CN115753455B - Multi-dimensional load prediction method of electric drive system based on model and data hybrid drive - Google Patents
Multi-dimensional load prediction method of electric drive system based on model and data hybrid drive Download PDFInfo
- Publication number
- CN115753455B CN115753455B CN202211369253.7A CN202211369253A CN115753455B CN 115753455 B CN115753455 B CN 115753455B CN 202211369253 A CN202211369253 A CN 202211369253A CN 115753455 B CN115753455 B CN 115753455B
- Authority
- CN
- China
- Prior art keywords
- model
- load
- failure
- drive system
- electric drive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000013528 artificial neural network Methods 0.000 claims abstract description 36
- 230000006378 damage Effects 0.000 claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 230000007246 mechanism Effects 0.000 claims abstract description 10
- 230000004927 fusion Effects 0.000 claims abstract description 9
- 230000035882 stress Effects 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 15
- 239000000463 material Substances 0.000 claims description 9
- 230000032683 aging Effects 0.000 claims description 8
- 238000004088 simulation Methods 0.000 claims description 7
- 238000005299 abrasion Methods 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 238000004804 winding Methods 0.000 claims description 6
- 230000015556 catabolic process Effects 0.000 claims description 5
- 238000006731 degradation reaction Methods 0.000 claims description 5
- 230000005284 excitation Effects 0.000 claims description 5
- 238000005050 thermomechanical fatigue Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 230000002068 genetic effect Effects 0.000 claims description 4
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 3
- 229910000831 Steel Inorganic materials 0.000 claims description 3
- 230000003902 lesion Effects 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 239000010959 steel Substances 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 2
- 238000012795 verification Methods 0.000 abstract description 4
- 238000012827 research and development Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 3
- 238000005452 bending Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003878 thermal aging Methods 0.000 description 1
- 230000008646 thermal stress Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Control Of Electric Motors In General (AREA)
Abstract
The invention discloses a multidimensional load prediction method of an electric drive system based on model and data mixed drive, which comprises the following steps: acquiring actual user operation data, and analyzing failure mechanisms and failure association loads of different components of the electric drive system based on the actual user operation data; extracting multidimensional failure association load by adopting a model driving method; adopting a model and data hybrid driving method to construct an electric driving system multidimensional load rapid prediction model based on neural network algorithm fusion; and constructing a load prediction precision evaluation index, and verifying the validity of the multi-dimensional load rapid prediction model of the electric drive system. The invention can realize failure associated load prediction of different time scales such as key stress, power loss, time delay temperature and the like of the electric drive system, greatly reduce the cost of acquiring the failure associated load, provide support for real-time evaluation and life dynamic prediction of damage of each component of the electric drive system, and simultaneously provide reliable data sources for product research and development and verification links.
Description
Technical Field
The invention relates to the technical field of health monitoring of electric drive systems, in particular to a multidimensional load prediction method of an electric drive system based on model and data hybrid drive.
Background
The electric drive system is used as a highly integrated electromechanical-hydraulic integrated product, bears complex dynamic alternating multi-physical field load in actual work, and different part failure mechanisms and failure association loads are different. The method can accurately and rapidly acquire the multidimensional load signals associated with failure of each component, and has important significance for monitoring the damage state and predicting the residual life of the electric drive system. At present, the method for collecting the load is direct by installing a plurality of sensors, but the problems of high cost, limited installation position, high data storage cost and the like are faced, and the related load data under the multiple failure modes are difficult to comprehensively obtain; the related load can be accurately acquired based on a physical model simulation or analysis model method, but the time consumption is long, and the prediction accuracy depends on model parameters; considering the data-driven approach alone may establish a nonlinear mapping relationship between input and output signals, but lacks the interpretability of the correlation mechanism. Therefore, the invention provides a multidimensional load prediction method of an electric drive system based on model and data mixed drive, so as to realize rapid prediction of failure association load of the electric drive system under different time scales.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a multidimensional load prediction method of an electric drive system based on model and data mixed drive, which can realize failure associated load prediction of different time scales such as key stress, power loss, time delay temperature and the like of the electric drive system, greatly reduce the cost of acquiring the failure associated load, provide support for real-time damage evaluation and life dynamic prediction of each component of the electric drive system, and simultaneously provide reliable data sources for product research and development and verification links.
