Electric vehicle dynamic working condition electromagnetic interference resistance and function stability evaluation method based on deep learning and entropy algorithm

Abstract

The invention provides an electric vehicle dynamic working condition electromagnetic anti-interference and function stability evaluation method based on deep learning and an entropy algorithm, and the method comprises the steps: generating a controllable and changeable electromagnetic field on an integrated test platform where an electric vehicle is located, enabling the electric vehicle to operate under the influence of the electromagnetic field, carrying out the visual collection of the electric vehicle, and carrying out the evaluation of the function stability of the electric vehicle. Respective dynamic working condition images of a plurality of subordinate target parts are obtained, a controllable and changeable electromagnetic interference environment is provided for testing, and dynamic continuous visual monitoring of different target parts is realized; identifying the dynamic working condition image to obtain dynamic operation state information of the target component so as to obtain an operation state time domain curve of the target component, continuously identifying the operation state of the target component along with time under electromagnetic interference, and providing a data basis for subsequent deep learning processing; and entropy algorithm processing is carried out based on the operation state time domain curve to obtain a time correlation stability evaluation result of the target component, so that electromagnetic anti-interference degree information of the target component is determined, and integrated, dynamic and comprehensive evaluation is carried out on electromagnetic anti-interference of the electric vehicle. And the effectiveness and the reliability of the electromobile electromagnetic compatibility test are improved.

Description

Technical Field

[0001] The present invention relates to the field of electric vehicles, and in particular to a method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithms. Background Art

[0002] Electric vehicles play an increasingly important role in modern transportation. With the popularization of electric vehicles, the electromagnetic compatibility problem of electric vehicles has become more prominent. Electric vehicles contain a large number of electronic components. These electronic components will generate electromagnetic radiation when working, which may cause electromagnetic interference to other electronic systems of electric vehicles, the external environment and other vehicles. Therefore, improving the electromagnetic anti-interference performance of electric vehicles and ensuring their reliable operation in complex electromagnetic environments are the key to ensuring traffic safety and the normal operation of electric vehicles. The electromagnetic compatibility test of existing electric vehicles is usually carried out in a laboratory simulation environment. It lacks the testing means under real working conditions, and the calculation work corresponding to the electromagnetic compatibility test is still limited to the conventional computer data processing level. It is impossible to conduct an integrated, dynamic and comprehensive evaluation of the electromagnetic anti-interference of electric vehicles, and it is impossible to promote the unified standardization of the electromagnetic compatibility test technology of electric vehicles, which reduces the effectiveness and reliability of the electromagnetic compatibility test of electric vehicles. Summary of the invention

[0003] The purpose of the present invention is to provide an electric vehicle dynamic working condition electromagnetic anti-interference and functional stability evaluation method based on deep learning and entropy algorithm, which generates a controllable and variable electromagnetic field on an integrated test platform where the electric vehicle is located, so that the electric vehicle runs under the influence of the electromagnetic field, performs visual acquisition on the electric vehicle, obtains dynamic working condition images of several subordinate target components, provides a controllable and changeable electromagnetic interference environment for the test and realizes dynamic and continuous visual monitoring of different target components; then recognizes the dynamic working condition image to obtain the dynamic operation state information of the target component, thereby obtaining the operation state time domain curve of the target component, continuously identifies the operation state of the target component over time under electromagnetic interference, and provides a data basis for subsequent deep learning processing; and also performs entropy algorithm processing based on the operation state time domain curve to obtain the time-related stability evaluation result of the target component, thereby determining the electromagnetic anti-interference degree information of the target component, and performing integrated, dynamic and comprehensive evaluation of the electromagnetic anti-interference of the electric vehicle, thereby improving the effectiveness and reliability of the electromagnetic compatibility test of the electric vehicle.

[0004] The present invention is achieved through the following technical solutions:

[0005] A method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic conditions based on deep learning and entropy algorithm, comprising:

[0006] Generate a controllable and variable electromagnetic field on the integrated test platform where the electric vehicle is located, so that the electric vehicle runs under the influence of the electromagnetic field; perform visual acquisition on the electric vehicle in a running state to obtain dynamic working condition images of several target components of the electric vehicle;

[0007] Identify the dynamic working condition image to obtain dynamic operating state information of the target component; obtain an operating state time domain curve of the target component based on the dynamic operating state information;

[0008] Based on the time domain curve of the operating state, entropy algorithm processing is performed to obtain a time-related stability evaluation result of the target component; based on the time-related stability evaluation result, the electromagnetic anti-interference degree information of the target component is determined.

[0009] Optionally, generating a controllably variable electromagnetic field on an integrated test platform where the electric vehicle is located, so that the electric vehicle operates under the influence of the electromagnetic field, includes:

[0010] Generate an electromagnetic field whose frequency and strength can be individually controlled to different types of antennas inside the integrated test platform where the electric vehicle is located, so that the electric vehicle can operate the corresponding target components under the coverage of the electromagnetic field;

[0011] The electromagnetic field strength data inside the integrated test platform is also collected by a field strength probe inside the integrated test platform, and feedback adjustment is performed on all types of antennas based on the electromagnetic field strength data.

