Thermoelectric equipment vibration fault online monitoring method and system
By performing segmented analysis and feature calculation of the vibration signals of thermoelectric equipment, the problem of low accuracy of vibration fault monitoring under the influence of electromagnetic interference is solved, and accurate judgment and monitoring of steam turbine faults is achieved.
Patent Information
- Application Number
- CN202510277278.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-10
- Publication Date
- 2025-06-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Thermoelectric equipment is susceptible to electromagnetic interference during operation, resulting in low accuracy in the acquisition and monitoring of vibration signals, making it difficult to accurately judge the vibration characteristics of turbine failures.
By obtaining the vibration signals at each preset bearing shell of the thermoelectric equipment, it is divided into two parts, and its waveform change factor, amplitude discrimination value and frequency response are analyzed. Based on these characteristics, the thermoelectric equipment failure factor is calculated to determine the cause of the fluctuation of the vibration signal.
It effectively eliminates the impact of electromagnetic interference on monitoring results, improves the accuracy of vibration fault monitoring of thermoelectric equipment, and can accurately judge the vibration characteristics of turbine faults.
Smart Images
Figure CN120102139A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of vibration fault monitoring, and in particular to an online monitoring method and system for vibration faults of thermoelectric equipment. Background Art
[0002] Thermoelectric equipment refers to equipment that can convert thermal energy into electrical energy or generate both electricity and thermal energy. Common thermoelectric equipment includes boilers, steam turbines, generators, etc. Thermoelectric equipment will generate mechanical vibration during operation, which is a manifestation of normal operation, but excessive vibration will cause equipment failure and safety hazards. Therefore, it is very necessary to monitor the vibration of thermoelectric equipment.
[0003] By monitoring the vibration status of the equipment, equipment failures, abnormal vibrations and structural problems can be discovered in time, the health status of the equipment can be predicted, and equipment failures and production interruptions can be avoided. When monitoring the vibration of equipment, the vibration levels of different equipment are different. For the same vibration level, it may perform normally on one device, but may fail on another device. Therefore, it is necessary to design a vibration monitoring method in a targeted manner according to the vibration characteristics of each device. When monitoring vibration faults of steam turbines, environmental factors such as electromagnetic fields may interfere with the transmission and collection of vibration signals, and electrical noise may cover up or confuse useful information in the vibration signals, resulting in low accuracy in vibration monitoring of steam turbine faults. Summary of the invention
[0004] In view of the above, it is necessary to provide a method and system for online monitoring of vibration faults of thermoelectric equipment to solve the above problems.
[0005] The first aspect of the present application provides a method for online monitoring of vibration faults of thermoelectric equipment, the method comprising:
[0006] Obtaining the vibration signal of each preset bearing of the thermoelectric device to be monitored at each sampling time;
[0007] The sequence composed of the vibration signals of each preset bearing at each sampling moment and a preset number of sampling moments before is divided into two parts, and the first sequence and the second sequence at each sampling moment are obtained; according to the distribution difference between the first sequence and the second sequence at each sampling moment, the waveform change factor at each sampling moment is obtained, and the vibration fluctuation moment is obtained;
[0008] According to the element change characteristic distribution of the differential sequence of the first sequence at each vibration fluctuation moment, the amplitude discrimination value at each vibration fluctuation moment is obtained; based on the frequency response of the first sequence and the second sequence at each vibration fluctuation moment in the frequency domain, combined with the amplitude discrimination value, the thermoelectric device failure factor at each vibration fluctuation moment is obtained;
[0009] Based on the failure factor of the thermoelectric device, monitoring results of each preset bearing of the thermoelectric device at each sampling time are obtained.
[0010] The first sequence and the second sequence at each sampling time are obtained as follows:
[0011] Arrange the vibration signals of each preset bearing at each sampling moment and a preset number of sampling moments before in reverse order in time sequence as a vibration sequence at each sampling moment;
[0012] For the vibration sequence, a sequence consisting of all vibration signals corresponding to the rounded value of half of the preset number at each sampling moment is taken as the first sequence; and a sequence consisting of the remaining vibration signals is taken as the second sequence.