In order to achieve the technical purpose, the invention provides a multi-dimensional load prediction method of an electric drive system based on model and data mixed drive, which comprises the following steps:
acquiring actual user operation data, and analyzing failure mechanisms and failure association loads of different parts of an electric drive system based on the actual user operation data;
extracting a multidimensional failure associated load time domain signal by adopting a model driving method;
constructing a multidimensional failure association load rapid prediction model of an electric drive system based on neural network algorithm fusion by adopting a model and data mixed drive method;
and constructing a load prediction precision evaluation index, and verifying the validity of the multidimensional failure associated load rapid prediction model of the electric drive system.
Optionally, the actual user operation data includes, but is not limited to, a vehicle speed, a motor rotation speed, a motor torque, a motor current, and a motor voltage acquired by the electric drive system during an actual operation;
the different components of the electric drive system include, but are not limited to, motor shafts, gears, bearings, stator windings, rotor magnetic bridges, rotor magnetic steels, power device IGBTs.
Optionally, the failure mechanism is a failure mode and a failure physical model of the different components of the electric drive system under a multi-dimensional excitation load;
the failure modes include, but are not limited to, fatigue failure, wear failure, aging failure, thermo-mechanical fatigue failure;
the physical model of failure includes, but is not limited to, a Basquin model under the fatigue failure, an Archard wear model under the wear failure, an Arrhenius degradation model under the aging failure, a Coffin-Manson model under the thermo-mechanical fatigue failure;
the failure-related loads are those that cause component failure, including, but not limited to, motor speed, motor torque, motor current, motor voltage, contact stress, power loss, temperature.
Alternatively, the model driving method includes, but is not limited to, a load acquisition method based on physical model simulation and a load acquisition method based on analytical model calculation.
Optionally, the model and data hybrid driving method includes:
based on the multidimensional failure association load obtained by the model driving method, an electric driving system multidimensional load rapid prediction model based on algorithm fusion of a BP neural network and an LSTM neural network of GA optimization is constructed by adopting a data driving method, and the structure and parameters of the electric driving system multidimensional load rapid prediction model are optimized.
Optionally, the algorithm is fused as:
and constructing a neural network middle layer based on the GA-BP algorithm by taking the predicted power loss as a main input signal of a temperature prediction model and combining an original input layer signal and the predicted power loss in the GA-BP algorithm, wherein the neural network middle layer is taken as an input layer of an LSTM neural network, and the multidimensional load rapid prediction model of the electric drive system is obtained.
Optionally, the optimization includes, but is not limited to, implicit layer optimization of the BP neural network, implicit layer node number optimization, initial weight and threshold optimization, and initial parameter optimization of the LSTM neural network.
Optionally, the load prediction accuracy evaluation index includes, but is not limited to, a correlation coefficient, a root mean square error, a time domain frequency distribution, and a damage recurrence ratio;
the correlation coefficient is larger than 0.9, the difference of the time domain frequency distribution is smaller than 10%, and the damage reproduction ratio is between 0.8 and 1.2.
Optionally, the root mean square error is calculated according to the following formula:
the calculation formula of the correlation coefficient is as follows:
wherein RMSE is root mean square error; r is R 2 Is a correlation coefficient; y is i 、Respectively a target value and a predicted value; />Is the average value of the target values; n is the number of samples;
the calculation formula of the damage recurrence ratio is as follows:
in delta i For the lesion reproduction ratio of component i,for the damage value of component i under predicted load, < >>Is the damage value of component i at the desired target load.