[0012] Optionally, a movable antenna is further provided inside the integrated test platform, and the movable antenna can be auxiliary adjusted, which includes:

[0013] Step A1, using the following formula (1), according to the electromagnetic field strength data inside the integrated test platform, controlling the movable antenna to enable auxiliary adjustment,

[0014]

[0015] In the above formula (1), P represents the enabling control value of the movable antenna for auxiliary adjustment; {X, Y, Z} represents the position coordinate set of the electromagnetic field strength collected from the field strength probe distribution position inside the integrated test platform that does not meet the preset electromagnetic field strength; E(x, y, z) represents the electromagnetic field strength value collected by the field strength probe at the (x, y, z) coordinate point position inside the integrated test platform; E0 represents the preset electromagnetic field strength threshold; {(x, y, z)|[E(x, y, z)-E0]≤0} represents the selection of the electromagnetic field strength value satisfying [E(x, y, z)-E0]≤0} among all the field strength probe distribution positions inside the integrated test platform. )-E0]≤0 corresponding to the (x, y, z) coordinate point position; Q{X,Y,Z} represents the total number of coordinate points in the coordinate set {X,Y,Z}; N represents the total number of distribution positions of all field strength probes in the integrated test platform; L({X,Y,Z}2) represents the distance value obtained by calculating the coordinate points in the coordinate set {X,Y,Z} in pairs; F{L({X,Y,Z}2)≤L0} represents the total number of distance values ​​less than L0 obtained by calculating the coordinate points in the coordinate set {X,Y,Z} in pairs; and represents logical AND, if the equations on both sides of and are both true, the output value is 1, otherwise the output value is 0;

[0016] If P=1, the movable antenna is enabled to perform auxiliary adjustment;

[0017] If P=0, the enabling of the movable antenna to perform auxiliary adjustment is turned off;

[0018] Step A2, using the following formula (2), according to the distribution of electromagnetic field strength data inside the integrated test platform, controlling the position of the movable antenna for auxiliary adjustment,

[0019]

[0020] In the above formula (2), (x0, y0, z0) represents the position coordinate point of the movable antenna for auxiliary adjustment; (L({X, Y, Z}2)≤L0)(a) represents the ath coordinate point whose distance value is less than L0 among the coordinate points in the coordinate set {X, Y, Z} that are obtained by calculating the distance between each other; It means taking the average of the horizontal coordinates, vertical coordinates and vertical coordinates of all coordinate points whose distance values ​​are less than L0 when the coordinate points satisfy the coordinate set {X, Y, Z} are calculated pairwise;

[0021] Step A3, using the following formula (3), according to the position where the movable antenna is auxiliary adjusted and the state of the electromagnetic field strength data around the position, control the electromagnetic field strength generated by the movable antenna,

[0022]

[0023] In the above formula (3), E D represents the electromagnetic field strength generated by the movable antenna; l0 represents the unit distance value; e0 represents the minimum electromagnetic field strength generated by the antenna at the coverage range distance; Lmax({X,Y,Z}2) represents the maximum value of the distance values ​​obtained by taking two by two coordinate points in the coordinate set {X,Y,Z}.

[0024] Optionally, visual acquisition is performed on the electric vehicle in operation to obtain dynamic working condition images of several target components of the electric vehicle, including:

[0025] Independent visual collection is performed on the wiper area, light area, airbag and steering wheel area of ​​the electric vehicle in operation, and dynamic working condition images of the wiper, turn signal, low beam, high beam, airbag and steering wheel of the electric vehicle are obtained.

[0026] Optionally, independent visual collection is performed on the wiper area, the headlight area, the airbag area and the steering wheel area of ​​the electric vehicle in operation to obtain dynamic working condition images of the wiper, the turn signal, the low beam, the high beam, the airbag and the steering wheel of the electric vehicle, including:

[0027] Perform binocular vision acquisition on the wiper area, the airbag and steering wheel area, and high-speed vision acquisition on the headlight area, respectively, to obtain corresponding binocular dynamic images of the wiper area, binocular dynamic images of the airbag and steering wheel area, and high-speed dynamic images of the headlight area;

[0028] The binocular dynamic image of the wiper area, the binocular dynamic image of the airbag and steering wheel area, and the high-speed dynamic image of the headlight area are respectively subjected to denoising and segmentation preprocessing to extract the dynamic working condition images of the wiper, turn signal, low beam, high beam, airbag, and steering wheel of the electric vehicle.

[0029] Optionally, identifying the dynamic working condition image to obtain dynamic operating state information of the target component includes:

[0030] Target detection and recognition are performed on the dynamic working condition image to obtain the swing state information of the wiper, the flashing state information of the turn signal, the switch action state information of the low beam and the high beam, the pop-up action state information of the airbag, and the rotation action state information of the steering wheel.

[0031] Optionally, obtaining a time domain curve of the operation state of the target component based on the dynamic operation state information includes:

[0032] The swing state information of the wiper, the flashing state information of the turn signal, the switch action state information of the low beam and the high beam, the pop-up action state information of the airbag, and the rotation action state information of the steering wheel are respectively processed by convolutional neural network to obtain the time domain curve of the swing angle of the wiper changing with time, the time domain curve of the flashing switching state of the turn signal changing with time, the time domain curve of the switch action switching state of the low beam and the high beam changing with time, the time domain curve of the pop-up action amplitude of the airbag changing with time, and the time domain curve of the steering wheel rotation angle changing with time.

