New energy commercial vehicle electric drive axle motor operation abnormity detection system

Abstract

The invention discloses a detection system for operation abnormity of an electric drive axle motor of a new energy commercial vehicle, and belongs to the technical field of motor abnormity detection. The system comprises a multi-source sensing module, a dynamic coupling analysis module, a harmonic distortion traceability module, a dynamic stability analysis module, an anomaly fusion decision module, a self-adaptive threshold generation module and a fault tree reasoning module. Multi-dimensional signals such as current, vibration, temperature and a rotor position angle are synchronously acquired through the multi-source sensing module, and multi-physics field collaborative analysis is performed through the dynamic coupling analysis module and the harmonic distortion traceability module, so that the fault diagnosis accuracy of operation abnormity of the electric drive axle motor of the new energy commercial vehicle is improved; the problem that in the prior art, detection only depends on a single physical quantity, and misjudgment or missing detection is easily caused by interference is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of motor anomaly detection, and in particular to a system for detecting abnormal operation of an electric drive axle motor of a new energy commercial vehicle. Background Art

[0002] As the core power source of new energy commercial vehicles, the electric drive axle motor makes accurate monitoring of its operating status crucial for driving safety and reliability. Existing motor anomaly detection technologies often rely on monitoring a single physical quantity, such as determining winding faults through three-phase current harmonic analysis or identifying mechanical damage based on vibration acceleration spectra. Due to their single detection dimension, these solutions struggle to fully characterize the complex operating conditions of the motor, particularly under the variable operating conditions of commercial vehicles, such as heavy-load climbing and frequent starts and stops.

[0003] The core flaw of single-physical-value detection lies in its inadequate anti-interference capabilities. For example, current detection can be susceptible to distortion of the current spectrum due to grid harmonics or switching noise from power devices, leading to false alarms in fault diagnosis based on current harmonics. Vibration detection, on the other hand, can be interfered with by non-fault factors like road bumps and suspension system vibrations, leading to real faults like bearing wear being drowned out by noise and missed. A single parameter cannot reflect the early-stage fault characteristics of multiple fields acting in concert, resulting in existing technologies' limited ability to identify anomalies in their early stages, making it difficult to meet the high-reliability requirements of commercial vehicles. Summary of the Invention

[0004] The embodiments of the present application provide a system for detecting abnormal operation of the electric drive axle motor of a new energy commercial vehicle, thereby solving the problem in the prior art of relying solely on detection of a single physical quantity, which is susceptible to interference and leads to misjudgment or missed detection, and thereby improving the accuracy of fault diagnosis of abnormal operation of the electric drive axle motor of a new energy commercial vehicle.

[0005] The embodiment of the present application provides a detection system for abnormal operation of the electric drive axle motor of a new energy commercial vehicle, including: a multi-source sensing module, a dynamic coupling analysis module, a harmonic distortion tracing module, a dynamic stability analysis module, an abnormal fusion decision module, an adaptive threshold generation module, and a fault tree reasoning module;

[0006] The multi-source sensing module is used to collect the three-phase current, speed, load torque, rotor position angle, winding temperature and bearing vibration acceleration of the electric drive axle motor of a new energy commercial vehicle in real time.

[0007] The dynamic coupling analysis module is used to generate magnetic field asymmetry and stress concentration factor based on rotor position angle, winding temperature and bearing vibration acceleration;

[0008] The harmonic distortion tracing module is used to calculate the harmonic distortion factor based on the three-phase current;

[0009] The dynamic stability analysis module is used to calculate the Lyapunov exponent based on the rotor position angle and speed;

[0010] The anomaly fusion decision module is used to output a comprehensive anomaly index based on the magnetic field asymmetry, stress concentration factor, harmonic distortion factor and Lyapunov index;

[0011] The adaptive threshold generation module is used to adjust the adaptive threshold based on the rotational speed and load torque;

[0012] The fault tree reasoning module is used to trigger an abnormality warning when the comprehensive abnormality index is greater than the abnormality threshold, and associate the abnormality with the fault minimum cut set.

[0013] Furthermore, the step of obtaining the magnetic field asymmetry in the dynamic coupling analysis module includes:

[0014] The air gap magnetic flux distribution is collected through the rotor position angle, and the circumference is divided into monitoring points. The relative deviation between the magnetic flux of each monitoring point and the average magnetic flux is counted, and the square root of the square sum is averaged to obtain the basic component of the magnetic flux asymmetry.

