Motor reverse working condition data processing method and system

Abstract

The invention provides a motor reverse working condition data processing method and system, and the method comprises the steps: detecting original driving parameters corresponding to a vehicle in real time when the vehicle is detected to be in a driving state in real time, and carrying out the preprocessing of the original driving parameters, so as to generate corresponding standard driving parameters; detecting a plurality of target data sets correspondingly contained in the standard driving parameters in real time, and performing multi-modal fusion processing on the plurality of target data sets based on a preset rule to generate corresponding multi-modal fusion data; a corresponding motor life prediction model is trained according to the multi-modal fusion data, and actual working parameters corresponding to a driving motor in the vehicle are collected in real time; and the working state and the remaining service time corresponding to the driving motor are detected in real time according to the actual working parameters through the motor service life prediction model. According to the invention, the working state of the driving motor can be objectively and comprehensively detected, and the working efficiency is correspondingly improved.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a method and system for processing motor reverse operating condition data. Background Art

[0002] With the advancement of science and technology and the rapid development of productivity, cars have become popular in people's daily lives and have become one of the indispensable means of transportation for people's daily travel, greatly facilitating people's lives.

[0003] Among them, the production technology of new energy electric vehicles is becoming more and more mature, and has gradually been recognized by people and gradually popularized in people's daily lives.

[0004] Furthermore, the drive motor is one of the core components of new energy electric vehicles and is used to drive the vehicle. Specifically, the existing drive motors need to monitor their working status in real time during actual operation. Among them, the motor reverse operating data is one of the important indicators for evaluating the performance of the drive motor. However, in the process of processing the motor reverse operating data, most of the existing technologies can only obtain a single data source and can only complete the corresponding evaluation according to a pre-set algorithm, resulting in low flexibility in data processing. At the same time, the processing structure is not comprehensive enough, which correspondingly reduces work efficiency. Summary of the invention

[0005] Based on this, the purpose of the present invention is to provide a method and system for processing motor reverse operating condition data to solve the problem that the prior art has low processing flexibility for electrode reverse operating condition data and the processing results are not comprehensive enough.

[0006] The first aspect of the embodiment of the present invention proposes:

[0007] A method for processing reverse working condition data of a motor, wherein the method comprises:

[0008] When it is detected in real time that the vehicle is in a driving state, original driving parameters corresponding to the vehicle are detected in real time, and the original driving parameters are preprocessed to generate corresponding standard driving parameters;

[0009] Detecting in real time a number of target data sets corresponding to the standard driving parameters, and performing multimodal fusion processing on the target data sets based on preset rules to generate corresponding multimodal fusion data;

[0010] Training a corresponding motor life prediction model according to the multimodal fusion data, and collecting actual working parameters corresponding to the drive motor inside the vehicle in real time;

[0011] The motor life prediction model detects the working state and remaining use time corresponding to the drive motor in real time according to the actual working parameters.

[0012] The beneficial effect of the present invention is that by collecting the original driving parameters of the vehicle in real time, the working status of the vehicle can be obtained accordingly, based on which the required multimodal fusion data can be further generated, so that the various parameters corresponding to the vehicle can be fully considered. Furthermore, the required click life prediction model is trained accordingly, and finally the working status and remaining use time of the current internal drive motor of the vehicle can be objectively and comprehensively detected through the model, which correspondingly improves the work efficiency.

[0013] Furthermore, the step of performing multimodal fusion processing on the target data sets based on preset rules to generate corresponding multimodal fusion data includes:

[0014] When a plurality of target data sets are acquired in real time, a target data chain corresponding to each target data set is constructed respectively;

[0015] Performing time alignment processing on each of the target data links to synchronize each of the target data links to the same time axis and generating corresponding aligned data links;

[0016] The aligned data links are subjected to multimodal fusion processing to generate the multimodal fusion data accordingly, and each of the target data links is unique.

[0017] Furthermore, the step of performing multimodal fusion processing on the aligned data chain to generate the multimodal fusion data includes:

[0018] When the alignment data chain is acquired in real time, feature extraction processing is performed on the alignment data chain to extract corresponding feature information;

[0019] Performing a full scan on the characteristic information to detect in real time a number of target characteristic values ​​contained in the characteristic information;

[0020] A multimodal fusion process is performed on a plurality of the target feature values ​​to generate the multimodal fusion data accordingly, and each of the target feature values ​​is unique.

[0021] Furthermore, the step of performing multimodal fusion processing on the target feature values ​​to generate the multimodal fusion data includes:

[0022] When a plurality of target characteristic values ​​are obtained in real time, the plurality of target characteristic values ​​are screened to correspondingly screen out a maximum characteristic value and a minimum characteristic value;

[0023] The maximum eigenvalue, the minimum eigenvalue and the target eigenvalues ​​are normalized by a first preset algorithm to generate corresponding normalized data, and the multimodal fusion data is correspondingly generated according to the normalized data.

[0024] Furthermore, the step of generating the multimodal fusion data according to the normalized data includes:

[0025] When the normalized data is acquired in real time, a plurality of normalized features contained in the normalized data are detected in real time;

[0026] A corresponding target weight is added to each of the normalized features, and the multimodal fusion data is generated according to the target weight and the normalized features through a second preset algorithm.

[0027] Furthermore, the expression of the first preset algorithm is:

[0028]

[0029] Among them, X ij ' represents the normalized data, min(X i ) represents the minimum eigenvalue, max(X i ) represents the maximum eigenvalue, X ij represents the jth feature of the i-th data source.

[0030] Furthermore, the expression of the second preset algorithm is:

[0031]

[0032] Wherein, F represents the multimodal fusion data, w i represents the target weight, X i ' represents the normalized feature.

[0033] The second aspect of the embodiment of the present invention proposes:

[0034] A motor reverse working condition data processing system, wherein the system comprises:

[0035] A detection module, for detecting original driving parameters corresponding to the vehicle in real time when it is detected in real time that the vehicle is in a driving state, and preprocessing the original driving parameters to generate corresponding standard driving parameters;

[0036] A fusion module, used for detecting in real time a plurality of target data sets corresponding to the standard driving parameters, and performing multimodal fusion processing on the plurality of target data sets based on preset rules to generate corresponding multimodal fusion data;

[0037] An acquisition module, used to train a corresponding motor life prediction model according to the multimodal fusion data, and to acquire actual working parameters corresponding to the drive motor inside the vehicle in real time;

[0038] The output module is used to detect the working state and remaining use time corresponding to the drive motor in real time according to the actual working parameters through the motor life prediction model.

[0039] Furthermore, the fusion module is specifically used for:

[0040] When a plurality of target data sets are acquired in real time, a target data chain corresponding to each target data set is constructed respectively;

[0041] Performing time alignment processing on each of the target data links to synchronize each of the target data links to the same time axis and generating corresponding aligned data links;

[0042] The aligned data links are subjected to multimodal fusion processing to generate the multimodal fusion data accordingly, and each of the target data links is unique.

[0043] Furthermore, the fusion module is specifically used for:

[0044] When the alignment data chain is acquired in real time, feature extraction processing is performed on the alignment data chain to extract corresponding feature information;

[0045] Performing a full scan on the characteristic information to detect in real time a number of target characteristic values ​​contained in the characteristic information;

[0046] A multimodal fusion process is performed on a plurality of the target feature values ​​to generate the multimodal fusion data accordingly, and each of the target feature values ​​is unique.

[0047] Furthermore, the fusion module is specifically used for:

[0048] When a plurality of target characteristic values ​​are obtained in real time, the plurality of target characteristic values ​​are screened to correspondingly screen out a maximum characteristic value and a minimum characteristic value;

[0049] The maximum eigenvalue, the minimum eigenvalue and the target eigenvalues ​​are normalized by a first preset algorithm to generate corresponding normalized data, and the multimodal fusion data is correspondingly generated according to the normalized data.

[0050] Furthermore, the fusion module is specifically used for:

[0051] When the normalized data is acquired in real time, a plurality of normalized features contained in the normalized data are detected in real time;

[0052] A corresponding target weight is added to each of the normalized features, and the multimodal fusion data is generated according to the target weight and the normalized features through a second preset algorithm.

[0053] Furthermore, the expression of the first preset algorithm is:

[0054]

[0055] Among them, X ij ' represents the normalized data, min(X i ) represents the minimum eigenvalue, max(X i ) represents the maximum eigenvalue, X ij represents the jth feature of the i-th data source.

[0056] Furthermore, the expression of the second preset algorithm is:

[0057]

[0058] Wherein, F represents the multimodal fusion data, w i represents the target weight, X i ' represents the normalized feature.

[0059] The third aspect of the embodiment of the present invention proposes:

[0060] A computer comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the motor reverse working condition data processing method as described above when executing the computer program.

[0061] The fourth aspect of the embodiments of the present invention proposes:

[0062] A readable storage medium stores a computer program, wherein when the program is executed by a processor, the method for processing motor reverse working condition data as described above is implemented.

[0063] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A flowchart of a method for processing motor reverse operating condition data provided by the first embodiment of the present invention;

[0065] Figure 2This is a structural block diagram of a motor reverse operating condition data processing system provided in the third embodiment of the present invention.

[0066] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0067] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0068] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0069] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0070] See also Figure 1 , shown is the motor reverse operating condition data processing method provided by the first embodiment of the present invention. The motor reverse operating condition data processing method provided in this embodiment can objectively and comprehensively detect the working status and remaining usage time of the vehicle's internal drive motor, thereby correspondingly improving work efficiency.

[0071] Specifically, this embodiment provides:

[0072] A method for processing reverse working condition data of a motor, specifically comprising the following steps:

[0073] Step S10, when it is detected in real time that the vehicle is in a driving state, original driving parameters corresponding to the vehicle are detected in real time, and the original driving parameters are preprocessed to generate corresponding standard driving parameters;

[0074] Step S20, detecting in real time a plurality of target data sets corresponding to the standard driving parameters, and performing multimodal fusion processing on the plurality of target data sets based on preset rules to generate corresponding multimodal fusion data;

[0075] Step S30, training a corresponding motor life prediction model according to the multimodal fusion data, and collecting actual working parameters corresponding to the drive motor inside the vehicle in real time;

[0076] Step S40: Using the motor life prediction model to detect in real time the working state and remaining use time corresponding to the drive motor according to the actual working parameters.

[0077] Specifically, in this embodiment, it should be noted that in order to objectively and comprehensively complete the processing of the motor reverse operating condition data generated by the drive motor, it is necessary to first obtain the real-time status of the vehicle, that is, the real-time driving parameters of the vehicle. Based on this, the present invention will first collect the original driving parameters generated by the vehicle during its specific implementation. Specifically, since the original driving parameters contain redundant data and the data formats are various, it is necessary to further pre-process the current original driving parameters and generate corresponding standard driving parameters.

[0078] Furthermore, the current standard driving parameters are immediately scanned in their entirety, and a number of target data sets contained within the current standard driving parameters can be detected accordingly. Preferably, the present invention will immediately perform multimodal fusion processing on the current number of target data sets according to pre-set rules, and can further generate the required multimodal fusion data. Based on this, the required motor life prediction model can be further trained through the pre-set neural network and the current multimodal fusion data. Furthermore, in order to accurately predict the remaining working state of the current drive motor, it is necessary to further collect the actual working parameters corresponding to the current drive motor. On this basis, the motor life prediction model can finally directly detect the actual working state of the current drive motor and the corresponding remaining usage time according to the current actual working parameters, so that the user can take corresponding measures and improve the working efficiency of the motor at the same time.

[0079] Second embodiment

[0080] Furthermore, the step of performing multimodal fusion processing on the target data sets based on preset rules to generate corresponding multimodal fusion data includes:

[0081] When a plurality of target data sets are acquired in real time, a target data chain corresponding to each target data set is constructed respectively;

[0082] Performing time alignment processing on each of the target data links to synchronize each of the target data links to the same time axis and generating corresponding aligned data links;

[0083] The aligned data links are subjected to multimodal fusion processing to generate the multimodal fusion data accordingly, and each of the target data links is unique.

[0084] Furthermore, the step of performing multimodal fusion processing on the aligned data chain to generate the multimodal fusion data includes:

[0085] When the alignment data chain is acquired in real time, feature extraction processing is performed on the alignment data chain to extract corresponding feature information;

[0086] Performing a full scan on the characteristic information to detect in real time a number of target characteristic values ​​contained in the characteristic information;

[0087] A multimodal fusion process is performed on a plurality of the target feature values ​​to generate the multimodal fusion data accordingly, and each of the target feature values ​​is unique.

[0088] Furthermore, the step of performing multimodal fusion processing on the target feature values ​​to generate the multimodal fusion data includes:

[0089] When a plurality of target characteristic values ​​are obtained in real time, the plurality of target characteristic values ​​are screened to correspondingly screen out a maximum characteristic value and a minimum characteristic value;

[0090] The maximum eigenvalue, the minimum eigenvalue and the target eigenvalues ​​are normalized by a first preset algorithm to generate corresponding normalized data, and the multimodal fusion data is correspondingly generated according to the normalized data.

[0091] Furthermore, the step of generating the multimodal fusion data according to the normalized data includes:

[0092] When the normalized data is acquired in real time, a plurality of normalized features contained in the normalized data are detected in real time;

[0093] A corresponding target weight is added to each of the normalized features, and the multimodal fusion data is generated according to the target weight and the normalized features through a second preset algorithm.

[0094] Furthermore, the expression of the first preset algorithm is:

[0095]

[0096] Among them, X ij ' represents the normalized data, min(X i ) represents the minimum eigenvalue, max(X i ) represents the maximum eigenvalue, Xij represents the jth feature of the i-th data source.

[0097] Furthermore, the expression of the second preset algorithm is:

[0098]

[0099] Wherein, F represents the multimodal fusion data, w i represents the target weight, X i ' represents the normalized feature.

[0100] In addition, in this embodiment, it is also necessary to explain that after obtaining the required several target data sets in real time through the above steps, in order to be able to quickly and effectively fuse the required multimodal fusion data, preferably, the present invention will first construct a target data chain corresponding to each current target data set, and further, in order to facilitate shortening the subsequent fusion time, the present invention will further perform time alignment processing on each current target data chain on the same time axis, and synchronously generate the required aligned data chain. Based on this, feature extraction processing is immediately performed on the current aligned data chain, and the required feature information can be correspondingly extracted. At the same time, the current feature information is further fully scanned, and several target feature values ​​contained in the current feature information can be further detected.

[0101] Furthermore, since the current target eigenvalues ​​contain specific information, it is only necessary to perform multimodal fusion processing on the current target eigenvalues. Preferably, the present invention will first screen out the maximum eigenvalue and the minimum eigenvalue contained in the current target eigenvalues, and further perform corresponding normalization processing on the current maximum eigenvalue, the minimum eigenvalue and the several target eigenvalues ​​through the above-mentioned first preset algorithm, and can further obtain the required normalized data. On this basis, it is finally necessary to input the current normalized data into the above-mentioned second preset algorithm, so that the current second preset algorithm can finally output the required multimodal fusion data for subsequent processing.

[0102] See also Figure 2 , the third embodiment of the present invention provides:

[0103] A motor reverse working condition data processing system, wherein the system comprises:

[0104] A detection module, for detecting original driving parameters corresponding to the vehicle in real time when it is detected in real time that the vehicle is in a driving state, and preprocessing the original driving parameters to generate corresponding standard driving parameters;

[0105] A fusion module, used for detecting in real time a plurality of target data sets corresponding to the standard driving parameters, and performing multimodal fusion processing on the plurality of target data sets based on preset rules to generate corresponding multimodal fusion data;

[0106] An acquisition module, used to train a corresponding motor life prediction model according to the multimodal fusion data, and to acquire actual working parameters corresponding to the drive motor inside the vehicle in real time;

[0107] The output module is used to detect the working state and remaining use time corresponding to the drive motor in real time according to the actual working parameters through the motor life prediction model.

[0108] Furthermore, the fusion module is specifically used for:

[0109] When a plurality of target data sets are acquired in real time, a target data chain corresponding to each target data set is constructed respectively;

[0110] Performing time alignment processing on each of the target data links to synchronize each of the target data links to the same time axis and generating corresponding aligned data links;

[0111] The aligned data links are subjected to multimodal fusion processing to generate the multimodal fusion data accordingly, and each of the target data links is unique.

[0112] Furthermore, the fusion module is specifically used for:

[0113] When the alignment data chain is acquired in real time, feature extraction processing is performed on the alignment data chain to extract corresponding feature information;

[0114] Performing a full scan on the characteristic information to detect in real time a number of target characteristic values ​​contained in the characteristic information;

[0115] A multimodal fusion process is performed on a plurality of the target feature values ​​to generate the multimodal fusion data accordingly, and each of the target feature values ​​is unique.

[0116] Furthermore, the fusion module is specifically used for:

[0117] When a plurality of target characteristic values ​​are obtained in real time, the plurality of target characteristic values ​​are screened to correspondingly screen out a maximum characteristic value and a minimum characteristic value;

[0118] The maximum eigenvalue, the minimum eigenvalue and the target eigenvalues ​​are normalized by a first preset algorithm to generate corresponding normalized data, and the multimodal fusion data is correspondingly generated according to the normalized data.

[0119] Furthermore, the fusion module is specifically used for:

[0120] When the normalized data is acquired in real time, a plurality of normalized features contained in the normalized data are detected in real time;

[0121] A corresponding target weight is added to each of the normalized features, and the multimodal fusion data is generated according to the target weight and the normalized features through a second preset algorithm.

[0122] Furthermore, the expression of the first preset algorithm is:

[0123]

[0124] Among them, X ij ' represents the normalized data, min(X i ) represents the minimum eigenvalue, max(X i ) represents the maximum eigenvalue, X ij represents the jth feature of the i-th data source.

[0125] Furthermore, the expression of the second preset algorithm is:

[0126]

[0127] Wherein, F represents the multimodal fusion data, w i represents the target weight, X i ' represents the normalized feature.

[0128] A fourth embodiment of the present invention provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the motor reverse operating condition data processing method as described above when executing the computer program.

[0129] A fifth embodiment of the present invention provides a readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method for processing motor reverse operating condition data as described above is implemented.

[0130] In summary, the motor reverse operating condition data processing method and system provided in the above embodiments of the present invention can objectively and comprehensively detect the working status and remaining usage time of the current internal drive motor of the vehicle, thereby correspondingly improving work efficiency.

[0131] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0132] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0133] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0134] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0135] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0136] The above-described embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A method for processing motor reverse working condition data, characterized in that: The method comprises: When it is detected in real time that the vehicle is in a driving state, original driving parameters corresponding to the vehicle are detected in real time, and the original driving parameters are preprocessed to generate corresponding standard driving parameters; Detecting in real time a number of target data sets corresponding to the standard driving parameters, and performing multimodal fusion processing on the target data sets based on preset rules to generate corresponding multimodal fusion data; Training a corresponding motor life prediction model according to the multimodal fusion data, and collecting actual working parameters corresponding to the drive motor inside the vehicle in real time; The motor life prediction model detects the working state and remaining use time corresponding to the drive motor in real time according to the actual working parameters.

2. The method for processing motor reverse operating condition data according to claim 1, characterized in that: The step of performing multimodal fusion processing on the target data sets based on preset rules to generate corresponding multimodal fusion data includes: When a plurality of target data sets are acquired in real time, a target data chain corresponding to each target data set is constructed respectively; Performing time alignment processing on each of the target data links to synchronize each of the target data links to the same time axis and generating corresponding aligned data links; The aligned data links are subjected to multimodal fusion processing to generate the multimodal fusion data accordingly, and each of the target data links is unique.

3. The method for processing motor reverse operating condition data according to claim 2, characterized in that: The step of performing multimodal fusion processing on the aligned data chain to correspondingly generate the multimodal fusion data includes: When the alignment data chain is acquired in real time, feature extraction processing is performed on the alignment data chain to extract corresponding feature information; Performing a full scan on the characteristic information to detect in real time a number of target characteristic values ​​contained in the characteristic information; A multimodal fusion process is performed on a plurality of the target feature values ​​to generate the multimodal fusion data accordingly, and each of the target feature values ​​is unique.

4. The method for processing motor reverse operating condition data according to claim 3, characterized in that: The step of performing multimodal fusion processing on the target feature values ​​to generate the multimodal fusion data accordingly includes: When a plurality of target characteristic values ​​are obtained in real time, the plurality of target characteristic values ​​are screened to correspondingly screen out a maximum characteristic value and a minimum characteristic value; The maximum eigenvalue, the minimum eigenvalue and the target eigenvalues ​​are normalized by a first preset algorithm to generate corresponding normalized data, and the multimodal fusion data is correspondingly generated according to the normalized data.

5. The method for processing motor reverse operating condition data according to claim 4, characterized in that: The step of generating the multimodal fusion data according to the normalized data includes: When the normalized data is acquired in real time, a plurality of normalized features contained in the normalized data are detected in real time; A corresponding target weight is added to each of the normalized features, and the multimodal fusion data is generated according to the target weight and the normalized features through a second preset algorithm.

6. The method for processing motor reverse operating condition data according to claim 5, characterized in that: The expression of the first preset algorithm is: Among them, X ij ' represents the normalized data, min(X i ) represents the minimum eigenvalue, max(X i ) represents the maximum eigenvalue, X ij represents the jth feature of the i-th data source.

7. The method for processing motor reverse operating condition data according to claim 6, characterized in that: The expression of the second preset algorithm is: Wherein, F represents the multimodal fusion data, w i represents the target weight, X i ' represents the normalized feature.

8. A motor reverse working condition data processing system, wherein: The system comprises: A detection module, for detecting original driving parameters corresponding to the vehicle in real time when it is detected in real time that the vehicle is in a driving state, and preprocessing the original driving parameters to generate corresponding standard driving parameters; A fusion module, used for detecting in real time a plurality of target data sets corresponding to the standard driving parameters, and performing multimodal fusion processing on the plurality of target data sets based on preset rules to generate corresponding multimodal fusion data; An acquisition module, used to train a corresponding motor life prediction model according to the multimodal fusion data, and to acquire actual working parameters corresponding to the drive motor inside the vehicle in real time; The output module is used to detect the working state and remaining use time corresponding to the drive motor in real time according to the actual working parameters through the motor life prediction model.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for processing motor reverse operating condition data as described in any one of claims 1 to 7 is implemented.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for processing motor reverse operating condition data as described in any one of claims 1 to 7 is implemented.

Images