[0033] Optionally, entropy algorithm processing is performed based on the operating state time domain curve to obtain a time-dependent stability evaluation result of the target component, including:

[0034] Based on the sample entropy algorithm and the multi-scale entropy algorithm, the time domain curve of the operation state is analyzed to obtain the stability evaluation results of the target component at different time scales;

[0035] Based on the Renyi entropy algorithm and the waveform entropy algorithm, the time domain curve of the operating state is analyzed to obtain the time domain stability evaluation result of the target component;

[0036] The stability assessment results at different time scales and the time domain stability assessment results are integrated to obtain the time-related stability assessment results of the target component; wherein the time-related stability assessment results include the stability assessment results corresponding to the target component at different lengths of working duration and different lengths of accumulated working time.

[0037] Optionally, determining the electromagnetic anti-interference degree information of the target component based on the time-dependent stability evaluation result includes:

[0038] Based on the time-related stability evaluation result, the maximum time length information corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different intensities and frequencies is determined; based on the maximum time length information, the electromagnetic anti-interference degree information of the target component is determined; wherein the electromagnetic anti-interference program information includes the electromagnetic interference intensity information that the target component can resist.

[0039] Optionally, determining the maximum time length information includes:

[0040] Step S1, assuming that the electromagnetic field intensity of the target electromagnetic field is I, and the frequency of the electromagnetic field is F, then the rate of change of the energy density of the target electromagnetic field over time is:

[0041] E=IF (4)

[0042] In the above formula (4), E is the rate of change of the energy density of the target electromagnetic field over time;

[0043] Step S2: Assume that the stability threshold of the target component is T, then the stability coefficient of the target component in the target electromagnetic field is:

[0044]

[0045] In the above formula (5), f T is the stability coefficient of the target component in the target electromagnetic field;

[0046] Step S3, based on the calculation results of the above steps S1 and S2, determine the maximum time length information corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different intensities and frequencies,

[0047]

[0048] In the above formula (6), H is the maximum time length corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different strengths and frequencies, R is the interval time when the target component responds to the target electromagnetic interference and begins to show signs of instability, T D is the rate at which the stability of the target component decays over time, which is related to the material of the target component, and e is a natural constant.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The method for evaluating the electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm provided in the present application generates a controllable and variable electromagnetic field on the integrated test platform where the electric vehicle is located, so that the electric vehicle operates under the influence of the electromagnetic field, performs visual acquisition on the electric vehicle, and obtains the dynamic working condition images of several subordinate target components, thereby providing a controllable and changeable electromagnetic interference environment for the test and realizing dynamic and continuous visual monitoring of different target components; then the dynamic working condition images are recognized to obtain the dynamic operating state information of the target component, thereby obtaining the operating state time domain curve of the target component, and continuously identifying the operating state of the target component over time under electromagnetic interference, thereby providing a data basis for subsequent deep learning processing; and also performs entropy algorithm processing based on the operating state time domain curve to obtain the time-related stability evaluation result of the target component, thereby determining the electromagnetic interference resistance degree information of the target component, and performing an integrated, dynamic and comprehensive evaluation of the electromagnetic interference resistance of the electric vehicle, thereby improving the effectiveness and reliability of the electromagnetic compatibility test of the electric vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0052] Figure 1 A flow chart of a method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic conditions based on deep learning and entropy algorithm provided by the present invention.

[0053] Figure 2 A structural block diagram of an integrated test platform used in the method for evaluating electromagnetic anti-interference and functional stability of electric vehicles under dynamic conditions based on deep learning and entropy algorithm provided by the present invention. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only some structures related to the present application are shown in the accompanying drawings, rather than all structures. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0055] The terms "include" and "have" and any variations thereof in this application are intended to cover non-exclusive inclusions. For example, a process, method, method, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0056] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0057] See also Figure 1As shown, an embodiment of the present application provides an electric vehicle dynamic condition electromagnetic anti-interference and functional stability evaluation method based on deep learning and entropy algorithm. The electric vehicle dynamic condition electromagnetic anti-interference and functional stability evaluation method based on deep learning and entropy algorithm includes:

[0058] Generate a controllable and variable electromagnetic field on the integrated test platform where the electric vehicle is located, so that the electric vehicle runs under the influence of the electromagnetic field; perform visual acquisition on the electric vehicle in operation to obtain dynamic working condition images of several target components of the electric vehicle;

[0059] Identify the dynamic working condition image to obtain dynamic operating state information of the target component; based on the dynamic operating state information, obtain an operating state time domain curve of the target component;

[0060] Based on the time domain curve of the operation state, entropy algorithm processing is performed to obtain a time-related stability evaluation result of the target component; based on the time-related stability evaluation result, the electromagnetic anti-interference degree information of the target component is determined.

[0061] The beneficial effects of the above embodiments are as follows: the method for evaluating the electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithms generates a controllable and variable electromagnetic field on the integrated test platform where the electric vehicle is located, so that the electric vehicle operates under the influence of the electromagnetic field, performs visual acquisition on the electric vehicle, and obtains the dynamic working condition images of several subordinate target components, thereby providing a controllable and variable electromagnetic interference environment for the test and realizing dynamic and continuous visual monitoring of different target components; then the dynamic working condition images are identified to obtain the dynamic operating state information of the target component, thereby obtaining the operating state time domain curve of the target component, and continuously identifying the operating state of the target component over time under electromagnetic interference, thereby providing a data basis for subsequent deep learning processing; and also performs entropy algorithm processing based on the operating state time domain curve to obtain the time-related stability evaluation result of the target component, thereby determining the electromagnetic interference resistance degree information of the target component, and performing an integrated, dynamic and comprehensive evaluation of the electromagnetic interference resistance of the electric vehicle, thereby improving the effectiveness and reliability of the electromagnetic compatibility test of the electric vehicle.