[0013] The waveform change factor at each sampling moment is obtained by measuring the distance between the first sequence and the second sequence at each sampling moment.
[0014] The step of obtaining the vibration fluctuation moment is as follows:
[0015] Calculate the Z-score value of the fluctuation change factor at each sampling moment in the corresponding vibration sequence. When the Z-score value is greater than the set value, the corresponding sampling moment is taken as the vibration fluctuation moment.
[0016] The amplitude discrimination value obtained at each vibration fluctuation moment is specifically:
[0017] According to the change characteristics of the adjacent elements of the first sequence at each vibration fluctuation moment, a counting sequence at each vibration fluctuation moment is obtained;
[0018] The amplitude discrimination value of each vibration fluctuation moment is recorded as E, and its formula is: Among them, t 1 represents the average value of all elements in the counting sequence at each vibration fluctuation moment; x 0 、x i Respectively represent the values of the first element and the last element in the first sequence at each sampling time; exp() represents an exponential function with a natural constant as the base; r 1 Represents the total number of elements in the counting sequence at each sampling moment; σ is a preset parameter.
[0019] The counting sequence of each vibration fluctuation moment is obtained as follows:
[0020] The first-order difference sequence of the first sequence at each vibration fluctuation moment is obtained, and the parts of the first-order difference sequence whose elements are continuously positive, continuously negative, and continuously zero are used as different data segments, and the sequence composed of the number of data in each data segment in the first-order difference sequence of the first sequence is used as a counting sequence.
[0021] The failure factor of the thermoelectric device at each vibration fluctuation moment is obtained as follows:
[0022] Obtaining the bandwidth difference between the first sequence and the second sequence at each vibration fluctuation moment;
[0023] Calculate the forward fusion results of the phase differences corresponding to all the same frequencies in the frequency responses of the first sequence and the second sequence at each vibration fluctuation moment;
[0024] Based on the bandwidth difference, the forward fusion result, the amplitude discrimination value and the fundamental frequency energy intensity of the first sequence at each vibration fluctuation moment, the thermoelectric equipment failure factor at each vibration fluctuation moment is obtained; wherein the thermoelectric equipment failure factor is negatively correlated with the bandwidth difference, and positively correlated with the forward fusion result, the amplitude discrimination value and the fundamental frequency energy intensity.
[0025] The specific calculation method of the thermoelectric device failure factor is as follows: the bandwidth difference is recorded as D, the forward fusion result is recorded as S, the fundamental frequency energy intensity is recorded as e, and the amplitude discrimination value is recorded as E. The formula form of the thermoelectric device failure factor is: Where W represents the failure factor of the thermoelectric device; norm() is the normalization function; exp() represents the exponential function with a natural constant as the base.
[0026] The process of obtaining the monitoring results of each preset bearing of the thermoelectric device at each sampling time is specifically as follows:
[0027] When the sampling moment is judged to be a vibration fluctuation moment, if the value of the thermoelectric device fault factor is greater than a preset threshold, the vibration signal corresponding to the sampling moment is regarded as a fault signal; otherwise, the vibration signal corresponding to the sampling moment is regarded as a normal signal.
[0028] In the second aspect, an embodiment of the present application also provides an online monitoring system for vibration faults of thermoelectric equipment, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above methods are implemented.
