Sensor-based frequency converter operation fault diagnosis method and system

Abstract

The invention relates to the technical field of fault diagnosis, in particular to a sensor-based frequency converter operation fault diagnosis method and system, and the method comprises the steps: obtaining the current sequence, temperature sequence and rotating speed sequence of each phase of a frequency converter in each collection period; acquiring the current precursor degree of each phase current sequence of the current acquisition period according to the fluctuation characteristics of each phase current sequence of the current acquisition period; the load asynchronous coefficient of each phase current sequence of the current acquisition period is obtained by combining the short-time high-frequency disturbance characteristic in each phase current sequence of the current acquisition period with the degree of correlation with the rotating speed data, and the temperature throughout of the current acquisition period is obtained by combining the fluctuation characteristic of the temperature sequence of the current acquisition period; and acquiring a fault threatening coefficient of the current acquisition period, and further judging whether the frequency converter has a fault. According to the method and the device, the distinguishing data characteristics during motor load change and IGBT breakdown fault are analyzed, so that the fault diagnosis accuracy of the frequency converter is improved.

Description

Technical Field

[0001] The present application relates to the technical field of fault diagnosis, and in particular to a method and system for diagnosing inverter operation faults based on sensors. Background Art

[0002] A frequency converter (VFD) is an electronic device used to control the speed of an AC motor. It modulates the motor's speed and operating mode by varying the power supply's frequency and voltage, thereby achieving frequency modulation. VFDs offer advantages such as energy saving, precise control, and reduced mechanical wear. Their superior performance has led to their widespread use in the power and industrial sectors. However, with extended use and component aging, VFDs can malfunction, posing risks to industrial production and personal safety. Therefore, fault detection of VFDs during real-time operation is necessary to improve the reliability and safety of industrial production.

[0003] The IGBT (Insulated Gate Bipolar Transistor) module is the core power component in the inverter. Its performance and stability directly affect the working efficiency and service life of the inverter. With frequent switching actions and heat accumulation, the IGBT module is prone to breakdown failure, which affects the normal use of the inverter. When detecting breakdown failures in the IGBT module of the inverter, the existing technology usually directly uses a single data point to compare with the threshold to determine whether a fault has occurred. It does not fully consider the difference between the current fluctuation caused by the change in motor load and the precursor of IGBT breakdown failure. It is easy to mistakenly detect the current fluctuation caused by the change in motor load as a precursor to IGBT breakdown failure, resulting in low accuracy of inverter fault diagnosis. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a sensor-based inverter operation fault diagnosis method and system. The technical solutions adopted are as follows: In a first aspect, an embodiment of the present application provides a sensor-based inverter operation fault diagnosis method, the method comprising the following steps: Obtain the current sequence, temperature sequence and speed sequence of each phase of the inverter in each acquisition cycle; The data with a value of 0 in each phase current sequence is recorded as a zero-point element. The current precursor degree of each phase current sequence in the current acquisition cycle is obtained based on the slope of the fitting straight line corresponding to the peak value in each phase current sequence in the current acquisition cycle and the correlation degree of the data in the neighborhood window corresponding to all adjacent zero-point elements in each phase current sequence. Divide each phase current sequence into multiple current subsequences, and obtain a speed subsequence with the same bit sequence as each current subsequence; obtain the high-frequency subsequence of each phase current sequence in the current acquisition period based on the bit sequence range corresponding to the neighborhood window of the zero-point element with high-frequency energy in each phase current sequence in the current acquisition period; obtain the load asynchrony coefficient of each phase current sequence in the current acquisition period based on the proportion of high-frequency subsequences with a discrete degree less than the discrete degree of the speed sequence in all high-frequency subsequences of each phase current sequence in the current acquisition period, the correlation between the average level of each phase current subsequence in the current acquisition period and the average level of each corresponding speed subsequence, and the current precursor degree of each phase current sequence; The temperature precursor coefficient of the current acquisition cycle is obtained based on the proportion of negative numbers in the first-order difference sequence of the temperature sequence of the current acquisition cycle, the degree of discreteness of the temperature sequence, and the difference between the average levels of the temperature sequences of the current acquisition cycle and the previous acquisition cycle. Combined with the average level of the load asynchrony coefficient of all phase current sequences of the current acquisition cycle, the fault precursor coefficient of the current acquisition cycle is obtained to determine whether the inverter has a fault.

