Hydrogen compressor state monitoring method based on vibration parameters

Abstract

The invention belongs to the technical field of hydrogen compressor monitoring, and particularly relates to a hydrogen compressor state monitoring method based on vibration parameters. The monitoring method comprises the following steps: for any vibration parameter of the hydrogen compressor, acquiring vibration data of a current sliding window according to window parameters of the current sliding window to calculate statistical data and a vibration feature vector of the current sliding window; the window parameters, the vibration data, the statistical data and the vibration feature vectors of the current sliding window jointly form current sliding window information; according to the sliding window information of each vibration parameter between adjacent monitoring moments and the exhaust pressure at the current monitoring moment, each clustering algorithm outputs a cluster result at the current monitoring moment; calculating the weight coefficient of each clustering algorithm at the current monitoring moment; and the clustering algorithm weight coefficients corresponding to the same cluster results are accumulated to serve as scores of the corresponding cluster results, and then the cluster result with the highest score serves as the running state of the hydrogen compressor at the current monitoring moment. According to the invention, the accuracy of monitoring the running state of the hydrogen compressor can be improved based on the vibration parameters.

Description

Technical Field

[0001] The invention belongs to the technical field of hydrogen compressor monitoring, and in particular relates to a hydrogen compressor state monitoring method based on vibration parameters. Background Art

[0002] As the core boosting equipment for hydrogen refueling stations and hydrogen filling, hydrogen compressors (hereinafter referred to as "hydrogen compressors") are an important link in the widespread application of hydrogen energy. The design pressure of hydrogen compressors is high, up to 90MPa or more, and the gas, water and oil circuits in the hydrogen compressors are complex and intertwined, with a large number of valves of various types.

[0003] Due to the influence of assembly process, transportation bumps, on-site operating environment, etc., even if the hydrogen compressor is tested qualified at the factory, it may fail during the actual operation, which will not only affect the operating efficiency of the hydrogen compressor, but also threaten the personal safety of the technicians on site. Therefore, in addition to regularly inspecting and maintaining the key components of the hydrogen compressor, the technicians will also map the status of the hydrogen compressor based on the exhaust pressure collected by the sensor during the operation of the hydrogen compressor through a certain clustering algorithm, that is, to obtain the current working condition of the hydrogen compressor, so as to determine whether there is a problem with the current hydrogen compressor.

[0004] However, the relative movement and vibration of the internal components of the hydrogen compressor during operation will further aggravate the performance degradation and aging of the internal parts of the hydrogen compressor.

[0005] Therefore, the existing technical methods for determining whether there is a problem with the hydrogen compressor have the following problems: ① Various vibration parameters of the hydrogen compressor influence each other and will affect the exhaust pressure in the future. This means that the existing technical methods can only obtain the current working conditions of the hydrogen compressor, but cannot accurately predict the working conditions of the hydrogen compressor in the future.

[0006] ② When the clustering algorithm does not have the ability to autonomously generate cluster results (that is, the cluster results of the clustering algorithm are completely set by the technicians, and the clustering algorithm will not generate new cluster clusters and corresponding cluster results): If a new operating condition occurs in the actual operation of the hydrogen compressor, and any set cluster result is not compatible with the current operating condition of the hydrogen compressor, then the current clustering algorithm will still output a cluster result set by the technicians, that is, this clustering algorithm has poor flexibility and cannot output truly accurate hydrogen compressor operating conditions.

[0007] ③ When the clustering algorithm has the ability to autonomously generate cluster results (that is, the clustering algorithm will autonomously generate new clusters and corresponding cluster results based on the cluster results set by the technicians): As the number of collected samples increases, the cluster results will continue to increase, or even grow explosively. Technicians can directly take corresponding measures on the hydrogen compressor based on the set cluster results; however, the new cluster results require verification and analysis by technicians to confirm whether measures need to be taken on the hydrogen compressor and what measures to take; and the verification and analysis of technicians are lagging, and this greatly increases the workload of technicians. In actual applications, after verification and analysis by technicians, it was found that: some new cluster results are completely wrong; some new cluster results are correct, but they can completely belong to a certain set cluster result, and only a small number of new cluster results are accurate and different from the set cluster results.

[0008] Therefore, how to improve the accuracy of hydrogen compressor operating status monitoring based on vibration parameters has become a difficult problem that needs to be solved urgently in hydrogen compressor monitoring technology. Summary of the invention

[0009] The purpose of the present invention is to overcome the deficiencies of the above-mentioned prior art and to provide a hydrogen compressor state monitoring method based on vibration parameters, which can improve the accuracy of hydrogen compressor operating state monitoring based on vibration parameters.

[0010] To achieve the above object, the present invention adopts the following technical solutions: A method for monitoring the state of a hydrogen compressor based on vibration parameters comprises the following steps: S1, for any vibration parameter of the hydrogen compressor: according to the window parameter of the current sliding window, obtain the vibration data of the current sliding window; the sliding window is arranged in time order; S2, calculating the statistical data and vibration characteristic vector of the current sliding window according to the vibration data of the current sliding window; the window parameters, vibration data, statistical data and vibration characteristic vector of the current sliding window together constitute the current sliding window information; S3, according to the sliding window information of each vibration parameter between the current monitoring moment and the previous monitoring moment and the exhaust pressure at the current monitoring moment, each clustering algorithm outputs the cluster result corresponding to the current monitoring moment; and at the same time calculates the weight coefficient of each clustering algorithm at the current monitoring moment; S4, the clustering algorithm weight coefficients corresponding to the same cluster results are accumulated as the scores of the corresponding cluster results, and then the cluster result with the highest score is used as the operating status of the hydrogen compressor at the current monitoring moment.

[0011] Preferably, after S2, S2' is further included: S2' calculates the window parameters of the next sliding window according to the statistical data and window parameters of the current sliding window.

[0012] Preferably, when the current hydrogen compressor is monitored for the first time, or during the first operation after the current hydrogen compressor replaces one or more key components, a new monitoring cycle is entered for any vibration parameter of the current hydrogen compressor, and the window parameters of the first sliding window in the new monitoring cycle are initial values; the window parameters include the window length and the sliding step; each sliding window contains only a number of vibration data of one vibration parameter arranged in time.

[0013] Preferably, S2' also includes the following contents: Remember the current sliding window The window length is , t is a positive integer, the current sliding window The previous sliding window is recorded as , then the next sliding window The window length : ; ; ; ; ; in, Indicates the current sliding window The window length adjustment amount; Indicates the next sliding window The window length adjustment amount; f represents the current sliding window The right boundary moment corresponds to the rotation frequency of the component where the vibration parameter is located; Indicates rounding up; is the first adjustment factor; is the second adjustment factor; Represents the weight coefficient of the i-th clustering algorithm. A total of n clustering algorithms are used, that is, 1≤i≤n; Represents sliding window Intra-cluster entropy in the ith clustering algorithm; Indicates that from the sliding window Start, including sliding window Inside, count the historical maximum entropy value of m sliding windows forward, where m is a positive integer and m≤t; Represents sliding window The mean vector of The modulus length is the sliding window With sliding window The difference between the average values ​​of the vibration data, The direction of the sliding window The average value of the vibration data points to the sliding window Average value of vibration data; express The 2-norm of ; is the maximum value function; Represents sliding window The intra-cluster entropy in the i-th clustering algorithm, Represents sliding window Intra-cluster entropy in the ith clustering algorithm; Indicates that from the sliding window Start, including sliding window In the process of i changing from 1 to n, we get the intra-cluster entropy of the corresponding clustering algorithm by counting m sliding windows forward. represents covariance; represents variance; Indicates the time constant of the hydrogen compressor system; Indicates the current sliding window The sampling period of vibration data is determined by the acquisition frequency of the corresponding sensor; Indicates the current sliding window The maximum permissible drift rate of the vibration parameters; Indicates the current sliding window Rated values ​​of vibration parameters.