[0029] In the above scheme, the vibration fault monitoring process of the thermoelectric equipment is easily interfered by other electrical equipment, resulting in the problem that the collected vibration signal cannot accurately reflect the actual operating status of the steam turbine: first, the vibration signal is collected and divided into two parts, so as to facilitate the subsequent analysis of the fluctuation difference of the vibration signal in the recent period and the previous period; according to the distribution difference between the first sequence and the second sequence at each sampling moment, the waveform change factor at each sampling moment is obtained, the fluctuation characteristics of the vibration signal are analyzed, and the time when the vibration signal fluctuates is obtained; further, according to the element change characteristics of the differential sequence of the first sequence at each vibration fluctuation moment, The characteristic distribution is used to obtain the amplitude discrimination value at each vibration fluctuation moment, so as to facilitate the subsequent judgment of whether the thermoelectric device is faulty according to the amplitude characteristics of the thermoelectric device; based on the frequency response of the first sequence and the second sequence in the frequency domain at each vibration fluctuation moment, combined with the amplitude discrimination value, the failure factor of the thermoelectric device at each vibration fluctuation moment is obtained, which has the beneficial effect of analyzing the amplitude characteristics, frequency characteristics, phase characteristics and periodic characteristics of the vibration signal when the thermoelectric device has a vibration failure and electromagnetic interference, and judging whether the cause of the vibration signal fluctuation is a turbine vibration failure or electromagnetic interference, thereby eliminating the influence of electromagnetic interference on the monitoring results and improving the accuracy of vibration fault monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 A flowchart of a method for online monitoring of vibration faults of thermoelectric equipment provided by one embodiment of the present application;
[0031] Figure 2 A schematic diagram of obtaining a failure factor of a thermoelectric device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0032] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.
[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.
[0034] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of protection of the present application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.
[0035] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0036] The specific scheme of a method and system for online monitoring vibration faults of thermoelectric equipment provided by the present application is described in detail below with reference to the accompanying drawings.
[0037] See also Figure 1 , which shows a flowchart of a method for online monitoring of vibration faults of thermoelectric equipment provided by an embodiment of the present application, the method comprising the following steps:
[0038] The first step is to obtain the vibration signal of each preset bearing of the thermoelectric device to be monitored at each sampling moment.
[0039] This application mainly analyzes thermal power generation equipment with rotating parts. This embodiment takes the steam turbine as an example for the following analysis: the bearing is a key component that supports the rotation of the steam turbine rotor. The vibration generated by the rotor during rotation will be directly transmitted to the bearing, and the bearing is connected to the bearing. When a vibration failure occurs in the bearing, the vibration of the bearing will also be transmitted to the bearing. Therefore, this application installs the smart sensor at the front and rear bearings of the steam turbine, respectively, wherein the smart sensor refers to a vibration sensor. By installing a vibration sensor at the bearing, these vibration signals can be captured in real time, and then the vibration failure of the steam turbine can be monitored. The vibration signal collected by the vibration sensor is an analog signal. In order to facilitate subsequent analysis, the analog signal needs to be sampled according to the sampling frequency F and converted into a digital signal. The setting of the sampling frequency must satisfy the Nyquist sampling theorem. In this embodiment, F is 50Hz.
[0040] The vibration signal is used as the input of the median filter algorithm to denoise the vibration signal. The median filter algorithm is a well-known technology, and the specific process will not be repeated here.
[0041] The second step: divide the sequence composed of the vibration signals of each preset bearing at each sampling moment and the previous preset number of sampling moments into two parts, and obtain the first sequence and the second sequence at each sampling moment; according to the distribution difference between the first sequence and the second sequence at each sampling moment, obtain the waveform change factor at each sampling moment, and obtain the vibration fluctuation moment.
[0042] When the steam turbine unit is running at a constant speed and under load, the rotor has a high operating temperature and is subjected to large centrifugal stress, which makes it easy to bend and deform. The thermal bending of the rotor will cause unbalanced force, which will lead to vibration failure. When the base of the bearing is not fixed firmly, the bearing will also have vibration failure. The bearing not only supports the rotor, but also connects the bearing. By real-time monitoring of the vibration signal at the bearing, the thermal bending failure of the rotor and the bearing vibration failure of the steam turbine can be discovered in time. However, in the process of collecting vibration signals, the electrical equipment around the steam turbine will generate electromagnetic interference, resulting in the collected vibration signal not accurately reflecting the actual vibration state of the steam turbine. In order to more accurately monitor whether the steam turbine has vibration failure, it is necessary to conduct in-depth analysis of the vibration signal.