[0015] Obtaining the winding temperature spatial gradient according to the winding temperature;

[0016] Obtain the thermal magnetic coupling coefficient and calculate the magnetic field asymmetry;

[0017] The specific calculation formula is:

[0018]

[0019] Where Ψ is the magnetic field asymmetry, θ is the rotor position angle, N is the total number of monitoring points, k is the monitoring point number, B k (θ) is the magnetic density at the monitoring point, is the average magnetic flux density, T w is the winding temperature, is the winding temperature spatial gradient, and η is the thermal magnetic coupling coefficient.

[0020] Furthermore, the method for obtaining the thermal magnetic coupling coefficient is:

[0021] At the saturation magnetic flux density point of the motor core, the partial derivatives of the magnetic field asymmetry with respect to the winding temperature and the partial derivative of the magnetic field asymmetry with respect to the magnetic flux density are calculated respectively. The thermal magnetic coupling coefficient is calculated based on the two sets of partial derivatives. The specific formula is:

[0022]

[0023] Among them, B sat is the saturation magnetic flux density, B is the magnetic flux density, For the partial derivative.

[0024] Furthermore, the stress concentration factor is obtained as follows:

[0025] Collect the bearing vibration acceleration baseline value under no-load conditions as a vibration reference during normal operation;

[0026] When the motor is running under load, the real-time value of the bearing vibration acceleration is collected, and the relative deviation from the bearing vibration acceleration baseline value is counted. The average value is integrated within the time interval to obtain the stress concentration factor.

[0027] The specific calculation formula is:

[0028]

[0029] Where σ is the stress concentration factor, μ a is the baseline value of bearing vibration acceleration, a v (t) is the real-time value of the bearing vibration acceleration, [t1, t2] is the time interval from the starting time t1 to the end time t2, and t is the time variable.

[0030] Furthermore, the step of obtaining the harmonic distortion factor includes:

[0031] Perform spectrum analysis on the three-phase current to obtain the fault energy and total harmonic energy under the fault state, and calculate their relative proportions;

[0032] The logarithm of the ratio of the fault state energy to the calibration state energy is taken to amplify the difference characteristics of the abnormal energy and obtain the harmonic distortion factor;

[0033] The formula for calculating the harmonic distortion factor is:

[0034]

[0035] Among them, Γ h is the harmonic distortion factor, is the k-th fault state energy, is the total harmonic energy, is the calibration state energy, h is the fault harmonic order number, j is the number of all harmonic orders, max It is the highest harmonic order in the entire frequency band.

[0036] Furthermore, the harmonic energy also includes a temperature compensation mechanism:

[0037] Taking the reference temperature T0 as the benchmark, the influence of temperature deviation on the calibration state energy is calculated using the resistance temperature coefficient ò, and the corrected calibration state energy is obtained;

[0038] The temperature compensation formula for the harmonic energy is:

[0039]

[0040] in, is the corrected harmonic energy, ò is the resistance temperature coefficient, T w is the winding temperature, T0 is the reference temperature.

[0041] Furthermore, the step of obtaining the Lyapunov exponent includes:

[0042] Construct a three-dimensional phase space using q-axis current, speed, and rotor position angle;

[0043] The Lyapunov exponent is obtained by iteratively calculating the modulus ratio of the offset vectors at adjacent moments and taking the natural logarithm average. The formula is:

[0044]

[0045] Among them, Λ is the Lyapunov exponent, δx(t g ) is the state offset vector at the gth moment, δx(t g-1 ) is the state offset vector at the g-1th moment, M is the total number of steps in the evolution of the phase space trajectory, representing the time from the initial moment t0 to the final moment t M The number of sampling points between, g is the step index, the phase space offset vector δx=[i q ,ω,θ] T ,i q is the q-axis current, ω is the speed, and θ is the rotor position angle.

[0046] Furthermore, the step of obtaining the comprehensive abnormality index includes:

[0047] The weighted sum of magnetic field asymmetry, stress concentration factor, key harmonic distortion factor and Lyapunov index term is used to obtain the comprehensive anomaly index formula:

[0048]

[0049] Among them, Φ is the comprehensive anomaly index, Ψ is the magnetic field asymmetry, σ is the stress concentration factor, is the sum of the key harmonic distortion factors, h is the fault harmonic order number, h max is the total number of fault harmonics, e Λ is the Lyapunov index term, and α, β, γ, κ are the optimal weights.

