Permanent magnet motor parameter operation regulation and control test system and method based on cloud service

Abstract

The invention discloses a permanent magnet motor parameter operation regulation and control test system and method based on cloud service, and relates to the technical field of motor control. The system comprises a data acquisition module, a data analysis module, a control node identification module, an optimization strategy generation module and a real-time monitoring and feedback module. The data acquisition module acquires historical and real-time operation data of the permanent magnet synchronous motor by using a sensor; the data analysis module performs comprehensive effectiveness scoring on the collected data and screens out data meeting conditions; the control node identification module sets control nodes based on the regulation and control scheme, extracts related parameters and timestamps from the integrated data set, and analyzes and judges a deviation coefficient to identify key control nodes; the optimization strategy generation module analyzes the association between the regulation and control scheme and the motor operation state by using a linear regression model, and establishes an optimization control strategy; and the real-time monitoring and feedback module monitors real-time operation data, judges a fault, outputs an alarm in time, and adjusts a regulation and control scheme based on a monitoring result.

Description

Technical Field

[0001] The present invention relates to the field of motor control technology, and in particular to a permanent magnet motor parameter operation control test system and method based on cloud services. Background Art

[0002] With the rapid development of industrial automation, permanent magnet synchronous motors have been widely used in aerospace, electric vehicles, wind power generation, industrial automation and other fields due to their high efficiency, high power density and excellent control performance. In particular, the successful application of permanent magnet synchronous motors in transmission systems with low power, high precision, high reliability and wide speed regulation range has attracted great attention from the industry. Moreover, the design, manufacturing and operation quality of permanent magnet synchronous motors directly affect the performance and reliability of the entire system. Therefore, it is particularly important to conduct comprehensive and accurate tests and inspections on them.

[0003] However, in practical applications, the operation parameter control of permanent magnet synchronous motors faces many challenges. The traditional permanent magnet motor parameter operation control test system is limited by local computing power and cannot process and analyze the massive data generated during the operation of the permanent magnet synchronous motor in real time, resulting in inaccurate judgment of the operation status of the permanent magnet synchronous motor and limited optimization space for the control strategy; in distributed or remote control scenarios, the traditional permanent magnet motor parameter operation control test system is difficult to achieve remote monitoring and real-time fault diagnosis of the permanent magnet synchronous motor, affecting the efficiency and accuracy of fault detection; most of the traditional permanent magnet motor parameter operation control test systems are based on fixed control strategies and lack the ability to perform intelligent control according to the real-time operation status and environmental changes of the permanent magnet synchronous motor, thus failing to give full play to the optimal performance of the permanent magnet synchronous motor. Summary of the invention

[0004] The purpose of the present invention is to provide a permanent magnet motor parameter operation control test system and method based on cloud service to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A cloud service-based permanent magnet motor parameter operation control test method, the method comprising the following steps:

[0007] Step S100. Acquire historical operation data of the permanent magnet synchronous motor, analyze the historical operation data, evaluate the validity of the historical operation data, and perform corresponding screening processing on the historical operation data according to the validity; acquire the screened historical operation data, and match the screened historical operation data with the control scheme of the permanent magnet synchronous motor;

[0008] Step S200. Based on the control scheme of the permanent magnet synchronous motor, the corresponding historical operation data is analyzed to obtain a control node data set corresponding to the control scheme of the permanent magnet synchronous motor; the deviation coefficient between the historical operation data and the ideal operation data of the control node data set is analyzed, and the key control nodes corresponding to the control scheme of the permanent magnet synchronous motor are obtained based on the deviation coefficient;

[0009] Step S300. Acquire the key control nodes and the control scheme of the permanent magnet synchronous motor, analyze the corresponding operating state change trend of the permanent magnet synchronous motor, thereby establishing a correlation between the control scheme of the permanent magnet synchronous motor and the operating state change trend, and obtain a corresponding optimization control strategy based on the correlation;

[0010] Step S400. Acquire the real-time operation data of the permanent magnet synchronous motor and identify the real-time key control nodes; analyze the real-time operation data corresponding to the real-time key control nodes to determine whether the current permanent magnet synchronous motor has a fault; if no fault occurs, adjust the control scheme of the permanent magnet synchronous motor accordingly according to the optimization control strategy.

[0011] Furthermore, step S100 includes:

[0012] S101. Use sensor equipment to obtain historical operating data of the permanent magnet synchronous motor in a selected period, and obtain reasonable physical limits of various operating parameters of the permanent magnet synchronous motor, and the reasonable physical limits of various operating parameters of the permanent magnet synchronous motor are expressed as: Li = [l_min, l_max]i, where Li represents the reasonable physical limit of the operating parameter of the ith permanent magnet synchronous motor, and l_min and l_max in [l_min, l_max]i represent the lower limit and upper limit of the reasonable physical limit of the operating parameter of the ith permanent magnet synchronous motor, respectively; physical validity judgment is performed according to the reasonable physical limits of various operating parameters of the permanent magnet synchronous motor, and the physical validity judgment rule is: if the measured value of a certain parameter Li falls within its reasonable physical limit, the parameter is valid, and the value is assigned to Wi = 1; if the measured value of a certain parameter Li is not within its reasonable physical limit, the parameter is invalid, and the value is assigned to Wi = 0;

