pressure drop, in the pipeline (200, 1200) across the component (100) installed in the pipeline (200, 1200) is taken into account for the diagnosis of the component (100). The method according to any one of claims 4 to 7, characterized in that the acoustic emission sensor signals (105) are evaluated over a sub-range (108) of the frequency range over which the acoustic emission signals are detected for the diagnosis of the component (100).The method according to claim 8 is characterized in that, for the purpose of creating the diagnosis of the component (100), the sound emission sensor signals (105) are evaluated over the sub-range (108) of the frequency range over which frequency range the sound emission signals are detected, by determining at least one characteristic number of the respective sound emission sensor signal for this sub-range (108).The method according to claims 2 and 9, characterized in that the diagnosis of the component (100) is carried out taking into account the first acoustic emission sensor signal and at least two further acoustic emission sensor signals, wherein the first position (51) is located, viewed along the flow path, between the two positions (52, 53, 54, 55) at which two of the at least two further acoustic emission signals have been detected, wherein, if for one of the at least one characteristic number a condition is met according to which one of the at least one characteristic number has a value determined for the sub-area of the first acoustic emission sensor signal which value is between the value determined for the sub-area of one of the two of the at least two further acoustic emission sensor signals and the value determined for the sub-area of the other of the two of the at least two further acoustic emission sensor signals. The determined value lies within the sub-range of the frequency range over which the sound emission signals are detected, and the sound emission sensor signals are shifted to higher frequencies for the purpose of creating the diagnosis of the component (100). The sound emission sensor signals are evaluated over the shifted sub-range of the frequency range over which the sound emission signals are detected by determining at least one characteristic value of the respective sound emission sensor signal for this shifted sub-range. 1.The method according to claim 9 or 10, characterized in that the diagnosis of the component (100) is made taking into account the first acoustic emission sensor signal and at least one further acoustic emission sensor signal, wherein, if for one of the at least one characteristic value a condition is met whereby the one of the at least one characteristic value determined for the sub-range of the first acoustic emission sensor signal has a value which is at least one limit value greater than the value determined for the sub-range of the at least one further acoustic emission sensor signal, the component (100) is diagnosed as defective. 2.The method according to any one of claims 1 to 9, characterized in that, for the purpose of creating the diagnosis of the component, the acoustic emission sensor signals (105) are evaluated over at least two mutually offset region sections (107) of the frequency range over which the acoustic emission signals are detected, by determining at least one characteristic value of the respective acoustic emission sensor signal (105) for each of these at least two mutually offset region sections (107). The method according to claims 2 and 12, characterized in that the diagnosis of the component is created taking into account the first acoustic emission sensor signal and at least two further acoustic emission sensor signals, wherein the first position (151) is located, viewed along the flow path, between the two positions (152, 153) at which two of the at least two further acoustic emission signals have been detected. wherein a classification is carried out on the basis of at least one of the key figures for each of the at least two area sections ( 107) by classifying the respective area section ( 107) as belonging to a first class if and only if a condition is met for one of the at least one key figure according to which one of the at least one key figure determined for the respective area section ( 107) of the first sound emission sensor signal has a value which is greater by at least one classification limit than the value determined for the respective area section ( 107) of one of the two of the at least two further sound emission sensor signals and is greater by at least the classification limit than the value determined for the respective area section ( 107) of the other of the two of the at least two further sound emission sensor signals,or wherein a classification is carried out for each of the at least two area sections (107) based on one of the at least one identifier, by classifying the respective area section (107) as belonging to the first class if and only if a condition is met for one of the at least one identifier, according to which one of the at least one identifier for the respective area section (107) of the first sound emission sensor signal has a value which is at least the classification limit value lower than the value determined for the respective area section (107) of one of the two of the at