Motor torque control and battery energy management integration method and system based on AI

Abstract

The invention relates to the field of motor control, and discloses an AI-based motor torque control and battery energy management integration method and system, and the method comprises the steps: constructing an edge computing network of a to-be-controlled motor and a to-be-managed battery; constructing a motor mixing depth DRL model of a to-be-controlled motor, and establishing a battery unsupervised management model of a to-be-managed battery; integrating the motor hybrid depth DRL model and the battery unsupervised management model into an edge computing network to obtain an integrated computing network, analyzing a motor state of a to-be-controlled motor, analyzing a battery state of a to-be-managed battery, constructing an integrated computing model of the integrated computing network, and establishing an AI multi-target algorithm of the integrated computing model to obtain an AI multi-target algorithm; and analyzing the integrated control instruction of the to-be-controlled motor and the to-be-managed battery, and executing integrated control of the to-be-controlled motor and the to-be-managed battery based on the integrated control instruction. According to the invention, the integrated collaborative optimization effect of motor torque control and battery energy management can be improved.

Description

Technical Field

[0001] The present invention relates to the field of motor control, and in particular to an AI-based motor torque control and battery energy management integrated method and system. Background Art

[0002] The integration of motor torque control and battery energy management refers to the process of combining motor torque control technology and battery energy management technology to form a unified system to optimize the performance, efficiency and reliability of the entire electric drive system.

[0003] The traditional method of integrating motor torque control and battery energy management usually adopts independent control units to manage the motor and battery respectively, using fixed control algorithms and relatively simple data processing methods. This method often ignores the interaction and synergistic optimization potential between the motor and the battery, resulting in poor final integrated control effect. Summary of the invention

[0004] The present invention provides an AI-based integrated method and system for motor torque control and battery energy management, the main purpose of which is to improve the integrated collaborative optimization effect of motor torque control and battery energy management.

[0005] To achieve the above objectives, the present invention provides an AI-based motor torque control and battery energy management integration method, comprising:

[0006] Determine the performance indicators of the motor to be controlled, define the management objectives of the battery to be managed, and build a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and the management objectives;

[0007] Calculate the instantaneous coefficient of the sensor network, and when the instantaneous coefficient meets the preset instantaneous coefficient threshold, construct an edge computing node of the sensor network, configure a redundant computing node of the edge computing node, and construct an edge computing network of the motor to be controlled and the battery to be managed through the edge computing node and the redundant computing node;

[0008] Acquire motor control data and battery energy management data of the motor to be controlled and the battery to be managed, construct a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, and establish a battery unsupervised management model of the battery to be managed through the battery energy management data;

[0009] Integrate the motor hybrid deep DRL model and the battery unmanaged supervision model into the edge computing network to obtain an integrated computing network, use the sensor network to collect real-time motor data and real-time battery data of the motor to be controlled and the battery to be managed, analyze the motor state of the motor to be controlled through the real-time motor data, and analyze the battery state of the battery to be managed according to the real-time battery data;

[0010] Based on the motor state and the battery state, an integrated computing model of the integrated computing network is constructed, and through the performance indicators and management objectives, an AI multi-objective algorithm of the integrated computing model is established, and through the AI ​​multi-objective algorithm, the integrated control instructions of the motor to be controlled and the battery to be managed are analyzed, and based on the integrated control instructions, integrated control of the motor to be controlled and the battery to be managed is performed.

[0011] Optionally, constructing a sensor network of the motor to be controlled and the battery to be managed based on the performance indicator and the management target includes:

[0012] Identifying the working environment of the motor to be controlled and the battery to be managed;

[0013] Determine the sensor equipment of the motor to be controlled and the battery to be managed according to the performance indicators, management objectives and working environment;

[0014] Analyzing the device performance of the sensing device, wherein the device performance includes sensitivity, linearity, repeatability, and durability;

[0015] When the device performance meets a preset device performance threshold, analyzing the coordinate location of the sensor device;

[0016] Constructing a star topology of the sensor device through the coordinate locations;

[0017] According to the star topology, a data transmission protocol of the sensor device is defined;

[0018] Based on the data transmission protocol, a sensor network of the motor to be controlled and the battery to be managed is constructed.

[0019] Optionally, analyzing the device performance of the sensing device includes:

[0020] Performing a performance test on the sensor device to obtain a performance test parameter;

[0021] By means of the performance test parameters, the final output value, the initial output value, the final input value and the initial input value of the sensor device are analyzed,

[0022] The sensitivity of the sensor device is calculated using the following formula using the final output value, the initial output value, the final input value and the initial input value:

[0023] σ=Δ(O_f-R_f) / Δ(D_f-U_f)

[0024] Wherein, σ represents the sensitivity of the sensor device, Δ(O_f-R_f) represents the output change of the f-th measurement point of the sensor device, Δ(D_f-U_f) represents the input change of the f-th measurement point of the sensor device, O_f represents the final output value of the f-th measurement point of the sensor device, R_f represents the initial output value of the f-th measurement point of the sensor device, D_f represents the final input value of the f-th measurement point of the sensor device, and U_f represents the initial input value of the f-th measurement point of the sensor device;

[0025] According to the final output value, the linearity of the sensor device is calculated using the following formula:

[0026]

[0027] Wherein, L represents the linearity of the sensor device, O_f represents the final output value of the f-th measurement point of the sensor device, O_f,th ​​represents the theoretical output value of the f-th measurement point of the sensor device, and N represents the number of corresponding measurement points of the sensor device;

[0028] Analyzing the coefficient of consistency and the number of cycles of the sensing device based on the final output value, the initial output value, the final input value, and the initial input value;

[0029] Determining the repeatability of the sensing device based on the coefficient of consistency;

[0030] Determining the durability of the sensing device through the number of cycles;

[0031] The device performance of the sensing device is analyzed based on the sensitivity, linearity, repeatability and durability.

[0032] Optionally, the edge computing node for constructing the sensor network includes:

[0033] Analyzing the data processing requirements of the sensor network, wherein the data processing requirements include: data real-time requirements, computational complexity, and storage requirements;

[0034] Based on the data processing requirements, determining edge computing requirement resources of the sensor network;

[0035] Determining edge computing hardware components of the sensor network according to the edge computing demand resources;

[0036] Based on the edge computing hardware components, establishing an edge computing software architecture of the sensor network;

[0037] Constructing an initial edge computing node of the sensor network according to the edge computing software architecture and edge computing hardware components;

[0038] Calculating a collaboration coefficient of the initial edge computing node;

[0039] When the cooperation coefficient meets a preset cooperation coefficient threshold, the initial edge computing node is used as an edge computing node of the sensor network.

[0040] Optionally, analyzing the data processing requirements of the sensor network includes:

[0041] Analyzing preset data collection time requirements and preset data processing time requirements of the sensor network;

[0042] Determining the data real-time requirement of the sensor network through the preset data collection time requirement and the preset data processing time requirement;

[0043] Identifying a preset data volume and data size of the sensor network, and determining a storage requirement of the sensor network based on the preset data volume and data size;

[0044] Defining the data algorithm complexity and data preprocessing times of the sensor network;

[0045] Based on the data algorithm complexity and the number of data preprocessing times, the computational complexity of the sensor network is calculated using the following formula:

[0046] C_complexity=m*Σ(C_algorithm_i*m_i)

[0047] Wherein, C_complexity represents the computational complexity of the sensor network, m represents the number of data preprocessing times of the sensor network, C_algorithm_i represents the data algorithm complexity of data point i in the sensor network, and m_i represents the number of preprocessing times of data point i in the number of data preprocessing times of the sensor network;

[0048] The data processing requirements of the sensor network are determined according to the data real-time requirements, computational complexity and storage requirements.

[0049] Optionally, constructing a motor hybrid deep DRL model of the motor to be controlled based on the motor control data includes:

[0050] Defining the state space, torque action space and reward mechanism of the motor to be controlled;

[0051] Analyzing a Q value data set of the motor to be controlled based on the motor control data, the state space, the torque action space, and the reward mechanism, wherein the Q value data set includes a current state, a torque action, a next state, and a reward;

[0052] Calculating the motor Q value of the motor to be controlled by using the Q value data set;

[0053] According to the motor Q value, construct an initialization Q table of the motor to be controlled;

[0054] Using a preset experience replay pool, the initialized Q table is updated to obtain an updated Q table;

[0055] Calculating the expected value of the updated Q table;

[0056] When the expected value meets the preset expected standard value, the motor hybrid depth DRL model of the motor to be controlled is constructed using the updated Q table.

[0057] Optionally, calculating the motor Q value of the motor to be controlled by using the Q value data set includes:

[0058] Constructing a Q value function of the motor to be controlled;

[0059] Determining a learning rate and a discount factor of the Q-value function;

[0060] Based on the learning rate, discount factor and Q value data set, the motor Q value of the motor to be controlled is calculated using the Q value function:

[0061] Q(s,a)=(1-α)*Q(s,a)+α*[ρ+ε*max_a'Q(s',a')-Q(s,a)]

[0062] Among them, Q(s,a) represents the motor Q value of the motor to be controlled in the Q value dataset corresponding to the current state s and torque action a, Q(s',a') represents the motor Q value of the motor to be controlled in the Q value dataset corresponding to the next state s' and torque action a', α represents the learning rate of the Q value function, ε represents the discount factor of the Q value function, ρ represents the reward corresponding to the Q value dataset, and max_a' represents the maximum value of the torque action in the Q value dataset.

[0063] Optionally, establishing a battery unsupervised management model of the battery to be managed by using the battery energy management data includes:

[0064] Normalizing the battery energy management data to obtain normalized management data;

[0065] extracting energy management features of the normalized management data;

[0066] Calculating characteristic principal component coefficients of the energy management characteristic;

[0067] Extracting key energy management features of the energy management features according to the feature principal component coefficients, wherein the key energy management features include voltage change, current change, and temperature change;

[0068] Determining an unsupervised learning algorithm for the battery to be managed;

[0069] A battery unsupervised supervision model of the battery to be managed is constructed according to the key energy management features and the unsupervised learning algorithm.

[0070] Optionally, analyzing the integrated control instructions of the motor to be controlled and the battery to be managed by the AI ​​multi-objective algorithm includes:

[0071] According to the performance indicators and management objectives corresponding to the motor to be controlled and the battery to be managed, using the integrated calculation model corresponding to the motor to be controlled and the battery to be managed to analyze the initial optimization parameter group of the motor to be controlled and the battery to be managed;

[0072] Calculate the parameter group response value of the initial optimization parameter group corresponding to the initial optimization parameter group by using the AI ​​multi-objective algorithm;

[0073] Determining a target optimized parameter group in the initial optimized parameter group based on the parameter group response value;

[0074] According to the target optimization parameter group, integrated control instructions for the motor to be controlled and the battery to be managed are determined.

[0075] In order to solve the above problems, the present invention also provides an AI-based motor torque control and battery energy management integrated system, the system comprising:

[0076] A sensor network construction module, used to determine the performance indicators of the motor to be controlled, define the management objectives of the battery to be managed, and construct a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and the management objectives;

[0077] An edge computing network construction module is used to calculate the instantaneous coefficient of the sensor network, and when the instantaneous coefficient meets the preset instantaneous coefficient threshold, construct an edge computing node of the sensor network, and configure a redundant computing node of the edge computing node, and construct an edge computing network of the motor to be controlled and the battery to be managed through the edge computing node and the redundant computing node;

[0078] A battery management model building module is used to obtain the motor control data and battery energy management data of the motor to be controlled and the battery to be managed, and to build a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, and to establish a battery unsupervised management model of the battery to be managed through the battery energy management data;

[0079] An integrated computing network building module is used to integrate the motor hybrid deep DRL model and the battery unmanaged supervision model into the edge computing network to obtain an integrated computing network, and use the sensor network to collect real-time motor data and real-time battery data of the motor to be controlled and the battery to be managed, analyze the motor state of the motor to be controlled through the real-time motor data, and analyze the battery state of the battery to be managed according to the real-time battery data;

[0080] The motor and battery integrated control module is used to construct an integrated computing model of the integrated computing network based on the motor state and the battery state, and to establish an AI multi-objective algorithm of the integrated computing model through the performance indicators and management objectives, analyze the integrated control instructions of the motor to be controlled and the battery to be managed through the AI ​​multi-objective algorithm, and perform integrated control of the motor to be controlled and the battery to be managed based on the integrated control instructions.

[0081] The present invention constructs a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and management objectives, thereby constructing an efficient and reliable sensor network to provide accurate data support for motor torque control and battery energy management; the present invention provides real-time data processing and analysis capabilities for the sensor network by constructing edge computing nodes of the sensor network; further, the present invention configures redundant computing nodes of the edge computing nodes, and constructs an edge computing network of the motor to be controlled and the battery to be managed through the edge computing nodes and redundant computing nodes, thereby improving the reliability and real-time performance of the system and ensuring the stable operation of the integrated system of motor torque control and battery energy management; further, the present invention constructs a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, thereby constructing a model that adapts to different motor control tasks, thereby improving the effect of motor control; further, the present invention Through the battery energy management data, a battery unsupervised management model of the battery to be managed is established to automatically discover abnormal patterns during battery use, predict the remaining service life (RUL) and health state (SOH) of the battery, thereby realizing effective management and maintenance of the battery. The present invention analyzes the motor state of the motor to be controlled through the real-time motor data, and analyzes the battery state of the battery to be managed according to the real-time battery data. The state analysis based on the real-time motor data and the real-time battery data helps to timely discover abnormal conditions of the motor and the battery, and take corresponding measures to deal with them, thereby improving the reliability and safety of the system. Finally, the present invention analyzes the integrated control instructions of the motor to be controlled and the battery to be managed through the AI ​​multi-objective algorithm to realize the coordinated optimization of motor torque control and battery energy management, which helps to improve the overall performance and efficiency of the system, and also can improve the intelligence level of the system. Therefore, the present invention can improve the integrated coordinated optimization effect of motor torque control and battery energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 A schematic flow chart of an integrated method for motor torque control and battery energy management based on AI provided in one embodiment of the present invention;

[0083] Figure 2 A functional module diagram of an AI-based motor torque control and battery energy management integrated system provided in one embodiment of the present invention;

[0084] Figure 3 A schematic diagram of the structure of an electronic device of an AI-based motor torque control and battery energy management integrated system provided by an embodiment of the present invention;

[0085] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0086] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0087] The embodiment of the present application provides an AI-based integrated method for motor torque control and battery energy management. The execution subject of the AI-based integrated method for motor torque control and battery energy management includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the AI-based integrated method for motor torque control and battery energy management can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0088] Reference Figure 1 As shown, it is a flow chart of an integrated method of motor torque control and battery energy management based on AI provided by an embodiment of the present invention. In this embodiment, the integrated method of motor torque control and battery energy management based on AI includes:

[0089] S1. Determine the performance indicators of the motor to be controlled, define the management objectives of the battery to be managed, and build a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and the management objectives.

[0090] It should be explained that the performance indicators include torque accuracy, response time, efficiency and other indicators, and the management goals include charging efficiency, battery life, energy utilization and other goals.

[0091] The present invention constructs a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and management objectives, thereby constructing an efficient and reliable sensor network to provide accurate data support for motor torque control and battery energy management.

[0092] In detail, the sensor network of the motor to be controlled and the battery to be managed is constructed based on the performance indicators and management objectives, including:

[0093] Identifying the working environment of the motor to be controlled and the battery to be managed;

[0094] Determine the sensor equipment of the motor to be controlled and the battery to be managed according to the performance indicators, management objectives and working environment;

[0095] Analyzing the device performance of the sensing device, wherein the device performance includes sensitivity, linearity, repeatability, and durability;

[0096] When the device performance meets a preset device performance threshold, analyzing the coordinate location of the sensor device;

[0097] Constructing a star topology of the sensor device through the coordinate locations;

[0098] According to the star topology, a data transmission protocol of the sensor device is defined;

[0099] Based on the data transmission protocol, a sensor network of the motor to be controlled and the battery to be managed is constructed.

[0100] Among them, the working environment refers to the specific environmental conditions of the motor to be controlled and the battery to be managed, including but not limited to temperature, humidity, vibration, electromagnetic interference, etc. The sensor device refers to the sensor required for monitoring and controlling the motor torque and battery energy management, the sensitivity refers to the response ability of the sensor device to the change of the measured quantity, the linearity refers to the straightness of the relationship between the output signal of the sensor and the measured physical quantity, the repeatability refers to the stability of the result obtained when the sensor device measures the same physical quantity multiple times under the same conditions, the durability refers to the ability of the sensor device to continue to work stably under a specific working environment, including anti-wear, anti-corrosion and other characteristics, the coordinate site refers to the specific installation position of the sensor on the motor and battery, the star topology refers to a layout method of the sensor network, in which all sensors are directly connected to a central node (such as a data acquisition unit) to form a star-like structure, the data transmission protocol refers to a set of data transmission rules defined between sensor devices and between sensor devices and data acquisition units, and the sensor network refers to a system composed of multiple sensor devices, a network for collecting, processing and transmitting status information of motors and batteries.

[0101] In detail, analyzing the device performance of the sensing device includes:

[0102] Performing a performance test on the sensor device to obtain a performance test parameter;

[0103] By means of the performance test parameters, the final output value, the initial output value, the final input value and the initial input value of the sensor device are analyzed,

[0104] The sensitivity of the sensor device is calculated using the following formula using the final output value, the initial output value, the final input value and the initial input value:

[0105] σ=Δ(O_f-R_f) / Δ(D_f-U_f)

[0106] Wherein, σ represents the sensitivity of the sensor device, Δ(O_f-R_f) represents the output change of the f-th measurement point of the sensor device, Δ(D_f-U_f) represents the input change of the f-th measurement point of the sensor device, O_f represents the final output value of the f-th measurement point of the sensor device, R_f represents the initial output value of the f-th measurement point of the sensor device, D_f represents the final input value of the f-th measurement point of the sensor device, and U_f represents the initial input value of the f-th measurement point of the sensor device;

[0107] According to the final output value, the linearity of the sensor device is calculated using the following formula:

[0108]

[0109] Wherein, L represents the linearity of the sensor device, O_f represents the final output value of the f-th measurement point of the sensor device, O_f,th ​​represents the theoretical output value of the f-th measurement point of the sensor device, and N represents the number of corresponding measurement points of the sensor device;

[0110] Analyzing the coefficient of consistency and the number of cycles of the sensing device based on the final output value, the initial output value, the final input value, and the initial input value;

[0111] Determining the repeatability of the sensing device based on the coefficient of consistency;

[0112] Determining the durability of the sensing device through the number of cycles;

[0113] The device performance of the sensing device is analyzed based on the sensitivity, linearity, repeatability and durability.

[0114] Among them, the final output value refers to the actual output value of the sensor device at all measurement points, the initial output value refers to the initial predicted output value of the sensor device at all measurement points, the final input value refers to the actual input value of the sensor device at all measurement points, the initial input value refers to the predicted input value of the sensor device at all measurement points, the theoretical output value refers to the predicted output value of the sensor device under a specific input value at all measurement points, the consistency coefficient refers to the degree of consistency of the sensor device between different measurement points, and the number of cycles refers to the number of cycles that the sensor device can withstand in a durability test under specific working conditions. The higher the number of cycles, the better the durability of the sensor device.

[0115] S2. Calculate the instantaneous coefficient of the sensor network. When the instantaneous coefficient meets the preset instantaneous coefficient threshold, construct an edge computing node of the sensor network, and configure redundant computing nodes of the edge computing nodes. Through the edge computing nodes and redundant computing nodes, construct an edge computing network of the motor to be controlled and the battery to be managed.

[0116] It should be explained that the instantaneous coefficient refers to the real-time performance of the sensor network in data collection, transmission and other operations, which can improve the control effect of the motor to be controlled and the battery to be managed in the later stage. The instantaneous coefficient threshold refers to the threshold used to determine whether the instantaneous coefficient meets the requirements.

[0117] The present invention provides real-time data processing and analysis capabilities for the sensor network by constructing edge computing nodes of the sensor network.

[0118] In detail, the edge computing node of the sensor network is constructed, including:

[0119] Analyzing the data processing requirements of the sensor network, wherein the data processing requirements include: data real-time requirements, computational complexity, and storage requirements;

[0120] Based on the data processing requirements, determining edge computing requirement resources of the sensor network;

[0121] Determining edge computing hardware components of the sensor network according to the edge computing demand resources;

[0122] Based on the edge computing hardware components, establishing an edge computing software architecture of the sensor network;

[0123] Constructing an initial edge computing node of the sensor network according to the edge computing software architecture and edge computing hardware components;

[0124] Calculating a collaboration coefficient of the initial edge computing node;

[0125] When the cooperation coefficient meets a preset cooperation coefficient threshold, the initial edge computing node is used as an edge computing node of the sensor network.

[0126] Among them, the data real-time requirement refers to the speed requirement for data processing in the sensor network, the computational complexity refers to the amount of computation required in the data processing process, including the complexity of the algorithm and the consumption of computing resources, the storage requirement refers to the space requirement for data storage, including the storage of historical data and the buffering of real-time data, the edge computing demand resources refer to the computing power, storage capacity and network bandwidth required by the edge computing nodes to meet the data processing requirements, the edge computing software architecture refers to the software system architecture deployed on the edge computing hardware components, including data processing flow, algorithm implementation, communication protocol, etc., and the edge computing hardware components refer to the hardware components used to build The physical equipment of the edge computing node, such as processor, memory, storage medium, network interface, etc., the initial edge computing node refers to the edge computing node built according to the edge computing requirement resources, software architecture and hardware components, the collaboration coefficient refers to the effect of the edge computing node collaborating with other nodes when processing sensor network data, the collaboration coefficient threshold refers to the preset collaboration coefficient standard, only when the collaboration coefficient of the edge computing node reaches or exceeds this threshold, it can serve as an effective edge computing node of the sensor network, the edge computing node refers to the edge computing device deployed in the sensor network, which is responsible for processing real-time data, reducing latency, and forwarding data to the cloud.

[0127] Further, the analyzing the data processing requirements of the sensor network includes:

[0128] Analyzing preset data collection time requirements and preset data processing time requirements of the sensor network;

[0129] Determining the data real-time requirement of the sensor network through the preset data collection time requirement and the preset data processing time requirement;

[0130] Identifying a preset data volume and data size of the sensor network, and determining a storage requirement of the sensor network based on the preset data volume and data size;

[0131] Defining the data algorithm complexity and data preprocessing times of the sensor network;

[0132] Based on the data algorithm complexity and the number of data preprocessing times, the computational complexity of the sensor network is calculated using the following formula:

[0133] C_complexity=m*∑(C_algorithm_i*m_i)

[0134] Wherein, C_complexity represents the computational complexity of the sensor network, m represents the number of data preprocessing times of the sensor network, C_algorithm_i represents the data algorithm complexity of data point i in the sensor network, and m_i represents the number of preprocessing times of data point i in the number of data preprocessing times of the sensor network;

[0135] The data processing requirements of the sensor network are determined according to the data real-time requirements, computational complexity and storage requirements.

[0136] Among them, the preset data collection time requirement refers to the time required from the start of data collection by the desired sensor to the completion of data collection, the preset data processing time requirement refers to the expected time required from the completion of data collection to the completion of data processing, the preset data volume refers to the total amount of data expected to be collected by the sensor network, the data size refers to the amount of data for each data point, the data algorithm complexity refers to the amount of calculation required for the data processing algorithm, and the number of data preprocessing times refers to the number of expected data processing times.

[0137] The present invention configures redundant computing nodes of the edge computing nodes, and constructs an edge computing network of the motor to be controlled and the battery to be managed through the edge computing nodes and the redundant computing nodes, which can improve the reliability and real-time performance of the system and ensure the stable operation of the motor torque control and battery energy management integrated system. The redundant computing nodes refer to backup computing resources deployed in the edge computing network, and the edge computing network refers to a network composed of edge computing nodes, including master nodes and redundant nodes.