[0043] First, taking the vibration signal at the front bearing as an example, the sequence composed of the vibration signals at the current sampling time and the previous k consecutive sampling times collected by the vibration sensor at the front bearing is recorded as the vibration sequence at the current sampling time, recorded as X = [x 0 ,x 1 ,…,x k ], where x 0 、x 1 and x k Represent the vibration amplitudes at the current sampling moment, the previous sampling moment, and the previous k-th sampling moment, respectively, where k is a preset value, which is 2000 in this embodiment and can be adjusted by the implementer according to the actual situation. The sequence of elements is taken as the first sequence, denoted as X 1 ; Remove sequence X from the vibration sequence X 1 The remaining sequence of elements is taken as the second sequence, denoted as X 2 . int() is a rounding function, which is used to round the input data to an integer. When a vibration fault occurs in the turbine, the vibration signal in the recent period will show obvious fluctuations and changes. The greater the difference between the first sequence and the second sequence, the greater the difference between the first sequence and the second sequence.
[0044] Based on the above characteristics, a waveform change factor is constructed to characterize the possibility of changes in the vibration signal waveform: the distance measurement between the first sequence and the second sequence is used as the waveform change factor at the current moment, indicating the possibility of fluctuations in the vibration signal collected in the recent period. In this embodiment, the distance measurement between the two sequences is obtained by calculating dynamic time warping (DTW). The implementer can choose a suitable distance measurement method at his own discretion, and this application does not limit this.
[0045] It should be understood that, when the DTW distance between the first sequence and the second sequence is larger, it means that the difference between the vibration signal in the recent period and the vibration signal in the previous period is larger, which further indicates that the vibration signal in the recent period has fluctuated.
[0046] The fluctuation change factor at each sampling moment is calculated and recorded, and the sequence composed of the fluctuation change factors is recorded as the fluctuation change sequence A. The Z-score value of the fluctuation change factor at each sampling moment in the sequence A is calculated, and when the Z-score value is greater than the set value, the corresponding sampling moment is regarded as the vibration fluctuation moment. In this embodiment, the set value is 2, and the calculation of the Z-score value is a well-known technology, and the specific process is not repeated.
[0047] The third step: according to the element change characteristic distribution of the differential sequence of the first sequence at each vibration fluctuation moment, the amplitude discrimination value at each vibration fluctuation moment is obtained; based on the frequency response of the first sequence and the second sequence at each vibration fluctuation moment in the frequency domain, combined with the amplitude discrimination value, the failure factor of the thermoelectric equipment at each vibration fluctuation moment is obtained.
[0048] Furthermore, it is necessary to analyze whether the vibration signal at the moment of vibration fluctuation is caused by turbine vibration failure or electromagnetic interference. The reason for electromagnetic interference is that there are some interference sources near the bearing, such as electromagnetic noise generated by equipment that is starting or stopping, and equipment operation. When the vibration signal is subject to electromagnetic interference, there will be not only high-frequency components in the vibration signal, but also low-frequency components. The originally stable waveform will be deformed, and the amplitude of the vibration waveform will become large and small. When the rotor is thermally deformed, as the temperature rises, the amplitude in the vibration signal waveform diagram will gradually increase. The rotor vibration frequency is determined by its own rotation speed, and the thermal deformation of the rotor usually does not directly change the rotation speed, so the vibration frequency usually does not change or changes slightly; in addition, since the thermal deformation of the rotor may change the original vibration rhythm, the phase of the vibration waveform may change, and this phase change may be larger or smaller. When a bearing has a vibration failure, the amplitude of the vibration waveform will gradually increase as the severity of the failure increases. The failure point of the bearing will periodically contact the rotating body, thereby generating periodic impact and vibration, causing the vibration signal to have a strong periodicity. It should be noted that a bearing failure may also cause the phase of the vibration waveform to shift.
[0049] A continuous segment of positive numbers, a continuous segment of negative numbers, and a continuous segment of zeros in the first-order difference sequence of the first sequence are recorded as data segments, and the sequence composed of the number of data in each data segment in the first-order difference sequence of the first sequence is taken as a counting sequence, recorded as XD 1If the first-order difference sequence of the first sequence is [2,2,1,-1,-3,-4,0,2,1,2,4,-3], then its counting sequence is [3,3,1,4,1].