[0062] In another embodiment, an electromagnetic field that can be controlled and changed is generated on an integrated test platform where an electric vehicle is located, so that the electric vehicle operates under the influence of the electromagnetic field, including:

[0063] Generate an electromagnetic field whose frequency and strength can be individually controlled to different types of antennas inside the integrated test platform where the electric vehicle is located, so that the electric vehicle can operate the corresponding target components under the coverage of the electromagnetic field;

[0064] The electromagnetic field strength data inside the integrated test platform is also collected through the field strength probe inside the integrated test platform, and feedback adjustment is performed on all types of antennas based on the electromagnetic field strength data.

[0065] The beneficial effect of the above embodiment is that the electromagnetic field generated by the internal electronic components of the electric vehicle during actual driving is not fixed, but will change in terms of electromagnetic field strength and frequency, and the circuit structures of different target components inside the electric vehicle are different, and the anti-interference performance of different target components to the electromagnetic field is also different. In order to be able to perform comprehensive and effective electromagnetic anti-interference tests on all target components inside the electric vehicle, different types of antennas such as biconical antennas, logarithmic periodic antennas, and horn antennas are set in the half-wave darkroom of the integrated test platform. The above different types of antennas can generate electromagnetic fields with different distributions, and all antennas are also connected to the signal generator, power meter, switching unit and power amplifier in the control room of the integrated test platform, so that all antennas can be individually controlled, thereby independently changing the frequency and intensity of the electromagnetic field generated by each antenna. In addition, a field strength probe is provided inside the half-wave darkroom to detect the electromagnetic field strength inside the half-wave darkroom, and the field strength probe is also connected to the host computer in the control room through a field strength meter, and the host computer is also connected to the signal generator, thus forming a closed-loop control of the antenna. The electromagnetic field strength data inside the integrated test platform is collected based on the field strength probe, and feedback adjustment is performed on all types of antennas, which can improve the accuracy of antenna adjustment. In addition, a chassis dynamometer and a camera are also provided in the half-wave darkroom to perform chassis testing and visual acquisition on electric vehicles, and the chassis dynamometer and the camera are connected to the host computer through an industrial computer and a controller, respectively. The structure of the integrated test platform is as follows: Figure 2 As shown, no detailed description is given here.

[0066] In another embodiment, a movable antenna is further provided inside the integrated test platform, and the movable antenna can be assisted in adjustment, which includes:

[0067] Step A1, using the following formula (1), according to the electromagnetic field strength data inside the integrated test platform, control the movable antenna to enable auxiliary adjustment,

[0068]

[0069] In the above formula (1), P represents the enabling control value of the movable antenna for auxiliary adjustment; {X, Y, Z} represents the position coordinate set of the electromagnetic field strength collected from the distribution positions of the field strength probes inside the integrated test platform that does not meet the preset electromagnetic field strength; E(x, y, z) represents the electromagnetic field strength value collected by the field strength probe at the (x, y, z) coordinate point position inside the integrated test platform; E0 represents the preset electromagnetic field strength threshold; {(x, y, z)|[E(x, y, z)-E0]≤0} represents the selection of the electromagnetic field strength value satisfying [E(x, y, z)-E0]≤0 among all the field strength probe distribution positions inside the integrated test platform. E0]≤0 corresponding to the (x,y,z) coordinate point position; Q{X,Y,Z} represents the total number of coordinate points in the coordinate set {X,Y,Z}; N represents the total number of distribution positions of all field strength probes in the integrated test platform; L({X,Y,Z}2) represents the distance value obtained by calculating the coordinate points in the coordinate set {X,Y,Z} in pairs; F{L({X,Y,Z}2)≤L0} represents the total number of distance values ​​less than L0 obtained by calculating the coordinate points in the coordinate set {X,Y,Z} in pairs; and represents logical AND. If the equations on both sides of and are both true, the output value is 1, otherwise the output value is 0;

[0070] If P=1, the movable antenna is enabled for auxiliary adjustment;

[0071] If P = 0, the enabling of the movable antenna for auxiliary adjustment is turned off;

[0072] Step A2, using the following formula (2), according to the distribution of electromagnetic field strength data inside the integrated test platform, control the position of the movable antenna for auxiliary adjustment,

[0073]

[0074] In the above formula (2), (x0, y0, z0) represents the position coordinate point of the movable antenna for auxiliary adjustment; (L({X, Y, Z}2)≤L0)(a) represents the ath coordinate point whose distance value is less than L0 among the coordinate points in the coordinate set {X, Y, Z} that are obtained by calculating the distance between each other; It means taking the average of the horizontal coordinates, vertical coordinates and vertical coordinates of all coordinate points whose distance values ​​are less than L0 when the coordinate points satisfy the coordinate set {X, Y, Z} are calculated pairwise;

[0075] Step A3, using the following formula (3), according to the position where the movable antenna is to be assisted in adjustment and the state of the electromagnetic field strength data around the position, control the electromagnetic field strength generated by the movable antenna,

[0076]

[0077] In the above formula (3), E D represents the electromagnetic field strength generated by the movable antenna; l0 represents the unit distance value; e0 represents the minimum electromagnetic field strength generated by the antenna at the coverage distance; Lmax({X,Y,Z}2) represents the maximum value of the distance values ​​obtained by taking two by two coordinate points in the coordinate set {X,Y,Z}.

[0078] The beneficial effect of the above embodiment is that the above formula (1) is used to control the enabling of the auxiliary adjustment of the movable antenna according to the electromagnetic field strength data inside the integrated test platform, thereby ensuring the reliability of the auxiliary adjustment of the movable antenna; then the above formula (2) is used to control the position of the movable antenna for auxiliary adjustment according to the distribution of the electromagnetic field strength data inside the integrated test platform, thereby automatically calculating the position of the movable antenna for automatic movement, which reflects the intelligent characteristics of the system; then the above formula (3) is used to control the generated electromagnetic field strength of the movable antenna according to the position of the movable antenna for auxiliary adjustment and the state of the electromagnetic field strength data around the position, thereby using the movable antenna to automatically and intelligently adjust the electromagnetic field strength inside the integrated test platform, which can improve the system adjustment efficiency.

[0079] In another embodiment, visual acquisition is performed on an electric vehicle in operation to obtain dynamic working condition images of several target components of the electric vehicle, including:

[0080] Independent visual collection is performed on the wiper area, light area, airbag and steering wheel area of ​​an electric vehicle in operation to obtain dynamic working condition images of the wiper, turn signal, low beam, high beam, airbag and steering wheel of the electric vehicle.

[0081] The beneficial effects of the above embodiments are that the target components such as wipers, turn signals, low beams, high beams, airbags, and steering wheels of electric vehicles all have complex circuit structures inside, so that these target components will inevitably be disturbed by the electromagnetic field during operation and cause work disorder, such as the wipers cannot swing at a uniform speed, the turn signals cannot flash normally, the low beams and high beams cannot be turned on or off normally, the airbags cannot pop out in time, and the steering wheel cannot be turned normally. In order to comprehensively and accurately obtain the dynamic working conditions of all target components during the electromagnetic anti-interference test of electric vehicles, several cameras are set to perform real-time visual acquisition for different areas of the electric vehicle. For example, different cameras can be set in front of the electric vehicle to perform independent visual shooting of the wiper area and the headlight area of ​​the electric vehicle, and a camera can be set above the main driver's seat inside the electric vehicle to aim at the airbag and steering wheel area. In this way, it can be ensured that the action conditions of the corresponding target components can be continuously and completely recorded during the entire electromagnetic anti-interference test, providing reliable image data support for the subsequent analysis of whether the target components have abnormal conditions caused by electromagnetic interference.

[0082] In another embodiment, the wiper area, the headlight area, the airbag area and the steering wheel area of ​​the electric vehicle in operation are respectively visually captured to obtain dynamic working condition images of the wiper, the turn signal, the low beam, the high beam, the airbag and the steering wheel of the electric vehicle, including:

[0083] Perform binocular vision acquisition on the wiper area, the airbag and steering wheel area, and high-speed vision acquisition on the headlight area, respectively, to obtain corresponding binocular dynamic images of the wiper area, binocular dynamic images of the airbag and steering wheel area, and high-speed dynamic images of the headlight area;

[0084] The binocular dynamic image of the wiper area, the binocular dynamic image of the airbag and steering wheel area, and the high-speed dynamic image of the headlight area are denoised and segmented pre-processed respectively, and the dynamic working condition images of the wiper, turn signal, low beam, high beam, airbag and steering wheel of the electric vehicle are extracted.

[0085] The beneficial effects of the above embodiments are that the operating actions of the wipers, airbags and steering wheels all occur in three-dimensional space. In order to accurately visually capture the dynamic working conditions of the wipers, airbags and steering wheels, a binocular camera can be used to perform binocular visual capture of the wiper area, the airbag and steering wheel areas respectively, and obtain corresponding binocular dynamic images of the wiper area, and binocular dynamic images of the airbag and steering wheel areas; and the turn signals, low beams and high beams all work by emitting light of specific shapes. In order to accurately capture the light emitted by the turn signals, low beams and high beams, a high-speed industrial camera can be used to perform high-speed visual capture of the headlight area to obtain a high-speed dynamic image of the headlight area, which can improve the reliability of visual capture of dynamic working conditions. In addition, the binocular dynamic image of the wiper area, the binocular dynamic image of the airbag and steering wheel area, and the high-speed dynamic image of the headlight area are denoised and segmented pre-processed respectively, and the dynamic working condition images of the wiper, turn signal, low beam, high beam, airbag and steering wheel of the electric vehicle are extracted, so that each dynamic working condition image corresponds to only one target component, effectively improving the credibility of the dynamic working condition image and reducing the noise interference of the image.

[0086] In another embodiment, the dynamic working condition image is identified to obtain the dynamic operating state information of the target component, including:

[0087] Target detection and recognition are performed on the dynamic working condition image to obtain the swing state information of the wiper, the flashing state information of the turn signal lamp, the switch action state information of the low beam lamp and the high beam lamp, the pop-up action state information of the airbag, and the rotation action state information of the steering wheel.

[0088] The beneficial effects of the above embodiments: in actual image processing, the corresponding deep learning neural network model can be used to detect and identify the corresponding target components of the dynamic working condition image, so as to obtain the swing state information of the wiper (such as the swing angular velocity and swing amplitude of the wiper, etc.), the flashing state information of the turn signal (such as the flashing frequency of the turn signal, etc.), the switch action state information of the low beam and the high beam (such as the lighting brightness and switch response speed of the low beam and the high beam, etc.), the pop-up action state information of the airbag (such as the pop-up response speed and pop-up coverage of the airbag, etc.), the rotation action state information of the steering wheel (such as the smoothness of the rotation of the steering wheel, etc.), so as to accurately identify the dynamic working conditions of all target components that change over time, and provide a reliable basis for the subsequent judgment of whether the target components fail due to electromagnetic interference.

[0089] In another embodiment, obtaining the time domain curve of the operation state of the target component based on the dynamic operation state information includes:

[0090] The swing state information of the wiper, the flashing state information of the turn signal, the respective switch action state information of the low beam and the high beam, the pop-up action state information of the airbag, and the rotation action state information of the steering wheel are respectively processed by convolutional neural network to obtain the time domain curve of the swing angle of the wiper changing with time, the time domain curve of the flashing switching state of the turn signal changing with time, the time domain curve of the switch action switching state of the low beam and the high beam changing with time, the time domain curve of the pop-up action amplitude of the airbag changing with time, and the time domain curve of the rotation angle of the steering wheel changing with time.

[0091] The beneficial effect of the above embodiment is that the swing state information of the wiper, the flashing state information of the turn signal, the respective switch action state information of the low beam and the high beam, the pop-up action state information of the airbag, and the rotation action state information of the steering wheel are respectively processed by convolutional neural network to obtain the time domain curve of the swing angle of the wiper changing with time, the time domain curve of the flashing switching state of the turn signal changing with time, the time domain curve of the switch action switching state of the low beam and the high beam changing with time, the time domain curve of the pop-up action amplitude of the airbag changing with time, and the time domain curve of the rotation angle of the steering wheel changing with time. All of the above time domain curves can globally reflect the changes in the operating state of the corresponding target component under the action of electromagnetic interference of different frequencies and intensities over time, and construct the correlation between the operating state of the target component and the electromagnetic interference.

[0092] In another embodiment, entropy algorithm processing is performed based on the operation state time domain curve to obtain the time-dependent stability evaluation result of the target component, including:

[0093] Based on the sample entropy algorithm and the multi-scale entropy algorithm, the time domain curve of the operating state is analyzed to obtain the stability evaluation results of the target component at different time scales;

[0094] Based on the Renyi entropy algorithm and the waveform entropy algorithm, the time domain curve of the operating state is analyzed to obtain the time domain stability evaluation result of the target component;

[0095] The stability evaluation results at different time scales and the time domain stability evaluation results are integrated to obtain the time-related stability evaluation result of the target component; wherein the time-related stability evaluation result includes the stability evaluation results corresponding to the target component at different lengths of working duration and different lengths of accumulated working time.

[0096] The beneficial effects of the above embodiments are as follows: in order to refine the correlation between the operating state of the target component and the electromagnetic interference, the operating state time domain curve is analyzed based on the sample entropy algorithm and the multi-scale entropy algorithm to obtain the stability evaluation results of the target component at different time scales, that is, the stability evaluation results corresponding to the target component at different time lengths during the electromagnetic interference process; and based on the Renyi entropy algorithm and the waveform entropy algorithm, the operating state time domain curve is analyzed to obtain the time domain stability evaluation results of the target component, that is, the stability evaluation results corresponding to the change of the cumulative working time of the target component during the electromagnetic interference process. Among them, the sample entropy algorithm, the multi-scale entropy algorithm, the Renyi entropy algorithm and the waveform entropy algorithm are all conventional algorithms in this field, and are not introduced in detail here. There is also an integration of the stability evaluation results at different time scales and the time domain stability evaluation results to obtain the stability evaluation results corresponding to the working durations of different lengths and the accumulated working time of different lengths of the target component, so that the performance of the target component in maintaining a normal working state under the action of electromagnetic interference can be accurately evaluated.

[0097] In another embodiment, determining the electromagnetic interference resistance level information of the target component based on the time-dependent stability evaluation result includes:

[0098] Based on the time-related stability evaluation result, the maximum time length information corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different intensities and frequencies is determined; based on the maximum time length information, the electromagnetic anti-interference degree information of the target component is determined; wherein the electromagnetic anti-interference program information includes the electromagnetic interference intensity information that the target component can resist.

[0099] The beneficial effect of the above embodiment is that, based on the time-related stability evaluation result, the maximum time length information corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different intensities and frequencies is determined, that is, the maximum continuous duration length corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different intensities and frequencies is determined; then based on the maximum time length information, the performance of the target component is comprehensively evaluated to determine the electromagnetic interference intensity information that the target component can resist, thereby quantifying the electromagnetic anti-interference performance of the target component, wherein the comprehensive evaluation belongs to the conventional technical means in the field, which can be achieved through a convolutional neural network and is not described in detail here.

[0100] In another embodiment, determining the maximum time length information includes:

[0101] Step S1, assuming that the electromagnetic field intensity of the target electromagnetic field is I, and the frequency of the electromagnetic field is F, then the rate of change of the energy density of the target electromagnetic field over time is:

[0102] E=IF (4)

[0103] In the above formula (4), E is the rate of change of the energy density of the target electromagnetic field over time;

[0104] Step S2: Assume that the stability threshold of the target component is T, then the stability coefficient of the target component in the target electromagnetic field is:

[0105]

[0106] In the above formula (5), f T is the stability coefficient of the target component in the target electromagnetic field;

[0107] Step S3, based on the calculation results of the above steps S1 and S2, determine the maximum time length information corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different intensities and frequencies,

[0108]

[0109] In the above formula (6), H is the maximum time length corresponding to the target component maintaining a stable working state under the electromagnetic field of different strengths and frequencies, R is the interval time when the target component responds to the target electromagnetic interference and begins to show signs of instability, T D is the rate at which the stability of the target component decays over time, which is related to the material of the target component, and e is a natural constant.

[0110] The beneficial effects of the above embodiments are as follows: the maximum time length information is a measure of the maximum time length that the target component can maintain stable operation under external electromagnetic interference, and the accuracy of its value is related to the safety of the electric vehicle. Therefore, the determination of the maximum time length information, especially the determination of the maximum time length information under the action of electromagnetic fields of different intensities and frequencies, is crucial; based on the relevant information of the target electromagnetic field and the stability of the target component, the maximum time length that the target component can maintain stable operation under the electromagnetic interference of the target electromagnetic field is accurately calculated, providing important guarantee for the safety of the electric vehicle.

[0111] In general, the method for evaluating the electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm generates a controllable and variable electromagnetic field on the integrated test platform where the electric vehicle is located, so that the electric vehicle operates under the influence of the electromagnetic field, and performs visual acquisition on the electric vehicle to obtain the dynamic working condition images of several subordinate target components, thereby providing a controllable and changeable electromagnetic interference environment for the test and realizing dynamic and continuous visual monitoring of different target components; the dynamic working condition images are then recognized to obtain the dynamic operating state information of the target component, thereby obtaining the operating state time domain curve of the target component, and continuously identifying the operating state of the target component over time under electromagnetic interference, providing a data basis for subsequent deep learning processing; the entropy algorithm is also used based on the operating state time domain curve to obtain the time-related stability evaluation result of the target component, thereby determining the electromagnetic interference resistance degree information of the target component, and performing an integrated, dynamic and comprehensive evaluation of the electromagnetic interference resistance of the electric vehicle, thereby improving the effectiveness and reliability of the electromagnetic compatibility test of the electric vehicle.

[0112] The above is only a specific implementation of the present invention, and any other improvements made based on the concept of the present invention are considered to be within the protection scope of the present invention.

Claims

1. A method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm, characterized in that: include: Generating a controllably variable electromagnetic field on an integrated test platform where the electric vehicle is located, so that the electric vehicle operates under the influence of the electromagnetic field; Performing visual acquisition on an electric vehicle in operation to obtain dynamic working condition images of several target components of the electric vehicle; Identifying the dynamic working condition image to obtain dynamic operating state information of the target component; Based on the dynamic operation status information, a time domain curve of the operation status of the target component is obtained; based on the operation status time domain curve, entropy algorithm processing is performed to obtain a time-related stability evaluation result of the target component; based on the time-related stability evaluation result, the electromagnetic anti-interference degree information of the target component is determined.

2. The method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm according to claim 1, characterized in that: Generate a controllable and variable electromagnetic field on an integrated test platform where an electric vehicle is located, so that the electric vehicle operates under the influence of the electromagnetic field, including: Generate an electromagnetic field whose frequency and strength can be individually controlled to different types of antennas inside the integrated test platform where the electric vehicle is located, so that the electric vehicle can operate the corresponding target components under the coverage of the electromagnetic field; The electromagnetic field strength data inside the integrated test platform is also collected by a field strength probe inside the integrated test platform, and feedback adjustment is performed on all types of antennas based on the electromagnetic field strength data.

3. The method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm according to claim 2, characterized in that: The integrated test platform is also provided with a movable antenna, which can be assisted in adjustment, including: Step A1, using the following formula (1), according to the electromagnetic field strength data inside the integrated test platform, controlling the movable antenna to enable auxiliary adjustment, In the above formula (1), P represents the enabling control value of the movable antenna for auxiliary adjustment; {X, Y, Z} represents the position coordinate set of the electromagnetic field strength collected from the field strength probe distribution position inside the integrated test platform that does not meet the preset electromagnetic field strength; E(x, y, z) represents the electromagnetic field strength value collected by the field strength probe at the (x, y, z) coordinate point position inside the integrated test platform; E0 represents the preset electromagnetic field strength threshold; {(x, y, z)|[E(x, y, z)-E0]≤0} represents the selection of the electromagnetic field strength value satisfying [E(x, y, z)-E0]≤0} among all the field strength probe distribution positions inside the integrated test platform. )-E0]≤0 corresponding to the (x, y, z) coordinate point position; Q{X,Y,Z} represents the total number of coordinate points in the coordinate set {X,Y,Z}; N represents the total number of distribution positions of all field strength probes in the integrated test platform; L({X,Y,Z}2) represents the distance value obtained by calculating the coordinate points in the coordinate set {X,Y,Z} in pairs; F{L({X,Y,Z}2)≤L0} represents the total number of distance values ​​less than L0 obtained by calculating the coordinate points in the coordinate set {X,Y,Z} in pairs; and represents logical AND, if the equations on both sides of and are both true, the output value is 1, otherwise the output value is 0; If P=1, the movable antenna is enabled to perform auxiliary adjustment; If P=0, the enabling of the movable antenna to perform auxiliary adjustment is turned off; Step A2, using the following formula (2), according to the distribution of electromagnetic field strength data inside the integrated test platform, controlling the position of the movable antenna for auxiliary adjustment, In the above formula (2), (x0, y0, z0) represents the position coordinate point of the movable antenna for auxiliary adjustment; (L({X, Y, Z}2)≤L0)(a) represents the ath coordinate point whose distance value is less than L0 among the coordinate points in the coordinate set {X, Y, Z} that are obtained by calculating the distance between each other; It means taking the average of the horizontal coordinates, vertical coordinates and vertical coordinates of all coordinate points whose distance values ​​are less than L0 when the coordinate points satisfy the coordinate set {X, Y, Z} are calculated pairwise; Step A3, using the following formula (3), according to the position where the movable antenna is auxiliary adjusted and the state of the electromagnetic field strength data around the position, control the electromagnetic field strength generated by the movable antenna, In the above formula (3), E D represents the electromagnetic field strength generated by the movable antenna; l0 represents the unit distance value; e0 represents the minimum electromagnetic field strength generated by the antenna at the coverage range distance; Lmax({X,Y,Z}2) represents the maximum value of the distance values ​​obtained by taking two by two coordinate points in the coordinate set {X,Y,Z}.

4. The method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm according to claim 1, characterized in that: Visual acquisition is performed on the electric vehicle in operation to obtain dynamic working condition images of several target components of the electric vehicle, including: Independent visual collection is performed on the wiper area, light area, airbag and steering wheel area of ​​the electric vehicle in operation, and dynamic working condition images of the wiper, turn signal, low beam, high beam, airbag and steering wheel of the electric vehicle are obtained.

5. The method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm according to claim 4, characterized in that: Independent visual collection is performed on the wiper area, light area, airbag and steering wheel area of ​​the electric vehicle in operation to obtain dynamic working condition images of the wiper, turn signal, low beam, high beam, airbag and steering wheel of the electric vehicle, including: Perform binocular vision acquisition on the wiper area, the airbag and steering wheel area, and high-speed vision acquisition on the headlight area, respectively, to obtain corresponding binocular dynamic images of the wiper area, binocular dynamic images of the airbag and steering wheel area, and high-speed dynamic images of the headlight area; The binocular dynamic image of the wiper area, the binocular dynamic image of the airbag and steering wheel area, and the high-speed dynamic image of the headlight area are respectively subjected to denoising and segmentation preprocessing to extract the dynamic working condition images of the wiper, turn signal, low beam, high beam, airbag, and steering wheel of the electric vehicle.

6. The method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm according to claim 5, characterized in that: Identifying the dynamic working condition image to obtain dynamic operating state information of the target component includes: Target detection and recognition are performed on the dynamic working condition image to obtain the swing state information of the wiper, the flashing state information of the turn signal, the switch action state information of the low beam and the high beam, the pop-up action state information of the airbag, and the rotation action state information of the steering wheel.

7. The method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm according to claim 6, characterized in that: Based on the dynamic operation state information, a time domain curve of the operation state of the target component is obtained, including: The swing state information of the wiper, the flashing state information of the turn signal, the switch action state information of the low beam and the high beam, the pop-up action state information of the airbag, and the rotation action state information of the steering wheel are respectively processed by convolutional neural network to obtain the time domain curve of the swing angle of the wiper changing with time, the time domain curve of the flashing switching state of the turn signal changing with time, the time domain curve of the switch action switching state of the low beam and the high beam changing with time, the time domain curve of the pop-up action amplitude of the airbag changing with time, and the time domain curve of the steering wheel rotation angle changing with time.

8. The method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm according to claim 1, characterized in that: The entropy algorithm is processed based on the operation state time domain curve to obtain the time-dependent stability evaluation result of the target component, including: Based on the sample entropy algorithm and the multi-scale entropy algorithm, the time domain curve of the operation state is analyzed to obtain the stability evaluation results of the target component at different time scales; Based on the Renyi entropy algorithm and the waveform entropy algorithm, the time domain curve of the operating state is analyzed to obtain the time domain stability evaluation result of the target component; The stability assessment results at different time scales and the time domain stability assessment results are integrated to obtain the time-related stability assessment results of the target component; wherein the time-related stability assessment results include the stability assessment results corresponding to the target component at different lengths of working duration and different lengths of accumulated working time.

9. The method for evaluating electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm according to claim 8, characterized in that: Determining electromagnetic interference resistance information of the target component based on the time-dependent stability evaluation result includes: Based on the time-related stability evaluation result, the maximum time length information corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different intensities and frequencies is determined; based on the maximum time length information, the electromagnetic anti-interference degree information of the target component is determined; wherein the electromagnetic anti-interference program information includes the electromagnetic interference intensity information that the target component can resist.

10. The method for evaluating the electromagnetic interference resistance and functional stability of electric vehicles under dynamic working conditions based on deep learning and entropy algorithm according to claim 9, characterized in that: Determining the maximum time length information includes: Step S1, assuming that the electromagnetic field intensity of the target electromagnetic field is I, and the frequency of the electromagnetic field is F, then the rate of change of the energy density of the target electromagnetic field over time is: E=IF (4) In the above formula (4), E is the rate of change of the energy density of the target electromagnetic field over time; Step S2: Assume that the stability threshold of the target component is T, then the stability coefficient of the target component in the target electromagnetic field is: In the above formula (5), f T is the stability coefficient of the target component in the target electromagnetic field; Step S3, based on the calculation results of the above steps S1 and S2, determine the maximum time length information corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different intensities and frequencies, In the above formula (6), H is the maximum time length corresponding to the target component maintaining a stable working state under the action of electromagnetic fields of different strengths and frequencies, R is the interval time when the target component responds to the target electromagnetic interference and begins to show signs of instability, T D is the rate at which the stability of the target component decays over time, which is related to the material of the target component, and e is a natural constant.

Images