The invention has the following technical effects:
according to the method, based on actual user operation data, failure mechanisms and failure associated loads of different parts of an electric drive system are analyzed, a multidimensional failure associated load time domain signal is extracted through a model drive method, the effectiveness of the model drive method is verified by combining actual test data, a multidimensional load rapid prediction model of the electric drive system based on neural network algorithm fusion is built based on the model and data hybrid drive method, reasonable load prediction precision evaluation indexes are built, and the effectiveness of a prediction model is built from multi-angle analysis. According to the technical method, failure associated load prediction of different time scales such as key stress, power loss, time delay temperature and the like of the electric drive system can be realized, the cost for acquiring the failure associated load is greatly reduced, support is provided for real-time evaluation and life dynamic prediction of damage of each component of the electric drive system, and meanwhile, reliable data sources can be provided for product research and development and verification links.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block flow diagram of a method for predicting multidimensional load of an electric drive system based on model and data hybrid driving in an embodiment of the invention;
FIG. 2 is a schematic diagram of a multidimensional load prediction model based on GA-BP-LSTM algorithm fusion in an embodiment of the invention;
FIG. 3 is a schematic diagram of prediction errors of BP network model under different hidden layer node numbers according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a BP network model prediction error under different crossover and mutation probabilities according to an embodiment of the present invention;
FIG. 5 is a schematic diagram showing a comparison of the time domain of the predicted result of the stress and the critical loss according to the embodiment of the present invention;
FIG. 6 is a schematic diagram showing time domain comparison of different temperature prediction results according to an embodiment of the present invention;
FIG. 7 is a graph showing the comparison of the frequency distribution of different load forecast values and expected values according to an embodiment of the present invention;
FIG. 8 is a schematic diagram showing the comparison of predicted damage to expected damage for different components according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the invention discloses a model and data hybrid driving-based multidimensional load prediction method of an electric drive system, which comprises the following steps:
s1, acquiring actual user operation data, and analyzing failure mechanisms and failure association loads of different components of the electric drive system based on the actual user operation data. Under the multi-source excitation load, various parts of the electric drive system have multiple failure modes such as fatigue, abrasion, aging, thermal mechanical fatigue and the like, the load transfer rule of various parts of the electric drive system is researched, and support is provided for load prediction and damage monitoring.
Specifically, in the present embodiment, the actual user operation data described in S1 includes, but is not limited to, a vehicle speed, a motor rotation speed, a motor torque, a motor current, and a motor voltage obtained by the electric drive system during the actual operation; the various components of the electric drive system include, but are not limited to, motor shafts, gears, bearings, stator windings, rotor magnetic bridges, rotor magnetic steels, power device IGBTs, and the like. The failure mechanism is a failure mode and a failure physical model of different parts of the electric drive system under a multidimensional excitation load; failure modes include, but are not limited to, fatigue failure, wear failure, aging failure, thermo-mechanical fatigue failure, including in particular: the failure modes of different parts under the multi-source excitation load are different, and the motor shaft is subjected to the shear stress generated under the alternating torque, so that torsional fatigue failure is easy to occur; the gear component is easy to cause contact fatigue failure and bending fatigue failure under alternating load of rotating speed and torque; the bearing component is influenced by radial force, axial force and centrifugal force under alternating load of rotating speed and torque, and fatigue and abrasion failure are easy to cause; the motor rotor receives mechanical stress and thermal stress under the working conditions of high dynamic alternating rotating speed and torque, and fatigue failure is easy to generate; under the operating condition, the temperature change is caused by the loss change in the stator and rotor, and the continuous temperature load can cause thermal aging failure on the stator and rotor iron cores, windings and the like; the power device IGBT module is easy to generate thermal mechanical fatigue and aging failure under the temperature alternation working condition.
The failure physical model specifically comprises: different failure physical models can be adopted for life assessment under different failure modes, such as a Basquin life model can be adopted for life assessment under fatigue failure; an Archard abrasion model can be adopted under abrasion failure; arrhenius degradation model can be adopted under aging failure; coffin-Manson model can be used under the condition of thermal mechanical fatigue failure. The damage calculation model includes, but is not limited to, employing a linear cumulative damage criterion, a bilinear cumulative damage criterion, a nonlinear cumulative damage criterion, and the like;
the calculation formula of the Basquin life model is:
ΔS m N＝C
wherein DeltaS is stress amplitude, N is fatigue life under the action of stress amplitude S, and m and C are constants related to materials.
The calculation formula of the Archard abrasion model is as follows:
wherein W is the wear volume, s is the frictional sliding distance, P is the applied load, P m K is the wear coefficient between materials, which is the flow pressure of the materials.
The calculation formula of the Arrhenius degradation model is as follows:
L＝A·e -E/kT
where L is lifetime, A is a constant, frequency factor, E is activation energy, material related, k is Boltzmann constant, T is temperature stress, and Kelvin. The calculation formula of the Coffin-Manson model is as follows:
N f ＝Af -α ΔT -β G(T max )
wherein N is f For part life, G (T max ) The Arrhenius activation energy of the highest temperature stress, delta T is the temperature difference between the highest temperature and the lowest temperature, the unit is Kelvin, f is the circulation frequency, the unit is Hertz, and A, alpha and beta are constants.