[0014] Preferably, in S2, calculating the vibration feature vector of the current sliding window according to the vibration data of the current sliding window further includes the following sub-steps: S21, performing local mean decomposition on the vibration parameter signal corresponding to the vibration parameter in the current sliding window: ; Wherein, T represents time; X(T) represents the vibration parameter signal in the current sliding window, and the N vibration data contained in the current sliding window are fitted into a vibration parameter signal curve, and the vibration parameter signal represented by this vibration parameter signal curve is X(T); represents the kth PF component, k=1,...,K, and K is a positive integer greater than 1; represents the Kth residual, is a monotonic function; S22, extract the characteristic parameters of each PF component to form the vibration characteristic vector of the current sliding window: ; ; ; ; in, represents the kth PF component The skewness coefficient of represents the kth PF component The kurtosis coefficient of represents the kth PF component energy; represents the kth PF component The energy ratio in the vibration parameter signal X(T); represents the hth vibration data in the current sliding window arranged in time order; express The average value of the N PF component values ​​that are at the same time point as the N vibration data in the current sliding window; express The standard deviation of the N PF component values ​​that are the same as the N vibration data time points in the current sliding window; a represents the time point at the left boundary of the current sliding window; b represents the time point at the right boundary of the current sliding window; E represents the energy of the vibration parameter signal X(T); S23, based on the characteristic parameters of the K PF components, obtain K vibration characteristic vectors of the current sliding window: ; in, Represents the kth vibration eigenvector of the current sliding window.

[0015] Preferably, the next sliding window The sliding step length for: ; ; ; in, Indicates the next sliding window The overlap ratio; Indicates the current sliding window The overlap ratio; Indicates the next sliding window The attenuation coefficient of Indicates the target overlap ratio; Indicates the total number of sliding windows that need to transition; and They are all known quantities determined by the operating status of the hydrogen compressor at the last monitoring moment; Indicates that the next sliding window is included The remaining number of sliding windows that need to transition, , Indicates that the current sliding window is included The remaining number of sliding windows that need to be transitioned.

[0016] Preferably, S3 further includes the following contents: n different clustering algorithms are used, among which some clustering algorithms do not have the ability to generate cluster results autonomously, while others have the ability to generate cluster results autonomously; the sliding window information of each vibration parameter between the current monitoring moment and the previous monitoring moment and the exhaust pressure at the current monitoring moment are sent to each clustering algorithm, and each clustering algorithm outputs the cluster result corresponding to the hydrogen compressor at the current monitoring moment; at the same time, the weight coefficient of each clustering algorithm at the current monitoring moment is calculated , 1≤i≤n and i is a positive integer: if the current monitoring moment is the first monitoring moment in the current monitoring cycle, the weight coefficients of each clustering algorithm at the current monitoring moment are obtained based on solving the multi-objective optimization function; if the current monitoring moment is not the first monitoring moment in the current monitoring cycle, the weight coefficients of each clustering algorithm at the previous monitoring moment are used to obtain the weight coefficients of each clustering algorithm at the current monitoring moment.

[0017] Preferably, the weight coefficients of each clustering algorithm at the current monitoring moment are obtained based on solving a multi-objective optimization function, and the following contents are also included: constructing a multi-objective optimization function F and then solving it to obtain the value of the weight coefficient of each clustering algorithm at the current monitoring moment: ; ; The constraints are: ; in, is the second constant parameter; Represents the weight coefficient corresponding to the i-th clustering algorithm; represents the sum of squared errors of the i-th clustering algorithm; represents the first weight matrix, which is a column vector consisting of weight coefficients; represents the second weight matrix, which is the first weight matrix The transpose of is a row vector; Represents the first weight matrix With the correlation matrix The quadratic form of is the regularization parameter.

[0018] Preferably, the weight coefficients of the clustering algorithms at the current monitoring moment are obtained based on the weight coefficients of the clustering algorithms at the previous monitoring moment, and the following contents are also included: The current monitoring time is , the last monitoring time is , z ≥ 2 and z is a positive integer, then the current monitoring time The weight coefficient of the i-th clustering algorithm for: ; in, Indicates the last monitoring time The i-th clustering algorithm weight coefficient; Indicates the last monitoring time The j-th clustering algorithm weight coefficient, 1≤j≤n and j is a positive integer; represents the learning rate; Represents the global distribution at the last monitoring moment; Represents the distribution of the i-th clustering algorithm at the last monitoring moment; represents the distribution of the jth clustering algorithm at the last monitoring moment; represents JS divergence; Representation distribution With global distribution JS divergence; Representation distribution With global distribution JS divergence.

[0019] Preferably, S4 also includes S5: S5, if the cluster result obtained by the clustering algorithm with the ability to autonomously generate cluster results does not become the cluster result with the highest score, then the cluster result obtained by the clustering algorithm with the ability to autonomously generate cluster results will be recorded as a set to be verified. After the technicians regularly verify and analyze the set to be verified, if the cluster results obtained by a clustering algorithm in the set to be verified are considered correct by the technicians for y consecutive times and are different from the cluster results set by the technicians, then the technicians increase the weight coefficient of the corresponding clustering algorithm.

[0020] The beneficial effects of the present invention are: (1) The hydrogen compressor state monitoring method of the present invention can improve the accuracy of monitoring the operating state of the hydrogen compressor based on vibration parameters.

[0021] (2) A single parameter cannot effectively realize the monitoring and early warning of the equipment. The hydrogen compressor status monitoring method of the present invention does not directly process a single type of data collected by the sensor, but uses the sliding window as the unit of data collection to cluster the sliding window information between two adjacent monitoring moments. For any vibration parameter, the vibration data in a sliding window is time-series, and the adjacent sliding windows are also time-series (new sliding windows can only be born with the passage of time); there is also some overlap of vibration data between adjacent sliding windows, which enables the clustering algorithm to mine and learn the potential relationship and correlation between adjacent sliding windows when processing sliding window information with time series, thereby improving the accuracy of the cluster results obtained by each clustering algorithm in the present invention.

[0022] (3) In the hydrogen compressor status monitoring method of the present invention, a sliding window only contains one type of vibration parameter. The sliding windows of different vibration parameters in the same time period overlap because the time when the sensor collects data overlaps, so the sliding windows also overlap in time. The clustering algorithm in the present invention is not based on the isolated vibration data at a certain moment; but based on the sliding window information of this kind of time-series, temporally correlated and overlapping vibration data, and there is also temporal overlap between the sliding windows of different vibration parameters. The clustering algorithm will also mine and learn the potential relationship and correlation between these sliding window information of different vibration parameters with temporal overlap and the exhaust pressure, which enables the clustering algorithms in the present invention to make a more accurate prediction of the working conditions of the current hydrogen compressor in the future, thereby improving the accuracy of the cluster results output by each clustering algorithm; this also greatly improves the accuracy of the new cluster clusters and the corresponding cluster results obtained by the clustering algorithm with the ability to autonomously generate cluster results.

[0023] (4) The window length and sliding step of the sliding window are directly related to the sample data input into each clustering algorithm, and indirectly related to the accuracy of the cluster results output by each clustering algorithm. In each monitoring cycle of the present invention, the window length and sliding step are adjusted automatically based on the previous sliding window, the previous sliding windows and the cluster entropy obtained by each clustering algorithm based on the previous sliding windows. No manual intervention is required. The technician only needs to set the window parameters (i.e., the initial value) of the first sliding window in each monitoring cycle, which greatly reduces the labor cost.

[0024] (5) The present invention not only has a high degree of automation in adjusting the window length and sliding step size of the sliding window during the entire monitoring process, but also balances the computational overhead and storage resource usage in the process of processing the sliding window information. It also enables the clustering algorithm to better mine and learn the potential relationship and correlation between the sliding windows, so that each clustering algorithm can better process the sliding window information and effectively perceive the long-term slowly deteriorating monitoring objects.

[0025] (6) The sliding window information of the present invention includes the vibration feature vector of the sliding window, the time-frequency distribution results of the vibration data in the sliding window, the distribution of signal energy at different spatial scales, and the sensitivity coefficient to the surface damage fault of the body, thereby further improving the perception sensitivity of each clustering algorithm to the hydrogen compressor state.