[0050] Furthermore, the step of adjusting the adaptive threshold includes:

[0051] Based on the reference threshold, the adaptive threshold is adjusted according to the normalized speed and load torque, combined with the speed weight and load weight. The formula is:

[0052]

[0053] wherein, Φ th is an adaptive threshold, Φ0 is a reference threshold, ω is a rotational speed, ω max is a rated rotational speed, is a rotational speed weight, is a load weight, τ is a load torque, τ max is a maximum torque.

[0054] Further, the fault minimal cut set is:

[0055] When the ratio of the fifth harmonic distortion factor to the third harmonic distortion factor is significantly higher than the reference ratio in normal operation, and the stress concentration coefficient exceeds the pre-set vibration stress abnormal threshold, the bearing wear is determined.

[0056] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0057] 1. By synchronously collecting multi-dimensional signals such as current, vibration, temperature, rotor position angle, etc. through a multi-source sensing module, and performing multi-physical field collaborative analysis through a dynamic coupling analysis module, a harmonic distortion tracing module, etc., the fault diagnosis accuracy of the operation abnormality of the electric drive axle motor of the new energy commercial vehicle is improved, and the problem that in the prior art, only single physical quantity detection is relied on, and misjudgment or missed detection is easily caused by interference is effectively solved.

[0058] 2. The air gap magnetic flux density distribution is collected through the rotor position angle, the winding temperature spatial gradient and the thermal-magnetic coupling coefficient are introduced, and a magnetic field asymmetry calculation model is constructed; at the same time, the harmonic energy reference value is temperature corrected based on the resistance temperature coefficient, and temperature bidirectional compensation of electromagnetic characteristics is realized.

[0059] 3. The stress concentration coefficient is calculated through the no-load vibration baseline and the load vibration integral, the ratio of the fifth harmonic distortion factor to the third harmonic distortion factor is combined to construct a fault minimal cut set judgment rule with double conditions, multi-index cross verification of mechanical faults is realized, and misjudgment or missed detection caused by single vibration or harmonic index easily affected by non-fault factors is avoided.

[0060] 4. The abnormal threshold is dynamically adjusted based on the rotational speed and the load torque, the phase space is constructed through the q-axis current, the rotational speed and the rotor position angle, the Lyapunov index is used to quantify the system trajectory divergence rate, dynamic stability evaluation under working condition fluctuation is realized, and the problem that the fixed threshold cannot adapt to variable working condition operation and the traditional analysis method cannot capture the early chaos characteristics of the system is solved. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 is a new energy commercial vehicle electric drive axle motor operation abnormality detection system structure diagram provided by the embodiments of the present application. DETAILED DESCRIPTION

[0062] The embodiments of the present application provide a detection system for abnormal operation of the electric drive axle motor of a new energy commercial vehicle, thereby solving the problem in the prior art of relying solely on detection of a single physical quantity, which is susceptible to interference and leads to misjudgment or missed detection. By synchronously collecting multi-dimensional signals such as current, vibration, temperature, and rotor position angle through a multi-source sensing module, and performing multi-physical field collaborative analysis through a dynamic coupling analysis module, a harmonic distortion tracing module, etc., the accuracy of fault diagnosis of abnormal operation of the electric drive axle motor of a new energy commercial vehicle is improved.

[0063] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0064] like Figure 1 As shown, the embodiment of the present application provides a detection system for abnormal operation of the electric drive axle motor of a new energy commercial vehicle, including: a multi-source sensing module, a dynamic coupling analysis module, a harmonic distortion tracing module, a dynamic stability analysis module, an abnormal fusion decision module, an adaptive threshold generation module, and a fault tree reasoning module;

[0065] The multi-source sensing module is used to collect the three-phase current, speed, load torque, rotor position angle, winding temperature and bearing vibration acceleration of the electric drive axle motor of a new energy commercial vehicle in real time.