S2, extracting multidimensional failure association load by adopting a model driving method;
specifically, in the embodiment S2, based on load working conditions such as the vehicle speed, the motor rotation speed, the motor torque, the motor current, the motor voltage and the like which are easy to obtain in the actual running process of the electric drive system, a physical simulation model or an analytical model for obtaining the failure load under different components is established by adopting a model driving method, and the multidimensional failure related loads such as key stress, power loss, time delay temperature and the like in the electric drive system are extracted by combining the actual materials, structures and performance parameters of each component. And the validity of the established physical simulation model or the analytical model is verified by monitoring the response signals through corresponding bench tests.
The model driving method includes, but is not limited to, a load acquisition method based on physical model simulation and a load acquisition method based on analytical model calculation. According to the model driving method, load data such as motor shaft tangential stress, gear contact stress, gear bending stress, bearing radial force and axial force, coupling stress of a rotor magnetic bridge under multiple physical fields, motor stator and rotor loss, motor stator and rotor temperature, power device IGBT loss and temperature and the like in an electric driving system can be obtained based on actual operation conditions. The validity of the model driving method is verified through the real test data, the method is long in time consumption, but failure associated load data under different accurate user working conditions can be obtained, so that an actual operation user working condition data and failure associated load data training set is established and used in a data-driving-based load rapid prediction model.
In the verification of the real test data, the fact that loads such as loss, rotor stress and temperature under multiple physical fields and the like are difficult to collect through the sensor is considered, but the temperature distribution trend of adjacent parts is basically consistent, whether the rotor temperature distribution rule is reasonable or not can be verified by monitoring the loads of adjacent parts, such as monitoring the temperature of a stator through arrangement of a thermistor, and in addition, the rationality of motor loss and other temperature simulation results can be further verified by combining an analytical model such as a motor thermal resistance model.
S3, constructing a multi-dimensional failure association load rapid prediction model of an electric drive system based on fusion of a Genetic Algorithm (GA) -optimized back propagation neural network (BP) and a long-short-time memory neural network (LSTM) algorithm by adopting a model and data hybrid drive method; because the electric drive system bears multi-source load in the running process, different loads have different time scale characteristics, and multi-scale load prediction is difficult to realize through a single neural network model. Therefore, for signals such as stress, loss and the like which are fast in response in an electric drive system, a mapping relation of strong correlation among signals can be established through a GA-BP neural network optimized by a genetic algorithm. For delayed temperature signals with hysteresis, LSTM neural network can be adopted to solve the problem of long sequence dependence, and rapid prediction of delayed temperature load is realized.
Specifically, in this embodiment, the algorithm described in S3 is fused to a GA-BP based algorithm, where the predicted power loss is used as a main input signal of the temperature prediction model, and a neural network intermediate layer is constructed by combining an original input layer signal and the predicted power loss in the GA-BP algorithm, and the neural network intermediate layer is used as an input layer of the LSTM neural network, so as to obtain a multidimensional load rapid prediction model of the electric drive system, and achieve rapid prediction of different temperature loads.
Fig. 2 is a schematic diagram of a multidimensional load prediction model based on GA-BP-LSTM algorithm fusion, input load data in fig. 2 is motor rotation speed, motor torque and motor current under a user working condition, rapid prediction of stress and loss load can be achieved through a GA-BP neural network, and predicted loss is used as an intermediate layer input signal for predicting stator winding temperature, stator core temperature, rotor core temperature and IGBT junction temperature. And the BP neural network structure and parameters are optimized, different hidden layers and different hidden layer node numbers of the BP neural network are respectively optimized, and for loads of quick response such as stress, loss and the like in an electric drive system, the prediction precision is higher when a single hidden layer is adopted and the hidden layer node number is 8, as shown in figure 3. And optimizing the initial threshold and the weight of the BP neural network by a genetic algorithm, wherein the cross probability and the variation probability are optimal parameters under the condition of minimum root mean square error, as shown in fig. 4.
S4, based on the multidimensional failure association load rapid prediction model of the electric drive system fused by the neural network algorithm constructed in the S3, the failure association load prediction of key stress, power loss, time delay temperature and the like is realized. Constructing a load prediction precision evaluation index: correlation coefficient, root mean square error, time domain frequency distribution and damage reproduction ratio, and verifying the prediction accuracy of the multi-dimensional load rapid prediction model of the electric drive system;
specifically, in this embodiment, a time domain comparison between predicted values and expected values of different loads is obtained through a multidimensional failure associated load fast prediction model of the electric drive system, as shown in fig. 5 and 6. S4 root mean square error RMSE, correlation coefficient R 2 The expression is as follows:
wherein y is i 、Respectively a target value and a predicted value; />Is the average value of the target values; n is the number of samples;
the time domain frequency distribution is a frequency distribution histogram of different failure load predicted values and expected values, and as shown in fig. 7, the predicted value and expected value distribution range is basically consistent with each interval frequency. The damage reproduction ratio in S4 is the degree to which damage to each component under the expected load can be reproduced for each component under the predicted load, as shown in fig. 8. The damage recurrence ratio calculation formula is as follows:
in delta i For the lesion reproduction ratio of component i,for the damage value of component i under predicted load, < >>Is the damage value of component i at the desired target load.