[0026] (7) The monitoring method of the present invention will automatically update the monitoring cycle, which is reflected in: when the current hydrogen compressor is monitored for the first time, or during the first operation after the current hydrogen compressor replaces one or more key components, a new monitoring cycle is entered for any vibration parameter of the current hydrogen compressor. Even if it is a hydrogen compressor of the same model, it has passed the pre-factory test and has certain pre-factory test data; however, the process of a hydrogen compressor being transported, installed on site and officially running is the period monitored by the monitoring method of the present invention, that is, the first time a hydrogen compressor is monitored. Therefore, before the first monitoring of a hydrogen compressor, the hydrogen compressor may still be damaged or incompatible due to transportation and on-site installation. The same is true for the first operation of the current hydrogen compressor after replacing one or more key components. Both of these situations mean that the hydrogen compressor as a whole needs to go through the running-in period, stabilization period and degradation period again. And in each monitoring cycle, the window length and sliding step are based on the previous sliding window, so the window length and sliding step of the new sliding window in these two cases cannot be obtained based on the previous sliding window, so we need to let the hydrogen compressor in these two cases enter a new monitoring cycle.

[0027] (8) The update of the window length and sliding step size of the sliding window is related to the changes in the frequency of sample input and the amount of sample data for the subsequent clustering algorithm. The monitoring method of the present invention automatically updates the monitoring cycle and automatically adjusts the window length and sliding step size of the sliding window in each monitoring cycle to make the frequency of sample input and the amount of sample data adaptive to the subsequent clustering algorithm processing process, further improving the efficiency of the entire monitoring process and the accuracy of the cluster results output by the clustering algorithm; therefore, the monitoring method of the present invention can better adapt to each hydrogen compressor it monitors.

[0028] (9) The hydrogen compressor status monitoring method of the present invention does not use a single clustering algorithm to monitor the operating status of the hydrogen compressor, but uses multiple clustering algorithms for joint monitoring. These clustering algorithms include not only clustering algorithms that have the ability to autonomously generate cluster results, but also clustering algorithms that do not have the ability to autonomously generate cluster results. The cluster results obtained by each of these clustering algorithms may be partially the same or completely different. However, the present invention will ultimately use the cluster result with the highest score as the operating status of the hydrogen compressor at the current monitoring time. The cluster result with the highest score is also the cluster result of most clustering algorithms. After random inspection and verification by technical personnel, they are basically the operating status of the hydrogen compressor at the current monitoring time.

[0029] (10) The score of the cluster result is obtained by accumulating the weight coefficients of the clustering algorithms corresponding to the same cluster result, and the weight coefficients in the monitoring method of the present invention also change with the monitoring cycle and the monitoring time within each monitoring cycle: the weight coefficients of each clustering algorithm at the first monitoring time in each monitoring cycle are determined by solving the multi-objective optimization function; and the weight coefficients of each clustering algorithm at the remaining monitoring times in each monitoring cycle need to be obtained based on the weight coefficients of each clustering algorithm at the previous monitoring time. This ensures that the weight coefficients of each clustering algorithm will not change suddenly while changing with the monitoring time; and it has been verified by technical personnel that only when a clustering algorithm obtains several cluster results in succession that are all the operating status of the hydrogen compressor at the corresponding monitoring time, the weight coefficient of the clustering algorithm will gradually increase.

[0030] (11) The hydrogen compressor status monitoring method of the present invention also takes into account a special case with an extremely low probability: if the clustering algorithm with the ability to autonomously generate cluster results obtains a new cluster result corresponding to the current monitoring time, and the weight coefficient of the clustering algorithm that generates this new cluster result is small, then this new cluster result cannot be used as the operating status of the hydrogen compressor at the current monitoring time; and the content of S5 is adopted accordingly. In this way, on the one hand, it can be avoided that the clustering algorithm with the ability to autonomously generate cluster results will generate multiple new cluster results without restraint to interfere with the technicians' evaluation of the operating status of the hydrogen compressor, greatly reducing the workload of the technicians. On the other hand, it can also ensure through a small amount of manual intervention that when the hydrogen compressor really has a situation other than the cluster result preset by the technicians, the clustering algorithm with a high weight coefficient and the ability to autonomously generate cluster results can accurately determine the operating status of the hydrogen compressor at the current monitoring time.

[0031] (12) In the hydrogen compressor status monitoring method of the present invention, the operating status of the hydrogen compressor at the current monitoring time can be accurately determined, and the operating status of the hydrogen compressor includes not only the operating condition of the hydrogen compressor at the current monitoring time, but also the prediction of the operating condition of the current hydrogen compressor in the future; so the number of cluster results pre-set by the technician can be more: for example, the judgment of the hydrogen compressor operating condition at the current monitoring time is the same in multiple cluster results, but the prediction of the operating condition of the current hydrogen compressor in the future is different. This is directly different from the prior art that determines the operating condition of the hydrogen compressor at the current monitoring time based on the exhaust pressure collected by the sensor; and the monitoring method of the present invention will not be prone to misjudgment due to the technician pre-setting too many cluster results as in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a flow chart of a hydrogen compressor state monitoring method based on vibration parameters of the present invention; Figure 2is the clustering result obtained using the GMM clustering algorithm; Figure 3 This is the clustering result obtained using the DBSCAN clustering algorithm; Figure 4 This is the clustering result obtained using the OPTICS clustering algorithm; Figure 5 This is the clustering result obtained using the hydrogen compressor state monitoring method of the present invention. DETAILED DESCRIPTION

[0033] In order to make the technical solution of the present invention clearer and more specific, the present invention is clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The solutions derived from equivalent replacements of the technical features of the technical solution of the present invention and conventional reasoning by ordinary technicians in this field without making any creative work all fall within the protection scope of the present invention.

[0034] like Figure 1 As shown, it is a flow chart of a hydrogen compressor state monitoring method based on vibration parameters of the present invention, which includes the following steps: S1, for any vibration parameter of the hydrogen compressor: according to the window parameter of the current sliding window, obtain the vibration data of the current sliding window; the sliding window is arranged in time order; S2, calculating the statistical data and vibration characteristic vector of the current sliding window according to the vibration data of the current sliding window; the window parameters, vibration data, statistical data and vibration characteristic vector of the current sliding window together constitute the current sliding window information; S3, according to the sliding window information of each vibration parameter between the current monitoring moment and the previous monitoring moment and the exhaust pressure at the current monitoring moment, each clustering algorithm outputs the cluster result corresponding to the current monitoring moment; and at the same time calculates the weight coefficient of each clustering algorithm at the current monitoring moment; S4, the clustering algorithm weight coefficients corresponding to the same cluster results are accumulated as the scores of the corresponding cluster results, and then the cluster result with the highest score is used as the operating status of the hydrogen compressor at the current monitoring moment.

[0035] After S2 also include S2´: S2´, calculates the window parameters of the next sliding window based on the statistical data and window parameters of the current sliding window.

[0036] In S1, the following are also included: The vibration parameters of hydrogen compressors are classified by components into the vibration parameters of south / north intake valves, south / north exhaust valves, crankshaft vibration parameters, motor vibration parameters, machine body vibration parameters, bearing vibration parameters, etc. Specifically, they include the compressor rotation frequency, crankshaft rotation angle, and the vibration amplitude of the south exhaust valve along the x, y, and z directions.

[0037] The key components of the hydrogen compressor include diaphragm assembly, gas valve assembly, crankshaft mechanism, sealing system, cooling system, drive motor and control system, etc. Among them, the diaphragm assembly is the core power transmission component, and changes in its diaphragm material, thickness, number of layers, etc. are all considered as replacement of the diaphragm assembly; the gas valve assembly is one of the most critical components, including the intake valve / exhaust valve, and changes in valve sheet material, spring stiffness, valve clearance, etc. are all considered as replacement of the gas valve assembly; the crankshaft mechanism is the core of power conversion, and changes in its clearance, counterweight, etc. are all considered as replacement of the crankshaft mechanism; the sealing system includes static seals and dynamic seals, and changes in its packing materials and sizes are all considered as replacement of the sealing system; changes in the properties of the cooling medium in the cooling system are considered as replacement of the cooling system; changes in the motor efficiency, power, PID control parameters, etc. in the drive motor and control system are all considered as replacement of the drive motor and control system.

