Integrated electric drive system testing method and device for forklifts

Abstract

This application proposes a method and device for testing an integrated electric drive system for a forklift, comprising the following steps: obtaining the factory parameters of the electric drive system of the forklift to be tested, and inputting the factory parameters of the electric drive system into a pre-trained adaptive physical model in combination with the test operating conditions to obtain simulated electric drive parameters; obtaining multiple sets of simulated electric drive parameters of the forklift to be tested under different test conditions as evaluation data sets, and inputting these evaluation data sets into a pre-trained performance evaluation model to obtain the operating temperature range, load limit, and maximum travel speed of the forklift to be tested. By integrating an adaptive multi-body dynamics physical model with a multimodal forklift performance evaluation model, a parametric virtual test system for the electric drive system is constructed, enabling efficient testing of all operating conditions without the need for actual vehicle movement and real-world environment simulation.

Description

Technical Field

[0001] The present application relates to the field of machine learning, and in particular to a method and device for testing an integrated electric drive system for a forklift. Background Art

[0002] In the current field of forklift electric drive system testing, traditional technology mainly relies on physical testing of actual vehicles under real working conditions. It is necessary to build a variety of test environments such as slopes, loads, and different road friction coefficients, and directly collect operating data of the motor, braking system, and kinetic energy recovery system through sensors. This method not only requires a lot of manpower and material resources to build the test scene, but also is difficult to reproduce extreme working conditions (such as low temperatures of -30°C, climbing a 15° full-load slope, etc.) due to site conditions. At the same time, frequent actual vehicle testing will lead to hardware losses such as aging of motor winding insulation and wear of brake pads. The cost of a single test can reach tens of thousands of yuan.

[0003] Although some solutions introduce physical models based on multi-body dynamics for simulation, most existing models use fixed parameter modeling, ignoring the electromagnetic-thermal coupling effect of the motor, the nonlinear characteristics of the brake hydraulic system, and the bidirectional energy flow characteristics during kinetic energy recovery. They are also unable to adaptively correct key parameters such as the friction coefficient and damping coefficient through real-time data feedback, resulting in simulation errors of more than 15% under complex working conditions.

[0004] In addition, existing AI evaluation models are mostly based on traditional algorithms such as BP neural networks, and rely on limited manually labeled working condition data (usually only covering 60%-70% of standard working conditions) for training. They lack the ability to extract features for extreme scenarios such as non-steady-state braking and sudden load mutations. The evaluation accuracy is generally lower than 85%, and it is impossible to form a data closed loop with the physical model. It is difficult to meet the needs of electric drive system R&D stage for rapid verification of multiple working conditions and early warning of design defects. As a result, the cycle from R&D to mass production of new forklift drive systems generally exceeds 18 months, seriously restricting the efficiency of industry technology iteration. Summary of the Invention

[0005] The embodiments of the present application provide a method and device for testing an integrated electric drive system for a forklift. By integrating an adaptive multi-body dynamics physics model with a multimodal forklift performance evaluation model, a parametric virtual test system for the electric drive system is constructed to achieve efficient testing of all working conditions without the need for actual vehicle movement and real environment simulation.

[0006] In a first aspect, an embodiment of the present application provides a method for testing an integrated electric drive system for a forklift, the method comprising:

[0007] Obtaining factory parameters of the electric drive system of the forklift under test, and inputting the factory parameters of the electric drive system into a pre-trained adaptive physical model in combination with test conditions to obtain simulated electric drive parameters, wherein the test conditions include road slope, ambient temperature, and load. The simulated electric drive parameters are parameters of the electric drive system of the forklift under test under the test conditions. The electric drive system includes a battery, a motor, and a kinetic energy recovery device.

[0008] Multiple sets of simulated electric drive parameters of the forklift to be tested under different test conditions are obtained as evaluation data sets, and the evaluation data sets are input into a pre-trained performance evaluation model to obtain the operating temperature range, load limit and maximum driving speed of the forklift to be tested.