[0013] S102. Perform time series analysis on the historical operation data of the permanent magnet synchronous motor, and the obtained time series is expressed as: D(t)=(t1,P1),(t2,P2),...,(tn,Pn), where D(t) represents the time series data, t1 in (t1,P1) represents the first timestamp, and P1 represents the operating parameter value at time t1; t2 in (t2,P2) represents the second timestamp, and P2 represents the operating parameter value at time t2; and so on, tn in (tn,Pn) represents the nth timestamp, and Pn represents the operating parameter value at time tn, and n is a positive integer; for each pair of adjacent data points Pi and Pi+1, calculate the change rate Ri between the two, and Ri=|Pi+1-Pi|; compare Ri with the corresponding change rate threshold R, if Ri≤R, assign Bi=1, otherwise assign Bi=0;

[0014] S103. Use the Z-score method to identify abnormal values ​​in the historical operation data of the permanent magnet synchronous motor, calculate the mean μ and standard deviation σ of all operating parameters; for each operating parameter Pi, calculate the Z-score, and the calculation formula is: Zi = (Pi-μ) / σ, compare the Zi corresponding to each operating parameter Pi with the preset threshold Z, if |Zi|>Z, then judge that the data point is an abnormal value, assign Ji = 1, otherwise assign Ji = 0;

[0015] S104. Comprehensively consider Wi, Bi and Ji, and calculate a comprehensive effectiveness score Si for each data point, where Si = α × Wi + β × Bi + γ × Ji, and α, β and γ are all weight coefficients, α + β + γ = 1; compare the comprehensive effectiveness score Si with the corresponding screening threshold S, and screen the data points that satisfy Si ≥ S; store the screened data points in the historical operation data set D1, and obtain the control scheme of the permanent magnet synchronous motor, including control strategy, operation mode, parameter setting and other information; match the data points in the historical operation data set D1 with the control strategy of the corresponding time period in the control scheme through the timestamp, and map each operation parameter Pi with the corresponding control parameter, so as to form an integrated data set Dc, which contains each screened operation data point and its corresponding control scheme information, and the data structure is expressed as: Dc = {(ti, Pi, Cj) | ti is the timestamp, Pi is the operation parameter, and Cj is the corresponding control scheme}.

[0016] Further, step S200 includes:

[0017] S201. Extract all operating parameters and their corresponding timestamps from the integrated data set Dc, set the control nodes based on the control scheme of the permanent magnet synchronous motor, divide the operating parameters extracted from the integrated data set Dc and their corresponding timestamps into time windows, thereby forming a data set Dw, perform time matching on the data set Dw and the control nodes in the control scheme, and form a control node data set K, where K = {k1, k2, ..., km}, where k1 represents the first control node data, k2 represents the second control node data, and so on, km represents the mth control node data;

[0018] S202. Based on the control node data set K, the ideal operation data of the corresponding control node is obtained to form an ideal data set G, and G = {g1, g2, ..., gm}, wherein g1 represents the ideal operation data corresponding to the first control node, g2 represents the ideal operation data corresponding to the second control node, and so on, gm represents the ideal operation data corresponding to the mth control node, and each control node in the ideal data set G corresponds one-to-one to the control node in the control node data set K; for each data point in the control node data set K, the deviation coefficient between the historical operation data and the ideal operation data is calculated, and the specific calculation formula is:

[0019]

[0020] Wherein, Hx(t) represents the deviation coefficient between the historical operation data of the control node x at time t and the ideal operation data, kx(t) represents the historical operation data of the control node x at time t, gx(t) represents the ideal operation data of the control node x at time t, b represents the parameter factor, a represents the weight coefficient, Vx(t) represents the change rate of the historical operation data of the control node x at time t, and Vx(t)=|kx(t)-kx(t-1)|;

[0021] S203. For each control node in the control node data set K, calculate the corresponding deviation coefficient according to the calculation formula of the deviation coefficient in S202; obtain the corresponding fault log, and according to the timestamp corresponding to the fault event recorded in the fault log, take the control node corresponding to the same stamp as the fault node, summarize the deviation coefficients corresponding to all fault nodes and calculate the average value, so as to obtain the fault threshold H0; for the control nodes other than the fault node in the control node data set K, compare the deviation coefficients of the remaining control nodes with the preset deviation threshold H, and take the control nodes greater than or equal to the deviation threshold H as the key control nodes, so as to obtain the key control nodes corresponding to the control scheme of the permanent magnet synchronous motor, and the deviation threshold H is less than the fault threshold H0.

[0022] Furthermore, step S300 includes:

[0023] S301. Extract the key control node data set K and the corresponding permanent magnet synchronous motor control scheme information C, analyze the time series of the operating parameters of the key control nodes, and define the trend function: T(k) = (1 / c)Σt∈[1,c], k(t), where c is the time window length, and k(t) represents the operating parameter value of the key control node at time t; use the linear regression model to analyze the correlation between the control scheme C and the permanent magnet synchronous motor operating state change U, and establish the model: U = w0+w1·C+d, where U represents the permanent magnet synchronous motor operating state change, C represents the control scheme parameters, w0 and w1 represent the regression coefficients, and d represents the error term;

[0024] S302. Calculate the response index Ex of each key control node, and Ex = Δkx / ΔCx, where Δkx represents the change in the operating parameter value of the key control node x, and ΔCx represents the change in the control scheme parameter of the key control node x; according to the results of the correlation analysis, the optimized control strategy E1 is obtained: E1 = E + λ·(UT(k)), where λ is the adjustment coefficient. The new strategy E1 is based on the original control strategy E, and is adjusted according to the deviation between the current operating state and the expected trend. By adding the adjustment amount λ·(UT(k)), the control strategy can be dynamically corrected to make the actual operating state of the motor closer to the ideal state, thereby improving the control effect and system performance.