[0066] The dynamic coupling analysis module is used to generate magnetic field asymmetry and stress concentration factor based on rotor position angle, winding temperature and bearing vibration acceleration;

[0067] The harmonic distortion tracing module is used to calculate the harmonic distortion factor based on the three-phase current;

[0068] The dynamic stability analysis module is used to calculate the Lyapunov exponent based on the rotor position angle and speed;

[0069] The anomaly fusion decision module is used to output a comprehensive anomaly index based on the magnetic field asymmetry, stress concentration factor, harmonic distortion factor and Lyapunov index;

[0070] The adaptive threshold generation module is used to adjust the adaptive threshold based on the rotational speed and load torque;

[0071] The fault tree reasoning module is used to trigger an abnormality warning when the comprehensive abnormality index is greater than the abnormality threshold, and associate the abnormality with the fault minimum cut set.

[0072] Furthermore, the step of obtaining the magnetic field asymmetry in the dynamic coupling analysis module includes:

[0073] The air gap magnetic flux distribution is collected through the rotor position angle, and the circumference is divided into monitoring points. The relative deviation between the magnetic flux of each monitoring point and the average magnetic flux is counted, and the square root of the square sum is averaged to obtain the basic component of the magnetic flux asymmetry.

[0074] Obtaining the winding temperature spatial gradient according to the winding temperature;

[0075] Obtain the thermal magnetic coupling coefficient and calculate the magnetic field asymmetry;

[0076] The specific calculation formula is:

[0077]

[0078] Where Ψ is the magnetic field asymmetry, θ is the rotor position angle, N is the total number of monitoring points, k is the monitoring point number, B k (θ) is the magnetic density at the monitoring point, is the average magnetic flux density, T w is the winding temperature, is the winding temperature spatial gradient, and η is the thermal magnetic coupling coefficient.

[0079] The thermal-magnetic coupling coefficient is introduced to account for the spatial gradient of winding temperature. This temperature gradient can lead to uneven core permeability, exacerbating magnetic field distortion. A dual-item structure of "magnetic flux density deviation statistics + thermal-magnetic coupling correction" allows for dynamic characterization of magnetic field asymmetry.

[0080] Furthermore, the method for obtaining the thermal magnetic coupling coefficient is:

[0081] At the saturation magnetic flux density point of the motor core, the partial derivatives of the magnetic field asymmetry with respect to the winding temperature and the partial derivative of the magnetic field asymmetry with respect to the magnetic flux density are calculated respectively. The thermal magnetic coupling coefficient is calculated based on the two sets of partial derivatives. The specific formula is:

[0082]

[0083] Among them, B sat is the saturation magnetic flux density, B is the magnetic flux density, For the partial derivative.

[0084] The ratio of the two reflects the relative influence of temperature change on magnetic field distortion. When the magnetic density is saturated, the change in magnetic permeability caused by temperature is more significant. At this time, η can accurately characterize the thermal magnetic coupling strength.

[0085] Furthermore, the stress concentration factor is obtained as follows:

[0086] Collect the bearing vibration acceleration baseline value under no-load conditions as a vibration reference during normal operation;

[0087] When the motor is running under load, the real-time value of the bearing vibration acceleration is collected, and the relative deviation from the bearing vibration acceleration baseline value is counted. The average value is integrated within the time interval to obtain the stress concentration factor.

[0088] The specific calculation formula is:

[0089]

[0090] Where σ is the stress concentration factor, μ a is the baseline value of bearing vibration acceleration, a v (t) is the real-time value of the bearing vibration acceleration, [t1, t2] is the time interval from the starting time t1 to the end time t2, and t is the time variable.

[0091] Through the "baseline comparison-time integration" method, instantaneous vibration anomalies are converted into cumulative stress concentration indicators, effectively filtering high-frequency noise interference and highlighting the vibration characteristics of progressive faults such as bearing wear.

[0092] Furthermore, the step of obtaining the harmonic distortion factor includes:

[0093] Perform spectrum analysis on the three-phase current to obtain the fault energy and total harmonic energy under the fault state, and calculate their relative proportions;

[0094] The logarithm of the ratio of the fault state energy to the calibration state energy is taken to amplify the difference characteristics of the abnormal energy and obtain the harmonic distortion factor;

[0095] The formula for calculating the harmonic distortion factor is:

[0096]

[0097] Among them, Γ h is the harmonic distortion factor, is the k-th fault state energy, is the total harmonic energy, is the calibration state energy, h is the fault harmonic order number, j is the number of all harmonic orders, max It is the highest harmonic order in the entire frequency band.

[0098] Make the distortion degree of specific harmonics (such as 3rd, 5th, and 7th) more distinguishable in comprehensive evaluation.

[0099] Furthermore, the harmonic energy also includes a temperature compensation mechanism:

[0100] Taking the reference temperature T0 as the benchmark, the influence of temperature deviation on the calibration state energy is calculated using the resistance temperature coefficient ò, and the corrected calibration state energy is obtained;

[0101] The temperature compensation formula for the harmonic energy is:

[0102]

[0103] wherein, is the modified harmonic energy, is the temperature coefficient of resistance, T w is the winding temperature, T0 is the reference temperature.

[0104] Since the winding temperature change will cause the coil resistance to change, and then affect the harmonic energy distribution, therefore, the calibration state harmonic energy needs to be dynamically corrected. When the actual winding temperature is higher than the reference temperature, the resistance increases, which makes the harmonic energy attenuate, so the reference energy value is down-regulated by the [1+ò(T w -T0)] factor, so that the calculation reference of the harmonic distortion factor is consistent under different temperature conditions.

[0105] Further, the obtaining step of the Lyapunov index comprises:

[0106] A three-dimensional phase space is constructed by the q-axis current, the speed, and the rotor position angle;

[0107] The modulus ratio of the offset vector at adjacent time points is calculated by iteration, and the Lyapunov index is calculated by taking the natural logarithm average, and the formula is:

[0108]

[0109] wherein, Λ is the Lyapunov index, δx(t g ) is the state offset vector at the gth time point, δx(t g-1 ) is the state offset vector at the (g-1)th time point, M is the total number of evolution steps of the phase space trajectory, which represents the number of sampling points between the initial time t0 and the termination time t M , g is the step index, the phase space offset vector δx=[i q , ω, θ] T , i q is the q-axis current, ω is the speed, and θ is the rotor position angle.

[0110] The Lyapunov index is the exponential divergence rate of the system trajectory, when Λ>0, it indicates that the system enters the chaotic state, which indicates mechanical failure or control instability.

[0111] Further, the obtaining step of the comprehensive abnormality index comprises:

[0112] The magnetic field asymmetry, the stress concentration coefficient, the key harmonic distortion factor, and the Lyapunov index are weighted and summed to obtain the comprehensive abnormality index formula:

[0113]

[0114] Among them, Φ is the comprehensive anomaly index, Ψ is the magnetic field asymmetry, σ is the stress concentration factor, is the sum of the key harmonic distortion factors, h is the fault harmonic order number, h max is the total number of fault harmonics, e Λ is the Lyapunov index term, and α, β, γ, κ are the optimal weights.

[0115] The weight coefficient is obtained by maximizing F β Score optimization:

[0116]

[0117] where e Λ The effect of stability deterioration is amplified by exponential operation; β The score is the objective function. According to the weight adjustment factor β, the precision (Precision) and recall (Recall) of the binary classification problem of motor operation anomalies are balanced. The optimal weights α, β, γ, and κ are determined through the optimization algorithm, realizing the three-level fusion of "multi-physical quantity coupling-nonlinear mapping-intelligent weight optimization" to improve the robustness of anomaly detection.

[0118] The steps for obtaining the weight adjustment factor β include:

[0119] Collect motor operation data containing different fault types (such as bearing wear and winding short circuit), annotate real abnormal labels, and build a training set;

[0120] Traverse the range of β values ​​and calculate the F corresponding to each β β Score, select β corresponding to the maximum value as the optimal value;

[0121] In the actual vehicle test, the changes in precision and recall are monitored in real time through the confusion matrix, and the β value is dynamically adjusted according to false alarms / missed detection events.

[0122] Furthermore, the step of adjusting the adaptive threshold includes:

[0123] Based on the reference threshold, the adaptive threshold is adjusted according to the normalized speed and load torque, combined with the speed weight and load weight. The formula is:

[0124]

[0125] Among them, Φ th is the adaptive threshold, Φ0 is the reference threshold, ω is the speed, ω max is the rated speed, is the speed weight, is the load weight, τ is the load torque, τ max is the maximum torque.

[0126] When the motor approaches the rated speed ω max or the maximum torque τ max , the mechanical stress and electromagnetic loss intensify, the fluctuation range of physical quantities in normal operation expands, so the threshold is raised by the square term nonlinearity to avoid false alarms in high load conditions, and adaptive adjustment of the threshold is realized.

[0127] Further, the fault minimal cut set is:

[0128] When the ratio of the fifth harmonic distortion factor to the third harmonic distortion factor is significantly higher than the baseline ratio in normal operation, and the stress concentration coefficient exceeds the pre-set vibration stress abnormal threshold, the bearing wear is determined.

[0129] Bearing wear will cause rotor eccentricity, causing the fifth harmonic energy to be significantly higher than the third harmonic, and the ratio of the two deviating from the normal range identifies the magnetic density asymmetric anomaly; the mechanical impact caused by wear makes the vibration acceleration deviate from the baseline value, and the cumulative stress concentration coefficient exceeds the vibration threshold to reflect the bearing damage. Both conditions must be met to exclude false positives caused by a single factor (such as power grid harmonic interference or transient vibration).

[0130] In summary, the embodiments of the present application synchronously collect multi-dimensional signals such as current, vibration, temperature, rotor position angle, etc. through a multi-source sensing module, and perform multi-physical field collaborative analysis through a dynamic coupling analysis module, a harmonic distortion tracing module, etc. to improve the fault diagnosis accuracy of the motor operation anomaly of the electric drive axle of the new energy commercial vehicle.

[0131] Those skilled in the art will appreciate that embodiments of the application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0132] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 Each flow or multiple flows and / or blocks Figure 1A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0135] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0136] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A detection system for abnormal operation of electric drive axle motor of new energy commercial vehicle, characterized by: include: Multi-source sensing module, dynamic coupling analysis module, harmonic distortion tracing module, dynamic stability analysis module, abnormal fusion decision module, adaptive threshold generation module, fault tree reasoning module; The multi-source sensing module is used to collect the three-phase current, speed, load torque, rotor position angle, winding temperature and bearing vibration acceleration of the electric drive axle motor of a new energy commercial vehicle in real time. The dynamic coupling analysis module is used to generate magnetic field asymmetry and stress concentration factor based on rotor position angle, winding temperature and bearing vibration acceleration; The harmonic distortion tracing module is used to calculate the harmonic distortion factor based on the three-phase current; The dynamic stability analysis module is used to calculate the Lyapunov exponent based on the rotor position angle and speed; The anomaly fusion decision module is used to output a comprehensive anomaly index based on the magnetic field asymmetry, stress concentration factor, harmonic distortion factor and Lyapunov index; The adaptive threshold generation module is used to adjust the adaptive threshold based on the rotational speed and load torque; The fault tree reasoning module is used to trigger an abnormality warning when the comprehensive abnormality index is greater than the abnormality threshold, and associate the abnormality with the fault minimum cut set.

2. A detection system for abnormal operation of an electric drive axle motor of a new energy commercial vehicle as claimed in claim 1, characterized in that: The step of obtaining the magnetic field asymmetry in the dynamic coupling analysis module includes: The air gap magnetic flux distribution is collected through the rotor position angle, and the circumference is divided into monitoring points. The relative deviation between the magnetic flux of each monitoring point and the average magnetic flux is counted, and the square root of the square sum is averaged to obtain the basic component of the magnetic flux asymmetry. Obtaining the winding temperature spatial gradient according to the winding temperature; Obtain the thermal magnetic coupling coefficient and calculate the magnetic field asymmetry; The specific calculation formula is: Where Ψ is the magnetic field asymmetry, θ is the rotor position angle, N is the total number of monitoring points, k is the monitoring point number, B k (θ) is the magnetic density at the monitoring point, is the average magnetic flux density, T w is the winding temperature, ▽T w is the winding temperature spatial gradient, and η is the thermal magnetic coupling coefficient.

3. A detection system for abnormal operation of an electric drive axle motor of a new energy commercial vehicle as claimed in claim 2, characterized in that: The method for obtaining the thermal magnetic coupling coefficient is: At the saturation magnetic flux density point of the motor core, the partial derivatives of the magnetic field asymmetry with respect to the winding temperature and the partial derivative of the magnetic field asymmetry with respect to the magnetic flux density are calculated respectively. The thermal magnetic coupling coefficient is calculated based on the two sets of partial derivatives. The specific formula is: Among them, B sat is the saturation magnetic flux density, B is the magnetic flux density, For the partial derivative.

4. A detection system for abnormal operation of an electric drive axle motor of a new energy commercial vehicle as claimed in claim 1, characterized in that: The stress concentration factor is obtained as follows: Collect the bearing vibration acceleration baseline value under no-load conditions as a vibration reference during normal operation; When the motor is running under load, the real-time value of the bearing vibration acceleration is collected, and the relative deviation from the bearing vibration acceleration baseline value is counted. The average value is integrated within the time interval to obtain the stress concentration factor. The specific calculation formula is: Where σ is the stress concentration factor, μ a is the bearing vibration acceleration baseline value, a v (t) is the real-time value of the bearing vibration acceleration, [t1, t2] is the time interval from the starting time t1 to the end time t2, and t is the time variable.

5. A detection system for abnormal operation of an electric drive axle motor of a new energy commercial vehicle as claimed in claim 1, characterized in that: The step of obtaining the harmonic distortion factor includes: Perform spectrum analysis on the three-phase current to obtain the fault energy and total harmonic energy under the fault state, and calculate their relative proportions; The logarithm of the ratio of the fault state energy to the calibration state energy is taken to amplify the difference characteristics of the abnormal energy and obtain the harmonic distortion factor; The formula for calculating harmonic distortion factor is: Among them, Γ h is the harmonic distortion factor, is the k-th fault state energy, is the total harmonic energy, is the calibration state energy, h is the fault harmonic order number, j is the number of all harmonic orders, max It is the highest harmonic order in the entire frequency band.

6. A detection system for abnormal operation of an electric drive axle motor of a new energy commercial vehicle as claimed in claim 5, characterized in that: The harmonic energy also includes a temperature compensation mechanism: Taking the reference temperature T0 as the benchmark, using the resistance temperature coefficient Calculate the effect of temperature deviation on the calibration state energy and obtain the corrected calibration state energy; The temperature compensation formula for the harmonic energy is: in, is the corrected harmonic energy, is the temperature coefficient of resistance, T w is the winding temperature, T0 is the reference temperature.

7. A detection system for abnormal operation of an electric drive axle motor of a new energy commercial vehicle as claimed in claim 1, characterized in that: The steps of obtaining the Lyapunov exponent include: Construct a three-dimensional phase space using q-axis current, speed, and rotor position angle; The Lyapunov exponent is obtained by iteratively calculating the modulus ratio of the offset vectors at adjacent moments and taking the natural logarithm average. The formula is: Among them, Λ is the Lyapunov exponent, δx(t g ) is the state offset vector at the gth moment, δx(t g-1 ) is the state offset vector at the g-1th moment, M is the total number of steps in the evolution of the phase space trajectory, representing the time from the initial moment t0 to the final moment t M The number of sampling points between, g is the step index, the phase space offset vector δx=[i q ,ω,θ] T ,i q is the q-axis current, ω is the speed, and θ is the rotor position angle.

8. A detection system for abnormal operation of an electric drive axle motor of a new energy commercial vehicle as claimed in claim 1, characterized in that: The step of obtaining the comprehensive abnormality index includes: The weighted sum of magnetic field asymmetry, stress concentration factor, key harmonic distortion factor and Lyapunov index term is used to obtain the comprehensive anomaly index formula: Among them, Φ is the comprehensive anomaly index, Ψ is the magnetic field asymmetry, σ is the stress concentration factor, is the sum of the key harmonic distortion factors, h is the fault harmonic order number, h max is the total number of fault harmonics, e Λ is the Lyapunov index term, and α, β, γ, κ are the optimal weights.

9. A detection system for abnormal operation of an electric drive axle motor of a new energy commercial vehicle as claimed in claim 1, characterized in that: The step of adjusting the adaptive threshold comprises: Based on the reference threshold, the adaptive threshold is adjusted according to the normalized speed and load torque, combined with the speed weight and load weight. The formula is: Among them, Φ th is the adaptive threshold, Φ0 is the reference threshold, ω is the speed, ω max is the rated speed, is the speed weight, is the load weight, τ is the load torque, τ max is the maximum torque.

10. A detection system for abnormal operation of an electric drive axle motor of a new energy commercial vehicle as claimed in claim 1, characterized in that: The fault minimum cut set is: When the ratio of the fifth harmonic distortion factor to the third harmonic distortion factor is significantly higher than the benchmark ratio during normal operation, and the stress concentration factor exceeds the preset vibration stress abnormality threshold, the bearing is determined to be worn.

Images