least two further sound emission sensor signals and is at least the classification limit value lower than the value determined for the respective area section (107) of the other of the two of the at least two further sound emission sensor signals. The method according to claim 13, characterized in that,If a proportion of the at least two area sections (107) has been classified as belonging to the first class, and this proportion is greater than a proportion limit, the component is diagnosed as defective. The method according to one of claims 1 to 14, characterized in that the diagnosis of the component (100) is generated by an evaluation method based on supervised machine learning. A computer program product (5) for carrying out the method according to any one of claims 1 to 15. A method for diagnosing a component (100), in particular a valve (1000), by means of acoustic emission testing, which component (100) is installed in a pipeline (200, 1200), which pipeline (200, 1200) is designed for guiding a fluid along a flow path in a flow direction (201), a) wherein the first acoustic emission signal is detected by one of at least one acoustic emission sensor (2.1, 2.2) at a first position (51, 151) on the pipeline (200, 1200) and by that of the at least one acoustic emission sensor (2.1, 2.2) with which the first acoustic emission signal is detected at the first position (51, 151) on the pipeline (200, 1200), which corresponds to the detected first a) sound emission signal corresponding to the first sound emission sensor signal is output, b) wherein with one of the at least one sound emission sensor (2.1, 2.2) at a second position (52, 152) on the pipeline (200, 1200) the second acoustic emission signal is detected and the second acoustic emission sensor signal corresponding to the second acoustic emission signal is output by the at least one acoustic emission sensor (2.1, 2.2) with which the second acoustic emission signal is detected at the second position (52, 152) on the pipeline (200, 1200), wherein the first acoustic emission sensor signal is transmitted to a diagnostic module (4) connected to the at least one acoustic emission sensor (2.1, 2.2) with which the first acoustic emission signal was detected, for creating the diagnosis of the component (100) and the second acoustic emission sensor signal is transmitted to the module connected to the at least one acoustic emission sensor (2.1, 2.2) with which the first acoustic emission signal was detected.2), with which the second sound emission signal has been detected, connected diagnostic module (4) for creating the diagnosis of the component (100) is transmitted and by means of the diagnostic module taking into account the first sound emission sensor signal and the second sound emission sensor signal the diagnosis of the component (100) is created using the method according to one of claims 1 to 15. The method according to claim 17, characterized in that the third sound emission signal is detected by one of the at least one sound emission sensor (2.1, 2.2) at the third position (53, 153) on the pipeline (200, 1200) and the third sound emission sensor signal corresponding to the third sound emission signal is output by the third sound emission sensor (2.1, 2.2) of the at least one sound emission sensor (2.1, 2.2) with which the third sound emission signal is detected at the third position (53, 153) on the pipeline (200, 1200), wherein the third sound emission sensor signal is output to the third sound emission sensor (2.1, 2.2) with which the third sound emission signal has been detected.connected diagnostic module (4) for creating the diagnosis of the component (100) is transmitted and the diagnosis of the component (100) is created using the diagnostic module with additional consideration of the third sound emission sensor signal using the method according to one of claims 2 to 15. Arrangement (1) for carrying out the method according to 17 or 18, comprising a) at least one acoustic emission sensor (2.1, 2.2) for detecting a first acoustic emission signal at a first position (51, 151) on a pipeline (200, 1200) and outputting a first acoustic emission sensor signal, wherein the first acoustic emission sensor signal corresponds to the detected first acoustic emission signal, for detecting a second acoustic emission signal at a second position (52, 152) on the pipeline (200, 1200) and outputting a second acoustic emission sensor signal, wherein the second acoustic emission sensor signal corresponds to the detected second acoustic emission signal,and b) a diagnostic unit (3) with the diagnostic module (4) for creating the diagnosis of the component (100) taking into account the first sound emission sensor signal and the second sound emission sensor signal, the diagnosis of the component (100) using the method according to one of claims 1 to 15, wherein the diagnostic unit (3) with the diagnostic module (4) for receiving the first sound emission sensor signal is connected to that of the at least one sound emission sensor (2.1, 2.2) with which the first, to detect the sound emission signal, and is connected to receive the second sound emission sensor signal with that of the at least one sound emission sensor (2.1 , 2.2) with which the second sound emission signal is to be detected.