[0050] Based on the above analysis, if the current moment is judged as a vibration fluctuation moment, an amplitude discrimination value is constructed to judge the similarity between the amplitude characteristics of the vibration signal in the recent period and the amplitude characteristics of the vibration signal when the turbine fails. The formula is: Where E is the amplitude discrimination value at the current moment; t 1 Represents the average value of all elements in the counting sequence at the current moment; x 0 、x i They represent the values of the first element and the last element in the first sequence at the current moment respectively; exp() represents an exponential function with a natural constant as the base; r 1 Represents the total number of elements in the counting sequence at the current moment; σ is a preset parameter to prevent the denominator from being 0, and can be any real number greater than 0 and less than 0.1. In this embodiment, it is 0.01.
[0051] It should be understood that when the amplitude of the vibration signal in recent time is fluctuating, more data segments will appear in the first-order difference sequence of the vibration signal, and the shorter the length of the data segment, the smaller the average value of all elements of the count sequence of the first sequence will be, and the more the total number of elements will be. 1 Larger, r 1 When exp(x 0 -x i ) is larger, indicating that the amplitude in the recent period is increasing, and the amplitude characteristics of the vibration signal in the recent period are more similar to the amplitude characteristics of the vibration signal caused by the turbine fault.
[0052] If the current moment is determined to be a vibration fluctuation moment, the first sequence and the second sequence at the current moment are respectively used as inputs of discrete Fourier transform to obtain the frequency responses of the first sequence and the second sequence in the frequency domain. Discrete Fourier transform is a well-known technology, and the specific process is not repeated here.
[0053] Furthermore, according to the characteristics of the vibration signal when the turbine fails, a thermoelectric equipment failure factor at the current moment is constructed to determine the possibility that the vibration signal at the current moment belongs to the vibration signal caused by the turbine failure: the bandwidth difference between the first sequence and the second sequence at the current moment is obtained; the forward fusion result of the phase difference corresponding to all the same frequencies in the frequency response of the first sequence and the second sequence at the current moment is calculated; based on the bandwidth difference, the forward fusion result, the amplitude discrimination value and the fundamental frequency energy intensity of the first sequence at the current sampling moment, the thermoelectric equipment failure factor at the current sampling moment is obtained; wherein the thermoelectric equipment failure factor is negatively correlated with the bandwidth difference, and positively correlated with the forward fusion result, the amplitude discrimination value and the fundamental frequency energy intensity.
[0054] In this embodiment, the bandwidth is calculated by subtracting the minimum frequency from the maximum frequency in the frequency response; the bandwidth difference and the phase difference are determined by the difference, and the bandwidth difference is recorded as D; the forward fusion result is determined by the sum of all phase differences, and the forward fusion result is recorded as S; the fundamental frequency energy intensity is recorded as e; the amplitude discrimination value is recorded as E, and the formula form of the thermoelectric device failure factor is: Wherein, W represents the failure factor of the thermoelectric device at the current moment; norm() is a normalization function used to normalize the failure factor of the thermoelectric device; exp() represents an exponential function with a natural constant as the base.
[0055] It should be understood that, the larger the value of S is, the larger the phase of the vibration signal in recent time is compared with the phase of the vibration signal in previous time, which indicates that the vibration signal is more likely to be caused by turbine fault; the larger the value of e is, the stronger the periodicity of the vibration signal in recent time is, which indicates that the vibration signal is more likely to be caused by turbine fault; the larger the value of E is, the more similar the amplitude characteristic of the vibration signal is to the amplitude characteristic of the vibration signal caused by turbine fault; the smaller the value of exp(D) is, the more stable the frequency is in the vibration signal in recent time, which indicates that the vibration signal is more likely to be caused by turbine fault.
[0056] Among them, the schematic diagram of obtaining the failure factor of thermoelectric equipment is as follows: Figure 2 shown.
[0057] Furthermore, if the current moment is not a vibration fluctuation moment, it means that the vibration signal has not fluctuated, and furthermore, it means that the steam turbine is in a normal operating state.
