Motor operation abnormal monitoring method and system for electric tricycle

Abstract

The present invention discloses a method and system for monitoring abnormal operation of an electric motor for an electric tricycle, relating to the technical field of electric transportation means. The method includes: by setting an action instruction analysis module between a starting device and the electric motor, the module includes a plurality of monitoring and analysis units, and each unit corresponds to a set of action instructions. By obtaining the action instructions of the electric tricycle in real time, activating the corresponding monitoring unit to extract real-time action parameters, and performing load state prediction. By using multi-source sensing devices to obtain the state data of the electric motor and associated components, combining the load state prediction and the state data to perform abnormal risk assessment, and dynamically adjusting the operation parameters of the electric motor according to the assessment results. It solves the technical problem in the prior art that the mutual influence between the electric motor and other components is ignored, resulting in the inability to accurately predict and monitor the abnormality of the electric motor of the electric tricycle under complex load changes, and achieves the technical effect of accurately monitoring and warning the abnormality of the electric motor of the electric tricycle.

Description

Technical Field

[0001] This application relates to the technical field of electric vehicles, and particularly to a method and system for monitoring abnormal operation of an electric motor for an electric tricycle. Background Art

[0002] With the popularization of electric tricycles, their motor systems, as core components, directly affect the performance and safety of the vehicles. Electric tricycles usually face frequent load changes. Especially in urban traffic, frequent starts, stops, accelerations, and decelerations can cause problems such as motor overload and overheating, and even damage the motor. However, existing motor monitoring systems often ignore the mutual influence between the motor and other associated components (such as batteries, controllers, braking systems, etc.), making it difficult to accurately identify abnormal conditions of the motor under complex load changes and unable to perform real-time and accurate prediction on the motor. The integrated design of electric tricycles makes motor abnormalities often closely related to other systems. Existing technologies cannot fully consider these factors, resulting in poor abnormal detection effects. Therefore, there is an urgent need for a monitoring method that can real-time monitor the load status of the motor and comprehensively evaluate it in combination with the status of associated components to improve the safety and reliability of the electric tricycle motor.

[0003] In the current related technologies, there are technical problems of ignoring the mutual influence between the motor and other components, resulting in the inability to accurately predict and monitor the abnormalities of the electric tricycle motor under complex load changes. Summary of the Invention

[0004] This application provides a method and system for monitoring abnormal operation of an electric motor for an electric tricycle, which solves the technical problems in the prior art that the mutual influence between the motor and other components is ignored, resulting in the inability to accurately predict and monitor the abnormalities of the electric tricycle motor under complex load changes.

[0005] This application provides a method for monitoring abnormal operation of an electric motor for an electric tricycle, including:

[0006] Establish an action instruction analysis module between the starting device and the motor. The action instruction analysis module includes multiple monitoring and analysis units, and each monitoring and analysis unit corresponds to a set of action instructions; obtain the real-time action instructions of the electric tricycle, and based on the real-time action instructions, activate the corresponding target monitoring and analysis unit to extract associated parameters and obtain real-time action parameters; based on the real-time action parameters, perform load status prediction through the target monitoring and analysis unit to obtain a motor load status prediction sequence; obtain multi-source motor status data and associated component status data through multi-source sensing devices; combine the motor load status prediction sequence, the multi-source motor status data, and the associated component status data to perform motor abnormal risk assessment, and dynamically adjust the motor operation parameters according to the risk assessment results.

[0007] The present application also provides a motor operation abnormal monitoring system for an electric tricycle, including:

[0008] An action instruction analysis module establishment module, which is used to establish an action instruction analysis module between the starting device and the motor. The action instruction analysis module includes a plurality of monitoring and analysis units, and each monitoring and analysis unit corresponds to a set of action instructions; an associated parameter extraction module, which is used to obtain the real-time action instructions of the electric tricycle, and according to the real-time action instructions, activate the corresponding target monitoring and analysis unit to extract associated parameters and obtain real-time action parameters; a load state prediction module, which is used to predict the load state through the target monitoring and analysis unit based on the real-time action parameters to obtain a motor load state prediction sequence; a state data acquisition module, which is used to acquire multi-source motor state data and associated component state data through multi-source sensing devices; a motor abnormal risk assessment module, which is used to combine the motor load state prediction sequence, the multi-source motor state data and the associated component state data to conduct a motor abnormal risk assessment, and dynamically adjust the motor operation parameters according to the risk assessment result.

[0009] It is intended to propose a motor operation abnormal monitoring method and system for an electric tricycle according to the present application. First, an action instruction analysis module is set between the starting device and the motor. This module includes a plurality of monitoring and analysis units, and each unit corresponds to a set of action instructions. By obtaining the action instructions of the electric tricycle in real time, the corresponding monitoring unit is activated to extract real-time action parameters and conduct a load state prediction. The state data of the motor and associated components are obtained through multi-source sensing devices, and an abnormal risk assessment is conducted by combining the load state prediction and the state data. The motor operation parameters are dynamically adjusted according to the assessment result, achieving the technical effect of accurately monitoring and warning the abnormal situation of the electric tricycle motor under complex load changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0011] Figure 1 It is a schematic flowchart of a motor operation abnormal monitoring method for an electric tricycle provided by an embodiment of the present application.

[0012] Figure 2It is a schematic structural diagram of a motor operation abnormal monitoring system for an electric tricycle provided by an embodiment of the present application.

[0013] Explanation of reference numerals: Action instruction analysis module establishment module 10, associated parameter extraction module 20, load status prediction module 30, status data acquisition module 40, motor abnormal risk assessment module 50. Detailed implementation manners

[0014] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0015] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0016] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first\second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0017] An embodiment of the present application provides a method for monitoring abnormal operation of a motor for an electric tricycle, as Figure 1 shown, the method includes:

[0018] Step S100: Establish an action instruction analysis module between the starting device and the motor. The action instruction analysis module includes multiple monitoring and analysis units, and each monitoring and analysis unit corresponds to a set of action instructions. Specifically, an action instruction analysis module is constructed between the starting device and the motor of the electric tricycle. The module consists of multiple monitoring and analysis units. Corresponding units are established for common action instructions such as acceleration, braking, and steering to analyze the impact of each instruction on the motor. For example, when accelerating, analyze the changes in motor current, voltage, and heat; when braking, analyze the braking feedback, the rate of speed reduction, and the changes in internal magnetic field current; when steering, analyze the wheel speed difference and torque distribution. Collect actual usage data to statistically analyze the daily usage frequency of different instructions. Increase the weight of the monitoring and analysis units for high-frequency action instructions such as acceleration and braking, and use more relevant scenario data to train the model to accurately identify the impacts and detect abnormalities. Also, prioritize ensuring the integrity and timeliness of data during data processing, storage, and transmission to improve the safety and stability of the motor operation system.