[0009] In a second aspect, an embodiment of the present application provides an integrated electric drive system testing device for a forklift, comprising:

[0010] a simulation module for obtaining factory parameters of the electric drive system of the forklift under test, and inputting the factory parameters of the electric drive system into a pre-trained adaptive physical model in combination with test conditions to obtain simulated electric drive parameters, wherein the test conditions include road slope, ambient temperature, and load capacity. The simulated electric drive parameters are parameters of the electric drive system of the forklift under test under the test conditions, wherein the electric drive system includes a battery, a motor, and a kinetic energy recovery device;

[0011] The evaluation module is used to obtain multiple sets of simulated electric drive parameters of the forklift to be tested under different test conditions as evaluation data sets, and input the evaluation data sets into a pre-trained performance evaluation model to obtain the operating temperature range, load limit and maximum driving speed of the forklift to be tested.

[0012] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a method for testing an integrated electric drive system for a forklift.

[0013] In a fourth aspect, an embodiment of the present application provides a readable storage medium, in which a computer program is stored. The computer program includes a program code for controlling a process to execute a process. When the program code is executed by a processor, a method for testing an integrated electric drive system for a forklift is implemented.

[0014] The main contributions and innovations of the present invention are as follows:

[0015] This solution obtains simulated electric drive parameters by inputting the factory parameters of the forklift electric drive system under test into a pre-trained adaptive physical model (including battery, motor and kinetic energy recovery simulation models) in combination with test conditions such as road slope, ambient temperature and load. After preprocessing and dimensional unification to form an evaluation data set, it is input into the performance evaluation model (through structures such as multi-branch parallel connection, feature fusion and multi-head self-attention mechanism). It can accurately predict the operating temperature range, load limit and maximum driving speed. It has the advantages of combining the advantages of physical models and deep learning models, integrating multi-dimensional parameters to achieve multi-objective accurate evaluation, and can be optimized through historical data training and applicable to different test conditions. It provides an efficient and comprehensive solution for forklift electric drive system performance testing.

[0016] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a flow chart of a method for testing an integrated electric drive system for a forklift according to an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of a kinetic energy recovery simulation model, a motor simulation model, and a battery simulation model coupled to each other according to an embodiment of the present application;

[0020] Figure 3 is a schematic structural diagram of a performance evaluation model according to an embodiment of the present application;

[0021] Figure 4 This is a structural block diagram of a forklift integrated electric drive system testing device according to an embodiment of the present application;

[0022] Figure 5 Schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments are not intended to represent all implementations consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of one or more embodiments of this specification, as detailed in the appended claims.

[0024] It should be noted that in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the method may include more or fewer steps than those described in this specification. In addition, a single step described in this specification may be broken down into multiple steps for description in other embodiments, and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0025] Example 1

[0026] The present application provides a method for testing an integrated electric drive system for a forklift. By integrating an adaptive multi-body dynamics physical model with a multi-modal forklift performance evaluation model, a parameterized virtual test system for the electric drive system is constructed to achieve efficient testing of all working conditions without the need for real vehicle motion and real environment simulation. Specifically, Figure 1 , the method comprising:

[0027] Obtaining factory parameters of the electric drive system of the forklift under test, and inputting the factory parameters of the electric drive system into a pre-trained adaptive physical model in combination with test conditions to obtain simulated electric drive parameters, wherein the test conditions include road slope, ambient temperature, and load. The simulated electric drive parameters are parameters of the electric drive system of the forklift under test under the test conditions. The electric drive system includes a battery, a motor, and a kinetic energy recovery device.

[0028] Multiple sets of simulated electric drive parameters of the forklift to be tested under different test conditions are obtained as evaluation data sets, and the evaluation data sets are input into a pre-trained performance evaluation model to obtain the operating temperature range, load limit and maximum driving speed of the forklift to be tested.

[0029] In some specific embodiments, the electric drive system in this solution is mainly composed of a battery, a motor and a kinetic energy recovery device, so the factory parameters of the electric drive system include the factory parameters of the battery, the factory parameters of the motor and the factory parameters of the kinetic energy recovery device.

[0030] Specifically, the battery factory parameters include rated capacity, internal resistance, OSC-OCV curve, charge and discharge rate, and heat capacity coefficient.

[0031] Specifically, the factory parameters of the motor include peak torque, rated power, efficiency MAP diagram, winding thermal group and magnetic saturation characteristic curve.

[0032] Specifically, the kinetic energy recovery factory parameters include maximum recovery power, recovery efficiency curve and mechanical-electrical energy conversion coefficient.

[0033] Specifically, batteries, motors, and kinetic energy recovery devices are generally tested before leaving the factory, and the test results are written in the technical manual or the manufacturer's official website. By querying the technical manual or official website, the corresponding battery factory parameters, motor factory parameters, and kinetic energy recovery factory parameters can be obtained.

[0034] In some specific embodiments, the adaptive physical model includes a battery simulation model, a motor simulation model, and a kinetic energy recovery simulation model, and the battery simulation model, the motor simulation model, and the kinetic energy recovery simulation model are mathematical models, and MATLAB is used to train and solve the adaptive physical model.

[0035] Specifically, this solution obtains historical electric drive system test data under different test conditions as training data, and uses MATLAB to train the adaptive physical model based on the training data. During the training process, the adaptive physical model learns the impact of different working conditions on different parameters in the adaptive physical model to complete the training.

[0036] Furthermore, the formula of the battery simulation model is expressed as:

[0037]

[0038] in, is the battery terminal voltage, is the open circuit voltage-state of charge function, I is the operating current, is the battery's internal resistance in ohms, To reflect the electrochemical polarization internal resistance, To reflect the polarization internal resistance of deep polarization, 、 is the time constant, and t is the duration of the current acting on the battery.

[0039] Specifically, the parameters for constructing the battery simulation model are provided by the battery factory parameters. For example, during the training process of the battery simulation model, MATLAB is used to calculate the influence of ambient temperature on the open circuit voltage-state of charge function, the influence of ambient temperature on the battery ohmic internal resistance, the influence of ambient temperature on the polarization internal resistance reflecting electrochemistry, the polarization internal resistance reflecting deep polarization, and the influence of load and slope on the operating current. In the battery simulation model, the time constant is not affected by any working conditions.

[0040] For example, it can be seen from the calculation results of MATLAB that the temperature correction formula of the open circuit voltage-state of charge function is: ,in, is the battery open circuit voltage, is the open circuit voltage at 25°C, is the reference temperature, k is the temperature coefficient, It is the difference between the actual ambient temperature and the reference temperature; the battery's ohmic internal resistance and the polarization internal resistance reflecting electrochemistry decrease with increasing ambient temperature; the polarization internal resistance reflecting deep polarization is affected by the state of charge (SOC); the operating current is positively correlated with the load / slope.

[0041] Furthermore, the formula of the motor simulation model is expressed as:

[0042]

[0043] in, is the electromagnetic torque generated by the motor, is the number of motor pole pairs, is the permanent magnet flux, is the d-axis inductance, is the q-axis inductance, is the current component of the d-axis, is the current component of the q axis, is the instantaneous rate of change of angular velocity, is the load torque, is the damping torque caused by viscous friction, is the moment of inertia.

[0044] Specifically, the parameters for constructing the motor simulation model are provided by the motor factory parameters. For example, during the training process of the motor simulation model, MATLAB is used to calculate the influence of ambient temperature on the permanent magnet flux, the influence of d-axis inductance and q-axis inductance on current, the influence of ambient temperature on the damping torque caused by viscous friction, and the influence of load torque on load and slope. The remaining parameters are fixed.

[0045] For example, it can be seen from the calculation results of MATLAB that the magnetic flux of the permanent magnet decreases as the ambient temperature increases, the d-axis inductance and the q-axis inductance decrease as the current increases, the damping torque caused by viscous friction increases slightly with the increase of ambient temperature, and the load torque is directly calculated from the load and slope.

[0046] Furthermore, the formula of the kinetic energy recovery simulation model is expressed as:

[0047]

[0048] in, is the electric power of kinetic energy recovery, is the energy recovery efficiency of kinetic energy recovery, m is the total weight of the forklift, v is the driving speed of the forklift, is the kinetic energy of the forklift, The minimum speed threshold for kinetic energy recovery.

[0049] Specifically, the parameters for constructing the kinetic energy recovery simulation model are provided by the kinetic energy recovery factory parameters. For example, during the training process of the kinetic energy recovery simulation model, MATLAB is used to calculate the ambient temperature, the impact on the energy recovery efficiency of kinetic energy recovery, and the impact of load on the vehicle mass.

[0050] For example, it can be seen from the calculation results of MATLAB that the lower the ambient temperature, the lower the energy recovery efficiency of kinetic energy recovery.

[0051] In some specific embodiments, the kinetic energy recovery simulation model, the motor simulation model, and the battery simulation model in this solution are coupled to each other, that is, the parameters in the kinetic energy recovery simulation model, the motor simulation model, and the battery simulation model will affect each other. The schematic diagram of the mutual coupling of the kinetic energy recovery simulation model, the motor simulation model, and the battery simulation model is as follows: Figure 2 shown.

[0052] That is to say, in this solution, the battery factory parameters, motor factory parameters and kinetic energy recovery factory parameters are obtained, and the motor simulation model is used to simulate based on the motor factory parameters and test conditions to obtain simulated motor parameters. The battery address model is used to simulate based on the battery factory parameters, simulated motor parameters and test conditions to obtain simulated battery parameters. The kinetic energy recovery simulation model is used to simulate based on the kinetic energy recovery factory parameters, test conditions and simulated motor parameters to obtain simulated recovery parameters. The simulated electric drive parameters are composed of the simulated motor parameters, simulated battery parameters and simulated recovery parameters.

[0053] Specifically, in the process of simulating the battery, the output current and power of the battery are determined by the motor. The heavier the forklift load and the greater the slope, the higher the speed of the motor, and the greater the current required to be transmitted by the battery as a power supply. Therefore, in the process of simulating the battery, the simulation motor parameters must be obtained first; similarly, the simulation of the kinetic energy recovery device also requires the operating conditions of the motor to obtain the operating speed of the forklift, so in the process of simulating the kinetic energy recovery device, the simulation motor parameters must also be obtained first.

[0054] In some specific embodiments, the simulated motor parameters include motor peak temperature, rated power, speed range, efficiency curve, winding resistance, and continuous output torque; the simulated battery parameters include battery operating voltage, capacity, internal resistance, open circuit voltage (OCV), and temperature coefficient; and the simulated recovery parameters include kinetic energy recovery efficiency, recovery torque threshold, energy recovery power upper limit, and braking distribution coefficient.

[0055] Specifically, by performing simulation in MATLAB, the simulation parameters of the motor, battery and kinetic energy recovery device under the test conditions can be obtained based on the pre-defined simulation model, so that the simulated motor parameters, simulated battery parameters and simulated recovery parameters can be obtained by analyzing the simulation parameters.

[0056] In some specific embodiments, multiple sets of simulated electric drive parameters of forklifts to be tested under different test conditions are preprocessed and dimensionally unified to obtain an evaluation data set. Specifically, through preprocessing and dimension unification, physical quantity characteristics of different units can be placed in the same dimension, which facilitates understanding and analysis of the performance evaluation model.

[0057] Specifically, preprocessing is completed through data cleaning and normalization.

[0058] In some embodiments, the structure of the performance evaluation model is as follows Figure 3 As shown, the first layer of the performance evaluation model is composed of a battery feature branch, a motor feature branch and a kinetic energy recovery feature branch connected in parallel. The battery feature branch extracts features of all simulated battery parameters in the evaluation data set through a convolution layer to obtain battery features. The motor feature branch extracts features of all simulated motor parameters in the evaluation data set to obtain motor features. The kinetic energy recovery branch extracts features of all simulated recovery parameters in the evaluation data set to obtain kinetic energy recovery features. The second layer of the performance evaluation model is a feature fusion layer. The feature fusion layer fuses battery features, motor features and kinetic energy recovery features to obtain feature fusion results. The third layer of the performance evaluation model is composed of a first multi-head self-attention mechanism, a second multi-head self-attention mechanism and a third multi-head self-attention mechanism connected in parallel. The first multi-head self-attention mechanism is aimed at predicting the operating temperature range. The first multi-head self-attention result is obtained by weighting different types of features in the feature fusion result; the second multi-head self-attention mechanism weights different types of features in the feature fusion result with the goal of predicting the upper limit of load to obtain a second multi-head self-attention result; the third multi-head self-attention mechanism weights different types of features in the feature fusion result with the goal of predicting the maximum driving speed to obtain a third multi-head self-attention result; the fourth layer of the performance evaluation model is composed of a temperature fully connected layer, a load fully connected layer and a speed fully connected layer in parallel, the temperature fully connected layer predicts the operating temperature range based on the first multi-head self-attention result, the load fully connected layer predicts the upper limit of load based on the second multi-head self-attention result, and the speed fully connected layer predicts the maximum driving speed based on the third multi-head self-attention result.

[0059] Specifically, this solution uses historical test data of forklifts under different working conditions as training samples to train the performance evaluation model, and uses the corresponding historical test results to correct the prediction results of the performance evaluation model.

[0060] Specifically, since the performance evaluation model of this scheme inputs a multimodal data set and the output is not a single prediction result, this scheme uses different multi-head self-attention layers to distribute rights for different prediction targets. That is to say, when predicting the operating temperature range, the first multi-head self-attention mechanism will automatically learn and highlight the features closely related to temperature changes, such as the correlation weights of parameters such as motor peak temperature and battery temperature coefficient; when predicting the load upper limit, the second multi-head self-attention mechanism will strengthen the analysis of feature dimensions such as rated power, continuous output torque, and battery capacity that affect load capacity; similarly, the third multi-head self-attention mechanism will focus on the weight distribution of parameters directly related to speed performance, such as speed range and energy recovery power upper limit.

[0061] Specifically, this differentiated feature weight allocation mechanism for different prediction targets enables the model to more accurately capture the information dimensions in the input data that are most relevant to the specific output target, thereby achieving better prediction results.

[0062] Specifically, in addition to the electric drive system parameters mentioned in this solution, those skilled in the art can use the same method to simulate the parameters of other electric drive systems to obtain desired test results.

[0063] Specifically, this solution can obtain simulated electric drive parameters by constructing a front-end page and inputting test conditions on the front-end page.

[0064] Example 2

[0065] Based on the same concept, refer to Figure 4 , this application also proposes an integrated electric drive system testing device for a forklift, comprising:

[0066] a simulation module for obtaining factory parameters of the electric drive system of the forklift under test, and inputting the factory parameters of the electric drive system into a pre-trained adaptive physical model in combination with test conditions to obtain simulated electric drive parameters, wherein the test conditions include road slope, ambient temperature, and load capacity. The simulated electric drive parameters are parameters of the electric drive system of the forklift under test under the test conditions, wherein the electric drive system includes a battery, a motor, and a kinetic energy recovery device;

[0067] The evaluation module is used to obtain multiple sets of simulated electric drive parameters of the forklift to be tested under different test conditions as evaluation data sets, and input the evaluation data sets into a pre-trained performance evaluation model to obtain the operating temperature range, load limit and maximum driving speed of the forklift to be tested.

[0068] Example 3

[0069] This embodiment also provides an electronic device, referring to Figure 5 , includes a memory 404 and a processor 402, wherein the memory 404 stores a computer program, and the processor 402 is configured to run the computer program to perform the steps in any of the above method embodiments.

[0070] Specifically, the processor 402 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0071] Memory 404 may include a large-capacity memory 404 for data or instructions. By way of example, and not limitation, memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 404 may include removable or non-removable (or fixed) media. Where appropriate, memory 404 may be internal or external to the data processing device. In certain embodiments, memory 404 is non-volatile memory. In certain embodiments, memory 404 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. In appropriate circumstances, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM may be a fast page mode dynamic random access memory 404 (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0072] The memory 404 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 402 .

[0073] The processor 402 reads and executes computer program instructions stored in the memory 404 to implement any one of the forklift integrated electric drive system testing methods in the above embodiments.

[0074] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408 , wherein the transmission device 406 is connected to the processor 402 , and the input / output device 408 is connected to the processor 402 .

[0075] Transmission device 406 can be used to receive or transmit data via a network. Specific examples of such networks may include wired or wireless networks provided by the electronic device's communications provider. In one embodiment, the transmission device includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 406 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0076] The input / output device 408 is used to input or output information. In this embodiment, the input information may be factory parameters of the electric drive system, test conditions, etc., and the output information may be simulated electric drive parameters, etc.

[0077] Optionally, in this embodiment, the processor 402 may be configured to execute the following steps through a computer program:

[0078] Obtaining factory parameters of the electric drive system of the forklift under test, and inputting the factory parameters of the electric drive system into a pre-trained adaptive physical model in combination with test conditions to obtain simulated electric drive parameters, wherein the test conditions include road slope, ambient temperature, and load. The simulated electric drive parameters are parameters of the electric drive system of the forklift under test under the test conditions. The electric drive system includes a battery, a motor, and a kinetic energy recovery device.