Constructing reasonable load prediction precision evaluation indexes, wherein the specific evaluation indexes at least comprise: the correlation coefficient of the predicted load and the target load is larger than 0.9, the total frequency difference in time domain distribution is smaller than 10%, and the damage reproduction ratio of each part is between 0.8 and 1.2. If the index is not satisfied, the structure and parameters of the prediction model are further optimized and adjusted.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (2)
1. The multi-dimensional load prediction method of the electric drive system based on the model and data mixed drive is characterized by comprising the following steps of:
acquiring actual user operation data, and analyzing failure mechanisms and failure association loads of different parts of an electric drive system based on the actual user operation data;
extracting a multidimensional failure associated load time domain signal by adopting a model driving method;
constructing a multidimensional failure association load rapid prediction model of an electric drive system based on neural network algorithm fusion by adopting a model and data mixed drive method;
constructing a load prediction precision evaluation index, and verifying the validity of a multidimensional failure associated load rapid prediction model of the electric drive system;
the model driving method comprises, but is not limited to, a load acquisition method based on physical model simulation and a load acquisition method based on analytical model calculation;
the model and data hybrid driving method comprises the following steps:
based on the multidimensional failure association load obtained by the model driving method, constructing an electric driving system multidimensional load rapid prediction model based on algorithm fusion of a GA-BP neural network and an LSTM neural network by adopting a data driving method, and optimizing the structure and parameters of the electric driving system multidimensional load rapid prediction model;
the algorithm is fused as follows:
based on the GA-BP neural network, the predicted power loss is taken as a main input signal of a temperature prediction model, a neural network middle layer is constructed by combining an original input layer signal in the GA-BP neural network and the predicted power loss, the neural network middle layer is taken as an input layer of an LSTM neural network, and a multidimensional load rapid prediction model of the electric drive system is built;
the original input layer signals are motor rotating speed, motor torque and motor current under the working condition of a user, the stress and power loss load can be rapidly predicted through the GA-BP neural network, and the predicted power loss is used as the input signal of the middle layer of the neural network to be used for predicting the temperature of a stator winding, the temperature of a stator iron core, the temperature of a rotor iron core and the junction temperature of an IGBT (insulated gate bipolar transistor); optimizing the structure and parameters of the BP neural network, respectively optimizing the number of different hidden layers and the number of nodes of different hidden layers of the BP neural network, and predicting stress and power loss in an electric drive system, wherein the prediction accuracy is higher when the number of nodes of a single hidden layer is 8; optimizing an initial threshold value and a weight value of the BP neural network through a genetic algorithm, wherein the cross probability and the variation probability are optimal parameters under the condition of minimum root mean square error; in addition, the initial parameters of the LSTM neural network are optimized;
the failure mechanism is a failure mode and a failure physical model of the different components of the electric drive system under a multidimensional excitation load;
the failure modes include, but are not limited to, fatigue failure, wear failure, aging failure, thermo-mechanical fatigue failure;
the physical model of failure includes, but is not limited to, a Basquin model under the fatigue failure, an Archard wear model under the wear failure, an Arrhenius degradation model under the aging failure, a Coffin-Manson model under the thermo-mechanical fatigue failure;
the damage calculation model includes, but is not limited to, employing a linear cumulative damage criterion, a bilinear cumulative damage criterion, and a nonlinear cumulative damage criterion;
the calculation formula of the Basquin life model is:
ΔS m N＝C
wherein, delta S is stress amplitude, N is fatigue life under the action of the stress amplitude delta S, m and C are constants related to materials;
the calculation formula of the Archard abrasion model is as follows:
wherein W is the wear volume, s is the frictional sliding distance, P is the applied load, P m K is the wear coefficient between materials, which is the flow pressure of the materials;
the calculation formula of the Arrhenius degradation model is as follows:
L＝A·e -E/kT
wherein L is lifetime, A is a constant and frequency factor, E is activation energy, and is related to materials, k is a Boltzmann constant, T is temperature, and the unit is Kelvin;
the calculation formula of the Coffin-Manson model is as follows:
N f ＝Af -α ΔT -β G(T max )
wherein N is f For part life, G (T max ) For the highest temperature T max The Arrhenius activation energy of (a) is delta T, the unit is Kelvin, f is the circulation frequency, the unit is Hertz, and A, alpha and beta are constants;
the failure-related load is a related load that causes component failure, including but not limited to motor speed, motor torque, motor current, motor voltage, contact stress, power loss, temperature;
the load prediction accuracy evaluation index comprises, but is not limited to, a correlation coefficient, a root mean square error, time domain frequency distribution and damage reproduction ratio;
the correlation coefficient is larger than 0.9, the difference of the time domain frequency distribution is smaller than 10%, and the damage reproduction ratio is between 0.8 and 1.2;
the root mean square error is calculated by the following formula:
the calculation formula of the correlation coefficient is as follows:
wherein RMSE is root mean square error; r is R 2 Is a correlation coefficient;respectively a target value and a predicted value; y is the average value of the target values; n is the number of samples;
the calculation formula of the damage recurrence ratio is as follows:
in delta i For the lesion reproduction ratio of component i,for the damage value of component i under predicted load, < >>Is the damage value of component i at the desired target load.
2. The method for predicting the multidimensional load of an electric drive system based on the hybrid driving of the model and the data according to claim 1, wherein,
the actual user operation data include, but are not limited to, a vehicle speed, a motor rotation speed, a motor torque, a motor current and a motor voltage obtained by the electric drive system in an actual operation process;
the different components of the electric drive system include, but are not limited to, motor shafts, gears, bearings, stator windings, rotor magnetic bridges, rotor magnetic steels, power device IGBTs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211369253.7A CN115753455B (en) | 2022-11-03 | 2022-11-03 | Multi-dimensional load prediction method of electric drive system based on model and data hybrid drive |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211369253.7A CN115753455B (en) | 2022-11-03 | 2022-11-03 | Multi-dimensional load prediction method of electric drive system based on model and data hybrid drive |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115753455A CN115753455A (en) | 2023-03-07 |
| CN115753455B true CN115753455B (en) | 2024-02-13 |
Family
ID=85357554
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211369253.7A Active CN115753455B (en) | 2022-11-03 | 2022-11-03 | Multi-dimensional load prediction method of electric drive system based on model and data hybrid drive |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115753455B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004028948A (en) * | 2002-06-28 | 2004-01-29 | Ricoh Co Ltd | Method for deciding dynamic transmission characteristic of drive transmission system and recording medium |
| CN109687811A (en) * | 2019-01-28 | 2019-04-26 | 江苏理工学院 | The suppressing method of vehicle-mounted AC-battery power source drive system temperature effect |
| EP3663732A1 (en) * | 2018-12-05 | 2020-06-10 | Tata Consultancy Services Limited | Method and system for monitoring machine health using radar based segregation for induced machine vibrations |
| CN111859724A (en) * | 2020-05-27 | 2020-10-30 | 中铁第四勘察设计院集团有限公司 | Hybrid-driven ballastless track fatigue life prediction method and system |
| CN111931393A (en) * | 2019-04-28 | 2020-11-13 | 沈阳工业大学 | Prediction and evaluation method for residual life of key parts of waste machine tool |
| CN113092115A (en) * | 2021-04-09 | 2021-07-09 | 重庆大学 | Digital twin model construction method of digital-analog combined drive full-life rolling bearing |
| CN114881410A (en) * | 2022-04-02 | 2022-08-09 | 国网山西省电力公司电力科学研究院 | Model-data hybrid driven power system transient stability online evaluation method |
| CN114929000A (en) * | 2022-06-21 | 2022-08-19 | 温州大学 | Power supply water cooling system with mixed WBG (work breakdown voltage) and Si (silicon on insulator) devices and control strategy thereof |
| CN114936494A (en) * | 2022-05-23 | 2022-08-23 | 华东理工大学 | Data physical fusion driven high-temperature component reliability evaluation method and system |