[0038] When the current hydrogen compressor is monitored for the first time, or during the first operation after replacing one or more key components of the current hydrogen compressor, a new monitoring cycle is entered for any vibration parameter of the current hydrogen compressor, and the window parameters of the first sliding window in the new monitoring cycle are all initial values. The window parameters include the window length and the sliding step length. The initial values ​​of the window parameters are set by the technicians, and the initial values ​​of the windows of different vibration parameters can be different.

[0039] In addition to the above situation, no matter how many times the current hydrogen compressor is restarted after being shut down, for any vibration parameter of the hydrogen compressor, it is in the same monitoring cycle. In the same monitoring cycle, for a certain vibration parameter, assuming that the last sliding window of the current hydrogen compressor during the last operation is the 51st sliding window in the current cycle, the first sliding window after the current hydrogen compressor is restarted is the 52nd sliding window in the current cycle.

[0040] Each sliding window contains a number of vibration data of only one vibration parameter arranged in time. There are a number of vibration data overlaps between adjacent sliding windows of the same vibration parameter.

[0041] The sliding direction of the sliding window is unique and synchronized with the timing. The sliding window slides a sliding step each time. The sliding step is a time quantity. When the sliding window completes a sliding, it becomes a new sliding window. Each time the sliding window slides, its sliding step is the sliding step in the window parameters of the current sliding window.

[0042] For the same vibration parameter: the window length and window sliding step will directly affect the number of vibration data overlaps between adjacent sliding windows. The window length directly determines the number of vibration data in the sliding window.

[0043] The vibration data is collected regularly by the corresponding sensor, and the collection frequency of the sensor is generally fixed.

[0044] In S2: The statistical data of the current sliding window include: the mean value of vibration data, the variance of vibration data, the standard deviation of vibration data, the median of vibration data, the first quartile of vibration data, the third quartile of vibration data, the interquartile range of vibration data, the skewness of vibration data, the kurtosis of vibration data, the maximum value of vibration data, the minimum value of vibration data, and the coefficient of variation of vibration data.

[0045] “Calculating the vibration feature vector of the current sliding window according to the vibration data of the current sliding window” also includes sub-steps S21 to S23: S21, performing local mean decomposition on the vibration parameter signal corresponding to the vibration parameter in the current sliding window: ; Wherein, T represents time; X(T) represents the vibration parameter signal in the current sliding window. The current sliding window contains N vibration data. These N vibration data are fitted into a vibration parameter signal curve. The vibration parameter signal represented by this vibration parameter signal curve is X(T). represents the kth PF component, k=1,...,K, and K is a positive integer greater than 1; Represents the Kth residual; Determination of K: In the process of local mean decomposition of the vibration parameter signal X(T), the first PF component is obtained first and the first margin , when the first margin If it is not a monotonic function, then continue to add the first residual Decomposed into the second PF component and the second margin , until the Kth residual is a monotonic function.

[0046] Therefore, after local mean decomposition, the vibration parameter signal X(T) is represented as the sum of K PF components and 1 residual.

[0047] The vibration parameter signal is subjected to local mean decomposition to obtain multiple groups of PF components with instantaneous physical significance and the time-frequency distribution information, thereby reflecting the time-frequency distribution results of the vibration parameter signal and the distribution of signal energy at different spatial scales.

[0048] S22, extract the characteristic parameters of each PF component to form the vibration characteristic vector of the current sliding window: ; ; ; ; in, represents the kth PF component The skewness coefficient of represents the kth PF component The kurtosis coefficient of represents the kth PF component energy; represents the kth PF component The energy ratio in the vibration parameter signal X(T); represents the hth vibration data in the current sliding window arranged in time order; express The average value of the N PF component values ​​that are at the same time point as the N vibration data in the current sliding window; express The standard deviation of the N PF component values ​​in the same time point as the N vibration data in the current sliding window; a represents the time point of the left boundary of the current sliding window; b represents the time point of the right boundary of the current sliding window; E represents the energy of the vibration parameter signal X(T).

[0049] The skewness coefficient is used to describe the degree of deviation from the symmetry of the distribution. When the distribution is symmetrical, the skewness coefficient is zero. When the skewness coefficient is greater than 0, it means that the distribution is concentrated on the right side and the distribution is right-skewed. When the skewness coefficient is less than 0, it means that the distribution is concentrated on the left side and the distribution is left-skewed. The kurtosis coefficient reflects the statistical value of the distribution characteristics of the random variable. It is a dimensionless parameter that is particularly sensitive to impact signals and is particularly suitable for diagnosing damage faults on the surface of the body.

[0050] S23, based on the characteristic parameters of the K PF components, obtain K vibration characteristic vectors of the current sliding window: ; in, Represents the kth vibration eigenvector of the current sliding window.

[0051] The vibration eigenvector of the sliding window includes the time-frequency distribution results of the vibration data in the sliding window, the distribution of signal energy at different spatial scales, and the sensitivity coefficient (i.e., kurtosis coefficient) to the surface damage of the aircraft body.

[0052] The following are also included in S2´: The window length of the sliding window covers more than one integer period of the corresponding vibration parameter; Remember the current sliding window The window length is , t is a positive integer, the current sliding window The previous sliding window is recorded as , then the next sliding window The window length : ; ; ; ; ; in, Indicates the current sliding window The window length adjustment amount; Indicates the next sliding window The window length adjustment amount; f represents the rotation frequency of the component where the vibration parameter of the current sliding window is located, which is the current sliding window The right boundary moment corresponds to the rotation frequency of the component where the vibration parameter is located; Indicates rounding up; is the first adjustment factor; is the second adjustment factor; represents the weight coefficient of the i-th clustering algorithm. In the present invention, a total of n clustering algorithms are used, 1≤i≤n; Represents sliding window Intra-cluster entropy in the ith clustering algorithm; Indicates that from the sliding window Start (including sliding window ) The historical maximum entropy value of m sliding windows forward, where m is a positive integer and m≤t; Represents sliding window The mean vector of The modulus length is the sliding window With sliding window The difference between the average values ​​of the vibration data, The direction of the sliding window The average value of the vibration data points to the sliding window Average value of vibration data; express The 2-norm of ; is the maximum value function; Represents sliding window The intra-cluster entropy in the i-th clustering algorithm, Represents sliding window Intra-cluster entropy in the ith clustering algorithm; It represents the intra-cluster entropy in the corresponding clustering algorithm obtained from the beginning of the sliding window (including the sliding window) and the number of sliding windows forward when i changes from 1 to n; represents covariance; represents variance; Indicates the time constant of the hydrogen compressor system; Indicates the current sliding window The sampling period of vibration data is determined by the acquisition frequency of the corresponding sensor; Indicates the current sliding window The maximum permissible drift rate of the vibration parameters is set by the technicians based on experience; Indicates the current sliding window Rated values ​​of vibration parameters.

[0053] If 1=t<m, then from the sliding window Start (including sliding window ) There are only t sliding windows counting forward, then ; If 2=t<m, then ; If 3 = t < m, then .

[0054] Optionally, calculate the next sliding window The sliding step length : = , where γ is the first constant parameter, which is defined by the technicians. In this embodiment, γ=0.2.

[0055] Optionally, calculate the next sliding window The sliding step length : ; ; ; in, Indicates the next sliding window The overlap ratio; Indicates the current sliding window The overlap ratio; Indicates the next sliding window The attenuation coefficient of Indicates the target overlap ratio; Indicates the total number of sliding windows that need to transition; and They are all known quantities determined by the operating status of the hydrogen compressor at the last monitoring moment; Indicates that the next sliding window is included The remaining number of sliding windows that need to transition, , Indicates that the current sliding window is included The remaining number of sliding windows that need to be transitioned.

[0056] The present invention determines the "next sliding window The sliding step length In the process of ": Based on the smooth transition algorithm of state transfer, the state transfer equation is constructed, that is, and ; Timely adjustment of the sliding step size of the next sliding window means timely adjustment of the number of overlapping vibration data between adjacent sliding windows; and by continuously adjusting the transition of several sliding step sizes, that is, gradually changing the sliding step size of several sliding windows, a large stage-by-stage adjustment of the sliding step size can be achieved, thereby avoiding excessive changes in the sliding step size of adjacent sliding windows, thereby affecting the subsequent clustering algorithm's mining and learning of the potential relationship and correlation between adjacent sliding windows.

[0057] Sliding Window This is the first sliding window.

[0058] In this example, if the sliding window The average value of vibration data is greater than the sliding window The average value of vibration data is The direction is positive, otherwise it is negative.

[0059] The window length is adjusted every time the sliding window slides. After completing one sliding, the window length is also adjusted, and the next sliding window is formed. The window length is The window length of the sliding window can be adjusted by simply adjusting the right edge of the sliding window; the left edge of the sliding window does not need to be adjusted, and the distance between the left edges of adjacent sliding windows is a sliding step length.

[0060] In the calculation of intra-cluster entropy, if the clustering algorithm is Kmeans++ clustering algorithm, hierarchical clustering algorithm, DBSCAN clustering algorithm, GMM clustering algorithm, OPTICS clustering algorithm, etc., the intra-cluster entropy based on distance is calculated; for the spectral clustering algorithm, the intra-cluster entropy based on similarity is calculated.

[0061] In S3, the following are also included: n different clustering algorithms are used, among which some clustering algorithms do not have the ability to autonomously generate cluster results, while the other clustering algorithms have the ability to autonomously generate cluster results; sliding window information of each vibration state parameter between the current monitoring moment and the previous monitoring moment and the exhaust pressure at the current monitoring moment are sent to each clustering algorithm, and each clustering algorithm outputs the cluster result corresponding to the hydrogen compressor at the current monitoring moment; At the same time, calculate the weight coefficient of each clustering algorithm at the current monitoring moment , 1≤i≤n and i is a positive integer: if the current monitoring moment is the first monitoring moment in the current monitoring cycle, the weight coefficients of each clustering algorithm at the current monitoring moment are obtained based on solving the multi-objective optimization function; if the current monitoring moment is not the first monitoring moment in the current monitoring cycle, the weight coefficients of each clustering algorithm at the previous monitoring moment are used to obtain the weight coefficients of each clustering algorithm at the current monitoring moment.

[0062] The exhaust pressure is collected by the air pressure sensor.

[0063] In this embodiment, the sliding window information of each vibration parameter between the current monitoring moment and the previous monitoring moment is respectively sent to each clustering algorithm. This sliding window refers to a sliding window whose right boundary is located between the current monitoring moment and the previous monitoring moment.

[0064] In this embodiment, 10 different clustering algorithms are used, namely AP clustering algorithm (affinity propagation clustering algorithm), Agglomerative clustering algorithm (agglomerative hierarchical clustering algorithm), BIRCH clustering algorithm (balanced iterative reduction clustering algorithm), DBSCAN clustering algorithm (density-based spatial clustering application algorithm), GMM clustering algorithm (Gaussian mixture model clustering algorithm), Divisive clustering algorithm (divisive hierarchical clustering algorithm), Kmeans++ clustering algorithm (K-means++ clustering algorithm), MeanShift clustering algorithm (mean shift clustering algorithm), OPTICS clustering algorithm (ordered point clustering structure recognition algorithm), Spectral clustering algorithm (spectral clustering algorithm); the corresponding weight coefficients are ~ .

[0065] Among them, the Agglomerative clustering algorithm, GMM clustering algorithm, Divisive clustering algorithm, Kmeans++ clustering algorithm and Spectral clustering algorithm do not have the ability to autonomously generate cluster results; the AP clustering algorithm, BIRCH clustering algorithm, DBSCAN clustering algorithm, MeanShift clustering algorithm and OPTICS clustering algorithm have the ability to autonomously generate cluster results.

[0066] "Obtaining the weight coefficients of each clustering algorithm at the current monitoring moment based on solving the multi-objective optimization function" also includes the following: Based on Lyapunov stability theory, a multi-objective optimization function F is constructed and solved to obtain the value of the weight coefficient of each clustering algorithm at the current monitoring moment: ; ; The constraints are: ; in, is the second constant parameter; Represents the weight coefficient corresponding to the i-th clustering algorithm; represents the sum of squared errors of the i-th clustering algorithm; represents the first weight matrix, which is a column vector consisting of weight coefficients; represents the second weight matrix, which is the first weight matrix The transpose of is a row vector; Represents the first weight matrix With the correlation matrix The quadratic form of is the regularization parameter.

[0067] Correlation Matrix Used to describe the relationship between different clustering algorithms; regularization parameter It is set by technicians to control the impact of correlation between clustering algorithms.

[0068] In this embodiment, the multi-objective optimization function F is converted into a convex optimization using the CVXPY tool, and then the built-in solvers ECOS and SCS are called to solve it.

[0069] “Acquiring the weight coefficients of each clustering algorithm at the current monitoring time based on the weight coefficients of each clustering algorithm at the previous monitoring time” also includes the following: The current monitoring time is , the last monitoring time is , z ≥ 2 and z is a positive integer, then the current monitoring time The weight coefficient of the i-th clustering algorithm for: ; in, Indicates the last monitoring time The i-th clustering algorithm weight coefficient; Indicates the last monitoring time The j-th clustering algorithm weight coefficient; 1≤j≤n and j is a positive integer; Represents the learning rate, which is set by technicians to control the speed of updating the algorithm weight coefficients. When it increases, it means that the algorithm adjusts the weight coefficient more actively to adapt to the distribution faster; Represents the global distribution at the last monitoring moment. The global distribution at the last monitoring moment can be obtained based on the vibration data recorded in the current monitoring period and the weight coefficients of each algorithm, which is a known quantity. Represents the distribution of the i-th clustering algorithm at the last monitoring moment; represents the distribution of the jth clustering algorithm at the last monitoring moment; represents JS divergence; Representation distribution With global distribution JS divergence, used to measure and The difference in distribution With global distribution The more similar, the The larger the value; Representation distribution With global distribution JS divergence, used to measure and The difference in distribution With global distribution The more similar, the The larger the value.

[0070] After S4, S5 is also included: S5. If the cluster result obtained by the clustering algorithm with the ability to autonomously generate cluster results does not become the cluster result with the highest score, then the cluster result obtained by the clustering algorithm with the ability to autonomously generate cluster results will be recorded as a set to be verified. After the technicians regularly verify and analyze the set to be verified, if the cluster results obtained by a clustering algorithm in the set to be verified are considered correct by the technicians for y consecutive times and are different from the cluster results set by the technicians, then the technicians will increase the weight coefficient of the corresponding clustering algorithm.

[0071] In this embodiment, y=5.

[0072] In the prior art, a single type of data collected by the sensor, such as exhaust pressure, is directly processed, and because the data at the current time point is clustered to obtain a cluster result, the corresponding cluster result is output as the current working condition of the hydrogen compressor. Therefore, the prior art can generally only be used to determine the current working condition of a hydrogen compressor; and this determination of the current working condition of a hydrogen compressor is also affected by the selected clustering algorithm itself, and this influence will directly manifest as an inaccurate judgment of the current working condition of the hydrogen compressor, which we have already explained in the background technology and will not be repeated here.

[0073] Assume that the technicians have set cluster result 1 as "the hydrogen compressor continues to operate normally" and cluster result 2 as "the hydrogen compressor is currently operating normally, but in a low-pressure operating state". It can be seen that cluster result 1 not only includes the judgment of the current operating condition "the hydrogen compressor is operating normally", but also includes the prediction of the current operating condition of the hydrogen compressor in the future period of time "continuous normal operation". Cluster result 2 not only includes the judgment of the current operating condition of the hydrogen compressor "the hydrogen compressor is operating normally", but also includes the prediction of the current operating condition of the hydrogen compressor in the future period of time "in a low-pressure operating state"; when one or several components in the hydrogen compressor are about to enter a fatigue state, the hydrogen compressor will currently operate normally, but in the future, the corresponding components will enter a fatigue state, causing the hydrogen compressor to enter a low-pressure operating state. Although the compressor in the low-pressure operating state is also operating normally, the components in the fatigue state may be damaged, causing the hydrogen compressor to be unable to operate. However, the clustering algorithm of the prior art (regardless of whether it has the ability to autonomously generate cluster results) is unable to well predict the operating condition of the current hydrogen compressor in the future because it performs clustering processing on the data at the current time point (for example, the current hydrogen compressor is indeed "in a low-pressure operating state" in the future, but the prior art determines that it will "continue to operate normally" in the future). Even if the current operating state of the hydrogen compressor should fall into the cluster where cluster result 2 is located, the clustering algorithm of the prior art will make it fall into cluster result 1.

[0074] A single parameter cannot effectively realize the monitoring and early warning of the equipment, and the hydrogen compressor status monitoring method of the present invention does not directly process a single type of data collected by the sensor, but uses the sliding window as the unit of data collection to cluster the sliding window information between two adjacent monitoring moments. For any vibration parameter, the vibration data in a sliding window is time-series, and there is also time-series between adjacent sliding windows (new sliding windows can only be born with the passage of time); there is also some overlap of vibration data between adjacent sliding windows, which enables the clustering algorithm to mine and learn the potential relationship and correlation between adjacent sliding windows when processing sliding window information with time-series, thereby improving the accuracy of the cluster results obtained by each clustering algorithm in the present invention.

[0075] In the hydrogen compressor status monitoring method of the present invention, only one type of vibration parameter is included in a sliding window. The sliding windows of different vibration parameters in the same time period overlap in time because the sensor collects data. Therefore, the sliding windows also overlap in time. The clustering algorithm in the present invention is not based on the isolated vibration data at a certain moment; but is based on the sliding window information of this kind of time-series, temporally correlated and overlapping vibration data, and there is also temporal overlap between the sliding windows of different vibration parameters. The clustering algorithm will also mine and learn the potential relationship and correlation between these sliding window information of different vibration parameters with temporal overlap and the exhaust pressure. This allows the clustering algorithms in the present invention to make a more accurate prediction of the working conditions of the current hydrogen compressor in the future, thereby improving the accuracy of the cluster results output by each clustering algorithm; this also makes the clustering algorithm with the ability to autonomously generate cluster results, and the accuracy of the new cluster clusters and corresponding cluster results obtained is greatly improved.

[0076] From the above analysis, it can be seen that the window length and sliding step of the sliding window are directly related to the sample data input into each clustering algorithm, and indirectly related to the accuracy of the cluster results output by each clustering algorithm. In each monitoring cycle of the present invention, the window length and sliding step are adjusted automatically based on the previous sliding window, according to the previous sliding windows and the cluster entropy obtained by each clustering algorithm based on the previous sliding windows. No manual intervention is required. The technician only needs to set the window parameters (i.e., the initial value) of the first sliding window in each monitoring cycle, which greatly reduces the labor cost. If the window length is too long or the sliding step is too short, the clustering algorithm will have a large increase in computational overhead in the process of processing sliding window information and occupy a large amount of storage resources; if the window length is too short or the sliding step is too long, although the computational overhead and the occupation of storage resources are reduced, the vibration data overlapping between adjacent sliding windows is also greatly reduced or even 0, and the sliding window distribution with time overlap between different vibration parameter sliding windows will also change, which is very unfavorable for the clustering algorithm to mine and learn the potential relationship and correlation between sliding windows, and even affects the accuracy of the cluster results output by each clustering algorithm. Therefore, the adjustment of the window length and sliding step of the sliding window in the whole monitoring process of the present invention is not only highly automated, but also such adjustment balances the computational overhead and the occupation of storage resources in the process of processing sliding window information, and also enables the clustering algorithm to better mine and learn the potential relationship and correlation between sliding windows, so that each clustering algorithm can better process sliding window information and effectively perceive the long-term slowly deteriorating monitoring objects.

[0077] The sliding window information of the present invention includes the vibration characteristic vector of the sliding window, the time-frequency distribution results of the vibration data in the sliding window, the distribution of signal energy at different spatial scales, and the sensitivity coefficient to the surface damage fault of the body, thereby further improving the perception sensitivity of each clustering algorithm to the state of the hydrogen compressor.

[0078] The monitoring method of the present invention will automatically update the monitoring cycle, which is reflected in: when the current hydrogen compressor is monitored for the first time, or in the first operation after the current hydrogen compressor replaces one or more key components, a new monitoring cycle is entered for any vibration parameter of the current hydrogen compressor. Even if it is a hydrogen compressor of the same model, it has passed the test before leaving the factory and has certain pre-factory test data; however, the process of a hydrogen compressor being transported, arriving at the site, installed and officially running is the period monitored by the monitoring method of the present invention, that is, the first time a hydrogen compressor is monitored, so before the first monitoring of a hydrogen compressor, the hydrogen compressor may still be damaged or incompatible due to transportation and on-site installation; and the same is true for the first operation of the current hydrogen compressor after replacing one or more key components; both of these situations mean that the hydrogen compressor as a whole needs to go through the running-in period, stabilization period and deterioration period again. And in each monitoring cycle, the window length and sliding step are based on the previous sliding window, so the window length and sliding step of the new sliding window in these two cases cannot be obtained based on the previous sliding window, so we need to let the hydrogen compressor in these two cases enter a new monitoring cycle.

[0079] Based on the above analysis, it can also be seen that the update of the window length and sliding step size of the sliding window is related to the frequency of sample input and the change of sample data volume for the subsequent clustering algorithm. The monitoring method of the present invention automatically updates the monitoring cycle and automatically adjusts the window length and sliding step size of the sliding window in each monitoring cycle to make the frequency of sample input and the amount of sample data adaptive to the subsequent clustering algorithm processing process, further improving the efficiency of the entire monitoring process and the accuracy of the cluster results output by the clustering algorithm; therefore, the monitoring method of the present invention can better adapt to each hydrogen compressor it monitors. For ease of understanding, for example: after entering a new monitoring cycle, the monitoring method of the present invention needs to frequently input samples and increase the amount of input sample data in order to better understand the current situation of the hydrogen compressor in the current monitoring cycle; it has been verified by technical personnel that the present invention does make the window length of the sliding window grow slowly within a period of time after the monitoring cycle is updated (i.e., the running-in period), and the sliding step of the sliding window is relatively short, so as to meet the needs of frequent sample input and increase the amount of input sample data during the running-in period of the current monitoring cycle; and in the middle period of the new monitoring cycle (i.e., the stable period), the window length and the sliding step of the sliding window are indeed increased significantly, and there is no need to frequently input samples or input a large amount of sample data during the stable period of the current monitoring cycle (reflected in the reduction of overlapping vibration data between adjacent sliding windows and the increase of the sliding step of the sliding window); subsequently, as the clustering algorithm determines the operating status of the hydrogen compressor, the frequency of sample input and the amount of sample data input will be increased because the hydrogen compressor enters the degradation period of the current monitoring cycle, which will not be repeated here.

[0080] The hydrogen compressor status monitoring method of the present invention does not use a single clustering algorithm to monitor the operating status of the hydrogen compressor, but uses multiple clustering algorithms for joint monitoring, and these clustering algorithms include not only clustering algorithms with the ability to autonomously generate cluster results, but also clustering algorithms without the ability to autonomously generate cluster results; the cluster results obtained by each of these clustering algorithms may be partially the same or may be completely different, but the present invention will ultimately use the cluster result with the highest score as the operating status of the hydrogen compressor at the current monitoring time. The cluster result with the highest score is also the cluster result of most clustering algorithms. After random inspection by technical personnel, they are basically the operating status of the hydrogen compressor at the current monitoring time.