[0079] Multiple sets of simulated electric drive parameters of the forklift to be tested under different test conditions are obtained as evaluation data sets, and the evaluation data sets are input into a pre-trained performance evaluation model to obtain the operating temperature range, load limit and maximum driving speed of the forklift to be tested.

[0080] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be repeated here.

[0081] In general, various embodiments may be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects of the invention may be implemented in hardware, while other aspects may be implemented in firmware or software executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that, as non-limiting examples, the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0082] The embodiments of the present invention may be implemented by computer software that is executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets and / or macros may be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer executable components that are configured to perform an embodiment when the program is run. One or more computer executable components may be at least one software code or a portion thereof. In addition, it should be noted at this point that, for example, Figure 5 Any block of the logic flow in the program may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on physical media such as memory chips or memory blocks implemented within the processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. Physical media are non-transitory media.

[0083] Those skilled in the art should understand that the technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0084] The above embodiments merely illustrate several embodiments of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for testing an integrated electric drive system for a forklift, characterized in that: The following steps are involved: Obtaining factory parameters of the electric drive system of the forklift under test, and inputting the factory parameters of the electric drive system into a pre-trained adaptive physical model in combination with test conditions to obtain simulated electric drive parameters, wherein the test conditions include road slope, ambient temperature, and load. The simulated electric drive parameters are parameters of the electric drive system of the forklift under test under the test conditions. The electric drive system includes a battery, a motor, and a kinetic energy recovery device. Acquire multiple sets of simulated electric drive parameters of the forklift to be tested under different test conditions as evaluation data sets, and input the evaluation data sets into a pre-trained performance evaluation model to obtain the operating temperature range, load upper limit and maximum driving speed of the forklift to be tested, wherein the first layer of the performance evaluation model is composed of a battery feature branch, a motor feature branch and a kinetic energy recovery feature branch connected in parallel, the battery feature branch performs feature extraction on all simulated battery parameters in the evaluation data set through a convolutional layer to obtain battery features, the motor feature branch performs feature extraction on all simulated motor parameters in the evaluation data set to obtain motor features, and the kinetic energy recovery feature branch performs feature extraction on all simulated recovery parameters in the evaluation data set to obtain kinetic energy recovery features; the second layer of the performance evaluation model is a feature fusion layer, and the feature fusion layer fuses the battery features, motor features and kinetic energy recovery features to obtain a feature fusion result; the third layer of the performance evaluation model is composed of a first multi-head self-attention mechanism, a second multi-head self-attention mechanism, and a second multi-head self-attention mechanism. The intention mechanism and the third multi-head self-attention mechanism are connected in parallel, the first multi-head self-attention mechanism performs weight distribution on different types of features in the feature fusion result with the goal of predicting the working temperature range to obtain a first multi-head self-attention result, the second multi-head self-attention mechanism performs weight distribution on different types of features in the feature fusion result with the goal of predicting the upper limit of load to obtain a second multi-head self-attention result, the third multi-head self-attention mechanism performs weight distribution on different types of features in the feature fusion result with the goal of predicting the maximum driving speed to obtain a third multi-head self-attention result; the fourth layer of the performance evaluation model is composed of a temperature fully connected layer, a load fully connected layer and a speed fully connected layer connected in parallel, the temperature fully connected layer predicts the working temperature range based on the first multi-head self-attention result, the load fully connected layer predicts the upper limit of load based on the second multi-head self-attention result, and the speed fully connected layer predicts the maximum driving speed based on the third multi-head self-attention result.

2. A method for testing an integrated electric drive system for a forklift according to claim 1, characterized in that: The adaptive physical model includes a battery simulation model, a motor simulation model and a kinetic energy recovery simulation model, and the battery simulation model, the motor simulation model and the kinetic energy recovery simulation model are mathematical models. Historical electric drive system test data under different test conditions are obtained as training data. The adaptive physical model is trained using MATLAB based on the training data. During the training process, the adaptive physical model learns the impact of different working conditions on different parameters in the adaptive physical model to complete the training.

3. The method for testing an integrated electric drive system for a forklift according to claim 2, characterized in that: The formula of the battery simulation model is expressed as: in, is the battery terminal voltage, is the open circuit voltage-state of charge function, I is the operating current, is the battery's internal resistance in ohms, To reflect the electrochemical polarization internal resistance, To reflect the polarization internal resistance of deep polarization, 、 is the time constant, and t is the duration of the current acting on the battery.