[0025] Furthermore, step S400 includes:

[0026] S401. Acquire the real-time operation data of the permanent magnet synchronous motor, perform the same analysis on the real-time operation data as the historical operation data, thereby obtaining several real-time control nodes, and calculate the deviation coefficient H2 between the real-time operation data corresponding to the real-time control node and the ideal operation data, and compare the deviation coefficient H2 with the fault threshold H0. If the deviation coefficient H2 is less than the fault threshold H0, go to S402; if the deviation coefficient H2 is greater than or equal to the fault threshold H0, determine that the current permanent magnet synchronous motor has a fault, and output corresponding prompt information to relevant personnel;

[0027] S402. Compare the deviation coefficient H2 with the preset deviation threshold H, and take the control nodes that are greater than or equal to the deviation threshold H as the key real-time control nodes, and calculate the similarity between the real-time operation data of the key real-time control nodes and the historical operation data, select the key control node corresponding to the historical operation data with the greatest similarity as the matching node, and take the optimization control strategy corresponding to the matching node as the matching strategy, and make corresponding adjustments to the control scheme of the permanent magnet synchronous motor according to the matching strategy.

[0028] A cloud service-based permanent magnet motor parameter operation control test system, the system includes: a data acquisition module, a data analysis module, a control node identification module, an optimization strategy generation module and a real-time monitoring and feedback module;

[0029] The data acquisition module uses sensor equipment to obtain the historical operating data and real-time operating data of the permanent magnet synchronous motor; the data analysis module performs physical validity judgment, outlier detection and time series analysis on the collected historical operating data and real-time operating data, generates a comprehensive validity score, screens out the operating data that meets the conditions according to the validity score, forms an integrated data set, analyzes the deviation between the historical operating data or real-time operating data and the ideal operating data, calculates the deviation coefficient, and identifies the key control nodes; the control node identification module sets the control node based on the control scheme, extracts relevant operating parameters and timestamps from the integrated data set, analyzes the control node data set, and determines the deviation coefficient to identify the key control node; the optimization strategy generation module uses a linear regression model to analyze the correlation between the control scheme and the change in the motor's operating state, and establishes an optimized control strategy; the real-time monitoring and feedback module monitors and analyzes the real-time operating data of the motor, calculates the deviation coefficient of the real-time control node, determines whether the motor has a fault, and if a fault is detected, promptly outputs alarm information to relevant personnel, and adjusts the control scheme based on the real-time monitoring results.

[0030] Further, the data acquisition module includes a sensor data acquisition unit and a data preprocessing unit;

[0031] The sensor data acquisition unit acquires the historical operation data and real-time operation data of the permanent magnet synchronous motor; the data preprocessing unit cleans, denoises and formats the collected historical operation data and real-time operation data;

[0032] The data analysis module includes a validity assessment unit, a time series analysis unit, and a deviation calculation unit;

[0033] The effectiveness evaluation unit makes effectiveness judgments on the historical operation data and real-time operation data, generates effectiveness scores, and screens valid data points; the time series analysis unit performs time series analysis on the screened historical operation data and real-time operation data, calculates the data change rate, and identifies outliers; the deviation calculation unit calculates the deviation coefficient between the historical operation data or real-time operation data and the ideal operation data.

[0034] Further, the control node identification module includes a control node setting unit and a key node analysis unit;

[0035] The control node setting unit sets the control nodes according to the control scheme, performs time matching on the data set, and extracts the key control node data; the key node analysis unit identifies the key control nodes and calculates their deviation coefficients.

[0036] The optimization strategy generation module includes a correlation analysis unit and an optimization control strategy generation unit;

[0037] The correlation analysis unit uses a linear regression model to analyze the correlation between the control scheme and the change of the operating state and establishes a corresponding model; the optimization control strategy generation unit generates an optimization control strategy for the key control nodes based on the correlation analysis results.

[0038] Furthermore, the real-time monitoring and feedback module includes a real-time data analysis unit, a fault monitoring unit, and a control adjustment unit;

[0039] The real-time data analysis unit obtains the real-time operation data of the permanent magnet synchronous motor and compares and analyzes it with the historical data to obtain the corresponding matching information; the fault monitoring unit determines whether the motor has a fault based on the real-time deviation coefficient and issues a fault prompt message in time; the control adjustment unit adjusts the control scheme of the permanent magnet synchronous motor according to the matching information.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention introduces a comprehensive effectiveness scoring mechanism (Si), comprehensively considers factors such as physical effectiveness, time series change rate and outliers, effectively screens out high-quality historical operation data, and accurately matches it with the control scheme, constructs an integrated data set Dc, and provides a reliable data basis for subsequent analysis. By analyzing the deviation coefficient between the control node data set and the ideal operation data, the present invention can accurately identify the key control nodes of the permanent magnet synchronous motor, and establish the correlation between the control scheme and the change trend of the operation state based on these key nodes, and then formulate an optimized control strategy. The operation state of the permanent magnet synchronous motor is monitored in real time, and by calculating the deviation coefficient of the real-time control node and comparing it with the fault threshold, early warning and real-time adjustment of the motor fault are realized, reducing the downtime and production loss caused by the fault. By analyzing the historical operation data and real-time operation state of the permanent magnet synchronous motor, the present invention can dynamically adjust the control strategy based on an intelligent algorithm (such as a linear regression model) to adapt to the changes in the motor operation state and the external environment, so as to give full play to the best performance of the permanent magnet synchronous motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0042] Figure 1 It is a schematic diagram of a module of a permanent magnet motor parameter operation control test system based on cloud service of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] See also Figure 1 , the present invention provides a technical solution:

[0045] A cloud service-based permanent magnet motor parameter operation control test system, the system includes: a data acquisition module, a data analysis module, a control node identification module, an optimization strategy generation module and a real-time monitoring and feedback module;

[0046] The data acquisition module uses sensor equipment to obtain the historical operating data and real-time operating data of the permanent magnet synchronous motor; the data analysis module performs physical validity judgment, outlier detection and time series analysis on the collected historical operating data and real-time operating data, generates a comprehensive validity score, screens out the operating data that meets the conditions according to the validity score, forms an integrated data set, analyzes the deviation between the historical operating data or real-time operating data and the ideal operating data, calculates the deviation coefficient, and identifies the key control nodes; the control node identification module sets the control node based on the control scheme, extracts relevant operating parameters and timestamps from the integrated data set, analyzes the control node data set, and determines the deviation coefficient to identify the key control node; the optimization strategy generation module uses a linear regression model to analyze the correlation between the control scheme and the change in the motor's operating state, and establishes an optimized control strategy; the real-time monitoring and feedback module monitors and analyzes the real-time operating data of the motor, calculates the deviation coefficient of the real-time control node, determines whether the motor has a fault, and if a fault is detected, promptly outputs alarm information to relevant personnel, and adjusts the control scheme based on the real-time monitoring results.

[0047] The data acquisition module includes a sensor data acquisition unit and a data preprocessing unit;

[0048] The sensor data acquisition unit acquires the historical operation data and real-time operation data of the permanent magnet synchronous motor; the data preprocessing unit cleans, denoises and formats the collected historical operation data and real-time operation data;

[0049] The data analysis module includes a validity assessment unit, a time series analysis unit, and a deviation calculation unit;

[0050] The effectiveness evaluation unit makes effectiveness judgments on the historical operation data and real-time operation data, generates effectiveness scores, and screens valid data points; the time series analysis unit performs time series analysis on the screened historical operation data and real-time operation data, calculates the data change rate, and identifies outliers; the deviation calculation unit calculates the deviation coefficient between the historical operation data or real-time operation data and the ideal operation data.

[0051] The control node identification module includes a control node setting unit and a key node analysis unit;

[0052] The control node setting unit sets the control nodes according to the control scheme, performs time matching on the data set, and extracts the key control node data; the key node analysis unit identifies the key control nodes and calculates their deviation coefficients.

[0053] The optimization strategy generation module includes a correlation analysis unit and an optimization control strategy generation unit;

[0054] The correlation analysis unit uses a linear regression model to analyze the correlation between the control scheme and the change of the operating state and establishes a corresponding model; the optimization control strategy generation unit generates an optimization control strategy for the key control nodes based on the correlation analysis results.

[0055] The real-time monitoring and feedback module includes a real-time data analysis unit, a fault monitoring unit, and a control adjustment unit;

[0056] The real-time data analysis unit obtains the real-time operation data of the permanent magnet synchronous motor and compares and analyzes it with the historical data to obtain the corresponding matching information; the fault monitoring unit determines whether the motor has a fault based on the real-time deviation coefficient and issues a fault prompt message in time; the control adjustment unit adjusts the control scheme of the permanent magnet synchronous motor according to the matching information.

[0057] A cloud service-based permanent magnet motor parameter operation control test method, the method comprising the following steps:

[0058] Step S100. Acquire historical operation data of the permanent magnet synchronous motor, analyze the historical operation data, evaluate the validity of the historical operation data, and perform corresponding screening processing on the historical operation data according to the validity; acquire the screened historical operation data, and match the screened historical operation data with the control scheme of the permanent magnet synchronous motor;

[0059] Step S200. Based on the control scheme of the permanent magnet synchronous motor, the corresponding historical operation data is analyzed to obtain a control node data set corresponding to the control scheme of the permanent magnet synchronous motor; the deviation coefficient between the historical operation data and the ideal operation data of the control node data set is analyzed, and the key control nodes corresponding to the control scheme of the permanent magnet synchronous motor are obtained based on the deviation coefficient;

[0060] Step S300. Acquire the key control nodes and the control scheme of the permanent magnet synchronous motor, analyze the corresponding operating state change trend of the permanent magnet synchronous motor, thereby establishing a correlation between the control scheme of the permanent magnet synchronous motor and the operating state change trend, and obtain a corresponding optimization control strategy based on the correlation;

[0061] Step S400. Acquire the real-time operation data of the permanent magnet synchronous motor and identify the real-time key control nodes; analyze the real-time operation data corresponding to the real-time key control nodes to determine whether the current permanent magnet synchronous motor has a fault; if no fault occurs, adjust the control scheme of the permanent magnet synchronous motor accordingly according to the optimization control strategy.

[0062] Step S100 includes:

[0063] S101. Use sensor equipment to obtain historical operating data of the permanent magnet synchronous motor in a selected period, and obtain reasonable physical limits of various operating parameters of the permanent magnet synchronous motor, and the reasonable physical limits of various operating parameters of the permanent magnet synchronous motor are expressed as: Li = [l_min, l_max]i, where Li represents the reasonable physical limit of the operating parameter of the ith permanent magnet synchronous motor, and l_min and l_max in [l_min, l_max]i represent the lower limit and upper limit of the reasonable physical limit of the operating parameter of the ith permanent magnet synchronous motor, respectively; physical validity judgment is performed according to the reasonable physical limits of various operating parameters of the permanent magnet synchronous motor, and the physical validity judgment rule is: if the measured value of a certain parameter Li falls within its reasonable physical limit, the parameter is valid, and the value is assigned to Wi = 1; if the measured value of a certain parameter Li is not within its reasonable physical limit, the parameter is invalid, and the value is assigned to Wi = 0;

[0064] In this embodiment, the reasonable physical limits of the operating parameters of the permanent magnet synchronous motor are expressed as:

[0065] 1. Speed ​​(N):

[0066] Reasonable range: usually depends on the rated speed and design specifications of the motor;

[0067] Expressed as: N_min≤N≤N_max, for example: 0,rpm≤N≤3000,rp;

[0068] 2. Current (I):

[0069] Reasonable range: set according to the rated current and overload capacity of the motor.

[0070] It is expressed as: I_min≤I≤I_max, for example: 0,A≤I≤10,A;

[0071] 3. Torque (T):

[0072] Reasonable range: based on the rated torque and maximum output torque of the motor.

[0073] Expressed as: T_min≤T≤T_max, for example: 0,Nm≤T≤15,Nm;

[0074] 3. Temperature (T_temp):

[0075] Reasonable range: Based on the operating temperature range of the motor, usually based on the environment and insulation material.

[0076] Expressed as: T_min,temp≤T_temp≤T_max,temp, for example: -20,℃≤T_temp≤80,℃;

[0077] 4. Efficiency (η):

[0078] Reasonable range: Based on the design efficiency of the motor, high efficiency is usually maintained under high load.

[0079] Expressed as: η_min≤η≤η_max, for example: 80%≤η≤95%.

[0080] S102. Perform time series analysis on the historical operation data of the permanent magnet synchronous motor, and the obtained time series is expressed as: D(t)=(t1,P1),(t2,P2),...,(tn,Pn), where D(t) represents the time series data, t1 in (t1,P1) represents the first timestamp, and P1 represents the operating parameter value at time t1; t2 in (t2,P2) represents the second timestamp, and P2 represents the operating parameter value at time t2; and so on, tn in (tn,Pn) represents the nth timestamp, and Pn represents the operating parameter value at time tn, and n is a positive integer; for each pair of adjacent data points Pi and Pi+1, calculate the change rate Ri between the two, and Ri=|Pi+1-Pi|; compare Ri with the corresponding change rate threshold R, if Ri≤R, assign Bi=1, otherwise assign Bi=0;

[0081] S103. Use the Z-score method to identify abnormal values ​​in the historical operation data of the permanent magnet synchronous motor, calculate the mean μ and standard deviation σ of all operating parameters; for each operating parameter Pi, calculate the Z-score, and the calculation formula is: Zi = (Pi-μ) / σ, compare the Zi corresponding to each operating parameter Pi with the preset threshold Z, if |Zi|>Z, then judge that the data point is an abnormal value, assign Ji = 1, otherwise assign Ji = 0;

[0082] S104. Comprehensively consider Wi, Bi and Ji, and calculate a comprehensive effectiveness score Si for each data point, where Si = α × Wi + β × Bi + γ × Ji, and α, β and γ are all weight coefficients, α + β + γ = 1; compare the comprehensive effectiveness score Si with the corresponding screening threshold S, and screen the data points that satisfy Si ≥ S; store the screened data points in the historical operation data set D1, and obtain the control scheme of the permanent magnet synchronous motor, including control strategy, operation mode, parameter setting and other information; match the data points in the historical operation data set D1 with the control strategy of the corresponding time period in the control scheme through the timestamp, and map each operation parameter Pi with the corresponding control parameter, so as to form an integrated data set Dc, which contains each screened operation data point and its corresponding control scheme information, and the data structure is expressed as: Dc = {(ti, Pi, Cj) | ti is the timestamp, Pi is the operation parameter, and Cj is the corresponding control scheme}.

[0083] Step S200 includes:

[0084] S201. Extract all operating parameters and their corresponding timestamps from the integrated data set Dc, set the control nodes based on the control scheme of the permanent magnet synchronous motor, divide the operating parameters extracted from the integrated data set Dc and their corresponding timestamps into time windows, thereby forming a data set Dw, perform time matching on the data set Dw and the control nodes in the control scheme, and form a control node data set K, where K = {k1, k2, ..., km}, where k1 represents the first control node data, k2 represents the second control node data, and so on, km represents the mth control node data;

[0085] S202. Based on the control node data set K, the ideal operation data of the corresponding control node is obtained to form an ideal data set G, and G = {g1, g2, ..., gm}, wherein g1 represents the ideal operation data corresponding to the first control node, g2 represents the ideal operation data corresponding to the second control node, and so on, gm represents the ideal operation data corresponding to the mth control node, and each control node in the ideal data set G corresponds one-to-one to the control node in the control node data set K; for each data point in the control node data set K, the deviation coefficient between the historical operation data and the ideal operation data is calculated, and the specific calculation formula is:

[0086]

[0087] Wherein, Hx(t) represents the deviation coefficient between the historical operation data of the control node x at time t and the ideal operation data, kx(t) represents the historical operation data of the control node x at time t, gx(t) represents the ideal operation data of the control node x at time t, b represents the parameter factor, a represents the weight coefficient, Vx(t) represents the change rate of the historical operation data of the control node x at time t, and Vx(t)=|kx(t)-kx(t-1)|;

[0088] S203. For each control node in the control node data set K, calculate the corresponding deviation coefficient according to the calculation formula of the deviation coefficient in S202; obtain the corresponding fault log, and according to the timestamp corresponding to the fault event recorded in the fault log, take the control node corresponding to the same stamp as the fault node, summarize the deviation coefficients corresponding to all fault nodes and calculate the average value, so as to obtain the fault threshold H0; for the control nodes other than the fault node in the control node data set K, compare the deviation coefficients of the remaining control nodes with the preset deviation threshold H, and take the control nodes greater than or equal to the deviation threshold H as the key control nodes, so as to obtain the key control nodes corresponding to the control scheme of the permanent magnet synchronous motor, and the deviation threshold H is less than the fault threshold H0.

[0089] Step S300 includes:

[0090] S301. Extract the key control node data set K and the corresponding permanent magnet synchronous motor control scheme information C, analyze the time series of the operating parameters of the key control nodes, and define the trend function: T(k) = (1 / c)Σt∈[1,c], k(t), where c is the time window length, and k(t) represents the operating parameter value of the key control node at time t; use the linear regression model to analyze the correlation between the control scheme C and the permanent magnet synchronous motor operating state change U, and establish the model: U = w0+w1·C+d, where U represents the permanent magnet synchronous motor operating state change, C represents the control scheme parameters, w0 and w1 represent the regression coefficients, and d represents the error term;

[0091] S302. Calculate the response index Ex of each key control node, and Ex = Δkx / ΔCx, where Δkx represents the change in the operating parameter value of the key control node x, and ΔCx represents the change in the control scheme parameter of the key control node x; according to the results of the correlation analysis, the optimized control strategy E1 is obtained: E1 = E + λ·(UT(k)), where λ is the adjustment coefficient. The new strategy E1 is based on the original control strategy E, and is adjusted according to the deviation between the current operating state and the expected trend. By adding the adjustment amount λ·(UT(k)), the control strategy can be dynamically corrected to make the actual operating state of the motor closer to the ideal state, thereby improving the control effect and system performance.

[0092] Step S400 includes:

[0093] S401. Acquire the real-time operation data of the permanent magnet synchronous motor, perform the same analysis on the real-time operation data as the historical operation data, thereby obtaining several real-time control nodes, and calculate the deviation coefficient H2 between the real-time operation data corresponding to the real-time control node and the ideal operation data, and compare the deviation coefficient H2 with the fault threshold H0. If the deviation coefficient H2 is less than the fault threshold H0, go to S402; if the deviation coefficient H2 is greater than or equal to the fault threshold H0, determine that the current permanent magnet synchronous motor has a fault, and output corresponding prompt information to relevant personnel;

[0094] S402. Compare the deviation coefficient H2 with the preset deviation threshold H, and take the control nodes that are greater than or equal to the deviation threshold H as the key real-time control nodes, and calculate the similarity between the real-time operation data of the key real-time control nodes and the historical operation data, select the key control node corresponding to the historical operation data with the greatest similarity as the matching node, and take the optimization control strategy corresponding to the matching node as the matching strategy, and make corresponding adjustments to the control scheme of the permanent magnet synchronous motor according to the matching strategy.

[0095] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0096] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A cloud service-based permanent magnet motor parameter operation control test method, characterized in that: The method comprises the following steps: Step S100. Acquire historical operation data of the permanent magnet synchronous motor, analyze the historical operation data, evaluate the validity of the historical operation data, and perform corresponding screening processing on the historical operation data according to the validity; acquire the screened historical operation data, and match the screened historical operation data with the control scheme of the permanent magnet synchronous motor; Step S200. Based on the control scheme of the permanent magnet synchronous motor, the corresponding historical operation data is analyzed to obtain a control node data set corresponding to the control scheme of the permanent magnet synchronous motor; the deviation coefficient between the historical operation data and the ideal operation data of the control node data set is analyzed, and the key control nodes corresponding to the control scheme of the permanent magnet synchronous motor are obtained based on the deviation coefficient; Step S300. Acquire the key control nodes and the control scheme of the permanent magnet synchronous motor, analyze the corresponding operating state change trend of the permanent magnet synchronous motor, thereby establishing a correlation between the control scheme of the permanent magnet synchronous motor and the operating state change trend, and obtain a corresponding optimization control strategy based on the correlation; Step S400. Acquire the real-time operation data of the permanent magnet synchronous motor and identify the real-time key control nodes; analyze the real-time operation data corresponding to the real-time key control nodes to determine whether the current permanent magnet synchronous motor has a fault; if no fault occurs, adjust the control scheme of the permanent magnet synchronous motor accordingly according to the optimization control strategy.

2. According to a cloud service-based permanent magnet motor parameter operation control test method according to claim 1, it is characterized in that: The step S100 includes: S101. Use sensor equipment to obtain historical operating data of the permanent magnet synchronous motor in a selected period, and obtain reasonable physical limits of various operating parameters of the permanent magnet synchronous motor, and the reasonable physical limits of various operating parameters of the permanent magnet synchronous motor are expressed as: Li = [l_min, l_max]i, where Li represents the reasonable physical limit of the operating parameter of the ith permanent magnet synchronous motor, and l_min and l_max in [l_min, l_max]i represent the lower limit and upper limit of the reasonable physical limit of the operating parameter of the ith permanent magnet synchronous motor, respectively; physical validity judgment is performed according to the reasonable physical limits of various operating parameters of the permanent magnet synchronous motor, and the physical validity judgment rule is: if the measured value of a certain parameter Li falls within its reasonable physical limit, the parameter is valid, and the value is assigned to Wi = 1; if the measured value of a certain parameter Li is not within its reasonable physical limit, the parameter is invalid, and the value is assigned to Wi = 0; S102. Perform time series analysis on the historical operation data of the permanent magnet synchronous motor, and the obtained time series is expressed as: D(t)=(t1,P1),(t2,P2),...,(tn,Pn), where D(t) represents time series data, t1 in (t1,P1) represents the first timestamp, and P1 represents the operating parameter value at time t1; t2 in (t2,P2) represents the second timestamp, and P2 represents the operating parameter value at time t2; and so on, tn in (tn,Pn) represents the nth timestamp, and Pn represents the operating parameter value at time tn, and n is a positive integer; for each pair of adjacent data points Pi and Pi+1, calculate the change rate Ri between the two, and Ri=|Pi+1-Pi|; compare Ri with the corresponding change rate threshold R, if Ri≤R, assign Bi=1, otherwise assign Bi=0; S103. Use the Z-score method to identify abnormal values ​​in the historical operation data of the permanent magnet synchronous motor, calculate the mean μ and standard deviation σ of all operating parameters; for each operating parameter Pi, calculate the Z-score, and the calculation formula is: Zi = (Pi-μ) / σ, compare the Zi corresponding to each operating parameter Pi with the preset threshold Z, if |Zi|>Z, then judge that the data point is an abnormal value, assign Ji = 1, otherwise assign Ji = 0; S104. Comprehensively consider Wi, Bi and Ji, and calculate a comprehensive effectiveness score Si for each data point, where Si = α × Wi + β × Bi + γ × Ji, and α, β and γ are all weight coefficients, α + β + γ = 1; compare the comprehensive effectiveness score Si with the corresponding screening threshold S, and screen the data points that satisfy Si ≥ S; store the screened data points in the historical operation data set D1, obtain the control scheme of the permanent magnet synchronous motor, match the data points in the historical operation data set D1 with the control strategy of the corresponding time period in the control scheme through the timestamp, and map each operating parameter Pi with the corresponding control parameter, thereby forming an integrated data set Dc, which contains each screened operating data point and its corresponding control scheme information, and the data structure is expressed as: Dc = {(ti, Pi, Cj) | ti is the timestamp, Pi is the operating parameter, and Cj is the corresponding control scheme}.

3. A cloud service-based permanent magnet motor parameter operation control test method according to claim 2, characterized in that: The step S200 includes: S201. Extract all operating parameters and their corresponding timestamps from the integrated data set Dc, set the control nodes based on the control scheme of the permanent magnet synchronous motor, divide the operating parameters extracted from the integrated data set Dc and their corresponding timestamps into time windows, thereby forming a data set Dw, perform time matching on the data set Dw and the control nodes in the control scheme, and form a control node data set K, where K = {k1, k2, ..., km}, where k1 represents the first control node data, k2 represents the second control node data, and so on, km represents the mth control node data; S202. Based on the control node data set K, the ideal operation data of the corresponding control node is obtained to form an ideal data set G, and G = {g1, g2, ..., gm}, wherein g1 represents the ideal operation data corresponding to the first control node, g2 represents the ideal operation data corresponding to the second control node, and so on, gm represents the ideal operation data corresponding to the mth control node, and each control node in the ideal data set G corresponds one-to-one to the control node in the control node data set K; for each data point in the control node data set K, the deviation coefficient between the historical operation data and the ideal operation data is calculated, and the specific calculation formula is: Wherein, Hx(t) represents the deviation coefficient between the historical operation data of the control node x at time t and the ideal operation data, kx(t) represents the historical operation data of the control node x at time t, gx(t) represents the ideal operation data of the control node x at time t, b represents the parameter factor, a represents the weight coefficient, Vx(t) represents the change rate of the historical operation data of the control node x at time t, and Vx(t)=|kx(t)-kx(t-1)|; S203. For each control node in the control node data set K, calculate the corresponding deviation coefficient according to the calculation formula of the deviation coefficient in S202; obtain the corresponding fault log, and according to the timestamp corresponding to the fault event recorded in the fault log, take the control node corresponding to the same stamp as the fault node, summarize the deviation coefficients corresponding to all fault nodes and calculate the average value, so as to obtain the fault threshold H0; for the control nodes other than the fault node in the control node data set K, compare the deviation coefficients of the remaining control nodes with the preset deviation threshold H, and take the control nodes greater than or equal to the deviation threshold H as the key control nodes, so as to obtain the key control nodes corresponding to the control scheme of the permanent magnet synchronous motor, and the deviation threshold H is less than the fault threshold H0.

4. A cloud service-based permanent magnet motor parameter operation control test method according to claim 3, characterized in that: The step S300 includes: S301. Extract the key control node data set K and the corresponding permanent magnet synchronous motor control scheme information C, analyze the time series of the operating parameters of the key control nodes, and define the trend function: T(k) = (1 / c)Σt∈[1,c], k(t), where c is the time window length, and k(t) represents the operating parameter value of the key control node at time t; use the linear regression model to analyze the correlation between the control scheme C and the permanent magnet synchronous motor operating state change U, and establish the model: U = w0+w1·C+d, where U represents the permanent magnet synchronous motor operating state change, C represents the control scheme parameters, w0 and w1 represent the regression coefficients, and d represents the error term; S302. Calculate the response index Ex of each key control node, and Ex = Δkx / ΔCx, where Δkx represents the change in the operating parameter value of the key control node x, and ΔCx represents the change in the control scheme parameters of the key control node x; based on the correlation analysis results, obtain the optimized control strategy E1: E1 = E+λ·(UT(k)), where λ is the adjustment coefficient.

5. A cloud service-based permanent magnet motor parameter operation control test method according to claim 4, characterized in that: The step S400 includes: S401. Acquire the real-time operation data of the permanent magnet synchronous motor, perform the same analysis on the real-time operation data as the historical operation data, thereby obtaining several real-time control nodes, and calculate the deviation coefficient H2 between the real-time operation data corresponding to the real-time control node and the ideal operation data, and compare the deviation coefficient H2 with the fault threshold H0. If the deviation coefficient H2 is less than the fault threshold H0, go to S402; if the deviation coefficient H2 is greater than or equal to the fault threshold H0, determine that the current permanent magnet synchronous motor has a fault, and output corresponding prompt information to relevant personnel; S402. Compare the deviation coefficient H2 with the preset deviation threshold H, and take the control nodes that are greater than or equal to the deviation threshold H as the key real-time control nodes, and calculate the similarity between the real-time operation data of the key real-time control nodes and the historical operation data, select the key control node corresponding to the historical operation data with the greatest similarity as the matching node, and take the optimization control strategy corresponding to the matching node as the matching strategy, and make corresponding adjustments to the control scheme of the permanent magnet synchronous motor according to the matching strategy.

6. A cloud-based permanent magnet motor parameter operation control test system, applied to a cloud-based permanent magnet motor parameter operation control test method according to any one of claims 1 to 6, characterized in that: The system includes: a data acquisition module, a data analysis module, a control node identification module, an optimization strategy generation module and a real-time monitoring and feedback module; The data acquisition module uses sensor equipment to obtain historical operating data and real-time operating data of the permanent magnet synchronous motor; the data analysis module performs physical validity judgment, outlier detection and time series analysis on the collected historical operating data and real-time operating data, generates a comprehensive validity score, screens out qualified operating data according to the validity score, forms an integrated data set, analyzes the deviation between the historical operating data or the real-time operating data and the ideal operating data, calculates the deviation coefficient, and identifies the key control nodes; the control node identification module sets the control node based on the control scheme, extracts relevant operating parameters and timestamps from the integrated data set, analyzes the control node data set, and determines the deviation coefficient to identify the key control node; the optimization strategy generation module uses a linear regression model to analyze the correlation between the control scheme and the change of the motor operating state, and establishes an optimization control strategy; the real-time monitoring and feedback module monitors and analyzes the real-time operating data of the motor, calculates the deviation coefficient of the real-time control node, determines whether the motor has a fault, and if a fault is detected, promptly outputs an alarm message to relevant personnel, and adjusts the control scheme based on the real-time monitoring results.

7. The cloud-based permanent magnet motor parameter operation control test system according to claim 6 is characterized by: The data acquisition module includes a sensor data acquisition unit and a data preprocessing unit; The sensor data acquisition unit acquires historical operation data and real-time operation data of the permanent magnet synchronous motor; the data preprocessing unit cleans, removes noise and formats the collected historical operation data and real-time operation data; The data analysis module includes a validity assessment unit, a time series analysis unit and a deviation calculation unit; The effectiveness evaluation unit performs effectiveness judgment on the historical operation data and the real-time operation data, generates effectiveness scores, and screens valid data points; the time series analysis unit performs time series analysis on the screened historical operation data and the real-time operation data, calculates the data change rate, and identifies abnormal values; The deviation calculation unit calculates a deviation coefficient between the historical operation data or the real-time operation data and the ideal operation data.

8. The cloud-based permanent magnet motor parameter operation control test system according to claim 6 is characterized by: The control node identification module includes a control node setting unit and a key node analysis unit; The control node setting unit sets the control node according to the control scheme, performs time matching on the data set, and extracts key control node data; The key node analysis unit identifies key control nodes and calculates their deviation coefficients.

9. The cloud-based permanent magnet motor parameter operation control test system according to claim 6 is characterized by: The optimization strategy generation module includes a correlation analysis unit and an optimization control strategy generation unit; The correlation analysis unit uses a linear regression model to analyze the correlation between the control scheme and the change of the operating state, and establishes a corresponding model; the optimization control strategy generation unit generates an optimization control strategy for the key control node according to the correlation analysis result.

10. The cloud service-based permanent magnet motor parameter operation control test system according to claim 6, characterized in that: The real-time monitoring and feedback module includes a real-time data analysis unit, a fault monitoring unit and a control adjustment unit; The real-time data analysis unit obtains the real-time operation data of the permanent magnet synchronous motor and compares and analyzes it with the historical data to obtain corresponding matching information; the fault monitoring unit determines whether the motor has a fault based on the real-time deviation coefficient and issues a fault prompt information in a timely manner; The control adjustment unit adjusts the control scheme of the permanent magnet synchronous motor according to the matching information.

Images