System and method for detecting problems in turbomachinery by monitoring noise produced by the turbomachinery

Abstract

The innovative system (100) enables detecting problems within a turbomachine by monitoring noise generated by the turbomachine as the turbomachine operates, and includes at least one microphone (110) disposed in an area where the turbomachine is installed and operating, configured to capture noise generated by the turbomachine and propagating through the surrounding ambient air, an input interface (150) configured to receive signals generated by the at least one microphone (110), an output interface (170) configured to signal when a problem within the turbomachine is detected, and an electronic processing unit (130) electrically coupled to the input interface (150) and the output interface (170) and configured to process the input signal received from the input interface (150) and generate an output signal for the output interface (170). The processing of the input signal includes the steps of: a) determining an acoustic power value from the received input signal; b) comparing the determined acoustic power to at least a first power value; and c) determining an output value for the output signal associated with a difference between the determined acoustic power and the at least first power value. The processing of the received input signal by the electronic processing unit is carried out simultaneously through a set of algorithms, the algorithms of the set being of different types.

Description

[Technical Field]

[0001] The subject matter disclosed herein relates to systems and methods for detecting problems in turbomachinery. [Background technology]

[0002] During operation of a turbomachine, its components are subject to wear and / or deterioration, which typically leads to a decrease in performance and ultimately can result in damage to the turbomachine, and / or to other machinery adjacent to or coupled to the turbomachine, and / or to the environment surrounding the turbomachine.

[0003] It is therefore desirable to have a system for detecting problems in turbomachinery, for example in oil and gas applications, particularly before serious performance degradation and / or serious damage occurs.

[0004] Furthermore, it would be desirable to use the noise generated by the turbomachine to detect problems in an easy way, in particular without dismantling the turbomachine, as is known for example from US Pat. No. 6,507,790 (B1) or WO 2004 / 017038 (A1).

[0005] In accordance with the subject matter disclosed herein, detecting a problem does not necessarily mean identifying a particular worn or degraded part of a turbomachine, and even less means identifying the root cause of the problem, even though it may be desirable to identify both the worn or degraded part and possibly the root cause. Summary of the Invention

[0006] According to a first aspect, the subject matter disclosed herein relates to a system that enables detecting problems within a turbomachine by monitoring noise generated by the turbomachine as the turbomachine operates. The system includes at least one microphone disposed in an area where the turbomachine is installed and operated, configured to capture noise generated by the turbomachine and propagating through the surrounding ambient air; an input interface configured to receive signals generated by the at least one microphone; an output interface configured to signal when a problem within the turbomachine is detected; and an electronic processing unit electrically coupled to the input interface and the output interface and configured to process the input signal received from the input interface and generate an output signal for the output interface. The processing of the input signal includes: a) determining an acoustic power value from the received input signal; b) comparing the determined acoustic power to at least a first power value; and c) determining an output value of the output signal associated with a difference between the determined acoustic power and the at least first power value. The electronic processing unit is configured to perform at least these steps when processing the received input signal, thereby simultaneously processing the received input signal through different sets of algorithms.

[0007] According to a second aspect, the subject matter disclosed herein relates to a problem detection method that allows detecting problems in a turbomachine by monitoring noise generated by the turbomachine and propagating through the surrounding ambient air as the turbomachine operates. The method includes the steps of: a) determining an acoustic power value from the noise generated by the turbomachine; b) comparing the determined acoustic power with at least a first power value; and c) determining an output associated with a difference between the determined acoustic power and the at least first power value. Preferably, a set of algorithms are used simultaneously, the algorithms of the set being different or of different types.

[0008] According to a further aspect, the subject matter disclosed herein relates to a turbomachinery system including at least a turbomachine and an innovative problem detection system.

[0009] It should be noted that, according to the subject matter disclosed herein, once a problem is detected, it may be possible to take further steps to identify the specific worn or deteriorated part of the turbomachine and, in some cases, identify the root cause of the problem. In some cases, the relationship between the detected problem and the specific worn or deteriorated part is direct, while in other cases, further investigation is required. [Brief explanation of the drawings]

[0010] A more complete understanding of the disclosed embodiments of this invention and many of the attendant advantages thereof will be readily obtained as the same become better understood by reference to the following detailed description when considered in connection with the accompanying drawings. [Figure 1] FIG. 1 is a schematic block diagram of one embodiment of an innovative problem detection system. [Figure 2] 1 is a schematic block diagram of an embodiment of an innovative turbomachinery device; [Figure 3] 1 is a flow chart of one embodiment of an innovative problem detection method. DETAILED DESCRIPTION OF THE INVENTION

[0011] As a turbomachine operates, it generates sound emissions, i.e., acoustic waves, commonly referred to as “noise,” because they are annoying to any person located in the area in which the turbomachine is installed and operates. A turbomachine can become noisier if it has a problem, for example, if a portion of the turbomachine, such as a bearing, is damaged or broken. By monitoring the noise generated by the turbomachine and propagating through the surrounding ambient air, it is possible to detect a problem, or at least some problems or types of problems, within the turbomachine. Detecting a problem does not necessarily mean identifying a specific worn or deteriorated part of the turbomachine, and even less means identifying the root cause of the problem, even though it may be desirable to identify both the worn or deteriorated part and possibly the root cause. The innovative system and method take advantage of such considerations regarding the noise generated by the turbomachine during operation and propagating through the surrounding ambient air.

[0012] The above-mentioned sound emissions should not be confused with vibrations generated by turbomachinery and propagated within the machine, for example, by machine components. Sound emissions are detected by microphones located away from the machine, and vibrations are measured by sensors attached to the machine. Using sound emissions and using vibrations correspond to two different approaches to problem detection. The first approach aims for global detection, while the second approach aims for specific detection. For the first approach, only one microphone is sufficient, while for the second approach, several sensors are required. The first approach may be considered less accurate than the second approach. However, through the technical teachings disclosed herein, effective problem detection can be achieved through a noise (i.e., sound) capture system that is relatively simple from a hardware perspective.

[0013] Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the drawings. The examples and drawings are provided as an explanation of the present disclosure and should not be construed as limiting the disclosure. Indeed, it will be apparent to those skilled in the art that various modifications and variations can be made to the present disclosure without departing from the scope or spirit of the present disclosure. In the following description, like reference numerals are used in the illustrative figures of the embodiments to indicate elements that perform the same or similar functions. Moreover, for clarity of illustration, some reference numerals may not be repeated in all figures.

[0014] FIG. 1 shows a schematic diagram of an embodiment of an innovative problem detection system 100. The system 100 essentially includes at least one microphone 110 and an electronic processing unit 130. In FIG. 1, multiple microphone devices 110A, 110B, ... 110Z are shown to enable more accurate and reliable problem detection. Their number can vary, for example, from two to twenty. However, even a larger number should not be excluded. The microphone or microphones are arranged in an area (see reference numeral 270 in FIG. 2) where a turbomachine (not shown in FIG. 1) is installed and operates, and are configured to capture noise, i.e., acoustic waves, generated by the turbomachine and propagating through the ambient air around the turbomachine. Such an area may be a test environment or an operating environment. The noise captured by the microphones may have a frequency ranging from 20 Hz (or even lower, for example, 5 or 10 Hz) to 20 KHz (or even higher, for example, 30 or 50 KHz). Depending on the particular embodiment of the innovative system, the frequency range may be different, for example, 20 Hz to 20 kHz, or 20 Hz to 2 kHz, or 200 Hz to 20 kHz, or 50 Hz to 5 kHz.

[0015] It should be noted that the word "turbomachine" typically refers to machines that process fluids, such as compressors or expanders, but also to so-called "auxiliary equipment," i.e., other secondary machines that are associated with the primary machine and perform secondary functions. Noise can originate from the primary machine and from associated secondary machines, and according to some embodiments, can be captured by the innovative system.

[0016] Additionally, the system 100 of FIG. 1 includes an input interface 150 electrically coupled to the microphone 110 and configured to receive a microphone signal generated by the microphone 110, and an output interface 170 configured to signal when a problem within the turbomachine is detected.

[0017] Electronic processing unit 130 is electrically coupled to input interface 150 and output interface 170. Electronic processing unit 130 is configured to receive input signals from input interface 150, process the received input signals, generate output signals based on the received input signals, and send the generated output signals to output interface 170.

[0018] The output signal is associated with a detected problem within the turbomachine. If no problem is identified through the processing performed by unit 130, then no output signal is generated, or a specific output signal is generated that conveys the information that there is no problem with the turbomachine. If a problem is identified through the processing performed by unit 130, then an appropriate output signal may be generated and sent to interface 170, for example to notify an operator, for example through emitting a sound and / or emitting a light and / or displaying a message and / or sending a data packet. If two problems are identified through the processing performed by unit 130, then two appropriate output signals may be generated and sent to interface 170, or a single output signal is generated that conveys the information that there are two problems with the turbomachine.

[0019] Typically, the electronic processing unit 130 is a computer or controller including a processor 132, a data memory 134 for storing input and output data, and a program memory 136 for storing one or more programs. The processing performed by the processor depends on the programs stored in the program memory 136. Generally, the electronic processing unit 130 also includes an input / output interface (not shown in FIG. 1 ) for interacting with a user. Note that the processing performed by the unit 130 may also depend on input received by a user, who may, for example, select one or more programs in the program memory 136 and / or enter parameters that at least partially define the specifics of the processing to be performed. The signals received by the unit 130 from the interface 150 may be digital or analog. In the latter case, an analog-to-digital conversion circuit may be included in the unit 130. The signals transmitted by the unit 130 to the interface 170 may be digital or analog. In the latter case, a digital converter circuit may be included in the unit 130.

[0020] The electronic processing unit 130 is configured to receive input signals, process the received input signals, generate output signals based on the received input signals, and transmit the generated output signals. Such processing of the input signals generally involves: a) determining an acoustic power value from a received input signal; b) comparing the determined sound power with at least a first power value; c) determining an output value of the output signal that is associated with a difference between the determined acoustic power and the at least first power value.

[0021] These are the minimum steps that the innovative unit is configured to perform when processing a received input signal. As will become clear below, the innovative unit may advantageously be configured (for example by means of a program stored in its program memory) to simultaneously perform a larger set of algorithms, in particular of different types.

[0022] In fact, the electronic processing unit 130 simultaneously processes the received input signal through different sets of algorithms. This means that during the same time frame (e.g., 1 m, 1 s, or 1 ms), the processing of the same input signal is performed according to multiple algorithms. Two different algorithms can be designed to detect two different problems, or to detect the same problem in different ways. In the latter case, if both algorithms lead to the conclusion that a problem exists, it is more likely that a problem exists; if both algorithms lead to the conclusion that a problem does not exist, it is less likely that a problem exists; and if the two algorithms lead to two different conclusions, a criterion is used to determine the existence of a problem.

[0023] Generally, the input signal can be divided into successive time frames (which can be called "periods") of equal duration, typically 1 m, 1 s, or 1 ms. Portions of the input signal corresponding to the time frames (which can be sampled at several successive times within the time frame and continuously digitized) are processed within the time frames according to multiple algorithms. Typically, the time frame during which signal detection (and possibly sampling and possibly digitization) occurs differs from the time frame during which signal processing occurs, with the first time frame preceding the second. According to the first possibility, the algorithms execute in true parallel during the same time frame; that is, they start and end at approximately the same time. According to the second possibility, they execute one after the other, but still within the same time frame. Therefore, they can be said to be effectively parallel. Raw data, e.g., corresponding to the input signal, can be temporarily stored in volatile memory for simultaneous processing or permanently stored in non-volatile memory, e.g., on a disk, for offline detailed analysis. Such data, e.g., raw data, can be retained in memory until a complete diagnosis is completed.

[0024] As mentioned above, the algorithms in this set are of different types. For example, if this set consists of two algorithms, they may operate in two different frequency bands (e.g., two narrow bands or two wide bands or one narrow band and one wide band) (e.g., two fixed bands or two variable bands or one fixed band and one variable band), they may operate in the same or different ways, without considering the preceding time frame or by considering one or more preceding time frames, and they may operate using two different calculations (e.g., two different mathematical formulas). The possible combinations of types are many. The use of different algorithms should not be confused with using the same calculation (e.g., mathematical formula) but different parameters. It is possible for the first algorithm to perform analysis in the frequency domain and the second algorithm to perform analysis in the time domain. Analysis in the frequency domain may require applying an FFT (Fast Fourier Transform) or DFT (Discrete Fourier Transform) to the input signal or a portion of the input signal.

[0025] When using several different algorithms, it can be advantageous to assign different weights to each of them, especially if they are used to detect the same problem. One possibility is, for example, combining the results of the algorithms via a linear combination using different weights. The output signal (generated or transmitted) described above can be mathematically related to such a combination. For example, a first algorithm may be more reliable than a second algorithm in detecting the same specific problem, but using both in combination increases reliability. For example, a first algorithm may detect two different problems, while a second algorithm may only be able to detect one of these two different problems; therefore, using them in combination (think of them as a "decision criterion") can help more reliably identify the problem at hand.

[0026] The electronic processing unit may be configured to run a further algorithm based on the result(s) of one(or more) algorithms of the set. For example, if the results do not appear to be sufficiently reliable, another algorithm may be run later. For example, if two algorithms lead to two different conclusions, running a third algorithm and considering its results may be considered a "decision criterion."

[0027] In general, the decision criteria may also take into account the security impact of the detected problem: for example, a reliable detection of a dangerous problem may cause a bypass of all other algorithms and generate an immediate warning.

[0028] The above-mentioned first power value may be, for example, a maximum value of the acoustic power. In other words, the processing may consist in checking whether the power of the noise generated by the turbomachine at a particular time exceeds a predetermined value. Alternatively, the above-mentioned first power value may be, for example, an average value of the acoustic power. In other words, the processing may consist in checking whether the power of the noise generated by the turbomachine in a particular time frame exceeds a predetermined value.

[0029] According to an alternative example, the processing performed by unit 130 may, in step "b", compare the determined sound power with at least a first power value and a second power value, and in step "c", the output value may be related to the difference between the determined sound power and the at least the first power value and / or the second power value. For example, the first power value may correspond to the expected mean of the noise power plus the expected variance of the noise power, and the second power value may correspond to the expected mean of the noise power minus the expected variance of the noise power. In other words, the processing may consist in checking whether the power of the noise generated by the turbomachine at a particular time within a particular time frame is within a predetermined power range.

[0030] In step "c", the output value may be a binary value. A problem is either detected (e.g., the noise level is above a certain threshold) or not detected (e.g., the noise level is below a certain threshold). Alternatively, the output value may be multi-valued or continuous. For example, the output value corresponds to the difference between the determined sound power and the first power value, or a discretization of such difference. In this case, the output value may indicate the severity of the problem.

[0031] In step "c", the output value may be related to the difference between the determined acoustic power within the time frame and at least the first power value. In other words, the processing may consist in checking whether the power of the noise generated by the turbomachine exceeds a predetermined value for a certain amount of time, i.e. within the time frame. This is useful, for example, to avoid taking into account momentary or short noise peaks.

[0032] In step "a", the acoustic power value may be determined from the bandwidth of the received input signal. In other words, before the processing of the input signal is carried out by the electronic processing unit, the input signal may be filtered, in particular band-pass filtered. This is useful, for example, to avoid considering frequencies that may not be attributable to a particular problem or type of problem of the turbomachine under observation.

[0033] Advantageously, the received input signal may be filtered by a set of bandpass filters, and for each bandwidth a separate processing is performed (through the same algorithm or through a different algorithm) (see the embodiment of FIG. 3, in particular blocks 320 and 330, 330′ and 330″) to determine in particular a separate sound power value. This is useful, for example, when a first problem causes noise within a first fixed, predetermined bandwidth and a second problem causes noise within a second fixed, predetermined bandwidth. The two problems are considered to have two different “acoustic signatures”, and the same algorithm is used to determine the acoustic signature and compare it to known acoustic signatures (as in U.S. Pat. No. 6,507,790 B1).

[0034] According to some embodiments, the system may be configured to determine the current rotational speed of the turbomachine (see the embodiment of FIG. 3 , in particular block 336), and the processing of the input signal may depend on the determined current rotational speed. This is useful, for example, when monitoring turbomachines. Indeed, in this case, noises typically generated during normal operation have peaks at a first frequency corresponding to the rotational speed, a second frequency corresponding to twice the rotational speed, etc., and it is desirable not to confuse the "normal noise" with the "problem noise." In this case, the "normal noise" can be filtered out. Naturally, the processing becomes more complex when considering variable rotational speeds of the turbomachine. The determination of the rotational speed may be derived from a rotational speed sensor associated with the turbomachine, or from input signals coming from a system associated with the turbomachine and knowing the rotational speed, or from software processing input signals (e.g., audio input signals from an appropriately positioned microphone device).

[0035] The first power value and / or the second power value may depend on the determined current rotational speed. In other words, the comparison in step "b" may be adjusted to take into account "normal noise" due to rotation. Such adjustment may change from time to time, i.e., as the rotational speed of the turbomachine changes. An algorithm that takes rotational speed into account is of a different type than an algorithm that ignores rotational speed.

[0036] Advantageously, in step "a", the received input signal is preliminarily filtered by suppressing environmental noise, which may for example be determined via at least one appropriately positioned and oriented microphone device.

[0037] The processing of the received input signals by the electronic processing unit may be performed in parallel through several different algorithms. This may be useful when there is interest in different specific problems or types of problems detected in the same turbomachine. Various algorithms may have different importance, e.g., different weights, in a complex diagnostic system. One or more of the algorithms may, for example, be dedicated to or take into account noise generated by so-called "auxiliary equipment."

[0038] Advantageously, the system may be configured to determine a current operating mode of the turbomachine or a device including the turbomachine, and the processing of the received input signal by the electronic processing unit may depend on the determined current operating mode. This is useful because the turbomachine or turbomachinery device generates different "normal noises" in different operating modes. If the operating mode is known in some way (e.g., from input signals received from the turbomachine control unit), it is easier to avoid confusing the "normal noises" with the "problem noises." The algorithms used to process the received input signals may depend, for example, on the current operating mode. For example, one or more algorithms may be used in a first operating mode and one or more algorithms may be used in a second operating mode. One or more algorithms may be used in both operating modes.

[0039] Advantageously, the system may be configured to determine a current operating mode of the turbomachine or a device including the turbomachine, and the signaling by the system may depend on the determined current operating mode. This is useful because in a first operating mode, a noise may be considered "normal," while in a second operating mode, the same noise may be considered "problematic."

[0040] It may be provided that problem signaling is disabled in one or more operating modes, or more generally, problem signaling may differ for each operating mode.

[0041] Advantageously, the electronic processing unit may be configured to determine at least a particular problem with the turbomachine from the noise produced by the turbomachine, and the notification by the system may include information about at least the particular problem. Indeed, it should be expected that one or more particular problems may be easier to determine, while other problems may be easily detected but not determined.

[0042] As mentioned at the beginning of the detailed description, an innovative system may include a set of microphones (identical or different). For example, system 100 of FIG. 1 includes a set of microphone devices 110A, 110B, and 110Z. The microphones may be appropriately positioned and / or oriented relative to the turbomachine, and typically, each of them is separated (e.g., by a distance of 1 to 10 m) from the turbomachine or a noisy component of the turbomachine (although the distance is generally not the same for each microphone). As already mentioned, there may be additional microphones dedicated to detecting environmental noise. One or more dedicated algorithms can be used to extract the environmental noise from the microphone signals without using a dedicated microphone.

[0043] In this case, the signals from these microphone devices may be suitably processed and / or combined by an input interface and / or electronic processing unit.

[0044] In general, the electronic processing unit may be pre-trained. The training may be related to the particular turbomachine or turbomachine installation being monitored and / or the particular problem or type of problem being detected and / or the particular problem or type of problem being determined. It should be noted that this may apply to multiple particular problems or types of problems. The training may also be related to different delays and / or phase shifts and / or amplifications or attenuations used to process signals coming from separate microphones. This is particularly important when the noise generated by the turbomachine can be considered to come from separate noise sources located at (relatively) distant points. In other words, the training takes into account the particular positioning of the microphones and / or the particular positioning of the noise sources. It should be noted that such training may be repeated for different frequencies of the generated noise or for different frequency bandwidths of the generated noise. It should be noted that such training may be repeated for different operating modes of the turbomachine being observed.

[0045] The innovative problem detection system may be associated with a turbomachine. In this case, one can consider an innovative turbomachine arrangement 1000 comprising a turbomachine 200 and a system 100 for detecting problems with the turbomachine 200 as it operates by monitoring noises (schematically indicated by arrows 250 in FIG. 2 ) generated by the turbomachine 200 within an area 270 (closed or open) in which the turbomachine 200 is installed and operates, as shown in FIG. 2. Preferably, only one turbomachine should be associated with the innovative problem detection system, otherwise it would be difficult for the system to understand which turbomachine is the subject of the problem.

[0046] As previously mentioned, according to one aspect, the subject matter disclosed herein relates to a problem detection method that enables detecting a problem in a turbomachine by monitoring noise generated by the turbomachine as the turbomachine operates. As previously mentioned, the method includes at least the steps of: a) determining an acoustic power value from the noise generated by the turbomachine; b) comparing the determined acoustic power to at least a first power value; and c) determining an output power associated with a difference between the determined acoustic power and the at least first power value.

[0047] Figure 3 shows a flowchart 300 incorporating an embodiment of the innovative method. The method begins at START block 310 and ends at STOP block 390. Block 310 may provide for receiving one (or more) input signals from a microphone device, or may assume that one (or more) input signals have already been received before the method of Figure 3 begins. Block 390 may provide for transmitting an output signal, or may assume that an output signal is transmitted after the method of Figure 3 ends.

[0048] According to the embodiment of FIG. 3, the input signal is optionally filtered by three bandpass filters having three different bandwidths (block 320). The output of each filter is processed, preferably in parallel, and preferably in two or three different ways, by blocks 330, 330′, and 330″, respectively. Only one of these three blocks is shown in detail in FIG. 3.

[0049] After blocks 330, 330', and 330'', control passes to block 340, which corresponds to determining an output value related to problem detection. In the embodiment of FIG. 3, the determination is based on the processing outputs from blocks 330, 330', and 330''.

[0050] At block 330, steps are provided for determining an acoustic power value from the noise generated by the turbomachine (block 332) and comparing the determined acoustic power to at least a first power value (block 334).

[0051] In the embodiment of FIG. 3, there is also provided a step of determining the rotational speed of the turbomachine (block 336) and using such information in the comparing step (block 334).

[0052] In the embodiment of FIG. 3, for example, the processing in blocks 330′ and 330″ may not be based on a determination of rotation rate, unlike block 330. According to alternative embodiments of the embodiment of FIG. 3, the processing in blocks 330′ and 330″ may be based on the same bandwidth or on overlapping bandwidths.

Claims

1. 1. A system (100) for detecting problems in a turbomachine by monitoring noise produced by the turbomachine as the turbomachine operates, comprising: at least one microphone (110) arranged in an area (270) in which said turbomachine is installed and operates, said at least one microphone (110) being configured to capture noise generated by said turbomachine and propagated through the ambient air; an input interface (150) electrically coupled to the at least one microphone (110), the input interface (150) being configured to receive a signal generated by the at least one microphone (110); an output interface (170) configured to signal when a problem in said turbomachine is detected; an electronic processing unit (130) electrically coupled to the input interface (150) and the output interface (170), the electronic processing unit (130) configured to receive input signals from the input interface (150), process the received input signals, generate output signals based on the received input signals, and transmit the generated output signals to the output interface (170), the output signals being associated with detected problems in the turbomachine; The electronic processing unit, when processing the received input signal, a) determining an acoustic power value from a received input signal; b) comparing the determined acoustic power to at least a first power value; c) determining a power value of an output signal, the power value being related to a difference between the determined acoustic power and at least the first power value; A system (100) wherein the processing of the received input signal by the electronic processing unit is performed simultaneously through a set of algorithms, the algorithms of the set being of different types.

2. 2. The system according to claim 1, wherein the algorithms of the set have different importance, in particular different weights, in generating an output signal and / or in transmitting an output signal.

3. The system of claim 1 , wherein the electronic processing unit is configured to execute a further algorithm based on the results of the set of algorithms.

4. The system of claim 1 , wherein the output value is associated with a difference between the determined acoustic power and at least the first power value within a time frame.

5. The system of claim 1 , wherein the sound power value is determined from a bandwidth of a received input signal.

6. the system is configured to determine a current rotational speed of the turbomachine; The system of claim 1 , wherein the processing of the received input signal depends on the determined current rotational speed.

7. the system is configured to determine a current operating mode of the turbomachine or a current operating mode of a device including the turbomachine; The system of claim 1 , wherein the processing of the received input signal by the electronic processing unit depends on the determined current operating mode.

8. the electronic processing unit is configured to determine at least a specific problem with the turbomachine from noise generated by the turbomachine; The system (100) of claim 1, wherein the system signal includes at least information regarding the particular problem.

9. the determined acoustic power is compared to at least a first power value and a second power value; The system of claim 1 , wherein the output value is associated with a difference between the determined acoustic power and at least the first power value and / or the second power value.

10. The system of claim 5 , wherein additional sound power values ​​are determined from other bandwidths of the received input signal.

11. The system of claim 6 , wherein the first power value and / or the second power value is dependent on the determined current rotation speed.

12. The system of claim 1 , wherein the received input signal is pre-filtered by suppressing environmental noise.

13. The system of claim 12 , wherein the environmental noise is determined via at least one microphone.

14. the system is configured to determine a current operating mode of the turbomachine or a current operating mode of a device including the turbomachine; The system of claim 1 , wherein the signaling by the system is dependent on the determined current operating mode.

15. 15. The system of claim 14, wherein signaling is disabled in one or more modes of operation.

16. The system of claim 1 , wherein the system comprises a set of microphones.

17. The system of claim 1 , wherein the electronic processing unit is pre-trained.

18. A turbomachinery device (1000), comprising: a turbomachine (200), a system (100) for detecting problems in the turbomachine (200) by monitoring noise (250) generated by the turbomachine (200) and propagating through the ambient air when the turbomachine (200) is operating.

19. 1. A method (300) for detecting problems in a turbomachine by monitoring noises generated by the turbomachine as the turbomachine operates, comprising: a) determining (332) an acoustic power value from the noise generated by the turbomachine and propagated through ambient air; b) comparing the determined acoustic power to at least a first power value (334); c) determining (340) a power associated with a difference between the determined acoustic power and at least the first power value; Preferably, a set of algorithms is used simultaneously, said algorithms of said set being different or of different types, method (300).

Images