4. A method for testing an integrated electric drive system for a forklift according to claim 2, characterized in that: The formula of the motor simulation model is expressed as: in, is the electromagnetic torque generated by the motor, is the number of motor pole pairs, is the permanent magnet flux, is the d-axis inductance, is the q-axis inductance, is the current component of the d-axis, is the current component of the q axis, is the instantaneous rate of change of angular velocity, is the load torque, is the damping torque caused by viscous friction, is the moment of inertia.

5. The method for testing an integrated electric drive system for a forklift according to claim 2, characterized in that: The formula of the kinetic energy recovery simulation model is expressed as: in, is the electric power of kinetic energy recovery, is the energy recovery efficiency of kinetic energy recovery, m is the total weight of the forklift, v is the driving speed of the forklift, is the kinetic energy of the forklift, The minimum speed threshold for kinetic energy recovery.

6. The method for testing an integrated electric drive system for a forklift according to claim 1, characterized in that: Obtain the factory parameters of the battery, the factory parameters of the motor and the factory parameters of the kinetic energy recovery, use the motor simulation model to simulate based on the factory parameters of the motor and the test conditions to obtain the simulated motor parameters, use the battery simulation model to simulate based on the factory parameters of the battery, the simulated motor parameters and the test conditions to obtain the simulated battery parameters, use the kinetic energy recovery simulation model to simulate based on the factory parameters of the kinetic energy recovery, the test conditions and the simulated motor parameters to obtain the simulated recovery parameters, and the simulated electric drive parameters are composed of the simulated motor parameters, the simulated battery parameters and the simulated recovery parameters.

7. A forklift integrated electric drive system test device, comprising: a simulation module for obtaining factory parameters of the electric drive system of the forklift under test, and inputting the factory parameters of the electric drive system into a pre-trained adaptive physical model in combination with test conditions to obtain simulated electric drive parameters, wherein the test conditions include road slope, ambient temperature, and load capacity. The simulated electric drive parameters are parameters of the electric drive system of the forklift under test under the test conditions, wherein the electric drive system includes a battery, a motor, and a kinetic energy recovery device; An evaluation module is used to obtain multiple sets of simulated electric drive parameters of the forklift to be tested under different test conditions as evaluation data sets, and input the evaluation data sets into a pre-trained performance evaluation model to obtain the operating temperature range, load upper limit and maximum driving speed of the forklift to be tested. The first layer of the performance evaluation model is composed of a battery feature branch, a motor feature branch and a kinetic energy recovery feature branch connected in parallel. The battery feature branch extracts features from all simulated battery parameters in the evaluation data set through a convolution layer to obtain battery features. The motor feature branch extracts features from all simulated motor parameters in the evaluation data set to obtain motor features. The kinetic energy recovery feature branch extracts features from all simulated recovery parameters in the evaluation data set to obtain kinetic energy recovery features. The second layer of the performance evaluation model is a feature fusion layer, which fuses battery features, motor features and kinetic energy recovery features to obtain feature fusion results. The third layer of the performance evaluation model is composed of a first multi-head self-attention mechanism, a second multi-head self-attention mechanism, and a second multi-head self-attention mechanism. A multi-head self-attention mechanism and a third multi-head self-attention mechanism are connected in parallel, the first multi-head self-attention mechanism weights different types of features in the feature fusion result with the goal of predicting the working temperature range to obtain a first multi-head self-attention result, the second multi-head self-attention mechanism weights different types of features in the feature fusion result with the goal of predicting the upper limit of load to obtain a second multi-head self-attention result, the third multi-head self-attention mechanism weights different types of features in the feature fusion result with the goal of predicting the maximum driving speed to obtain a third multi-head self-attention result; the fourth layer of the performance evaluation model is composed of a temperature fully connected layer, a load fully connected layer and a speed fully connected layer in parallel, the temperature fully connected layer predicts the working temperature range based on the first multi-head self-attention result, the load fully connected layer predicts the upper limit of load based on the second multi-head self-attention result, and the speed fully connected layer predicts the maximum driving speed based on the third multi-head self-attention result.

8. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the method for testing an integrated electric drive system for a forklift according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which includes program code for controlling a process to execute a process. When the program code is executed by a processor, a method for testing an integrated electric drive system for a forklift according to any one of claims 1 to 6 is implemented.

Images