[0019] In a possible implementation manner, an action instruction analysis module is established between the starting device and the motor. The action instruction analysis module includes multiple monitoring and analysis units, and each monitoring and analysis unit corresponds to a set of action instructions. Step S100 further includes step S110: Obtain multiple reference action instructions according to the basic information of the target electric tricycle. The reference action instructions can be single action instructions or combined action instructions. Specifically, analyze the basic information of the target electric tricycle. The basic information covers aspects such as the vehicle model, usage, design parameters (such as motor power, battery capacity, vehicle self-weight, etc.), and the characteristics of the adapted control system. For example, if the target electric tricycle is a model used for heavy-load cargo transportation with a large motor power, when obtaining the reference action instructions, focus on analyzing the action instructions related to heavy-load transportation, such as frequent acceleration starts and slow and stable braking. Through comprehensive analysis of the basic information, accurately determine multiple reference action instructions. The instructions may be simple single action instructions such as acceleration, braking, and steering, or combined action instructions such as accelerating and steering simultaneously to comprehensively cover various operation situations that may occur during the actual operation of the vehicle.

[0020] Step S120: Based on the multiple reference action instructions, extract key monitoring indicators and establish multiple monitoring and analysis units respectively. Specifically, based on the obtained multiple reference action instructions, start to extract key monitoring indicators. For the acceleration instruction, the key monitoring indicators include the current rising rate of the motor, the voltage fluctuation amplitude, and the acceleration value of the rotor, etc., because these indicators can intuitively reflect the power output characteristics and operation stability of the motor during the acceleration process; for the braking instruction, the stroke depth of the brake pedal, the pressure change of the braking system, the back electromotive force magnitude of the motor, and the deceleration of the wheel, etc. become the key monitoring indicators, which help to judge the braking force, effect and the feedback impact on the motor. In terms of the steering instruction, the steering angle size of the steering wheel, the steering speed, the rotational speed difference between the left and right wheels, and the torque distribution ratio of the motor on both wheels are important monitoring indicators, which directly affect the evaluation of the vehicle steering flexibility, accuracy and the collaborative working ability of the motor during the steering process. According to the extracted key monitoring indicators, establish multiple monitoring and analysis units respectively. Each unit focuses on the collection, analysis and processing of data related to specific reference action instructions, thus laying a solid foundation for the subsequent accurate monitoring of the motor operation state under different actions.

[0021] Step S130: Based on the daily operation records of the target user, conduct user behavior analysis and generate a personalized correction plan. Specifically, collect the daily operation records of the target user. The records can be obtained through the sensors and data recording systems built into the vehicle and contain all the operation behavior data of the user on the electric tricycle over a period of time (such as one month or longer), such as the action instructions, operation time, operation frequency of each operation, and the vehicle driving environment information during operation (such as road slope, road surface condition, etc.). Conduct user behavior analysis on the daily operation records. Use the clustering analysis algorithm to classify the user's operation behaviors according to similarity and find out the typical operation patterns of the user in different driving scenarios (such as urban roads, rural roads, slope sections, etc.); use the time series analysis method to study the change law of the user's operation frequency and determine the peak and trough periods of the user's operations within a day or a week; analyze the correlation relationship between different action instructions through association rule mining technology, such as whether there are certain specific action combinations that frequently appear in the user's operations, etc. Generate a personalized correction plan according to the results of the user behavior analysis. If the analysis finds that the user frequently performs sudden acceleration and sudden braking operations in urban congestion conditions, then in the personalized correction plan, special parameter adjustments will be made for the monitoring and analysis units corresponding to acceleration and braking. For example, lower the sensitivity threshold of the acceleration instruction monitoring and analysis unit for the rapid rise of current because in this case of frequent sudden acceleration, the rapid rise of current may be part of normal operation rather than an abnormal situation; at the same time, increase the monitoring frequency of the braking instruction monitoring and analysis unit for the pressure change of the braking system to more timely detect abnormal braking situations, such as pressure leakage in the braking system. In addition, if it is found that the user often uses a specific action combination (such as accelerating and steering simultaneously) on a specific section (such as a slope section), then in the personalized correction plan, optimize the configuration of the monitoring and analysis unit for the relevant combined action instructions, such as increasing the monitoring index weight for the rationality of torque distribution of the motor under the combined action, etc., to better adapt to the actual operation habits and needs of the target user.

[0022] Step S140: Use the personalized correction scheme to initialize and configure the multiple monitoring and analysis units, and connect them to generate the action instruction analysis module. Specifically, use the generated personalized correction scheme to initialize and configure the multiple monitoring and analysis units established previously. Apply each parameter setting in the correction scheme (such as the threshold of the monitoring index, the data acquisition frequency, the weight of the data processing algorithm, etc.) to the corresponding monitoring and analysis unit one by one, so that each unit can work according to personalized requirements. Then, connect and integrate the initialized monitoring and analysis units to build a complete action instruction analysis module. During the connection process, ensure that the data transmission channels between each unit are unobstructed, enabling real-time data sharing and interaction. For example, when the acceleration instruction monitoring and analysis unit detects an abnormal current change, it can promptly transmit the relevant data to other associated monitoring and analysis units (such as the brake instruction monitoring and analysis unit and the steering instruction monitoring and analysis unit) to jointly determine whether this abnormal situation will affect the execution of other action instructions, thereby achieving comprehensive, accurate, and personalized monitoring and analysis of the operating state of the electric tricycle motor, effectively improving the safety and reliability of vehicle operation, and better adapting to the driving styles and usage requirements of different users.

[0023] In a possible implementation manner, according to the daily operation records of the target user, perform user behavior analysis to generate a personalized correction scheme. Step S130 further includes step S131: Based on the daily operation records of the target user, extract multiple sample operation records of multiple action instructions respectively. Specifically, analyze the daily operation record data of the target user, which details every operation detail during the actual use of the electric tricycle, including information such as the time when the operation occurs and the specific action instruction of the operation. For different action instructions, such as acceleration, braking, steering, etc., extract multiple sample operation records respectively. For example, for the acceleration action instruction, screen out all operation events related to acceleration from the daily operation records and organize them into a sample operation record set of the acceleration action. The sample operation records cover acceleration operation situations under different scenarios, road conditions, and driving requirements, providing a data basis for subsequent in-depth analysis.

[0024] Step S132: Perform multi - variable clustering on the multiple sample operation records to obtain the multi - variable action features of the multiple action instructions. The multi - variable action features include action type, action occurrence duration, and action occurrence frequency. Specifically, apply the multi - variable clustering algorithm to the extracted multiple sample operation records. Multi - variable clustering is a method of classifying and aggregating data based on features in multiple dimensions. During this process, use action type, action occurrence duration, action occurrence frequency, etc. as the key dimensions for clustering. For example, initially divide all the sample operation records of acceleration actions according to the length of the action occurrence duration, and group those with similar durations into one category; then further subdivide according to the action occurrence frequency, and aggregate the sample operation records of acceleration actions with similar occurrence frequencies within a specific time period. Through the multi - variable clustering process, obtain the multi - variable action features of each action instruction. Taking the braking action as an example, after clustering, it is possible to determine multi - variable action feature groups such as emergency braking (action type), short duration (action occurrence duration), low frequency (action occurrence frequency), as well as other feature groups such as gentle braking, long duration, and high frequency. The feature groups comprehensively describe the manifestation forms of different types of braking actions in the user's daily operations.

[0025] Step S133: Conduct a contribution analysis on the multi - variable action features and, based on the results of the contribution analysis, configure feature weights for the multi - variable action features. Specifically, conduct a contribution analysis on the obtained multi - variable action features. The analysis aims to determine the influence degree of each feature on the motor operating state and the overall vehicle performance. For example, for the acceleration action, the action type (such as gentle acceleration or emergency acceleration) has a relatively large impact on the load change of the motor, and its contribution degree is relatively high; if the action occurrence frequency is too high, it will cause the motor to frequently switch to a high - load state, which has an important impact on the heat dissipation and durability of the motor, and its contribution degree cannot be ignored; the action occurrence duration is closely related to the energy consumption and heat generation of the motor during an acceleration process. According to the results of the contribution analysis, configure corresponding feature weights for each multi - variable action feature. For example, determine the feature weight of the emergency acceleration action type to be 0.4, the feature weight of the high frequency to be 0.3, and the feature weight of the long duration to be 0.3. The weights reflect the relative importance of each feature when evaluating the impact of the acceleration action on the motor.

[0026] Step S134: Based on the multi - dimensional action features and the corresponding feature weights, conduct a personalized impact analysis on the multiple action instructions, and generate the personalized correction plan according to the impact analysis results. The personalized correction plan includes correction strategies for the monitoring and analysis units corresponding to each action instruction. Specifically, based on the multi - dimensional action features and the corresponding feature weights, conduct a personalized impact analysis on the multiple action instructions. Taking the steering action instruction as an example, if its multi - dimensional action features are large - angle steering (action type), short duration, and high frequency, and the corresponding feature weights are 0.5, 0.2, and 0.3 respectively, the comprehensive impact value of this steering action instruction in the user's daily operations can be calculated according to the information. Through analysis, comprehensively understand the specific impact of each action instruction on the motor operation under the user's personalized operation habits. Then, generate a personalized correction plan according to the impact analysis results. For the above - mentioned steering action instruction, if it is found through analysis that its high - frequency large - angle steering will pose a greater risk of wear to the motor shafting, then in the personalized correction plan, for the monitoring and analysis unit corresponding to the steering instruction, the sensitivity of the torque and temperature monitoring of the motor shafting will be increased, and the data acquisition frequency will be adjusted so that it can more timely detect potential abnormalities; at the same time, optimize the data - processing algorithm in the monitoring and analysis unit to conduct a more in - depth analysis of the data related to large - angle steering, so as to give early warnings of possible faults, thereby ensuring that the electric tricycle can still maintain a good motor operation state and vehicle performance under the user's personalized driving style, and improving the safety and reliability of the vehicle.

[0027] Step S200: Obtain the real - time action instructions of the electric tricycle, and according to the real - time action instructions, activate the corresponding target monitoring and analysis unit to extract associated parameters and obtain real - time action parameters. Specifically, in the control system of the electric tricycle, set up an instruction acquisition module to obtain action instructions in real - time. The module is closely connected to the operating components and can convert the driver's operations into digital instruction signals. For example, when stepping on the accelerator pedal, it can receive an acceleration instruction signal. After obtaining the instruction, activate the corresponding monitoring and analysis unit according to the preset corresponding relationship. For example, when receiving an acceleration instruction, activate its corresponding unit. Then, this unit obtains data from multiple sources such as motor current, voltage sensors, speed sensors, and load sensors, and through data cleaning, conversion, and fusion, extracts and integrates the associated parameters, and finally obtains real - time action parameters that can comprehensively and accurately reflect the actual operation state of the motor when executing real - time action instructions, providing a key data basis for subsequent work and ensuring the safe and stable operation of the vehicle.

[0028] Step S300, based on the real-time action parameters, the load state is predicted by the target monitoring and analysis unit to obtain a motor load state prediction sequence. Specifically, the target monitoring and analysis unit is embedded with a load state prediction model constructed based on a large number of real-time action parameters and motor load state information under different road conditions, loads, and driving styles. After obtaining the real-time action parameters, the model is input into the model. The model first parses and extracts key features closely related to the load, such as the current change rate during acceleration, the speed acceleration, and the load. Then, the built-in algorithm is used to dynamically predict the load state changes of the motor in the future based on the current parameters and similar historical situations. By continuously predicting multiple time nodes, a motor load state prediction sequence containing information such as load size and change trend is obtained, which provides a forward-looking basis for adjusting motor parameters in advance, optimizing vehicle performance, and preventing abnormalities, and ensures stable operation of the motor and safe driving of the vehicle.

[0029] In a possible implementation, based on the real-time action parameters, the load state prediction is performed by the target monitoring and analysis unit to obtain a motor load state prediction sequence, and step S300 further includes step S310, wherein the target monitoring and analysis unit is embedded with a load state prediction model, and the load state prediction model contains a user habit index for real-time action instructions. Specifically, the load state prediction model embedded in the target monitoring and analysis unit. In addition to the conventional prediction algorithm based on physical principles and a large amount of experimental data, the load state prediction model also integrates the user habit index for real-time action instructions. The user habit index is obtained by deeply analyzing the operation records of the target user over a period of time (for example, the past month). For example, for acceleration action instructions, if the user often uses the method of quickly and violently stepping on the accelerator pedal, the acceleration action instruction user habit index in the model will reflect the characteristics of the aggressive operation style; on the contrary, if the user always steps on the accelerator pedal slowly and steadily, the index will reflect this more conservative driving habit.