[0081] The score of the cluster result is obtained by accumulating the weight coefficients of the clustering algorithms corresponding to the same cluster result, and the weight coefficients in the monitoring method of the present invention also change with the monitoring period and the monitoring time within each monitoring period: the weight coefficients of each clustering algorithm at the first monitoring time in each monitoring period are determined by solving the multi-objective optimization function; and the weight coefficients of each clustering algorithm at the remaining monitoring times in each monitoring period need to be obtained based on the weight coefficients of each clustering algorithm at the previous monitoring time. This ensures that the weight coefficients of each clustering algorithm will not mutate as they change with the monitoring time; and it has been verified by technical personnel that only when a clustering algorithm obtains several cluster results in succession that are all the operating status of the hydrogen compressor at the corresponding monitoring time, the weight coefficient of the clustering algorithm will gradually increase.

[0082] Considering the special case with extremely small probability: if the clustering algorithm with the ability to autonomously generate cluster results obtains a new cluster result corresponding to the current monitoring moment, and the weight coefficient of the clustering algorithm that generates this new cluster result is small, then this new cluster result cannot be used as the operating state of the hydrogen compressor at the current monitoring moment. Therefore, the present invention records the cluster results obtained by all clustering algorithms with the ability to autonomously generate cluster results as a set to be verified, that is, in S5, after the technicians regularly verify and analyze the set to be verified, if the cluster results obtained by a certain clustering algorithm in the set to be verified are considered correct by the technicians for y consecutive times, and the cluster results are different from the cluster results set by the technicians, then the technicians increase the weight coefficient of the corresponding clustering algorithm, which means that although the cluster results output by the clustering algorithm are not the cluster results pre-set by the technicians, they are highly accurate. On the one hand, this can prevent the clustering algorithm with the ability to autonomously generate cluster results from indiscriminately generating multiple new cluster results to interfere with the technicians' evaluation of the operating status of the hydrogen compressor, greatly reducing the workload of the technicians. On the other hand, a small amount of manual intervention can be used to ensure that when the hydrogen compressor really has a situation other than the cluster results preset by the technicians, the clustering algorithm with a high weight coefficient and the ability to autonomously generate cluster results can accurately determine the operating status of the hydrogen compressor at the current monitoring moment.

[0083] In the hydrogen compressor status monitoring method of the present invention, the operating status of the hydrogen compressor at the current monitoring moment can be accurately determined eventually, and the operating status of the hydrogen compressor includes not only the operating condition of the hydrogen compressor at the current monitoring moment, but also the prediction of the operating condition of the current hydrogen compressor in the future; so the number of cluster results pre-set by the technician can be more: for example, the judgment of the hydrogen compressor operating condition at the current monitoring moment is the same in multiple cluster results, but the prediction of the operating condition of the current hydrogen compressor in the future is different. This is directly different from the prior art that determines the operating condition of the hydrogen compressor at the current monitoring moment based on the exhaust pressure collected by the sensor; and the monitoring method of the present invention will not be prone to misjudgment due to the technician pre-setting too many cluster results as in the prior art.

[0084] like Figure 2 to Figure 4 The figure shows the clustering results obtained by technicians using the GMM clustering algorithm, DBSCAN clustering algorithm and OPTICS clustering algorithm respectively, based on the vibration of the inner ring of the intake valve and the average exhaust pressure collected by the sensor during one rotation of the crankshaft (i.e. 360 degrees); the horizontal axis is the serial number of the data segment, and the vertical axis represents the vibration, i.e. the vibration acceleration. Figure 2In the data, green data points represent operating condition 0, purple data points represent operating condition 1, and yellow data points represent operating condition 2. Operating condition 0 indicates that the hydrogen compressor operates normally, operating condition 1 indicates that the hydrogen compressor operates at low pressure and no components are in a fatigue state, and operating condition 2 indicates that the hydrogen compressor operates at low pressure and the inner ring of the north exhaust valve is in a fatigue state. The technical staff verified that there are a small number of data points that should belong to operating condition 1 but are mistakenly identified as green or yellow. The yellow data points are scattered in the other two groups of operating conditions, and the probability of being misidentified is very high. Figure 3 In the data, green data points represent operating condition 0, and yellow data points represent operating condition 1, where operating condition 1 means that the hydrogen compressor is running at low pressure and the inner ring of the north exhaust valve is in a fatigue state, and operating condition 0 means that the hydrogen compressor is running normally. The technical staff verified that most of the data points in the interval with a large deviation from the peak value are marked in yellow, and a small number are marked in green. At the same time, a small number of data points that are in the final cycle and should belong to operating condition 0 are incorrectly marked in yellow. Due to the lack of rich operating condition types, the deviated data points cannot be correctly marked. Figure 4 In the figure, the green data point represents condition 0, and the yellow data point represents condition 1. Condition 1 means that the hydrogen compressor is running at low pressure and the inner ring of the north exhaust valve is in a fatigue state, and condition 0 means that the hydrogen compressor is running normally. The technical staff verified that: compared with Figure 3 , the number of data points that are in the final cycle and should belong to condition 0 but are incorrectly marked as yellow is greatly reduced; however, there are still cases where the deviated data points cannot be correctly marked due to insufficient operating condition types.

[0085] like Figure 5 As shown, the technicians use the monitoring method of the present invention to cluster the results based on multiple vibration parameters (such as the vibration parameters of the inner ring of the south exhaust valve, the vibration parameters of the inner ring of the north exhaust valve, the vibration parameters of the inner ring of the intake valve, and the vibration parameters of the inner ring of the exhaust valve, etc.) during one cycle of crankshaft rotation, based on the vibration of the inner ring of the intake valve collected by the sensor and the average exhaust pressure; the horizontal axis is the serial number of the data segment, and the vertical axis represents vibration, that is, vibration acceleration. Green data points represent operating state 0, purple data points represent operating state 1, and yellow data points represent operating state 2, where operating state 0 indicates normal operation of the hydrogen compressor, operating state 1 indicates low-pressure operation of the hydrogen compressor and no parts are in a fatigue state, and operating state 2 indicates low-pressure operation of the hydrogen compressor and the inner ring of the north exhaust valve is in a fatigue state; verified by technicians: the recognition accuracy of data points of various colors is high and the false alarm rate is low.

[0086] For the three cluster results pre-set by the technicians, the hydrogen compressor status monitoring method of the present invention is used, compared with the GMM clustering algorithm used in the prior art that does not have the ability to autonomously generate cluster results. The same hydrogen compressor is continuously monitored for 133 hours, with an interval of 5 minutes between adjacent monitoring times. After manual verification, the accuracy of the monitoring method of the present invention is as high as 91.36%, while the highest accuracy of the prior art is only 75.16%.

[0087] The technology, shape, and structure parts not described in detail in the present invention are all well-known technologies. It should also be pointed out that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. The components or steps in the embodiments of the present invention can be decomposed and / or recombined, and these decompositions and / or recombinations should be regarded as equivalent solutions of the present application and should fall within the protection scope of the present invention.

Claims

1. A hydrogen compressor state monitoring method based on vibration parameters, characterized in that: The following steps are involved: S1, for any vibration parameter of the hydrogen compressor: according to the window parameter of the current sliding window, obtain the vibration data of the current sliding window; the sliding window is arranged in time order; S2, calculating the statistical data and vibration characteristic vector of the current sliding window according to the vibration data of the current sliding window; the window parameters, vibration data, statistical data and vibration characteristic vector of the current sliding window together constitute the current sliding window information; S3, according to the sliding window information of each vibration parameter between the current monitoring moment and the previous monitoring moment and the exhaust pressure at the current monitoring moment, each clustering algorithm outputs the cluster result corresponding to the current monitoring moment; and at the same time calculates the weight coefficient of each clustering algorithm at the current monitoring moment; S4, the clustering algorithm weight coefficients corresponding to the same cluster results are accumulated as the scores of the corresponding cluster results, and then the cluster result with the highest score is used as the operating status of the hydrogen compressor at the current monitoring moment.