[0058] The fourth step: based on the failure factor of the thermoelectric device, the monitoring results of each preset bearing of the thermoelectric device at each sampling time are obtained.
[0059] The value of the thermoelectric device failure factor obtained at each vibration fluctuation moment is compared with the threshold a. When the value of the thermoelectric device failure factor is greater than the threshold a, the vibration fluctuation signal at the current moment is regarded as a fluctuation signal caused by a turbine failure. At this time, an alarm should be issued to remind the staff that a vibration failure has occurred in the rotor or bearing of the turbine. When the value of the thermoelectric device failure factor is less than the preset threshold a, it means that the vibration fluctuation signal at the current moment is a fluctuation caused by electromagnetic interference, so there is no need to issue an alarm at this time. The value of the preset threshold a needs to be set according to the actual situation. In this embodiment, a is 0.7.
[0060] Based on the same inventive concept as the above method, an embodiment of the present application also provides an online monitoring system for vibration faults of thermoelectric equipment, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned methods for online monitoring vibration faults of thermoelectric equipment are implemented.
[0061] In summary, the present application aims at the problem that the vibration fault monitoring process of thermoelectric equipment is easily interfered by other electrical equipment, resulting in that the collected vibration signal cannot accurately reflect the actual operating status of the steam turbine: first, the vibration signal is collected and divided into two parts to facilitate the subsequent analysis of the fluctuation difference of the vibration signal in recent time and previous time; according to the distribution difference between the first sequence and the second sequence at each sampling moment, the waveform change factor at each sampling moment is obtained, the fluctuation characteristics of the vibration signal are analyzed, and the moment when the vibration signal fluctuates is obtained; further, according to the element change of the differential sequence of the first sequence at each vibration fluctuation moment, Characteristic distribution is obtained to obtain the amplitude discrimination value at each vibration fluctuation moment, so as to facilitate the subsequent judgment of whether the thermoelectric device is faulty according to the amplitude characteristics of the thermoelectric device; based on the frequency response of the first sequence and the second sequence in the frequency domain at each vibration fluctuation moment, combined with the amplitude discrimination value, the failure factor of the thermoelectric device at each vibration fluctuation moment is obtained, which has the beneficial effect of analyzing the amplitude characteristics, frequency characteristics, phase characteristics and periodic characteristics of the vibration signal when the thermoelectric device has a vibration failure and electromagnetic interference, and judging whether the cause of the vibration signal fluctuation is a turbine vibration failure or electromagnetic interference, thereby eliminating the influence of electromagnetic interference on the monitoring results and improving the accuracy of vibration fault monitoring.
[0062] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two continuous operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.
[0063] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; the technical solutions recorded in the above embodiments are modified, or some of the technical features are replaced by equivalents, which does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.
Claims
1. A method for online monitoring of vibration faults of thermoelectric equipment, characterized in that: The method comprises the following steps: Obtaining the vibration signal of each preset bearing of the thermoelectric device to be monitored at each sampling time; The sequence composed of the vibration signals of each preset bearing at each sampling moment and a preset number of sampling moments before is divided into two parts, and the first sequence and the second sequence at each sampling moment are obtained; according to the distribution difference between the first sequence and the second sequence at each sampling moment, the waveform change factor at each sampling moment is obtained, and the vibration fluctuation moment is obtained; According to the element change characteristic distribution of the differential sequence of the first sequence at each vibration fluctuation moment, the amplitude discrimination value at each vibration fluctuation moment is obtained; based on the frequency response of the first sequence and the second sequence at each vibration fluctuation moment in the frequency domain, combined with the amplitude discrimination value, the thermoelectric device failure factor at each vibration fluctuation moment is obtained; Based on the failure factor of the thermoelectric device, monitoring results of each preset bearing of the thermoelectric device at each sampling time are obtained.
2. A method for online monitoring of vibration faults of thermoelectric equipment according to claim 1, characterized in that: The first sequence and the second sequence at each sampling moment are obtained as follows: Arrange the vibration signals of each preset bearing at each sampling moment and a preset number of sampling moments before in reverse order in time sequence as a vibration sequence at each sampling moment; For the vibration sequence, a sequence consisting of all vibration signals corresponding to the rounded value of half of the preset number at each sampling moment is taken as the first sequence; and a sequence consisting of the remaining vibration signals is taken as the second sequence.
3. A method for online monitoring of vibration faults of thermoelectric equipment according to claim 1, characterized in that: The waveform change factor at each sampling moment is obtained by measuring the distance between the first sequence and the second sequence at each sampling moment.
4. A method for online monitoring of vibration faults of thermoelectric equipment according to claim 1, characterized in that: The obtaining of the vibration fluctuation moment is specifically as follows: Calculate the Z-score value of the fluctuation change factor at each sampling moment in the corresponding vibration sequence. When the Z-score value is greater than the set value, the corresponding sampling moment is taken as the vibration fluctuation moment.
5. The method for online monitoring of vibration faults of thermoelectric equipment according to claim 1, characterized in that: The amplitude discrimination value obtained at each vibration fluctuation moment is specifically: According to the change characteristics of the adjacent elements of the first sequence at each vibration fluctuation moment, a counting sequence at each vibration fluctuation moment is obtained; The amplitude discrimination value of each vibration fluctuation moment is recorded as E, and its formula is: Among them, t1 represents the average value of all elements in the counting sequence at each vibration fluctuation moment; x0, x i They respectively represent the values of the first element and the last element in the first sequence at each sampling moment; exp() represents an exponential function with a natural constant as the base; r1 represents the total number of elements in the counting sequence at each sampling moment; σ is a preset parameter.
6. A method for online monitoring of vibration faults of thermoelectric equipment according to claim 5, characterized in that: The counting sequence of each vibration fluctuation moment is obtained as follows: The first-order difference sequence of the first sequence at each vibration fluctuation moment is obtained, and the parts of the first-order difference sequence whose elements are continuously positive, continuously negative, and continuously zero are used as different data segments, and the sequence composed of the number of data in each data segment in the first-order difference sequence of the first sequence is used as a counting sequence.
7. A method for online monitoring of vibration faults of thermoelectric equipment according to claim 1, characterized in that: The failure factor of the thermoelectric device at each vibration fluctuation moment is specifically: Obtaining the bandwidth difference between the first sequence and the second sequence at each vibration fluctuation moment; Calculate the forward fusion results of the phase differences corresponding to all the same frequencies in the frequency responses of the first sequence and the second sequence at each vibration fluctuation moment; Based on the bandwidth difference, the forward fusion result, the amplitude discrimination value and the fundamental frequency energy intensity of the first sequence at each vibration fluctuation moment, the thermoelectric equipment failure factor at each vibration fluctuation moment is obtained; wherein the thermoelectric equipment failure factor is negatively correlated with the bandwidth difference, and positively correlated with the forward fusion result, the amplitude discrimination value and the fundamental frequency energy intensity.
8. A method for online monitoring of vibration faults of thermoelectric equipment according to claim 7, characterized in that: The specific calculation method of the thermoelectric device failure factor is: record the bandwidth difference as D, record the forward fusion result as S, record the fundamental frequency energy intensity as e, and record the amplitude discrimination value as E. The formula form of the thermoelectric device failure factor is: Where W represents the failure factor of the thermoelectric device; norm() is the normalization function; exp() represents the exponential function with a natural constant as the base.
9. The method for online monitoring of vibration faults of thermoelectric equipment according to claim 1, characterized in that: The process of obtaining the monitoring results of each preset bearing of the thermoelectric device at each sampling time is specifically as follows: When the sampling moment is judged to be a vibration fluctuation moment, if the value of the thermoelectric device fault factor is greater than a preset threshold, the vibration signal corresponding to the sampling moment is regarded as a fault signal; otherwise, the vibration signal corresponding to the sampling moment is regarded as a normal signal.
10. An online monitoring system for vibration faults of thermoelectric equipment, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.