[0030] Step S320, according to the user habit index, analyze and obtain the duration of the real-time action instruction. Specifically, the duration of the real-time action instruction is analyzed and obtained according to the user habit index embedded in the model. Taking the braking action instruction as an example, if the user habit index shows that the user tends to slow down when braking, based on the index and some initial parameters at the beginning of the current braking action (such as the initial stepping force of the brake pedal, the initial speed of the vehicle, etc.), the model calculates the duration of the braking action instruction through pre-established associations and algorithms. Because the user's habits will largely determine the time characteristics of their operating actions, for example, users who are accustomed to slow deceleration will usually take a long time to completely stop the vehicle from the beginning of their braking action, while users who are accustomed to sudden braking will have a relatively short duration of braking action.

[0031] Step S330: Take the real-time action parameters and the duration as inputs, and through the load status prediction model, perform dynamic prediction of the load status to obtain the motor load status prediction sequence. Specifically, take the real-time action parameters and the derived duration as inputs and input them into the load status prediction model for dynamic prediction of the load status. For example, when receiving the real-time action parameters of the acceleration action (such as the real-time current, voltage, and speed of the motor) and the possible duration of the acceleration action analyzed based on the user habit index, the model will conduct comprehensive analysis. Based on the previous similar acceleration scenario data (which have been classified and labeled according to user habits), the model will predict the change of the motor load during the entire acceleration process. For instance, at the initial stage of acceleration, the motor load will increase rapidly as the speed rises, but due to the user's habit of smooth acceleration, the rate of load increase will be relatively moderate; as the acceleration continues, the load will gradually reach a peak and then tend to be stable as the vehicle speed approaches the target speed. By performing such prediction calculations at multiple future time nodes, the motor load status prediction sequence is finally obtained. The sequence details the estimated load status of the motor at different future moments, providing a crucial basis for subsequent motor operation control, fault prevention, etc., and can effectively ensure the stable and efficient operation of the electric tricycle motor under the premise of conforming to the user's driving habits.

[0032] Step S400: Through multi-source sensing devices, obtain multi-source motor status data and associated component status data. Specifically, according to the structure of the electric tricycle and the distribution of the motor and its associated components, reasonably deploy multi-source sensing devices. Install current, voltage, and temperature sensors on the motor to collect the current, voltage, and temperature data during its operation. The data can reflect the motor load, power supply stability, and heat dissipation situation, and after integration, form multi-source motor status data; install temperature sensors near components adjacent to the motor and likely to cause interference, such as the controller, and install vibration sensors on the drive chain or drive shaft to collect their temperature and vibration data. When the controller is overheated or the transmission components vibrate abnormally, it will affect the motor operation temperature and stability. Integrate the associated component status data and combine it with the motor status data, which can provide strong support for motor abnormal risk assessment and fault prevention, and ensure the stable and reliable operation of the motor and the power system.

[0033] In a possible implementation, multi-source motor status data and associated component status data are obtained through a multi-source sensing device. Step S400 further includes step S410 of obtaining the structural layout information and braking principle data of the electric tricycle. Specifically, the structural layout information of the electric tricycle is comprehensively obtained by referring to the design drawings, technical manuals of the electric tricycle and communicating with the vehicle manufacturer, etc., including the specific position of the motor in the vehicle, the layout of transmission components (such as drive shafts, chains, etc.) connected to the motor, the installation position of the battery pack, and the distribution of various controllers. At the same time, the braking principle data of the electric tricycle is deeply studied to understand the type of braking system it adopts (such as mechanical braking, hydraulic braking or electric braking), the force transmission path during braking, the working mode of the brake pads and brake discs, and the cooperative control logic between the braking system and the motor. For example, for an electric tricycle with hydraulic braking and energy recovery function, it is necessary to clarify how the motor switches to the power generation mode during braking, and how the hydraulic system cooperates with the regenerative braking of the motor to achieve smooth deceleration of the vehicle.

[0034] Step S420, based on the structural layout information and braking principle data, perform a correlation analysis on the associated components of the motor, and extract the braking associated components and interference associated components according to the correlation analysis results. Specifically, based on the obtained structural layout information and braking principle data, a correlation analysis on the associated components of the motor is performed. From the perspective of the structural layout, the reducer directly connected to the motor through the drive shaft can be regarded as a braking associated component, because when the vehicle brakes, the reverse resistance of the motor will be transmitted through the reducer, and parameters such as the gear ratio of the reducer will also affect the load characteristics of the motor during braking. From the aspect of the braking principle analysis, the braking controller is also an important braking associated component, which is responsible for coordinating the intervention degree of the regenerative braking and mechanical braking of the motor according to the braking operation instructions of the driver. For the interference associated components, considering the spatial position factors, such as the electronic control unit installed near the motor, since it generates heat during operation and is close to the motor, its temperature rise will interfere with the heat dissipation environment of the motor, thereby affecting the operating temperature of the motor; another example is some auxiliary equipment sharing the installation bracket with the motor, and its vibration during operation may be transmitted to the motor, affecting the stability of the motor and the force condition of the shafting. Through analysis, the braking associated components and interference associated components are accurately extracted.

[0035] Step S430: Deploy multi-source sensing devices to obtain the status data of the braking-related components and interference-related components, and form the status data of the related components. Specifically, based on the extracted braking-related components and interference-related components, reasonably deploy multi-source sensing devices. For the braking-related components, install torque sensors on the input shaft and output shaft of the reducer to monitor the torque change during braking, so as to understand the load change of the motor; install signal monitoring sensors on the brake controller to obtain information such as the intensity and frequency of the brake control signal in real time. For the interference-related components, install temperature sensors on the outer shell of the electronic control unit near the motor to accurately measure its working temperature; install vibration sensors on the auxiliary equipment brackets where there may be vibration transmission with the motor to monitor its vibration amplitude and frequency. Through the deployed multi-source sensing devices, continuously collect the status data of the braking-related components and interference-related components. Integrate the data from torque sensors, signal monitoring sensors, temperature sensors, vibration sensors, etc. to form the status data of the related components. The data can comprehensively reflect the working status of the components associated with the motor during the operation of the electric tricycle, providing a rich and crucial data basis for subsequent evaluation of the motor operating environment, prediction of possible abnormalities of the motor, and formulation of corresponding control strategies, which helps to ensure the stable and efficient operation of the electric tricycle motor and the safety performance of the entire vehicle.

[0036] Step S500: Combine the motor load status prediction sequence, the multi-source motor status data, and the status data of the related components to conduct an abnormal risk assessment of the motor, and dynamically adjust the motor operating parameters according to the risk assessment results. Specifically, first summarize the motor load status prediction sequence, the multi-source motor status data, and the status data of the related components, analyze the impact of the predicted load status and related components on the motor and generate an impact coefficient, and accordingly construct an abnormal risk assessment model for the motor. Incorporate the weights determined by the motor characteristics, failure cases, and experience into the model to calculate the evaluation value. Classify it into low, medium, and high risk states. When the risk is low, slightly adjust the input voltage and optimize the control algorithm to improve efficiency and reduce energy consumption. When the risk is medium, if the vibration of the transmission component in the related component status is large, reduce the power and increase heat dissipation according to the motor temperature. When the risk is high, significantly reduce the power or even stop the motor and trigger an alarm for inspection and repair. Thus, dynamically adjusting the motor parameters according to the evaluation results can prevent failures, improve reliability and safety, and ensure the normal operation of the vehicle.

[0037] In a possible implementation manner, in combination with the motor load state prediction sequence, the multi-source motor state data, and the associated component state data, a motor abnormal risk assessment is performed, and according to the risk assessment result, the motor operation parameters are dynamically adjusted. Step S500 further includes step S510 of preprocessing the motor load state prediction sequence, the multi-source motor state data, and the associated component state data to obtain a standard state data set. Specifically, comprehensive data preprocessing work is carried out for the motor load state prediction sequence, the multi-source motor state data, and the associated component state data. In the data cleaning link, the abnormal values and noise data in the data are carefully checked and removed. For example, for the motor current data, if there are extremely large or extremely small values that deviate significantly from the normal range and are judged to be caused by sensor failures or instantaneous electromagnetic interference and other reasons, they are removed from the data set. At the same time, the data is normalized so that data from different sources and different magnitudes can be compared and analyzed on the same scale. For example, the motor temperature data and the associated component temperature data are both normalized to the range of 0 to 1, which can more conveniently observe the relative relationship between them and the comprehensive impact on the motor abnormal risk. After these processes, a standard state data set is obtained, laying a foundation for subsequent accurate assessment.

[0038] Step S520 of determining the evaluation object, where the evaluation object is the motor and its associated components. Specifically, it is clear that the evaluation object is the motor and its associated components. As the core power component of the electric tricycle, the operation state of the motor directly determines the performance and safety of the vehicle. The associated components include components that are structurally connected or spatially adjacent to the motor, such as the controller, transmission gears, heat dissipation devices, etc. These associated components interact with the motor, and their working states will have a direct or indirect impact on the motor. For example, an abnormal output signal of the controller may cause the motor speed to get out of control, wear or jamming of the transmission gears will increase the load on the motor, and a failure of the heat dissipation device will cause the motor temperature to be too high. Therefore, including them in the evaluation object range can comprehensively and systematically evaluate the health status of the entire power system.

[0039] Step S530, select key indicators that can reflect the abnormal risk of the motor from the standard state data set as key evaluation indicators, and configure weights for each key evaluation indicator. Specifically, carefully select key evaluation indicators that can reflect the abnormal risk of the motor from the standard state data set. For the motor itself, the temperature change rate of the motor is an extremely critical indicator, because a sharp rise in the motor temperature often indicates internal faults such as winding short circuit or overload operation; the current fluctuation amplitude of the motor is also very important. Large current fluctuations may indicate that the electrical connection of the motor is unstable or the load changes are abnormally drastic. In terms of associated components, the difference between the temperature of the associated components and the normal working temperature of the motor is one of the key indicators. If the difference is too large, it may affect the heat dissipation environment of the motor and cause a fault; the vibration amplitude of the associated components is also an important indicator. Excessive vibration may cause uneven force on the motor shaft system, accelerating wear and damage. Weights are configured according to the relative importance of the key evaluation indicators to the abnormal risk of the motor. The weight of each key indicator is determined by analyzing a large amount of historical fault data and summarizing actual engineering experience. For example, statistics show that among many motor failure cases, failures caused by overtemperature account for a high proportion, so the weight of the motor temperature change rate will be relatively large, set to 0.4; and although the vibration amplitude of the associated components can also cause failures, it is relatively rare, and its weight may be set to 0.15. Through such a reasonable weight configuration, the impact of each indicator can be more accurately reflected in the evaluation process.

[0040] Step S540: Construct the ideal solution and the negative ideal solution, and perform motor abnormal risk assessment through the ideal solution and the negative ideal solution to obtain the risk assessment result. Specifically, construct the ideal solution and the negative ideal solution. The ideal solution refers to a virtual situation in which all evaluation indicators are in the best state. For example, the motor temperature change rate is zero, the current fluctuation amplitude is extremely small, the temperature difference between the associated component temperature and the normal operating temperature of the motor is zero, the vibration amplitude is zero, etc. It represents the perfect operating state of the motor and its associated components. The negative ideal solution, on the other hand, is in the worst state in all evaluation indicators, such as the motor temperature rising sharply, the current fluctuating greatly, the associated component temperature deviating severely from the normal range and vibrating violently, etc. This is the worst operating situation that the motor and its associated components may encounter. Perform motor abnormal risk assessment by calculating the relative distances between each evaluation object (the actual operating state of the motor and its associated components) and the ideal solution and the negative ideal solution. Adopt a specific distance calculation method, such as the Euclidean distance formula, to calculate the actual value of each key evaluation indicator of the evaluation object and the corresponding indicator values of the ideal solution and the negative ideal solution. Determine the abnormal risk level of the motor according to the calculated relative distances. For example, if the distance between the evaluation object and the ideal solution is relatively close and the distance from the negative ideal solution is relatively far, it indicates that the motor and its associated components are in a better operating state and the risk is low; conversely, if the distance from the ideal solution is far and the distance from the negative ideal solution is close, it indicates that the motor is in a high-risk state and a failure may occur soon. Through such an evaluation method, the motor abnormal risk assessment result can be quantitatively obtained, providing a scientific basis for subsequent measures such as early warning, maintenance, or adjustment of the motor operating parameters.

[0041] In a possible implementation manner, construct the ideal solution and the negative ideal solution, and perform motor abnormal risk assessment through the ideal solution and the negative ideal solution to obtain the risk assessment result. Step S540 further includes step S541: Calculate the relative distances between each evaluation object and the ideal solution and the negative ideal solution. Specifically, to calculate the relative distances between each evaluation object and the ideal solution and the negative ideal solution, it is necessary to select a suitable distance metric method, such as the Euclidean distance formula. For each key evaluation indicator of the motor and its associated components, substitute the actual value of the evaluation object on this indicator, the optimal value of the ideal solution on this indicator, and the worst value of the negative ideal solution on this indicator into the distance formula for calculation. For example, for the key indicator of the motor temperature change rate, assume that the motor temperature change rate of the evaluation object is , the motor temperature change rate of the ideal solution is , and the motor temperature change rate of the negative ideal solution is . Then, on this indicator, the distance between the evaluation object and the ideal solution is , and the distance from the negative ideal solution is . Perform such calculations for all key evaluation indicators of the motor and its associated components, so as to obtain the relative distance vectors of the evaluation object and the ideal solution and the negative ideal solution in multiple dimensions.

[0042] Step S542: Calculate the relative score of each evaluation object according to the relative distance. Specifically, based on the calculated relative distance, construct a relative score calculation model. The calculation of the relative score is based on the relative position relationship between the evaluation object and the ideal solution and the negative ideal solution. Let the distance between the evaluation object and the ideal solution be , and the distance from the negative ideal solution be , then the relative score . Substitute the relative distance calculated above into this formula to calculate the relative score of each evaluation object. The higher the relative score, the closer the evaluation object is to the ideal solution and the better its operating state; the lower the relative score, the closer it is to the negative ideal solution and the worse the operating state. For example, if the relative score of an evaluation object is close to 1, it means that the motor and its associated components perform well in all key indicators and are close to the perfect operating state; if the relative score is close to 0, it indicates that there are major problems with its operating state and it is close to the worst case.

[0043] Step S543: Extract the relative scores of each associated component according to the relative score for interference index analysis and generate multiple interference factors. Specifically, extract the relative scores of each associated component according to the relative score for interference index analysis. For each associated component, such as a controller, a transmission component, etc., its relative score reflects the degree of its influence on the operation of the motor. For example, a relatively low relative score of the controller may mean that its output signal is unstable or the temperature is too high, which will interfere with the operation of the motor. Through statistical analysis of the relative scores of each associated component, use methods such as factor analysis to generate multiple interference factors. If it is found that the relative scores of multiple associated components have commonalities in certain aspects, such as the temperature-related scores of multiple associated components are all relatively low, then a temperature interference factor can be generated, which represents the comprehensive interference degree of the high-temperature state of these associated components on the operation of the motor; if there are problems with the vibration-related scores of the associated components, a vibration interference factor can be generated, etc. These interference factors can more comprehensively and generally reflect the interference situation of the associated components on the operation of the motor.

[0044] Step S544: Based on the relative score, extract the relative score of the motor and correct its score through the multiple interference factors. Generate a motor abnormal risk level according to the corrected relative score of the motor. Specifically, based on the relative score, extract the relative score of the motor and correct its score through multiple interference factors. Since the state of the associated components will affect the operation of the motor, it is necessary to adjust the relative score of the motor according to the interference factors. For example, if there is a relatively high temperature interference factor, it means that the high temperature of the associated components may make it difficult for the motor to dissipate heat, thus increasing the risk of motor failure. Then, it is necessary to reduce the relative score of the motor. Let the original relative score of the motor be , the interference factor is , the relative score of the corrected motor , where is a correction coefficient determined based on experience or experiments. Based on the relative score of the corrected motor, the abnormal risk level of the motor is generated. The relative score of the corrected motor is compared with a preset risk level threshold. For example, if the relative score of the corrected motor is greater than 0.8, it is determined that the motor is in a low risk level, its operation is relatively stable, and only routine monitoring is required; if the score is between 0.5 and 0.8, it is a medium risk level, and further inspection and possible maintenance of the motor and its associated components are required; if the score is less than 0.5, it is a high risk level. At this time, the motor may be about to fail, and immediate measures need to be taken, such as stopping the motor operation and performing emergency repairs, so as to achieve effective evaluation and hierarchical management of the motor abnormal risk and ensure the safe operation of the electric tricycle motor.

[0045] In the embodiment of the present application, by setting an action instruction analysis module between the starting device and the motor, the module includes a plurality of monitoring and analysis units, and each unit corresponds to a set of action instructions. By obtaining the action instructions of the electric tricycle in real time, the corresponding monitoring unit is activated to extract real-time action parameters and perform load state prediction. The state data of the motor and its associated components are obtained through multi-source sensing devices, and the abnormal risk assessment is carried out in combination with the load state prediction and the state data. According to the evaluation result, the motor operation parameters are dynamically adjusted, achieving the technical effect of accurately monitoring and warning the abnormal situation of the electric tricycle motor under complex load changes.

[0046] In the above, reference is made to Figure 1 to describe in detail the method for monitoring the abnormal operation of the motor for an electric tricycle according to the embodiment of the present invention. Next, reference will be made to Figure 2 to describe the system for monitoring the abnormal operation of the motor for an electric tricycle according to the embodiment of the present invention.

[0047] The system for monitoring the abnormal operation of the motor for an electric tricycle according to the embodiment of the present invention solves the technical problem in the prior art that the mutual influence between the motor and other components is ignored, resulting in the inability to accurately predict and monitor the abnormality of the electric tricycle motor under complex load changes, and achieves the technical effect of accurately monitoring and warning the abnormal situation of the electric tricycle motor under complex load changes. The system for monitoring the abnormal operation of the motor for an electric tricycle includes: an action instruction analysis module establishment module 10, an associated parameter extraction module 20, a load state prediction module 30, a state data acquisition module 40, and a motor abnormal risk assessment module 50.

[0048] The Action Instruction Analysis Module Establishment Module 10 is used to establish an action instruction analysis module between the starting device and the motor. The action instruction analysis module includes a plurality of monitoring and analysis units, and each monitoring and analysis unit corresponds to a set of action instructions.

[0049] The Associated Parameter Extraction Module 20 is used to obtain the real-time action instructions of the electric tricycle, and based on the real-time action instructions, activate the corresponding target monitoring and analysis unit to extract associated parameters and obtain real-time action parameters.

[0050] The Load Status Prediction Module 30 is used to perform load status prediction through the target monitoring and analysis unit based on the real-time action parameters to obtain a motor load status prediction sequence.

[0051] The Status Data Acquisition Module 40 is used to acquire multi-source motor status data and associated component status data through multi-source sensing devices.

[0052] The Motor Abnormality Risk Assessment Module 50 is used to combine the motor load status prediction sequence, the multi-source motor status data and the associated component status data to perform motor abnormality risk assessment, and dynamically adjust the motor operation parameters according to the risk assessment result.

[0053] Next, the specific configuration of the Action Instruction Analysis Module Establishment Module 10 will be described in detail. As described above, an action instruction analysis module is established between the starting device and the motor. The action instruction analysis module includes a plurality of monitoring and analysis units, and each monitoring and analysis unit corresponds to a set of action instructions. The Action Instruction Analysis Module Establishment Module 10 further includes: a reference action instruction acquisition unit, which is used to obtain a plurality of reference action instructions according to the basic information of the target electric tricycle. The reference action instructions can be single action instructions or combined action instructions; a key monitoring index extraction unit, which is used to extract key monitoring indexes based on the plurality of reference action instructions and establish a plurality of monitoring and analysis units respectively; a user behavior analysis unit, which is used to perform user behavior analysis according to the daily operation records of the target user and generate a personalized correction plan; an initialization configuration unit, which is used to adopt the personalized correction plan to initialize the configuration of the plurality of monitoring and analysis units and connect them to generate the action instruction analysis module.

[0054] Among them, according to the daily operation records of the target user, user behavior analysis is carried out to generate a personalized correction plan. The user behavior analysis unit further includes: a sample operation record extraction subunit, which is used to extract multiple sample operation records of multiple action instructions based on the daily operation records of the target user; a multi-variate clustering subunit, which is used to perform multi-variate clustering on the multiple sample operation records to obtain the multi-variate action features of the multiple action instructions, and the multi-variate action features include action type, action occurrence duration, and action occurrence frequency; a contribution analysis subunit, which is used to perform contribution analysis on the multi-variate action features and configure feature weights for the multi-variate action features according to the contribution analysis results; a personalized impact analysis subunit, which is used to perform personalized impact analysis on the multiple action instructions based on the multi-variate action features and the corresponding feature weights, and generate the personalized correction plan according to the impact analysis results. The personalized correction plan includes correction strategies for the monitoring and analysis units corresponding to each action instruction.

[0055] Next, the specific configuration of the load status prediction module 30 will be described in detail. As described above, based on the real-time action parameters, the target monitoring and analysis unit is used to predict the load status, and a motor load status prediction sequence is obtained. The load status prediction module 30 further includes: a target monitoring and analysis unit composition unit, which is used to embed a load status prediction model in the target monitoring and analysis unit, and the load status prediction model contains a user habit index for real-time action instructions; an instruction duration analysis unit, which is used to analyze and obtain the duration of the real-time action instruction according to the user habit index; a load status prediction unit, which is used to use the real-time action parameters and duration as inputs, and through the load status prediction model, perform dynamic prediction of the load status to obtain a motor load status prediction sequence.

[0056] Next, the specific configuration of the state data acquisition module 40 will be described in detail. As described above, multi-source motor state data and associated component state data are acquired through multi-source sensing devices. The state data acquisition module 40 further includes: a structural principle data acquisition unit, which is used to acquire the structural layout information and braking principle data of the electric tricycle; an associated component extraction unit, which is used to perform correlation analysis of associated components on the motor based on the structural layout information and braking principle data, and extract braking associated components and interference associated components according to the correlation analysis results; a state data acquisition unit, which is used to deploy multi-source sensing devices to acquire the state data of the braking associated components and interference associated components, and form the associated component state data.

[0057] Next, the specific configuration of the motor abnormal risk assessment module 50 will be described in detail. As described above, in combination with the motor load state prediction sequence, the multi-source motor state data, and the associated component state data, a motor abnormal risk assessment is performed, and according to the risk assessment result, the motor operation parameters are dynamically adjusted. The motor abnormal risk assessment module 50 further includes: a state data preprocessing unit, which is used to preprocess the motor load state prediction sequence, the multi-source motor state data, and the associated component state data to obtain a standard state data set; an evaluation object determination unit, which is used to determine the evaluation object, and the evaluation object is the motor and its associated components; a key evaluation index determination unit, which is used to select key indexes that can reflect the motor abnormal risk from the standard state data set as key evaluation indexes and configure weights for each key evaluation index; a risk assessment result acquisition unit, which is used to construct an ideal solution and a negative ideal solution, and perform a motor abnormal risk assessment through the ideal solution and the negative ideal solution to obtain a risk assessment result.

[0058] Among them, constructing an ideal solution and a negative ideal solution, and performing a motor abnormal risk assessment through the ideal solution and the negative ideal solution to obtain a risk assessment result, the risk assessment result acquisition unit further includes: a relative distance calculation sub-unit, which is used to calculate the relative distances of each evaluation object from the ideal solution and the negative ideal solution; a relative score calculation sub-unit, which is used to calculate the relative score of each evaluation object according to the relative distance; an interference factor generation sub-unit, which is used to perform interference index analysis by extracting the relative scores of each associated component according to the relative score to generate a plurality of interference factors; a score correction sub-unit, which is used to extract the relative score of the motor based on the relative score, and correct the score through the plurality of interference factors, and generate a motor abnormal risk level according to the corrected relative score of the motor.

[0059] The motor operation abnormal monitoring system for an electric tricycle provided by the embodiment of the present invention can execute the motor operation abnormal monitoring method for an electric tricycle provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0060] Although various references are made to certain modules in the system according to embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0061] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recited in the present application can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for monitoring abnormal operation of a motor of an electric tricycle, characterized in that: The method comprises: Establishing an action instruction analysis module between the starting device and the motor, wherein the action instruction analysis module includes a plurality of monitoring and analysis units, each monitoring and analysis unit corresponding to a set of action instructions; Acquire the real-time action instruction of the electric tricycle, and according to the real-time action instruction, activate the corresponding target monitoring and analysis unit to extract the associated parameters to obtain the real-time action parameters; Based on the real-time action parameters, load state prediction is performed by the target monitoring and analysis unit to obtain a motor load state prediction sequence; Acquire multi-source motor status data and associated component status data through multi-source sensing devices; Combine the motor load state prediction sequence, the multi-source motor state data and the associated component state data to perform motor abnormality risk assessment, and dynamically adjust the motor operating parameters according to the risk assessment results; Through multi-source sensing devices, multi-source motor status data and associated component status data are obtained, including: Obtain the structural layout information and braking principle data of the electric tricycle. The structural layout information includes: the specific position of the motor in the vehicle, the layout of the transmission components connected to the motor, the installation position of the battery pack, and the distribution of the controller; the braking principle data includes: the type of braking system, the force transmission path during braking, the working mode of the brake pads and brake discs, and the coordinated control logic between the braking system and the motor; Based on the structural layout information and the braking principle data, a correlation analysis of associated components of the motor is performed, and according to the correlation analysis results, braking associated components and interference associated components are extracted, including: a reducer and a brake controller directly connected to the motor through a transmission shaft are braking associated components, and heat generated during operation affects the operating temperature of the motor and vibrations during operation are transmitted to the motor to affect the stability of the motor are interference associated components; Deploy multi-source sensing equipment to obtain status data of the braking-related components and the interference-related components to form the status data of the related components, including: continuously collecting status data of the braking-related components and the interference-related components by deploying multi-source sensing equipment; integrating data from torque sensors, signal monitoring sensors, temperature sensors and vibration sensors to form the status data of the related components.

2. The method for monitoring abnormal operation of a motor for an electric tricycle according to claim 1, characterized in that: An action instruction analysis module is established between the starting device and the motor, and the action instruction analysis module includes multiple monitoring and analysis units, including: According to the basic information of the target electric tricycle, a plurality of reference action instructions are obtained, wherein the reference action instructions may be a single action instruction or a combined action instruction; Based on the multiple benchmark action instructions, extract key monitoring indicators and establish multiple monitoring and analysis units respectively; Conduct user behavior analysis based on target users’ daily operation records and generate personalized correction plans; The personalized correction scheme is adopted to initialize the configuration of the multiple monitoring and analysis units, and connect and generate the action instruction analysis module.

3. The method for monitoring abnormal operation of a motor for an electric tricycle according to claim 2, characterized in that: Conduct user behavior analysis based on target users’ daily operation records and generate personalized correction plans, including: Based on the daily operation records of the target user, multiple sample operation records of multiple action instructions are extracted respectively; Performing multivariate clustering on the plurality of sample operation records to obtain multivariate action features of the plurality of action instructions, the multivariate action features including action type, action occurrence duration, and action occurrence frequency; Performing contribution analysis on the multivariate action features, and configuring feature weights for the multivariate action features according to the contribution analysis results; Based on the multivariate action features and the corresponding feature weights, a personalized impact analysis is performed on the multiple action instructions, and the personalized correction scheme is generated according to the impact analysis results. The personalized correction scheme includes a correction strategy for the monitoring and analysis unit corresponding to each action instruction.

4. The method for monitoring abnormal operation of a motor for an electric tricycle according to claim 1, characterized in that: Based on the real-time action parameters, the target monitoring and analysis unit performs load state prediction to obtain a motor load state prediction sequence, including: The target monitoring and analysis unit is embedded with a load state prediction model, wherein the load state prediction model includes a user habit index for real-time action instructions; Analyze and obtain the duration of the real-time action instruction according to the user habit index; The real-time action parameters and duration are used as inputs, and the load state prediction model is used to perform dynamic prediction of the load state to obtain a motor load state prediction sequence.

5. The method for monitoring abnormal operation of a motor for an electric tricycle according to claim 1, characterized in that: Combining the motor load state prediction sequence, the multi-source motor state data and the associated component state data, performing motor abnormality risk assessment includes: Preprocessing the motor load state prediction sequence, the multi-source motor state data and the associated component state data to obtain a standard state data set; Determining an evaluation object, wherein the evaluation object is a motor and its associated components; Selecting key indicators that can reflect the abnormal risk of the motor from the standard state data set as key evaluation indicators, and configuring a weight for each key evaluation indicator; An ideal solution and a negative ideal solution are constructed, and the risk assessment of motor abnormality is performed using the ideal solution and the negative ideal solution to obtain a risk assessment result.

6. The method for monitoring abnormal operation of a motor for an electric tricycle according to claim 5, characterized in that: The ideal solution and the negative ideal solution are used to evaluate the risk of motor abnormality, including: Calculate the relative distance of each evaluation object from the ideal solution and the negative ideal solution; Calculating a relative score for each evaluation object according to the relative distance; According to the relative scores, extracting the relative scores of the associated components to perform interference index analysis and generate multiple interference factors; Based on the relative score, the motor relative score is extracted, and the score is corrected using the multiple interference factors, and the motor abnormality risk level is generated based on the corrected motor relative score.

7. A motor abnormality monitoring system for an electric tricycle, characterized in that: The system is used to implement the motor operation abnormality monitoring method for an electric tricycle according to any one of claims 1 to 6, and the system comprises: An action instruction analysis module establishment module, wherein the action instruction analysis module establishment module is used to establish an action instruction analysis module between the starting device and the motor, wherein the action instruction analysis module includes a plurality of monitoring and analysis units, each monitoring and analysis unit corresponding to a set of action instructions; A correlation parameter extraction module, which is used to obtain the real-time action instructions of the electric tricycle, and according to the real-time action instructions, activate the corresponding target monitoring and analysis unit to extract the correlation parameters to obtain the real-time action parameters; A load state prediction module, the load state prediction module is used to perform load state prediction through the target monitoring and analysis unit based on the real-time action parameters to obtain a motor load state prediction sequence; A state data acquisition module, the state data acquisition module is used to acquire multi-source motor state data and associated component state data through a multi-source sensing device; A motor abnormality risk assessment module, the motor abnormality risk assessment module is used to combine the motor load state prediction sequence, the multi-source motor state data and the associated component state data to perform motor abnormality risk assessment, and dynamically adjust the motor operating parameters according to the risk assessment result; The status data acquisition module further includes: a structural principle data acquisition unit, which is used to acquire the structural layout information and braking principle data of the electric tricycle; an associated component extraction unit, which is used to perform associated component correlation analysis on the motor based on the structural layout information and braking principle data, and extract braking associated components and interference associated components according to the correlation analysis results; a status data acquisition unit, which is used to deploy multi-source sensing equipment, acquire the status data of the braking associated components and the interference associated components, and form the associated component status data.

Images