[0005] Preferably, the process of acquiring the current precursor degree of each phase current sequence in the current acquisition cycle is: Obtaining a first correlation degree of each phase current sequence in a current acquisition cycle according to the correlation degree of data in a neighborhood window corresponding to all adjacent zero-point elements in each phase current sequence; The calculation formula for the current precursor degree of each phase current sequence in the current acquisition cycle is: Where, is the current precursor degree of the A-phase current sequence in the current acquisition cycle; is the slope of the fitted straight line corresponding to all peak values ​​in the A phase current sequence of the current acquisition cycle, is an exponential function with the natural constant e as the base, is the first correlation of the A phase current sequence in the current acquisition cycle, is a preset constant.

[0006] Preferably, the process of obtaining the first correlation of each phase current sequence in the current acquisition cycle is as follows: constructing a window with each zero-point element in each phase current sequence as the center, the width of the window is an odd number closest to T / 2, and T is the average of the intervals between all adjacent peaks in each phase current sequence; calculating the correlation coefficient between all adjacent window data in each phase current sequence in the current acquisition cycle, and recording the average of the absolute values ​​of all correlation coefficients as the first correlation of each phase current sequence in the current acquisition cycle.

[0007] Preferably, the process of acquiring the high-frequency subsequence of each phase current sequence in the current acquisition cycle is as follows: performing Fourier transform on each phase current sequence in the current acquisition cycle to obtain the fundamental frequency of each phase current sequence; obtaining the spectrum sequence of the window centered on each zero-point element in each phase current sequence, and recording the cumulative sum of all energy components in the spectrum sequence of each window whose frequency is greater than the corresponding fundamental frequency as the high-frequency energy value of each window; recording the zero-point elements corresponding to all windows in each phase current sequence whose high-frequency energy values ​​are greater than a preset segmentation threshold as the local high-frequency zero points of each phase current sequence; and extracting the corresponding subsequence from the speed sequence according to the bit sequence range of the window data of all local high-frequency zero points in each phase current sequence in the current acquisition cycle, and recording it as the high-frequency subsequence of each phase current sequence in the current acquisition cycle.

[0008] Preferably, the process of acquiring the load asynchronous coefficient of each phase current sequence in the current acquisition cycle is: Obtaining a first ratio of each phase current sequence in the current acquisition period according to a proportion of high-frequency subsequences having a discrete degree less than a discrete degree of the speed sequence in all high-frequency subsequences of each phase current sequence in the current acquisition period; Calculate the mean of each current subsequence of each phase current sequence and the mean of each speed subsequence corresponding thereto, and construct the current mean sequence and speed mean sequence of each phase current according to the position order of each subsequence; Calculate the load asynchronous coefficient of each phase current sequence in the current acquisition cycle: Where, is the load asynchronous coefficient of the A-phase current sequence in the current acquisition cycle, is the current precursor degree of the A phase current sequence in the current acquisition cycle, is the absolute value of the correlation coefficient between the current mean value sequence of phase A current and its speed mean value sequence in the current acquisition cycle, The first ratio of the A-phase current sequence in the current acquisition cycle.

[0009] Preferably, the process of obtaining the first ratio of each phase current sequence in the current acquisition cycle is: calculating the variance of the speed sequence in the current acquisition cycle, recorded as z; calculating the variance of each high-frequency sub-sequence of each phase current sequence in the current acquisition cycle, and recording the proportion of data less than z in all variances as the first ratio of each phase current sequence in the current acquisition cycle.

[0010] Preferably, the calculation formula for the temperature precursor degree of the current acquisition cycle is: Where W is the temperature precursor degree of the current acquisition cycle; H is the ratio of the number of negative numbers in the first-order difference sequence of the temperature sequence in the current acquisition cycle to the total number of data in the first-order difference sequence; L is the variance of the temperature sequence in the current acquisition cycle; J is the ratio of the mean value of the temperature sequence in the previous acquisition cycle to the mean value of the temperature sequence in the current acquisition cycle.

[0011] Preferably, the calculation formula of the fault precursor coefficient of the current acquisition cycle is: ; Where R is the fault precursor coefficient of the current acquisition cycle, is the average value of the load asynchronous coefficient of the current sequence of phase A, phase B, and phase C in the current acquisition period, and W is the temperature precursor degree of the current acquisition period.

[0012] Preferably, the specific process of determining whether the frequency converter has a fault is as follows: if the normalized fault precursor coefficient is greater than or equal to a preset threshold, the frequency converter is determined to have a fault; otherwise, the frequency converter is determined to have no fault.

[0013] In the second aspect, an embodiment of the present application also provides a sensor-based inverter operation fault diagnosis system, 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, it implements the steps of any one of the above-mentioned sensor-based inverter operation fault diagnosis methods.

[0014] This application has at least the following beneficial effects: This application addresses the problem in the prior art that the difference between the current fluctuation caused by the load and the current fluctuation caused by the precursor of a breakdown fault is not fully considered, which leads to low detection accuracy. By constructing a current precursor degree, it is possible to reflect the current growth trend and the degree of zero-point waveform distortion, and accurately identify the current characteristics of the IGBT breakdown fault precursor; by constructing a load asynchronous coefficient, it is possible to reflect the synchronization difference between the inverter output current and the motor load, and eliminate the interference of normal load fluctuations on fault diagnosis; by constructing a temperature precursor degree, it is possible to reflect whether the temperature change of the IGBT module meets the implicit temperature rise in the precursor stage of the fault, and based on this, construct a fault precursor coefficient, so as to comprehensively evaluate the operating status of the inverter and achieve accurate diagnosis and early warning of the IGBT breakdown fault precursor of the inverter. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] Figure 1 A flowchart of a method for diagnosing inverter operation faults based on a sensor according to an embodiment of the present application; Figure 2A flowchart for obtaining the fault precursor coefficient of the current acquisition cycle is provided in one embodiment of the present application. DETAILED DESCRIPTION

[0017] To further illustrate the technical means and effectiveness of this application to achieve the intended invention objectives, the sensor-based inverter operation fault diagnosis method and system proposed in this application, along with the accompanying drawings and preferred embodiments, are described in detail below, along with their specific implementation, structure, features, and effectiveness. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0018] 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.

[0019] The specific scheme of the inverter operation fault diagnosis method and system based on sensors provided by the present application is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of a method for diagnosing inverter operation faults based on a sensor according to an embodiment of the present application, the method comprising the following steps: Step 1: Obtain the current sequence, temperature sequence, and speed sequence of each phase of the inverter during each acquisition cycle.

[0021] This application collects the inverter's output current data using a three-phase current sensor installed at the inverter's output terminal; uses a temperature sensor to obtain real-time IGBT module temperature; and uses a speed sensor to collect speed data from the motor drive shaft connected to the inverter to reflect changes in the motor's load. All data is collected synchronously and in real time, with a collection interval of 1 second and a collection period of Y minutes. In this embodiment, Y is 30. Phase A, B, and C current sequences, temperature sequences, and speed sequences are constructed for each collection period, based on the chronological order of data collection.

[0022] In order to eliminate the dimensional influence between the data, all the data are normalized. The normalization methods include Z-score, sigmoid normalization, maximum and minimum value normalization, etc. This embodiment adopts Z-score normalization.

[0023] Step 2: Record the data with a value of 0 in each phase current sequence as a zero-point element. According to the slope of the fitting straight line corresponding to the peak value in each phase current sequence in the current acquisition period and the correlation degree of the data in the neighborhood window corresponding to all adjacent zero-point elements in each phase current sequence, obtain the current precursor degree of each phase current sequence in the current acquisition period.

[0024] When the inverter is operating properly, the output current waveform collected by the sensor should be a stable sine wave, and the IGBT module temperature should remain within a safe range due to the stable heat dissipation system. However, if there are early signs of an IGBT breakdown failure, the current waveform will show significant distortion and distortion due to the degradation of the IGBT switching characteristics. Furthermore, due to problems such as abnormal current conduction within the module, partial discharge, or reduced insulation performance, the IGBT module temperature will rise.

[0025] However, considering that under normal circumstances, changes in motor load will also cause changes in the inverter's output current and temperature, it is difficult to distinguish between normal fluctuations of the inverter or precursors to breakdown failures based solely on fixed thresholds. Therefore, further in-depth analysis is required.

[0026] Due to the degradation of the switching characteristics of the damaged IGBT, the current vector is dynamically unbalanced, which will cause asymmetric conduction in the fault phase, thereby increasing and distorting the current. Therefore, the changes in the three-phase current can be used to preliminarily analyze whether there is an abnormality.

[0027] The analysis is carried out by taking the A-phase current sequence of the current acquisition cycle as an example.

[0028] All peak values ​​in the phase A current sequence are obtained using a peak detection algorithm, and all peak values ​​are linearly fitted using the least squares method. The peak detection algorithm is not limited to the AMPD peak detection algorithm or the maximum value detection algorithm. This embodiment uses the AMPD peak detection algorithm.

[0029] Furthermore, the degradation of IGBT switching characteristics can cause turn-on delay or turn-off residue near the current zero crossing point, which manifests as high-frequency glitch disturbance and waveform distortion.

[0030] The data with a value of 0 in the phase A current sequence before normalization are recorded as zero-point elements. After normalization, a window is constructed with each zero-point element as the center. The width of the window is the odd number closest to T / 2, where T is the mean of the intervals between all adjacent peaks in the phase A current sequence.

[0031] Calculate the correlation coefficients between all adjacent window data in the A-phase current sequence of the current acquisition cycle, and record the mean of the absolute values ​​of all correlation coefficients as the first correlation of the A-phase current sequence of the current acquisition cycle. The first correlation can reflect whether waveform distortion occurs at zero points. The smaller the value, the greater the waveform difference at all zero points, and the less it conforms to the characteristics of a good current waveform. The calculation algorithm of the correlation coefficient is not limited to the Pearson correlation coefficient, the Spearman correlation coefficient, and the cosine similarity. This embodiment uses the Pearson correlation coefficient.

[0032] As a preferred implementation, the current precursor degree of each phase current sequence in the current acquisition cycle is obtained based on the slope of the fitting straight line corresponding to the peak value in each phase current sequence in the current acquisition cycle and the correlation degree of the data in the neighborhood window corresponding to all adjacent zero-point elements in each phase current sequence, which is used to characterize the degree to which the current data of each phase in the current acquisition cycle conforms to the precursor of IGBT breakdown fault.

[0033] In this embodiment, the current precursor degree of the A phase current sequence in the current acquisition cycle is recorded as , its specific expression is: Where, is the current precursor degree of the A-phase current sequence in the current acquisition cycle; is the slope of the fitted straight line corresponding to all peak values ​​in the A phase current sequence of the current acquisition cycle, is an exponential function with the natural constant e as the base, is the first correlation of the A phase current sequence in the current acquisition cycle, This is a preset constant. In order to avoid the denominator being 0, the value is taken from the empirical range (0.005, 0.01). The value has little impact on the calculation and can be ignored. The implementer can choose the value at will.

[0034] It can reflect whether the peak value of the A-phase current sequence in the current acquisition cycle increases over time. The larger the value, the greater the increase in the A-phase current, and the greater the possibility of it being a precursor to IGBT breakdown failure. It can reflect whether there is current increase and distortion in the output current of the inverter in the current acquisition cycle. The larger the value, the more the current trend reflected by the A-phase current sequence conforms to the precursor characteristics of IGBT breakdown failure, and the greater the possibility of abnormal operation of the inverter.

[0035] Step 3: Divide each phase current sequence into multiple current subsequences, and obtain a speed subsequence with the same bit sequence as each current subsequence; obtain the high-frequency subsequence of each phase current sequence in the current acquisition period based on the bit sequence range corresponding to the neighborhood window of the zero-point element with high-frequency energy in each phase current sequence in the current acquisition period; obtain the load asynchrony coefficient of each phase current sequence in the current acquisition period based on the proportion of high-frequency subsequences with a discreteness less than that of the speed sequence in all high-frequency subsequences of each phase current sequence in the current acquisition period, the correlation between the average level of each phase current subsequence in the current acquisition period and the average level of its corresponding speed subsequence, and the current precursor degree of each phase current sequence.

[0036] Furthermore, considering that if the load of the motor connected to the inverter changes frequently, the output current of the inverter will also change frequently in order to make the motor run more stably. Therefore, if the operating status of the inverter is analyzed only by the output current changes collected by the sensor, errors may occur. It is necessary to combine the motor's operating data to achieve further analysis.

[0037] If no fault occurs, the output current of the inverter and the motor speed will have a synchronous change feature; however, if there is a precursor to a breakdown fault in the inverter, the synchronization feature between the output current and the motor speed will be destroyed.

[0038] The A-phase current sequence is divided into a plurality of current sub-sequences according to the peak value in the A-phase current sequence of the current acquisition cycle, and the speed sequence is divided into a plurality of speed sub-sequences according to the position sequence range of each current sub-sequence.

[0039] The mean of each current subsequence and each speed subsequence is calculated separately, and the current mean sequence and speed mean sequence are constructed according to the sorting order of the subsequences. Since the current waveform is constantly changing, constructing the mean sequence can effectively remove the influence of instantaneous fluctuations, thereby extracting the steady change trend of current and speed.

[0040] Furthermore, the current fluctuations caused by load changes are usually low-frequency and smooth; however, as the IGBT gradually deteriorates, the current data will jitter, manifesting as short-term high-frequency disturbances, and the abnormal disturbances will not immediately cause a synchronous response to the speed.

[0041] The phase A current sequence of the current acquisition cycle is Fourier transformed to obtain the fundamental frequency of the phase A current sequence. Then, in the phase A current sequence, the windows constructed with each zero-point element as the center are Fourier transformed to obtain the spectrum sequence of each window. The cumulative sum of all energy components in the spectrum sequence of each window with a frequency greater than the fundamental frequency is recorded as the high-frequency energy value of each window. The high-frequency energy values ​​of all windows in the phase A current sequence are used as the input of the Otsu threshold method, and the segmentation threshold is output. The segmentation threshold is recorded as the preset segmentation threshold, and the zero-point elements corresponding to all windows with high-frequency energy values ​​greater than the preset segmentation threshold are recorded as local high-frequency zero points. The Otsu threshold method can extract window data that produces high-frequency disturbances in the phase A current sequence.

[0042] Based on the bit sequence range of the window data for all local high-frequency zeros in the Phase A current sequence during the current acquisition cycle, the corresponding subsequence is extracted from the speed sequence and recorded as the high-frequency subsequence of the Phase A current sequence during the current acquisition cycle. The variance of the speed sequence during the current acquisition cycle is calculated, recorded as z. The variance of each high-frequency subsequence of the Phase A current sequence during the current acquisition cycle is then calculated, and the proportion of data with variances less than z is recorded as the first ratio of the Phase A current sequence during the current acquisition cycle. This first ratio reflects whether the motor speed exhibits a synchronous response during periods of high-frequency disturbances in the current data. A larger value indicates a greater number of stable speeds in the high-frequency subsequence, which in turn increases the likelihood that the sharp fluctuations in the output current are not caused by the motor speed and the likelihood of inverter failure.

[0043] As a preferred embodiment, based on the first ratio of each phase current sequence in the current acquisition cycle, the correlation between the average level of each phase current subsequence in the current acquisition cycle and the average level of each speed subsequence corresponding to it, and the current precursor degree of each phase current sequence, the load asynchronous coefficient of each phase current sequence in the current acquisition cycle is obtained, which is used to characterize the degree of asynchronous between each phase current in the current acquisition cycle and the motor load.

[0044] In this embodiment, the load asynchronous coefficient of the A phase current sequence of the current acquisition cycle is recorded as , whose expression is: Where, is the load asynchronous coefficient of the A-phase current sequence in the current acquisition cycle, is the current precursor degree of the A phase current sequence in the current acquisition cycle, is the absolute value of the correlation coefficient between the current mean value sequence of phase A current and its speed mean value sequence in the current acquisition cycle, The first ratio of the A-phase current sequence in the current acquisition cycle.

[0045] This factor reflects whether the inverter output current and motor speed still exhibit synchronous variation. Smaller values ​​indicate weaker synchronization, and thus a greater likelihood of an inverter operating abnormality. The load asynchrony coefficient comprehensively reflects the asynchronous relationship between the inverter output current and the motor load. Larger values ​​indicate greater abnormal fluctuations in the inverter output current and a lack of synchronization with the motor load, indicating a higher likelihood of an inverter operating abnormality.

[0046] Similarly, the load asynchronous coefficients of the B-phase current sequence and the C-phase current sequence can be obtained.

[0047] Step 4: Based on the proportion of negative numbers in the first-order difference sequence of the temperature sequence in the current acquisition cycle, the degree of discreteness of the temperature sequence, and the difference between the average levels of the temperature sequences in the current acquisition cycle and the previous acquisition cycle, the temperature precursor coefficient of the current acquisition cycle is obtained. Combined with the average level of the load asynchrony coefficient of each phase current sequence in the current acquisition cycle, the fault precursor coefficient of the current acquisition cycle is obtained to determine whether the inverter has a fault.

[0048] Furthermore, before a breakdown fault occurs in the IGBT module inside the inverter, not only will the output current fluctuate, but the temperature of the IGBT module will also rise. Therefore, the inverter can be comprehensively analyzed in combination with the temperature data collected by the temperature sensor. However, considering that no fault has occurred at this time, it is still in the pre-fault stage, and the temperature change has a lag and is not as significant as the change in current data. Therefore, its temperature may be difficult to identify due to the normal operation of the inverter's cooling system, that is, the inverter temperature has not exceeded the set temperature threshold. However, if it is in the pre-fault stage, even if the temperature has not reached the threshold, the change characteristics of its temperature data will still change. For example, the temperature data will increase at a faster rate, and over time, the average temperature of the inverter will be higher. At the same time, the cooling system will be used more frequently, and the temperature fluctuations will be larger and no longer relatively stable.

[0049] As a preferred implementation, the temperature precursor degree of the current acquisition cycle is obtained based on the proportion of negative numbers in the first-order difference sequence of the temperature sequence of the current acquisition cycle, the degree of discreteness of the temperature sequence, and the difference between the average levels of the temperature sequences of the current acquisition cycle and the previous acquisition cycle, to characterize the possibility of abnormality in the temperature data of the current acquisition cycle.

[0050] In this embodiment, the temperature precursor degree of the temperature sequence in the current acquisition cycle is recorded as , its specific expression is: Where W is the temperature precursor degree of the current acquisition cycle; H is the ratio of the number of negative numbers in the first-order difference sequence of the temperature sequence in the current acquisition cycle to the total number of data in the first-order difference sequence; L is the variance of the temperature sequence in the current acquisition cycle; J is the ratio of the mean value of the temperature sequence in the previous acquisition cycle to the mean value of the temperature sequence in the current acquisition cycle.

[0051] H can reflect the frequency of temperature drops in the current cycle. The larger its value, the more frequently the inverter cooling system is adjusted. J can reflect whether the overall temperature has increased during the current acquisition cycle compared to the previous one. The smaller its value, the higher the average temperature during the current acquisition cycle. L can reflect the degree of temperature fluctuation during the current acquisition cycle. The larger its value, the greater the temperature fluctuation during the current acquisition cycle. The temperature precursor W can reflect whether the temperature change of the IGBT module inside the inverter has been abnormal during the current acquisition cycle. The larger its value, the greater the possibility of abnormal temperature changes in the current acquisition cycle.

[0052] Furthermore, based on the load asynchronous coefficient of the A-phase, B-phase, and C-phase current sequences of the current acquisition cycle and the temperature precursor degree of the current acquisition cycle, the fault precursor coefficient of the current acquisition cycle is obtained to characterize the possibility that the operating data characteristics of the IGBT module inside the inverter in the current acquisition cycle belong to a breakdown fault.

[0053] As a preferred embodiment, the fault precursor coefficient of the current acquisition period is obtained based on the temperature precursor degree of the current acquisition period and the average level of the load asynchronous coefficient of all phase current sequences, which is used to characterize the possibility of the inverter breakdown fault in the current acquisition period. The flowchart for obtaining the fault precursor coefficient of the current acquisition period is as follows: Figure 2 shown.

[0054] In this embodiment, the fault precursor coefficient of the current acquisition cycle is recorded as , its specific expression is: ; Where R is the fault precursor coefficient of the current acquisition cycle, is the average value of the load asynchronous coefficient of the current sequence of phase A, phase B, and phase C in the current acquisition period, and W is the temperature precursor degree of the current acquisition period.

[0055] The fault precursor coefficient comprehensively considers the current load changes and temperature changes of the inverter, and can comprehensively analyze the health status of the inverter. The larger the value, the more consistent the operating data characteristics of the IGBT module inside the inverter are with the data characteristics before the breakdown fault, and the greater the possibility of abnormal inverter operation status.

[0056] The fault precursor coefficient of the current acquisition cycle is normalized using a sigmoid function, mapping the fault precursor coefficient to the range [0, 1]. If the normalized fault precursor coefficient is greater than or equal to a preset threshold, the inverter is judged to have a fault. The operating data collected by the sensor during the current acquisition cycle is more consistent with the precursor characteristics before the IGBT breakdown fault, and therefore the inverter needs to be repaired promptly. If the normalized fault precursor coefficient is less than the preset threshold, the inverter is judged to have no fault and is in good health with no signs of failure. It can continue to operate and use. In this embodiment, the preset threshold is 0.5, and the implementer can choose the value according to the actual situation.

[0057] Based on the same inventive concept as the above-mentioned method, an embodiment of the present application also provides a sensor-based inverter operation fault diagnosis system, 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, it implements the steps of any one of the above-mentioned sensor-based inverter operation fault diagnosis methods.

[0058] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0060] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A sensor-based inverter operation fault diagnosis method, characterized in that: The method comprises the following steps: Obtain the current sequence, temperature sequence and speed sequence of each phase of the inverter in each acquisition cycle; The data with a value of 0 in each phase current sequence is recorded as a zero-point element. The current precursor degree of each phase current sequence in the current acquisition cycle is obtained based on the slope of the fitting straight line corresponding to the peak value in each phase current sequence in the current acquisition cycle and the correlation degree of the data in the neighborhood window corresponding to all adjacent zero-point elements in each phase current sequence. Divide each phase current sequence into multiple current subsequences, and obtain a speed subsequence with the same bit sequence as each current subsequence; obtain the high-frequency subsequence of each phase current sequence in the current acquisition period based on the bit sequence range corresponding to the neighborhood window of the zero-point element with high-frequency energy in each phase current sequence in the current acquisition period; obtain the load asynchrony coefficient of each phase current sequence in the current acquisition period based on the proportion of high-frequency subsequences with a discrete degree less than the discrete degree of the speed sequence in all high-frequency subsequences of each phase current sequence in the current acquisition period, the correlation between the average level of each phase current subsequence in the current acquisition period and the average level of each corresponding speed subsequence, and the current precursor degree of each phase current sequence; The temperature precursor coefficient of the current acquisition cycle is obtained based on the proportion of negative numbers in the first-order difference sequence of the temperature sequence of the current acquisition cycle, the degree of discreteness of the temperature sequence, and the difference between the average levels of the temperature sequences of the current acquisition cycle and the previous acquisition cycle. Combined with the average level of the load asynchrony coefficient of all phase current sequences of the current acquisition cycle, the fault precursor coefficient of the current acquisition cycle is obtained to determine whether the inverter has a fault.

2. The method for diagnosing inverter operation faults based on sensors according to claim 1, wherein: The process of obtaining the current precursor degree of each phase current sequence in the current acquisition cycle is as follows: Obtaining a first correlation degree of each phase current sequence in a current acquisition cycle according to the correlation degree of data in a neighborhood window corresponding to all adjacent zero-point elements in each phase current sequence; The calculation formula for the current precursor degree of each phase current sequence in the current acquisition cycle is: Where, is the current precursor degree of the A-phase current sequence in the current acquisition cycle; is the slope of the fitted straight line corresponding to all peak values ​​in the A phase current sequence of the current acquisition cycle, is an exponential function with the natural constant e as the base, is the first correlation of the A phase current sequence in the current acquisition cycle, is a preset constant.

3. The method for diagnosing inverter operation faults based on sensors according to claim 2, wherein: The process of obtaining the first correlation of each phase current sequence in the current acquisition cycle is as follows: constructing a window with each zero-point element in each phase current sequence as the center, where the width of the window is an odd number closest to T / 2, and T is the average of the intervals between all adjacent peaks in each phase current sequence; calculating the correlation coefficients between all adjacent window data in each phase current sequence in the current acquisition cycle, and recording the average of the absolute values ​​of all correlation coefficients as the first correlation of each phase current sequence in the current acquisition cycle.

4. The method for diagnosing inverter operation faults based on sensors according to claim 3, wherein: The process of acquiring the high-frequency subsequence of each phase current sequence in the current acquisition cycle is as follows: performing Fourier transform on each phase current sequence in the current acquisition cycle to obtain the fundamental frequency of each phase current sequence; obtaining a spectrum sequence of a window centered on each zero-point element in each phase current sequence, and recording the cumulative sum of all energy components in the spectrum sequence of each window whose frequency is greater than the corresponding fundamental frequency as the high-frequency energy value of each window; recording the zero-point elements corresponding to all windows in each phase current sequence whose high-frequency energy values ​​are greater than a preset segmentation threshold as the local high-frequency zero points of each phase current sequence; and extracting the corresponding subsequence from the speed sequence based on the bit sequence range of the window data of all local high-frequency zero points in each phase current sequence in the current acquisition cycle, and recording it as the high-frequency subsequence of each phase current sequence in the current acquisition cycle.

5. The sensor-based inverter operation fault diagnosis method according to claim 1, characterized in that: The process of obtaining the load asynchronous coefficient of each phase current sequence in the current acquisition cycle is as follows: Obtaining a first ratio of each phase current sequence in the current acquisition period according to a proportion of high-frequency subsequences having a discrete degree less than a discrete degree of the speed sequence in all high-frequency subsequences of each phase current sequence in the current acquisition period; Calculate the mean of each current subsequence of each phase current sequence and the mean of each speed subsequence corresponding thereto, and construct the current mean sequence and speed mean sequence of each phase current according to the position order of each subsequence; Calculate the load asynchronous coefficient of each phase current sequence in the current acquisition cycle: Where, is the load asynchronous coefficient of the A-phase current sequence in the current acquisition cycle, is the current precursor degree of the A phase current sequence in the current acquisition cycle, is the absolute value of the correlation coefficient between the current mean value sequence of phase A current and its speed mean value sequence in the current acquisition cycle, The first ratio of the A-phase current sequence in the current acquisition cycle.

6. The method for diagnosing inverter operation faults based on sensors according to claim 5, characterized in that: The process of obtaining the first ratio of each phase current sequence in the current acquisition cycle is as follows: calculating the variance of the speed sequence in the current acquisition cycle, recorded as z; calculating the variance of each high-frequency subsequence of each phase current sequence in the current acquisition cycle, and recording the proportion of data less than z in all variances as the first ratio of each phase current sequence in the current acquisition cycle.

7. The method for diagnosing inverter operation faults based on sensors according to claim 1, wherein: The calculation formula of the temperature precursor degree of the current acquisition period is: Where W is the temperature precursor degree of the current acquisition period; H is the ratio of the number of negative numbers in the first-order difference sequence of the temperature sequence in the current acquisition period to the total number of data in the first-order difference sequence; L is the variance of the temperature series in the current acquisition cycle; J is the ratio of the mean of the temperature series in the previous acquisition cycle to the mean of the temperature series in the current acquisition cycle.

8. The method for diagnosing inverter operation faults based on sensors according to claim 1, wherein: The calculation formula of the fault precursor coefficient of the current acquisition cycle is: ; Where R is the fault precursor coefficient of the current acquisition cycle, is the average value of the load asynchronous coefficient of the current sequence of phase A, phase B, and phase C in the current acquisition period, and W is the temperature precursor degree of the current acquisition period.

9. The method for diagnosing inverter operation faults based on sensors according to claim 1, wherein: The specific process of determining whether the frequency converter has a fault is as follows: if the normalized fault precursor coefficient is greater than or equal to a preset threshold, the frequency converter is determined to have a fault; otherwise, the frequency converter is determined to have no fault.

10. A sensor-based inverter operation fault diagnosis system 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 sensor-based inverter operation fault diagnosis method as described in any one of claims 1 to 9 are implemented.

Images