-
2022
- 2022-11-03 CN CN202211369253.7A patent/CN115753455B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004028948A (en) * | 2002-06-28 | 2004-01-29 | Ricoh Co Ltd | Method for deciding dynamic transmission characteristic of drive transmission system and recording medium |
| EP3663732A1 (en) * | 2018-12-05 | 2020-06-10 | Tata Consultancy Services Limited | Method and system for monitoring machine health using radar based segregation for induced machine vibrations |
| CN109687811A (en) * | 2019-01-28 | 2019-04-26 | 江苏理工学院 | The suppressing method of vehicle-mounted AC-battery power source drive system temperature effect |
| CN111931393A (en) * | 2019-04-28 | 2020-11-13 | 沈阳工业大学 | Prediction and evaluation method for residual life of key parts of waste machine tool |
| CN111859724A (en) * | 2020-05-27 | 2020-10-30 | 中铁第四勘察设计院集团有限公司 | Hybrid-driven ballastless track fatigue life prediction method and system |
| CN113092115A (en) * | 2021-04-09 | 2021-07-09 | 重庆大学 | Digital twin model construction method of digital-analog combined drive full-life rolling bearing |
| CN114881410A (en) * | 2022-04-02 | 2022-08-09 | 国网山西省电力公司电力科学研究院 | Model-data hybrid driven power system transient stability online evaluation method |
| CN114936494A (en) * | 2022-05-23 | 2022-08-23 | 华东理工大学 | Data physical fusion driven high-temperature component reliability evaluation method and system |
| CN114929000A (en) * | 2022-06-21 | 2022-08-19 | 温州大学 | Power supply water cooling system with mixed WBG (work breakdown voltage) and Si (silicon on insulator) devices and control strategy thereof |
Non-Patent Citations (1)
| Title |
|---|
| 基于数据 -模型混合驱动的锂电池储能***状态估计及预警方法;吕力行等;《热力发电》;第50卷(第8期);第64-72页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115753455A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110531266B (en) | Synchronous motor excitation winding turn-to-turn short circuit fault early warning method | |
| CN103383433B (en) | The status monitoring of stator core of ship generator and fault early warning method | |
| Ondel et al. | Coupling pattern recognition with state estimation using Kalman filter for fault diagnosis | |
| Strangas et al. | The effect of failure prognosis and mitigation on the reliability of permanent-magnet AC motor drives | |
| EP4063875A1 (en) | Multi-information fusion-based fault early warning method and device for converter | |
| CN111505500B (en) | Intelligent motor fault detection method based on filtering in industrial field | |
| Ismail et al. | Gaussian process regression remaining useful lifetime prediction of thermally aged power IGBT | |
| CN116933637A (en) | Motor temperature prediction method and device and electronic equipment | |
| Charette et al. | The use of the genetic algorithm for in-situ efficiency measurement of an induction motor | |
| CN114741922B (en) | Turbine blade creep-fatigue life prediction method based on Attention mechanism | |
| Ismail et al. | Remaining useful life estimation for thermally aged power insulated gate bipolar transistors based on a modified maximum likelihood estimator | |
| Bejaoui et al. | A data-driven prognostics technique and rul prediction of rotating machines using an exponential degradation model | |
| Devarajan et al. | Detection and classification of mechanical faults of three phase induction motor via pixels analysis of thermal image and adaptive neuro-fuzzy inference system | |
| Rice et al. | Identification of the stability margin between safe operation and the onset of blade flutter | |
| Parvin et al. | A comprehensive interturn fault severity diagnosis method for permanent magnet synchronous motors based on transformer neural networks | |
| CN115753455B (en) | Multi-dimensional load prediction method of electric drive system based on model and data hybrid drive | |
| CN114091790A (en) | Life prediction method fusing field data and two-stage accelerated degradation data | |
| Najeh et al. | Degradation state prediction of rolling bearings using ARX-Laguerre model and genetic algorithms | |
| CN112782614A (en) | Fault early warning method and device of converter based on multi-information fusion | |
| CN102735435B (en) | Method for determining fault diagnosability of momentum wheel based on relevance model | |
| Ekwaro-Osire et al. | Incipient Fault Point Detection Based on Multiscale Diversity Entropy | |
| CN112782499B (en) | Multi-information fusion-based converter state evaluation method and device | |
| Chatterton et al. | An unconventional method for the diagnosis and study of generator rotor thermal bows | |
| Bradley et al. | A general approach for current-based condition monitoring of induction motors | |
| Ebrahimi et al. | Detection of partial demagnetization fault in wind turbine permanent magnet generator using a data-driven method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |