Fault diagnosis method for motor drive control system of electric vehicle

Abstract

The invention discloses a fault diagnosis method for a motor drive control system of an electric vehicle, and relates to the technical field of fault diagnosis, and the method comprises the steps: carrying out the global collection of real-time operation data, obtaining a global operation image, and constructing a three-dimensional operation model based on the global operation image; performing electrical and mechanical coupling relationship restoration on the three-dimensional operation model to obtain operation mechanism data; performing abnormal probability estimation on the motor driving control system based on the operation mechanism data and the global operation image to obtain fault probability data, and performing load impact energy increment calculation on the fault probability data to obtain abnormal impact energy data; according to the fault probability data and the abnormal impact energy data, carrying out local risk level assignment on the electric vehicle motor driving control system to form a local risk level map; and constructing a potential safety hazard identification optimization model, and sending the potential safety hazard identification optimization model to the vehicle-mounted diagnosis terminal. The method has the effect of improving the fault diagnosis efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fault diagnosis, in particular to a fault diagnosis method for an electric vehicle motor drive control system. BACKGROUND

[0002] With the rapid development of the new energy automobile industry, the reliability of the electric vehicle motor drive control system as the core power unit directly determines the driving safety and endurance of the vehicle. The current electric vehicle motor drive system has high integration and complex working conditions, and is prone to faults due to aging of electrical elements, mechanical wear, thermal management failure, etc. If not diagnosed in time, it may cause serious accidents such as motor burning and power interruption.

[0003] In related technologies, traditional fault diagnosis methods mostly rely on manual inspection or single-point sensor monitoring, which has the problems of data fragmentation and limited coverage dimension, and it is difficult to capture early hidden faults, and lacks dynamic trend prediction and visual modeling capabilities, which cannot meet the needs of accurate and early diagnosis of electric vehicles under complex working conditions, thereby reducing the fault diagnosis efficiency, and there is room for improvement. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a fault diagnosis method for an electric vehicle motor drive control system.

[0005] In a first aspect, the present application provides a fault diagnosis method for an electric vehicle motor drive control system, comprising the following steps:

[0006] Step S1: acquiring real-time operation data through a multi-source sensor unit arranged in the electric vehicle motor drive control system, and globally collecting the real-time operation data, obtaining a global operation image according to the global collection result, and constructing a three-dimensional operation model based on the global operation image;

[0007] Step S2: restoring the electrical and mechanical coupling relationship of the three-dimensional operation model to obtain operation mechanism data; estimating the abnormal probability of the motor drive control system based on the operation mechanism data and the global operation image to obtain fault probability data, and calculating the load impact energy increment of the fault probability data to obtain abnormal impact energy data;

[0008] Step S3: assigning a local risk level to the electric vehicle motor drive control system according to the fault probability data and the abnormal impact energy data to form a local risk level atlas;

[0009] Step S4: constructing a safety hazard identification optimization model of the motor drive control system based on the local risk level atlas, and sending the safety hazard identification optimization model to a vehicle-mounted diagnosis terminal to perform fault diagnosis of the electric vehicle motor drive control system.

[0010] Preferably, the step S1 comprises the following steps:

[0011] Step S11: Real-time acquisition of global operation data of the motor drive control system of the electric vehicle under different operating conditions by a sensor unit arranged on the motor controller, the motor stator and the motor shaft, to form a global operation image;

[0012] Step S12: Data normalization and distribution adjustment processing of the global operation image, and obtaining an operation state adjustment image based on the processing result;

[0013] Step S13: Operation characteristic point marking of the operation state adjustment image, the operation characteristic points including motor current fluctuation points, voltage drop points, speed abnormal points and temperature rise points, to obtain operation characteristic point marking data;

[0014] Step S14: Construction of a three-dimensional operation model of the motor drive control system of the electric vehicle based on the operation state adjustment image and the operation characteristic point marking data, and obtaining a three-dimensional operation model according to the construction result.

[0015] Preferably, the step S2 comprises the following steps:

[0016] Step S21: Motor current and voltage abnormal trend analysis of the three-dimensional operation model, to obtain electrical characteristic trend data;

[0017] Step S22: Electrical and mechanical coupling mechanism restoration of the three-dimensional operation model based on the electrical characteristic trend data, to obtain electrical and mechanical operation mechanism data;

[0018] Step S23: Abnormal probability estimation of the motor drive control system of the electric vehicle according to the electrical and mechanical operation mechanism data and the global operation image, to obtain fault probability data;

[0019] Step S24: Abnormal impact energy increment calculation of the fault probability data, to obtain abnormal impact energy data.

[0020] Preferably, the step S23 comprises the following steps:

[0021] Step S231: Vehicle-mounted power supply stability distribution analysis of the global operation image, to obtain power fluctuation distribution density;

[0022] Step S232: Electrical impact erosion degree decomposition of the power fluctuation distribution density and the three-dimensional operation model according to the electrical and mechanical operation mechanism data, to obtain electrical impact erosion degree data;

[0023] Step S233: performing stability evaluation on the motor controller based on the electrical impact erosion degree data, to obtain critical support loss data;

[0024] Step S234: performing risk difference coefficient deduction on the critical support loss data, to obtain risk difference coefficient data;

[0025] Step S235: performing failure probability estimation according to the electrical impact erosion degree data, the critical support loss data and the risk difference coefficient, to obtain failure probability data.

[0026] Preferably, the step S24 comprises the following steps:

[0027] Step S241: performing partition processing on the failure probability data, to obtain failure risk partition data;

[0028] Step S242: performing current fluctuation difference calculation between different risk regions based on the failure risk partition data, to obtain current fluctuation difference data;

[0029] Step S243: performing temperature rise variance calculation between different risk regions based on the risk partition data, to obtain temperature rise variance data;

[0030] Step S244: performing load change energy simulation on the electrical machinery operation mechanism data according to the current fluctuation difference data and the temperature rise variance data, to obtain load change energy data;

[0031] Step S245: performing abnormal impact energy increment calculation based on the load change energy data, to obtain abnormal impact energy data.

[0032] Preferably, the step S244 comprises the following steps:

[0033] Obtaining historical operation condition data, performing space-time distribution analysis on the historical operation condition data, to obtain load intensity distribution data;

[0034] Performing stability difference analysis on the electrical machinery operation mechanism data according to the current fluctuation difference data and the temperature rise variance data, to obtain stability difference data;

[0035] Performing anti-interference capability analysis on the stability difference data, to obtain anti-interference capability data;

[0036] Performing multi-dimensional impact simulation evaluation on the stability difference data and the anti-interference capability data based on the load intensity distribution data, to obtain impact carrying density data;

[0037] Performing increment analysis on the impact carrying density data, to obtain impact carrying density increment data;

[0038] According to the current fluctuation difference data and the temperature rise variance data, load change energy simulation is performed on the impact carrying density increment data, to obtain load change energy data.

[0039] Preferably, the step S3 comprises the following steps:

[0040] Step S31: normalizing the abnormal impact energy data to obtain abnormal impact energy normalized data;

[0041] Step S32: performing convolution calculation on the abnormal impact energy normalized data to obtain abnormal impact energy convolution data;

[0042] Step S33: according to the abnormal impact energy convolution data and the fault probability data, local risk level is assigned to the electric vehicle motor drive control system to obtain a local risk level atlas.

[0043] Preferably, the step S33 comprises the following steps:

[0044] Step S331: performing spatial coordinate re-labeling on the three-dimensional operation model to obtain spatial re-labeling coordinates;

[0045] Step S332: according to the abnormal impact energy convolution data and the fault probability data, risk linkage analysis is performed on the spatial re-labeling coordinates to obtain risk linkage data;

[0046] Step S333: based on the abnormal impact energy convolution data, the fault probability data and the risk linkage data, multivariate local risk index calculation is performed to obtain a multivariate local risk index;

[0047] Step S334: according to the multivariate local risk index, local risk level is assigned to the electric vehicle motor drive control system to obtain a local risk level atlas.

[0048] In a second aspect, the present application provides a fault diagnosis system of an electric vehicle motor drive control system, comprising:

[0049] A data acquisition module is configured to acquire real-time operation data through a plurality of source sensor units arranged in the electric vehicle motor drive control system, and to globally collect the real-time operation data, to obtain a global operation image based on the result of global collection, and to construct a three-dimensional operation model based on the global operation image.

[0050] An analysis and processing module is configured to restore the electrical and mechanical coupling relationship of the three-dimensional operation model to obtain operation mechanism data, to estimate the abnormal probability of the motor drive control system based on the operation mechanism data and the global operation image to obtain fault probability data, and to calculate the abnormal impact energy of the system based on the fault probability data to obtain abnormal impact energy data.

[0051] a risk division module configured to assign a local risk level to the motor drive control system of the electric vehicle according to the fault probability data and the abnormal impact energy data, and form a local risk level atlas;

[0052] an optimized deployment module configured to construct a safety hazard identification optimization model of the motor drive control system based on the local risk level atlas, and send the safety hazard identification optimization model to the vehicle-mounted diagnosis terminal to perform fault diagnosis on the motor drive control system of the electric vehicle.

[0053] In a third aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, cause the computer to perform the fault diagnosis method of the motor drive control system of the electric vehicle according to any one of the above aspects.

[0054] In summary, the present application includes at least one of the following beneficial technical effects:

[0055] The present application provides a fault diagnosis method of a motor drive control system of an electric vehicle, which collects real-time running data globally to obtain a global running image, constructs a three-dimensional running model based on the global running image, restores the electrical and mechanical coupling relationship of the three-dimensional running model to obtain running mechanism data, estimates the abnormal probability of the motor drive control system based on the running mechanism data and the global running image to obtain fault probability data, calculates the load impact energy increment of the fault probability data to obtain abnormal impact energy data, assigns a local risk level to the motor drive control system of the electric vehicle according to the fault probability data and the abnormal impact energy data to form a local risk level atlas, and constructs a safety hazard identification optimization model, which is sent to a vehicle-mounted diagnosis terminal to effectively improve the fault diagnosis efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used for the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0057] Figure 1 is a flow chart of the fault diagnosis method of the motor drive control system of the electric vehicle according to the embodiment of the present application.

[0058] Figure 2 is a schematic diagram of the fault diagnosis system of the motor drive control system of the electric vehicle according to the embodiment of the present application. DETAILED DESCRIPTION

[0059] The following will be described in combination with the drawingsFigures 1-2 The application is further described in detail.

[0060] Embodiment 1

[0061] The embodiment of the application discloses a fault diagnosis method of an electric vehicle motor drive control system.

[0062] Reference Figure 1 A fault diagnosis method of an electric vehicle motor drive control system comprises the following steps:

[0063] Step S1: Real-time operation data is acquired through a multi-source sensor unit arranged in the electric vehicle motor drive control system, and the real-time operation data is globally collected, a global operation image is obtained according to the global collection result, and a three-dimensional operation model is constructed based on the global operation image;

[0064] Step S2: The three-dimensional operation model is subjected to electrical and mechanical coupling relationship restoration, and operation mechanism data is obtained; the motor drive control system is subjected to abnormal probability estimation based on the operation mechanism data and the global operation image, and fault probability data is obtained; the fault probability data is subjected to load shock energy increment calculation, and abnormal shock energy data is obtained;

[0065] Step S3: The electric vehicle motor drive control system is subjected to local risk level assignment according to the fault probability data and the abnormal shock energy data, and a local risk level atlas is formed;

[0066] Step S4: A safety hazard identification optimization model of the motor drive control system is constructed based on the local risk level atlas, and the safety hazard identification optimization model is sent to a vehicle-mounted diagnosis terminal to perform fault diagnosis of the electric vehicle motor drive control system.

[0067] Specifically, multi-source sensor units are arranged in core components (a motor controller, a stator winding, a rotor shaft, a cooling system interface, etc.) of the electric vehicle motor drive control system, specifically including: current sensors and voltage sensors are installed at IGBT modules of the motor controller to collect three-phase current and bus voltage data in real time; temperature sensors are pasted on the surface of a stator core to record winding temperature rise; a speed encoder and a vibration sensor are installed at the end of the shaft to capture speed fluctuation and radial vibration amplitude; flow sensors and temperature sensors are arranged at the inlet and outlet of the cooling circuit to monitor the state of the cooling medium, and real-time operation data is globally collected; parameters of different components and different dimensions are integrated into a data set under a unified time axis, a global operation image is generated by using a data visualization tool, and a three-dimensional operation model is constructed based on the global operation image by using three-dimensional modeling technology; based on the physical size of the motor drive system, the real-time collected temperature distribution, current density and other data are attached to the corresponding components of the model through texture mapping technology;

[0068] Secondly, the electrical and mechanical coupling relationship of the three-dimensional operation model is restored: the correlation model of electrical parameters and mechanical state is established through mechanism analysis, for example, the relationship between stator current harmonic content and shaft eccentricity, the correlation between bus voltage fluctuation and motor controller capacitor aging, and the mapping between vibration frequency and bearing wear degree are analyzed, and finally the operation mechanism data is obtained. Based on the operation mechanism data and the global operation image, the Bayesian probability model is used to estimate the abnormal probability: taking the abnormal parameters in the global operation image as input, combining the prior probability of "abnormal parameter-fault type" in the operation mechanism data, calculating the posterior probability of each component failure of the system, forming the fault probability data, calculating the load impact energy increment of the fault probability data: combining the current load of the motor, analyzing the energy change of the high-fault-probability component under load change, when the controller fault probability is high, the load increase will cause the IGBT module power consumption to rise, and then additional impact energy is generated. By analyzing the energy difference before and after the load change, abnormal impact energy data is obtained.

[0069] Thirdly, the local risk level is assigned according to the fault probability data and the abnormal impact energy data: a risk assessment matrix is set, the horizontal direction is the fault probability (low: <30%, medium: 30%-60%, high: >60%), the vertical direction is the abnormal impact energy (low: <50J, medium: 50-100J, high: >100J), and the intersection of the two forms 9 risk levels (such as high probability+high energy for 1st risk level, low probability+low energy for 9th risk level); the three-dimensional operation model is divided into local areas such as controller area, stator area, shaft area and cooling area according to components, and the fault probability and impact energy of each area are calculated one by one, and the risk level matrix is matched, and finally the local risk level atlas marking the risk level of each area is formed.

[0070] Finally, a safety hazard identification optimization model is constructed based on the local risk level atlas: taking "area-risk level-abnormal parameter" in the risk level atlas as a training sample, a random forest algorithm is used to train the model, so that the model can automatically identify the hazard type according to the real-time collected parameters; through transfer learning, the historical fault data of different vehicle models and different working conditions are fused to optimize the generalization ability of the model, and the safety hazard identification optimization model is obtained. The safety hazard identification optimization model is packaged as an executable program and sent to the vehicle diagnostic terminal through the vehicle Ethernet. The terminal calls the model to analyze the sensor data in real time, and displays the fault position, risk level and emergency suggestion immediately when a hazard is identified, realizing the automation and intelligentization of fault diagnosis.

[0071] It should be noted that the step S1 includes the following steps:

[0072] Step S11: Real-time acquisition of global operation data of the electric vehicle motor drive control system under different operating conditions through sensor units arranged on the motor controller, motor stator and motor shaft, to form a global operation image;

[0073] Step S12: Data normalization and distribution reconciliation processing of the global operation image, and obtaining an operation state reconciliation image based on the processing result;

[0074] Step S13: Labeling of operation feature points on the operation state reconciliation image, the operation feature points including motor current fluctuation points, voltage drop points, speed abnormality points and temperature rise points, to obtain operation feature point labeling data;

[0075] Step S14: Construction of a three-dimensional operation model of the electric vehicle motor drive control system based on the operation state reconciliation image and the operation feature point labeling data, and obtaining a three-dimensional operation model according to the construction result.

[0076] Specifically, the sensor units are precisely arranged for the key components of the electric vehicle motor drive control system: a Hall current sensor is installed at both ends of the IGBT bridge arm inside the motor controller to collect real-time currents of U, V and W three-phase, a voltage sensor is installed at the input bus of the controller to monitor the DC bus voltage; a thermocouple temperature sensor is wound around the three-phase outgoing line of the stator winding to record the real-time temperature of the winding, a vibration sensor is pasted outside the stator core to collect radial vibration acceleration; an optical speed encoder is installed at the non-load end of the motor shaft to capture the shaft speed, a temperature sensor is installed at the shaft bearing seat to monitor the bearing temperature; flow and temperature sensors are installed at the inlet and outlet of the cooling system respectively to record the flow and temperature difference of the cooling medium, the sensor units are connected with the data acquisition module through the vehicle CAN-FD bus; preprocessing of the original data set corresponding to the global operation image: data normalization processing adopts min-max standardization algorithm to map parameters of different dimensions to the [0, 1] interval, eliminating the interference of dimension difference on subsequent analysis; distribution reconciliation processing adopts 3σ criterion to identify outliers, calculates the mean μ and standard deviation σ of each parameter, and eliminates data outside the range [μ-3σ, μ+3σ], and the linear interpolation method is used to fill in the missing points of the eliminated data; high-frequency noise is eliminated through data smoothing algorithm, and finally the operation state reconciliation image with uniform data distribution and no abnormal interference is obtained;

[0077] The running state reconciliation image is marked with running feature points: based on the fault mechanism and safety threshold of the electric vehicle motor drive system, feature point recognition rules are set, the motor current fluctuation point is the time point when the normalized current value changes at a rate of more than 0.1 / s, the voltage drop point is the time point when the bus voltage is lower than 95% of the rated value, the speed anomaly point is the time point when the actual speed deviates from the target speed by more than 5%, and the temperature rise point is the time point when the temperature changes at a rate of more than 2℃ / min. The feature recognition algorithm automatically scans the reconciliation image, records the time, parameter value and corresponding component of each feature point, and forms the running feature point marking data;

[0078] Based on the running state reconciliation image and the feature point marking data, a three-dimensional running model is constructed: based on the CAD three-dimensional drawing of the motor drive system, the SolidWorks software is imported, and the physical structure of the controller, stator, shaft and cooling pipeline is restored in 1:1 proportion; the real-time parameters in the running state reconciliation image are attached to the corresponding position of the model through texture mapping technology, for example, the stator winding is given a color gradient according to the temperature value, and the controller IGBT module displays brightness according to the current density; the abnormal points in the running feature point marking data are marked with a red flashing icon in the model, and a floating prompt box is added; the reconciliation image and the three-dimensional model are associated through a real-time data interface, so that the model parameters are dynamically updated with the real-time data of the reconciliation image, and finally a three-dimensional running model that can dynamically reflect the system running state and abnormal characteristics is obtained.

[0079] Further, the step S2 comprises the following steps:

[0080] Step S21: analyzing the motor current and voltage abnormal trend of the three-dimensional running model to obtain electrical feature trend data;

[0081] Step S22: based on the electrical feature trend data, the electrical and mechanical coupling mechanism of the three-dimensional running model is restored to obtain electrical and mechanical running mechanism data;

[0082] Step S23: according to the electrical and mechanical running mechanism data and the global running image, the abnormal probability of the electric vehicle motor drive control system is estimated to obtain fault probability data;

[0083] Step S24: calculating the abnormal impact energy increment of the fault probability data to obtain abnormal impact energy data.

[0084] Specifically, the motor current and voltage abnormal trend analysis is performed on the three-dimensional operation model: the continuous 5-minute current and voltage data are extracted from the real-time data interface of the three-dimensional model, imported into the signal analysis module of Matlab, the harmonic components of the current signal are decomposed by Fourier transform, and the instantaneous fluctuations of the voltage signal are captured by wavelet transform; the time-amplitude curve and harmonic spectrum of the current and voltage are drawn, the abnormal trend characteristics are analyzed, for example, if the current curve appears periodic peaks, it may correspond to uneven air gap; if the voltage curve appears continuous drop, it may correspond to abnormal conduction of controller IGBT; the long-term change trend of current and voltage is analyzed by trend fitting algorithm, the starting time, change amplitude and related components of abnormal trend are recorded, and the electrical characteristic trend data including harmonic content, fluctuation frequency and trend slope are formed;

[0085] The electrical and mechanical coupling mechanism of the three-dimensional operation model is restored based on the electrical characteristic trend data: the correlation between electrical parameters and mechanical state is established by mechanism analysis, for example, according to motor theory, the harmonic content of stator current is positively correlated with air gap eccentricity, combined with the vibration data of the rotating shaft in the three-dimensional model, a coupling model of "current harmonic content-vibration amplitude-air gap eccentricity" is established; according to the heat conduction theory, the increase of controller current leads to the increase of IGBT power consumption, and then the temperature rises, which in turn leads to the increase of IGBT on-resistance, further aggravating the current fluctuation, a positive feedback coupling model of "current fluctuation-temperature rise-resistance change" is established; according to the principle of tribology, bearing wear of rotating shaft will cause speed fluctuation, which will change the motor back electromotive force, and then cause bus voltage fluctuation, a coupling model of "bearing wear-speed fluctuation-voltage fluctuation" is established; these coupling relationships are quantified through mathematical model and input into the three-dimensional operation model, so that the model can back-propagate the mechanical state according to the electrical characteristic trend data, and finally obtain the electrical and mechanical operation mechanism data;

[0086] The abnormal probability estimation is performed by combining the electrical and mechanical operation mechanism data with the global operation image: the real-time parameters in the global operation image are matched with the coupling relationships in the electrical and mechanical operation mechanism data, for example, if the current harmonic content in the global image is 18%, the mechanism data "harmonic content 15%-20% corresponds to the probability of air gap eccentric fault is 85%", then the probability of air gap eccentric fault is preliminarily determined as 85%; the multi-factor weighted algorithm is introduced, and finally the fault probability data is obtained.

[0087] Load impact energy increment calculation on fault probability data: first, extract the current motor load data from the three-dimensional operation model, and set the load change scene; according to the electrical and mechanical operation mechanism data, analyze the energy change of the high-fault-probability components under different loads, for example, when the stator air gap eccentricity fault probability is 85%, the stator iron loss increases by 5% for every 10% increase in load rate, and the increase in iron loss leads to an increase in energy loss, thereby generating additional impact energy; analyze the energy difference before and after the load change through the principle of energy conservation, and the impact energy increment = total energy after load increase - total energy under current load, wherein the total energy includes electromagnetic energy, mechanical energy and thermal energy; calculate the impact energy increment of different high-fault-probability components respectively, and obtain the abnormal impact energy data by summarizing, and mark the correlation between energy increment and load change.

[0088] It should be noted that the step S23 comprises the following steps:

[0089] Step S231: vehicle-mounted power supply stability distribution analysis is performed on the global operation image to obtain power supply fluctuation distribution density;

[0090] Step S232: according to the electrical and mechanical operation mechanism data, the power supply fluctuation distribution density and the three-dimensional operation model are subjected to electrical impact erosion degree decomposition to obtain electrical impact erosion degree data;

[0091] Step S233: based on the electrical impact erosion degree data, the motor controller is subjected to stability evaluation to obtain critical support loss data;

[0092] Step S234: risk difference coefficient deduction is performed on the critical support loss data to obtain risk difference coefficient data;

[0093] Step S235: according to the electrical impact erosion degree data, the critical support loss data and the risk difference coefficient, fault probability estimation is performed to obtain fault probability data.

[0094] Specifically, vehicle-mounted power supply stability distribution analysis is performed on the global operation image: extract 1 hour of continuous vehicle-mounted power battery output voltage data from the global operation image, calculate the voltage fluctuation value and fluctuation frequency every 1 minute; using statistical analysis method, divide the voltage data according to time interval, calculate the fluctuation mean value and standard deviation of each interval, and draw the voltage fluctuation time distribution curve; combined with the driving cycle of electric vehicles, analyze the power supply stability difference under different working conditions, for example, under congestion working condition, frequent start-stop, power supply fluctuation mean value is 2V, fluctuation frequency is 15 times / minute; under high-speed working condition, the load is stable, the fluctuation mean value is 0.5V, and the fluctuation frequency is 3 times / minute; combine the fluctuation mean value and frequency, calculate the power supply fluctuation distribution density by using kernel density estimation method, form the power supply fluctuation distribution density data, and mark the working condition and time corresponding to the density peak value;

[0095] According to the electrical mechanical operation mechanism data, the power supply fluctuation distribution density is decomposed and the electrical impact erosion degree of the three-dimensional operation model is obtained: the correlation model of “power supply fluctuation-component damage” is extracted from the electrical mechanical operation mechanism data, for example, the service life of the controller capacitor is inversely proportional to the square of the voltage fluctuation amplitude, and the erosion degree of the stator winding insulation layer is positively correlated with the voltage fluctuation frequency; the power supply fluctuation distribution density data is input into the model, and the erosion degree of different components under the current fluctuation density is calculated by combining the material parameters of each component in the three-dimensional operation model, for example, the erosion degree of the controller capacitor in the interval of distribution density 0.8 (congestion working condition) is 5% (capacitance value attenuation of 5%) within 1 hour; the erosion degree of the stator insulation layer in the interval of distribution density 0.8 is 3% (insulation resistance decreases by 3%); the impact process of power supply fluctuation on components is simulated by finite element analysis software (such as ANSYS), and the erosion site (such as severe erosion at the capacitor pin and the stator winding end insulation layer) is intuitively displayed, and the electrical impact erosion degree data is formed;

[0096] Based on the electrical impact erosion degree data, the stability of the motor controller is evaluated: the key performance parameters of the motor controller are extracted from the three-dimensional operation model, and the erosion influence in the electrical impact erosion degree data is combined to establish a controller stability evaluation index system, including voltage ripple coefficient, switching loss rate, and temperature margin; the critical threshold of stability is set; the remaining time for the index to reach the critical threshold is calculated by monitoring the current value and change trend of the evaluation index in real time; the state where the remaining time is less than 24 hours is defined as the critical support loss state, and the corresponding index, remaining time, and erosion inducement are recorded to form the critical support loss data;

[0097] Risk difference coefficient deduction is performed on the critical support loss data: according to the functional importance of each component of the motor drive control system, the remaining time in the critical support loss data is combined to set the risk difference coefficient calculation rule—risk difference coefficient=(1 / remaining time) x component importance weight; for multiple critical indicators of the same component, the maximum risk difference coefficient is taken as the final coefficient of the component; by comparing the coefficients of different components, the risk difference of each component is quantified to form the risk difference coefficient data and mark the coefficient ranking;

[0098] Combined with the electrical impact erosion degree data, the critical support loss data, and the risk difference coefficient, the fault probability is estimated: the analytic hierarchy process is used to construct a fault probability evaluation model, and the three data are taken as the evaluation criterion layer: electrical impact erosion degree, critical support loss remaining time, and risk difference coefficient; the scoring standard is set for each criterion layer; the score is calculated according to the actual data of each component; the total score is mapped to the fault probability; the model is verified through historical fault cases, and the final fault probability data is obtained after adjusting the weight.

[0099] It should be noted that the step S24 comprises the following steps:

[0100] Step S241: partitioning the fault probability data to obtain fault risk partition data;

[0101] Step S242: calculating the current fluctuation difference between different risk areas based on the fault risk partition data to obtain current fluctuation difference data;

[0102] Step S243: calculating the temperature rise variance between different risk areas based on the risk partition data to obtain temperature rise variance data;

[0103] Step S244: simulating the load change energy based on the current fluctuation difference data and the temperature rise variance data to obtain load change energy data;

[0104] Step S245: calculating the abnormal impact energy increment based on the load change energy data to obtain abnormal impact energy data.

[0105] Specifically, the fault probability data is partitioned: according to the structure and function of the electric vehicle motor drive control system, the system is divided into four local areas: controller area (including IGBT module, capacitor, drive chip), stator area (including stator winding, core), rotor shaft area (including rotor, shaft, bearing), cooling system area (including cooling pump, pipeline, radiator); the fault probability of each internal component in each area is extracted from the fault probability data; the maximum value method is used to determine the area fault probability of each area; the fault risk partition is divided according to the area fault probability: high risk area (probability > 70%), medium risk area (30%-70%), low risk area (<30%), the boundaries and contained components of each partition are marked to form the fault risk partition data, and the partitions are marked with different colors in the three-dimensional operation model;

[0106] Based on the fault risk partition data, the current fluctuation difference between different risk areas is calculated: the current data of each area is extracted from the real-time data interface of the three-dimensional operation model, the IGBT output current is extracted from the controller area, the winding input current is extracted from the stator area, the excitation current is extracted from the rotor shaft area, and there is no current data in the cooling system area; the current fluctuation difference between adjacent areas is calculated: fluctuation difference = |area A current fluctuation value-area B current fluctuation value|; the fluctuation difference between areas is calculated; the fluctuation difference values, associated areas and calculation time of all areas are recorded to form the current fluctuation difference data, and the fluctuation difference direction is marked with arrows in the three-dimensional model;

[0107] Calculating temperature rise variance between different risk areas based on fault risk zoning data: Extracting temperature data of each area from the three-dimensional operation model-IGBT temperature in the controller area, winding temperature in the stator area, bearing temperature in the rotor shaft area, and outlet temperature in the cooling system area; Calculating the average temperature rise in 5 minutes for each area, such as 20℃ in the controller area, 15℃ in the stator area, 10℃ in the rotor shaft area, and 5℃ in the cooling system area; Calculating the temperature rise variance between different areas using the variance formula; Calculating the variance by grouping adjacent areas, recording the variance value, associated area, and temperature collection time to form temperature rise variance data;

[0108] Simulating load change energy based on electrical machinery operation mechanism data according to current fluctuation difference data and temperature rise variance data: Extracting the correlation model of "current fluctuation-energy loss" and "temperature rise-energy conversion" from the electrical machinery operation mechanism data-for example, the motor copper loss increases by 50W for every 10A increase in current fluctuation difference; The motor iron loss increases by 30W for every 10℃2 increase in temperature rise variance; Substituting the current fluctuation difference data and temperature rise variance data into the model to calculate the energy loss under the current load; Setting a load change scenario, calculating the energy loss under different load rates based on the correlation between "load rate-current fluctuation-temperature rise" in the mechanism data; Building a load energy change curve (horizontal axis: load rate, vertical axis: energy loss) through energy simulation software (such as PSCAD), marking the energy change trend under different load rates (such as energy loss increases rapidly when load rate > 80%), and forming load change energy data;

[0109] Calculating abnormal impact energy increment based on load change energy data: Defining abnormal impact energy increment as "energy loss under a certain load rate-energy loss under the reference load rate (50%)"; For example, the energy loss is 149.75W at a load rate of 60%, the reference loss is 118.75W, and the increment is 31W; When the load rate is 80%, the energy loss is 200W, and the increment is 81.25W; When the load rate is 100%, the energy loss is 280W, and the increment is 161.25W; Calculating the impact energy increment under different load rates for each fault risk zoning; Analyzing the correlation between the increment and the load rate, and marking the increment threshold of high-risk areas combined with the fault probability of the area; Finally, abnormal impact energy data is formed.

[0110] It should be noted that the step S244 includes the following steps:

[0111] Obtaining historical operation condition data, and performing space-time distribution analysis on the historical operation condition data to obtain load intensity distribution data;

[0112] Performing stability difference analysis on electrical machinery operation mechanism data according to current fluctuation difference data and temperature rise variance data to obtain stability difference data;

[0113] performing anti-interference capability analysis on the stability difference data to obtain anti-interference capability data;

[0114] performing multi-dimensional impact simulation evaluation on the stability difference data and the anti-interference capability data based on the load intensity distribution data to obtain impact carrying density data;

[0115] performing increment analysis on the impact carrying density data to obtain impact carrying density increment data;

[0116] performing load change energy simulation on the impact carrying density increment data according to the current fluctuation difference data and the temperature rise variance data to obtain load change energy data.

[0117] Specifically, the historical running condition data of the motor drive control system of the electric vehicle is obtained: the running data of the past 12 months is exported through the vehicle-mounted T-BOX terminal, covering the working conditions of different seasons (low temperature in winter, high temperature in summer), different road conditions (urban congestion, highway, rural road), and different driving habits (rapid acceleration, smooth driving, and rapid braking), with a data volume of 100,000+ groups; each data contains working condition type, driving time, environmental temperature, motor load rate, current, voltage, temperature, and other parameters; the historical data is cleaned to eliminate invalid data (such as blank data of offline sensors) caused by equipment failure, and 80,000+ valid data are retained to form a historical running condition data set.

[0118] Secondly, the historical running condition data is analyzed in time and space: from the time dimension, the time period is divided according to month, week, and hour, and the working condition distribution of different time periods is counted (for example, in winter from January to March, the average motor load rate is 40%; in summer from July to September, the average load rate is 55%; during the morning peak of weekdays from 7 to 9, the load rate fluctuates greatly with an average of 50%; during the night from 22 to 6, the load rate is low with an average of 20%); from the spatial dimension, the working condition characteristics of different regions (such as urban center congestion, load rate fluctuation frequency 15 times / hour; highway uniform speed, fluctuation frequency 3 times / hour) are counted by dividing the driving area (urban center, suburb, highway); the "time-space-load rate" three-dimensional heat map (horizontal axis for time, vertical axis for space, and color depth representing load rate) is drawn by using the heat map visualization tool, which intuitively shows the spatio-temporal distribution law of load intensity (for example, the urban center area in the morning peak of summer weekdays is a red high load area); the load rate mean, standard deviation, and peak value of each time-space interval are calculated through statistical analysis to form the load intensity distribution data containing time interval, space region, and load rate statistical value.

[0119] Subsequently, analyze the stability difference of the electrical mechanical operation mechanism data according to the current fluctuation difference data and the temperature rise variance data: extract the stability parameters (such as the voltage fluctuation tolerance value of the controller capacitor, the temperature stability coefficient of the stator winding) of each region (controller area, stator area, etc.) from the electrical mechanical operation mechanism data; input the current fluctuation difference data (such as the controller area-stator area 20A) and the temperature rise variance data (such as 6.25℃2) into the stability evaluation model, and calculate the stability scores of each region under the current fluctuation and variance - for example, the voltage fluctuation tolerance value of the controller area is 30A, the current fluctuation difference is 20A, and the score is 80; the temperature stability coefficient of the stator area is 10℃2, and the current variance is 6.25℃2, and the score is 75; compare the stability scores of different regions (such as the controller area 80 vs. the rotor area 85), identify the weak stability area (such as the stator area), and analyze the causes of the stability difference (such as the low score of the stator area due to the erosion of the winding insulation), record the region name, stability score, and difference causes, and form the stability difference data.

[0120] Next, analyze the anti-interference ability of the stability difference data: set interference test scenarios, including power supply voltage fluctuation interference (±10% rated voltage), electromagnetic radiation interference (100-300MHz frequency band), and temperature interference (environmental temperature ±20℃); input the stability difference data of each region (such as the stator area 75) into the anti-interference test model to simulate the stability score changes under different interference scenarios - for example, under power supply voltage fluctuation interference, the controller area score decreases from 80 to 72, and the stator area decreases from 75 to 65; under electromagnetic radiation interference, the controller area score decreases to 75, and the stator area decreases to 70; under temperature interference, the controller area score decreases to 78, and the stator area decreases to 68; calculate the anti-interference ability index of each region (the reciprocal of the difference value before and after interference, the smaller the difference value, the larger the index), such as the controller area power supply interference difference value 8, the index 0.125; the stator area difference value 10, the index 0.1; identify the weak anti-interference area (such as the stator area) through index comparison; and form the anti-interference ability data containing the region name, interference type, anti-interference ability index, and weak point.

[0121] Then, the stability difference data and the anti-interference ability data are evaluated based on the load intensity distribution data through multi-dimensional impact simulation: a multi-dimensional impact evaluation model is constructed, and the load intensity (time-space distribution), the stability difference (score), and the anti-interference ability (index) are taken as input dimensions; an evaluation scene is set, such as "summer weekday morning peak (high load intensity, load rate 55%) + urban center (congestion, high fluctuation) + power supply interference (±10%)"; the load intensity distribution data (load rate 55%, fluctuation frequency 15 times / hour), the stability difference data (controller area 80 points, stator area 75 points), and the anti-interference ability data (controller area 0.125, stator area 0.1) in the scene are input into the model; the Monte Carlo simulation algorithm is used to simulate 1000 times of impact processes in the scene, and the impact intensity (impact value of comprehensive load, stability, and anti-interference) of each area in each simulation is calculated; the distribution of the impact intensity (for example, the impact intensity of the controller area is concentrated in 80-100, and the impact intensity of the stator area is concentrated in 70-90) is counted, and the impact carrying density (probability of impact intensity distribution per unit time) is calculated by using the kernel density estimation method, for example, the peak value of the impact carrying density of the controller area is 0.9 (corresponding to the impact intensity 90), and the peak value of the impact carrying density of the stator area is 0.7 (corresponding to the impact intensity 80), to form the impact carrying density data.

[0122] Then, the impact carrying density data is analyzed incrementally: a reference scene (for example, winter weekday flat peak period, low load intensity 40%, no interference) is selected, and the impact carrying density in the scene (for example, controller area 0.5, stator area 0.4) is calculated; the density difference between the target scene (for example, high load in summer morning peak + interference) and the reference scene, that is, the impact carrying density increment (controller area 0.9-0.5=0.4, stator area 0.7-0.4=0.3), is calculated; the correlation between the increment and the scene parameters (for example, the load rate increases by 10% per time, and the controller area increment increases by 0.1; when there is power supply interference, the increment increases by 0.15) is analyzed; the high-increment scene (for example, load rate >60%+power supply interference, controller area increment >0.5) is marked, and the impact carrying density increment data is formed.

[0123] Finally, the load change energy simulation is performed on the impact carrying density increment data according to the current fluctuation difference data and the temperature rise variance data: the current fluctuation difference data and the temperature rise variance data (6.25℃2) are taken as weight factors to correct the impact carrying density increment data; the corrected increment data is input into the load change energy model, and the energy values under different load rates are calculated in combination with the energy loss basic values under different load rates; the "load rate-energy value" curve is generated by using the energy simulation software, and whether the energy under each load rate exceeds the safety threshold is marked; and finally, the load change energy data is formed.

[0124] It should be noted that the step S3 includes the following steps:

[0125] Step S31: normalizing the abnormal impact energy data to obtain abnormal impact energy normalized data;

[0126] Step S32: performing convolution calculation on the abnormal impact energy normalized data to obtain abnormal impact energy convolution data;

[0127] Step S33: assigning a local risk level to the electric vehicle motor drive control system according to the abnormal impact energy convolution data and the failure probability data to obtain a local risk level atlas.

[0128] It should be noted that the step S33 includes the following steps:

[0129] Step S331: performing spatial coordinate re-labeling on the three-dimensional operation model to obtain spatial re-labeling coordinates;

[0130] Step S332: performing risk linkage analysis on the spatial re-labeling coordinates according to the abnormal impact energy convolution data and the failure probability data to obtain risk linkage data;

[0131] Step S333: performing multivariate local risk index calculation based on the abnormal impact energy convolution data, the failure probability data and the risk linkage data to obtain a multivariate local risk index;

[0132] Step S334: assigning a local risk level to the electric vehicle motor drive control system according to the multivariate local risk index to obtain a local risk level atlas.

[0133] Specifically, in step S331, the three-dimensional operation model is subjected to spatial coordinate re-labeling: due to the possibility of component displacement and sensor installation position loosening of the motor drive system in long-term operation, the spatial coordinates of the original three-dimensional model deviate from the actual physical position; the laser range finder is used to actually measure the key reference points of the motor drive system - six reference points such as the controller shell corner point, the stator core end face center, and the rotating shaft axis are selected, and the actual three-dimensional coordinates (X, Y, Z) of each reference point are recorded; the actual coordinates are compared with the reference point coordinates in the original model, and the coordinate deviation value is calculated (for example, the controller corner point coordinates in the original model are (100, 200, 300), and the actual coordinates are (102, 201, 300), and the deviation is (2, 1, 0)); the spatial coordinate transformation algorithm (such as affine transformation) is used to correct the coordinates of the entire three-dimensional model according to the deviation values of the six reference points - for example, the X coordinate of all points in the model is increased by 2 mm, the Y coordinate is increased by 1 mm, and the Z coordinate remains unchanged; after correction, the coordinates of other non-reference points (such as the center of the IGBT module) are verified again using the laser range finder to ensure that the deviation is less than 0.5 mm; finally, the spatial re-labeled coordinates highly consistent with the actual physical position are obtained, and the coordinate system of the three-dimensional model is updated, so that each spatial unit in the model can accurately correspond to the physical position of the actual component;

[0134] According to the abnormal impact energy convolution data and the fault probability data, the risk linkage analysis of the spatial re-labeled coordinates is performed: the correlation between each spatial unit is extracted from the spatial re-labeled coordinates, for example, unit A in the controller area is connected to unit B in the stator area through a wire, and there is an electrical correlation; unit A and unit C in the cooling system area are in contact through a heat sink, and there is a thermal correlation; the abnormal impact energy convolution data and the fault probability data are input into the correlation analysis model; the risk transmission coefficient between the correlated units is calculated - according to the size of the transmission coefficient, the risk linkage strength is judged, for example, unit A and unit B are strongly linked, and unit A and unit C are strongly linked; record all correlated units, linkage types, transmission coefficients, and linkage strengths to form risk linkage data, and mark the correlation relationship with different colored lines in the three-dimensional model;

[0135] According to the multivariate local risk index, the motor drive system is assigned a local risk level: set the risk index threshold, divide the index into 9 risk levels - index >= 2.0 is level 1 (very high risk, bright red), 1.8-2.0 is level 2 (high risk, dark red), 1.6-1.8 is level 3 (medium-high risk, orange), 1.4-1.6 is level 4 (medium risk, orange-yellow), 1.2-1.4 is level 5 (medium-low risk, yellow), 1.0-1.2 is level 6 (low risk, light yellow), 0.8-1.0 is level 7 (lower risk, light green), 0.6-0.8 is level 8 (very low risk, green), <0.6 is level 9 (safe, dark green); compare the risk index of each spatial unit with the threshold to determine its risk level (e.g. unit A index 2.0 is level 1, unit B 1.5 is level 4, unit C 1.18 is level 6); in the three-dimensional model after spatial re-mapping, assign each unit the corresponding color according to the level, and add a floating information box; integrate the levels of all units to form a local risk level atlas covering all local areas of the motor drive system, with accurate coordinates and clear risk levels - in the atlas, the controller area unit with very high risk is bright red, the stator area unit with medium risk is orange-yellow, and the cooling system area unit with low risk is green, and the association lines (strong association) between red units and surrounding units are clearly visible, intuitively displaying the risk distribution and diffusion association.

[0136] Embodiment 2

[0137] The embodiments of the present application also disclose a fault diagnosis system of a motor drive control system of an electric vehicle.

[0138] Referring to Figure 2 A fault diagnosis system of a motor drive control system of an electric vehicle, comprising:

[0139] A data acquisition module, configured to acquire real-time operation data through a plurality of source sensor units arranged in the motor drive control system of the electric vehicle, and globally collect the real-time operation data, to obtain a global operation image according to the result of global collection, and to construct a three-dimensional operation model based on the global operation image;

[0140] An analysis and processing module, configured to restore electrical and mechanical coupling relationship of the three-dimensional operation model to obtain operation mechanism data, to estimate abnormal probability of the motor drive control system based on the operation mechanism data and the global operation image to obtain fault probability data, and to calculate energy increment of system load impact based on the fault probability data to obtain abnormal impact energy data;

[0141] A risk division module, configured to assign a local risk level to the motor drive control system of the electric vehicle according to the fault probability data and the abnormal impact energy data, to form a local risk level atlas;

[0142] The optimization deployment module is used for constructing a safety hazard identification optimization model of the motor drive control system based on the local risk level atlas, and sending the safety hazard identification optimization model to the vehicle-mounted diagnosis terminal to perform fault diagnosis of the motor drive control system of the electric vehicle.

[0143] The above is only an example and description of the concept of the present application. Those skilled in the art can make various modifications or supplements to the described specific embodiments or use similar ways to replace them, as long as they do not deviate from the concept of the present application, which shall fall within the protection scope of the present application.

[0144] In the description of the present specification, the description of the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are contained in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0145] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The preferred embodiments do not describe all the details and limit the present application to the specific embodiments. Obviously, many modifications and changes can be made according to the content of the present specification. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can well understand and utilize the present application.

Claims

1. A failure diagnosis method for an electric motor drive control system of an electric vehicle, characterized by, The method comprises the following steps: Step S1: obtaining real-time operation data through a multi-source sensor unit arranged in the motor drive control system of the electric vehicle, globally collecting the real-time operation data, obtaining a global operation image according to the result of the global collection, and constructing a three-dimensional operation model based on the global operation image; Step S2: restoring the electrical and mechanical coupling relationship of the three-dimensional operation model to obtain operation mechanism data; Based on the operation mechanism data and the global operation image, the abnormal probability of the motor drive control system is estimated to obtain fault probability data, and the fault probability data is subjected to load impact energy increment calculation to obtain abnormal impact energy data; Step S3: assigning a local risk level to the motor drive control system of the electric vehicle according to the fault probability data and the abnormal impact energy data to form a local risk level atlas; Step S4: constructing a safety hazard identification optimization model of the motor drive control system based on the local risk level atlas, and sending the safety hazard identification optimization model to the vehicle-mounted diagnostic terminal to perform fault diagnosis on the motor drive control system of the electric vehicle.

2. The fault diagnosis method of the electric motor drive control system of the electric vehicle according to claim 1, characterized in that, The step S1 comprises the following steps: Step S11: collecting global operation data of the motor drive control system of the electric vehicle under different operating conditions in real time through sensor units arranged in the motor controller, motor stator and motor shaft to form a global operation image; Step S12: performing data normalization and distribution reconciliation processing on the global operation image, and obtaining an operation state reconciliation image based on the processing result; Step S13: marking running feature points on the operation state reconciliation image, wherein the running feature points include motor current fluctuation points, voltage drop points, speed abnormal points and temperature rise points, and obtaining running feature point marking data; Step S14: constructing a three-dimensional operation model of the motor drive control system of the electric vehicle based on the operation state reconciliation image and the running feature point marking data, and obtaining a three-dimensional operation model according to the construction result.

3. The method of claim 1, wherein the method further comprises: The step S2 comprises the following steps: Step S21: performing motor current and voltage abnormal trend analysis on the three-dimensional operation model to obtain electrical characteristic trend data; Step S22: restoring the electrical and mechanical coupling mechanism of the three-dimensional operation model based on the electrical characteristic trend data to obtain electrical and mechanical operation mechanism data; Step S23: estimating the abnormal probability of the motor drive control system of the electric vehicle according to the electrical and mechanical operation mechanism data and the global operation image to obtain fault probability data; Step S24: performing abnormal impact energy increment calculation on the fault probability data to obtain abnormal impact energy data.

4. The fault diagnosis method of the electric motor drive control system of the electric vehicle according to claim 3, characterized in that, The step S23 comprises the following steps: Step S231: performing vehicle-mounted power supply stability distribution analysis on the global operation image to obtain power supply fluctuation distribution density; Step S232: decomposing the power supply fluctuation distribution density and the three-dimensional operation model according to the electrical and mechanical operation mechanism data to obtain electrical impact erosion degree data; Step S233: performing stability evaluation on the motor controller based on the electrical impact erosion degree data to obtain critical support loss data; Step S234: risk difference coefficient deduction is carried out on the critical support loss data, and risk difference coefficient data is obtained; Step S235: fault probability estimation is carried out according to the electrical impact erosion degree data, the critical support loss data and the risk difference coefficient, and fault probability data is obtained.

5. The method of claim 3, wherein the method further comprises: The step S24 includes the following steps: Step S241: the fault probability data is processed by partitioning, and fault risk partition data is obtained; Step S242: current fluctuation difference calculation between different risk regions is carried out based on the fault risk partition data, and current fluctuation difference data is obtained; Step S243: temperature rise variance calculation between different risk regions is carried out based on the risk partition data, and temperature rise variance data is obtained; Step S244: load change energy simulation is carried out on electrical machinery operation mechanism data according to current fluctuation difference data and temperature rise variance data, and load change energy data is obtained; Step S245: abnormal impact energy increment calculation is carried out based on the load change energy data, and abnormal impact energy data is obtained.

6. The fault diagnosis method of the electric motor drive control system of the electric vehicle according to claim 5, characterized in that, The step S244 includes the following steps: Obtain historical operation condition data, and obtain load intensity distribution data by analyzing the time and space distribution of the historical operation condition data; Stability difference data is obtained by carrying out stability difference analysis on electrical machinery operation mechanism data according to current fluctuation difference data and temperature rise variance data; Anti-interference capability data is obtained by carrying out anti-interference capability analysis on the stability difference data; Multi-dimensional impact simulation evaluation is carried out on the stability difference data and anti-interference capability data based on load intensity distribution data, and impact carrying density data is obtained; Impact carrying density increment data is obtained by carrying out increment analysis on the impact carrying density data; Load change energy data is obtained by carrying out load change energy simulation on the impact carrying density increment data according to current fluctuation difference data and temperature rise variance data.

7. The fault diagnosis method of the electric motor drive control system of the electric vehicle according to claim 1, characterized in that, The step S3 includes the following steps: Step S31: normalization processing is carried out on the abnormal impact energy data, and abnormal impact energy normalized data is obtained; Step S32: convolution calculation is carried out on the abnormal impact energy normalized data, and abnormal impact energy convolution data is obtained; Step S33: local risk level atlas is obtained by carrying out local risk level assignment on the electric vehicle motor drive control system according to the abnormal impact energy convolution data and the fault probability data.

8. The fault diagnosis method of the electric motor drive control system of the electric vehicle according to claim 1, characterized in that, The step S33 includes the following steps: Step S331: space coordinate re-labeling is carried out on the three-dimensional operation model, and space re-labeling coordinates are obtained; Step S332: risk linkage data is obtained by carrying out risk linkage analysis on the space re-labeling coordinates according to the abnormal impact energy convolution data and the fault probability data; Step S333: multivariate local risk index calculation is carried out based on the abnormal impact energy convolution data, the fault probability data and the risk linkage data, and multivariate local risk index is obtained; Step S334: local risk level atlas is obtained by carrying out local risk level assignment on the electric vehicle motor drive control system according to the multivariate local risk index.

9. A fault diagnosis system of an electric vehicle motor drive control system, applied to the fault diagnosis method of the electric vehicle motor drive control system according to any one of claims 1-8, characterized in that, It includes: The data acquisition module is configured to acquire real-time operation data through a plurality of source sensor units arranged in the motor drive control system of the electric vehicle, collect the real-time operation data globally, obtain a global operation image based on the global collection result, and construct a three-dimensional operation model based on the global operation image. The analysis processing module is configured to restore an electrical and mechanical coupling relationship of the three-dimensional operation model to obtain operation mechanism data. The operation mechanism data and the global operation image are used to estimate an abnormal probability of the motor drive control system to obtain fault probability data, and the fault probability data is used to calculate a system load impact energy increment to obtain abnormal impact energy data. The risk division module is configured to assign a local risk level to the motor drive control system of the electric vehicle based on the fault probability data and the abnormal impact energy data to form a local risk level atlas. The optimization deployment module is configured to construct a safety hazard identification optimization model of the motor drive control system based on the local risk level atlas, and send the safety hazard identification optimization model to a vehicle-mounted diagnostic terminal to perform fault diagnosis on the motor drive control system of the electric vehicle.

10. A computer-readable storage medium, characterized in that: The computer is caused to execute the fault diagnosis method of the motor drive control system of the electric vehicle when the instructions are executed on the computer.

Images