2. A hydrogen compressor state monitoring method based on vibration parameters according to claim 1, characterized in that: S2' is also included after S2: S2' calculates the window parameters of the next sliding window according to the statistical data and window parameters of the current sliding window.

3. A hydrogen compressor state monitoring method based on vibration parameters according to claim 1 or 2, characterized in that: When the current hydrogen compressor is monitored for the first time, or in the first operation after replacing one or more key components of the current hydrogen compressor, any vibration parameter of the current hydrogen compressor enters a new monitoring cycle, and the window parameter of the first sliding window in the new monitoring cycle is the initial value; The window parameters include the window length and the sliding step length; each sliding window contains a number of vibration data of only one vibration parameter arranged in time.

4. The method for monitoring hydrogen compressor status based on vibration parameters according to claim 2 is characterized in that: The following are also included in S2´: Remember the current sliding window The window length is , t is a positive integer, the current sliding window The previous sliding window is recorded as , then the next sliding window The window length : ； ； ； ； ； in, Indicates the current sliding window The window length adjustment amount; Indicates the next sliding window The window length adjustment amount; f represents the current sliding window The right boundary moment corresponds to the rotation frequency of the component where the vibration parameter is located; Indicates rounding up; is the first adjustment factor; is the second adjustment factor; Represents the weight coefficient of the i-th clustering algorithm. A total of n clustering algorithms are used, that is, 1≤i≤n; Represents sliding window Intra-cluster entropy in the ith clustering algorithm; Indicates that from the sliding window Start, including sliding window Inside, count the historical maximum entropy value of m sliding windows forward, where m is a positive integer and m≤t; Represents sliding window The mean vector of The modulus length is the sliding window With sliding window The difference between the average values ​​of the vibration data, The direction of the sliding window The average value of the vibration data points to the sliding window Average value of vibration data; express The 2-norm of ; is the maximum value function; Represents sliding window The intra-cluster entropy in the i-th clustering algorithm, Represents sliding window Intra-cluster entropy in the ith clustering algorithm; Indicates that from the sliding window Start, including sliding window In the process of i changing from 1 to n, we get the intra-cluster entropy of the corresponding clustering algorithm by counting m sliding windows forward. represents covariance; represents variance; Indicates the time constant of the hydrogen compressor system; Indicates the current sliding window The sampling period of vibration data is determined by the acquisition frequency of the corresponding sensor; Indicates the current sliding window The maximum permissible drift rate of the vibration parameters; Indicates the current sliding window Rated values ​​of vibration parameters.

5. The method for monitoring hydrogen compressor status based on vibration parameters according to claim 1, characterized in that: In S2, calculating the vibration feature vector of the current sliding window according to the vibration data of the current sliding window also includes the following sub-steps: S21, performing local mean decomposition on the vibration parameter signal corresponding to the vibration parameter in the current sliding window: ； Wherein, T represents time; X(T) represents the vibration parameter signal in the current sliding window, and the N vibration data contained in the current sliding window are fitted into a vibration parameter signal curve, and the vibration parameter signal represented by this vibration parameter signal curve is X(T); represents the kth PF component, k=1,...,K, and K is a positive integer greater than 1; represents the Kth residual, is a monotonic function; S22, extract the characteristic parameters of each PF component to form the vibration characteristic vector of the current sliding window: ； ； ； ； in, represents the kth PF component The skewness coefficient of represents the kth PF component The kurtosis coefficient of represents the kth PF component energy; represents the kth PF component The energy ratio in the vibration parameter signal X(T); represents the hth vibration data in the current sliding window arranged in time order; express The average value of the N PF component values ​​that are at the same time point as the N vibration data in the current sliding window; express The standard deviation of the N PF component values ​​that are the same as the N vibration data time points in the current sliding window; a represents the time point at the left boundary of the current sliding window; b represents the time point at the right boundary of the current sliding window; E represents the energy of the vibration parameter signal X(T); S23, based on the characteristic parameters of the K PF components, obtain K vibration characteristic vectors of the current sliding window: ； in, Represents the kth vibration eigenvector of the current sliding window.

6. The method for monitoring hydrogen compressor status based on vibration parameters according to claim 4, characterized in that: Next Slide Window The sliding step length for: ； ； ； in, Indicates the next sliding window The overlap ratio; Indicates the current sliding window The overlap ratio; Indicates the next sliding window The attenuation coefficient of Indicates the target overlap ratio; Indicates the total number of sliding windows that need to transition; and They are all known quantities determined by the operating status of the hydrogen compressor at the last monitoring moment; Indicates that the next sliding window is included The remaining number of sliding windows that need to transition, , Indicates that the current sliding window is included The remaining number of sliding windows that need to be transitioned.

7. The method for monitoring hydrogen compressor status based on vibration parameters according to claim 1, characterized in that: In S3, the following are also included: n different clustering algorithms are used, among which some clustering algorithms do not have the ability to autonomously generate cluster results, while the other clustering algorithms have the ability to autonomously generate cluster results; the sliding window information of each vibration parameter between the current monitoring moment and the previous monitoring moment and the exhaust pressure at the current monitoring moment are sent to each clustering algorithm, and each clustering algorithm outputs the cluster result corresponding to the hydrogen compressor at the current monitoring moment; At the same time, calculate the weight coefficient of each clustering algorithm at the current monitoring moment , 1≤i≤n and i is a positive integer: if the current monitoring moment is the first monitoring moment in the current monitoring cycle, the weight coefficients of each clustering algorithm at the current monitoring moment are obtained based on solving the multi-objective optimization function; if the current monitoring moment is not the first monitoring moment in the current monitoring cycle, the weight coefficients of each clustering algorithm at the previous monitoring moment are used to obtain the weight coefficients of each clustering algorithm at the current monitoring moment.

8. A hydrogen compressor state monitoring method based on vibration parameters according to claim 7, characterized in that: Based on solving the multi-objective optimization function, the weight coefficients of each clustering algorithm at the current monitoring time are obtained, which also includes the following: After constructing the multi-objective optimization function F, we solve it and get the value of the weight coefficient of each clustering algorithm at the current monitoring moment: ； ； The constraints are: ; in, is the second constant parameter; Represents the weight coefficient corresponding to the i-th clustering algorithm; represents the sum of squared errors of the i-th clustering algorithm; represents the first weight matrix, which is a column vector consisting of weight coefficients; represents the second weight matrix, which is the first weight matrix The transpose of is a row vector; Represents the first weight matrix With the correlation matrix The quadratic form of is the regularization parameter.

9. The method for monitoring hydrogen compressor status based on vibration parameters according to claim 7, characterized in that: Based on the weight coefficients of each clustering algorithm at the previous monitoring time, the weight coefficients of each clustering algorithm at the current monitoring time are obtained, which also includes the following: The current monitoring time is , the last monitoring time is , z ≥ 2 and z is a positive integer, then the current monitoring time The weight coefficient of the i-th clustering algorithm for: ； in, Indicates the last monitoring time The i-th clustering algorithm weight coefficient; Indicates the last monitoring time The j-th clustering algorithm weight coefficient, 1≤j≤n and j is a positive integer; represents the learning rate; Represents the global distribution at the last monitoring moment; Represents the distribution of the i-th clustering algorithm at the last monitoring moment; represents the distribution of the jth clustering algorithm at the last monitoring moment; represents JS divergence; Representation distribution With global distribution JS divergence; Representation distribution With global distribution JS divergence.

10. The method for monitoring hydrogen compressor status based on vibration parameters according to claim 1, characterized in that: S4 also includes S5: S5, if the cluster result obtained by the clustering algorithm with the ability to autonomously generate cluster results does not become the cluster result with the highest score, then the cluster result obtained by the clustering algorithm with the ability to autonomously generate cluster results will be recorded as a set to be verified. After the technical personnel regularly verify and analyze the set to be verified, if the cluster result obtained by a clustering algorithm in the set to be verified is considered correct by the technical personnel for y consecutive times and is different from the cluster result set by the technical personnel, then the technical personnel will increase the weight coefficient of the corresponding clustering algorithm.

Images