[0138] S3. Obtain the motor control data and battery energy management data of the motor to be controlled and the battery to be managed, construct a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, and establish a battery unmanaged supervision model of the battery to be managed through the battery energy management data.

[0139] It should be explained that the motor control data refers to the input information used to guide the motor torque control decision. It usually includes the real-time status information of the motor such as current, voltage, speed, temperature, etc. The battery energy management data refers to the input information used to guide the battery charging and discharging strategy and health status monitoring. It usually includes the real-time status information of the battery such as voltage, current, temperature, state-of-charge (SOC), etc.

[0140] The present invention constructs a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, and can construct a model that adapts to different motor control tasks, thereby improving the effect of motor control.

[0141] In detail, the step of constructing a motor hybrid deep DRL model of the motor to be controlled based on the motor control data includes:

[0142] Defining the state space, torque action space and reward mechanism of the motor to be controlled;

[0143] Analyzing a Q value data set of the motor to be controlled based on the motor control data, the state space, the torque action space, and the reward mechanism, wherein the Q value data set includes a current state, a torque action, a next state, and a reward;

[0144] Calculating the motor Q value of the motor to be controlled by using the Q value data set;

[0145] According to the motor Q value, construct an initialization Q table of the motor to be controlled;

[0146] Using a preset experience replay pool, the initialized Q table is updated to obtain an updated Q table;

[0147] Calculating the expected value of the updated Q table;

[0148] When the expected value meets the preset expected standard value, the motor hybrid depth DRL model of the motor to be controlled is constructed using the updated Q table.

[0149] Among them, the state space refers to the set of all possible states that can be observed when the motor is running, the torque action space refers to the set of all possible torque actions that the motor can take, the reward mechanism refers to the reward defined according to the control effect and environmental response of the motor, the current state refers to the specific state of the motor at a certain point in time, the torque action refers to the specific torque action taken by the motor in the current state, for example, the current state can be [speed 1, current 1, temperature 1, voltage 1], the next state refers to the next state of the motor after taking a certain torque action, such as [speed 2, current 2, temperature 2, voltage 2], and the reward refers to the feedback of the environment on the motor control effect after taking a certain torque action, such as the reward for efficiency improvement. The reward is positive when the efficiency decreases, and the reward is negative when the efficiency decreases. The motor Q value refers to the Q value of the motor under a given state and torque action, that is, the expected cumulative reward. The experience replay pool refers to a data pool that stores historical experience, including state, torque action, reward and next state. The updated Q table refers to the Q table updated by the learning algorithm, which contains the Q value of the state-torque action pair. The expected value refers to the expected cumulative reward after taking a certain torque action in the current state. The expected standard value refers to the preset expected value threshold. When the expected value of the updated Q table meets this standard value, it indicates that the model has converged and a motor hybrid deep DRL model can be constructed. The motor hybrid deep DRL model refers to a motor control model that combines deep learning and reinforcement learning algorithms.

[0150] Further, calculating the motor Q value of the motor to be controlled by using the Q value data set includes:

[0151] Constructing a Q value function of the motor to be controlled;

[0152] Determining a learning rate and a discount factor of the Q-value function;

[0153] Based on the learning rate, discount factor and Q value data set, the motor Q value of the motor to be controlled is calculated using the Q value function:

[0154] Q(s,a)=(1-α)*Q(s,a)+α*[ρ+ε*max_a'Q(s',a')-Q(s,a)]

[0155] Among them, Q(s,a) represents the motor Q value of the motor to be controlled in the Q value dataset corresponding to the current state s and torque action a, Q(s',a') represents the motor Q value of the motor to be controlled in the Q value dataset corresponding to the next state s' and torque action a', α represents the learning rate of the Q value function, ε represents the discount factor of the Q value function, ρ represents the reward corresponding to the Q value dataset, and max_a' represents the maximum value of the torque action in the Q value dataset.

[0156] Among them, the learning rate refers to the step size of network parameter update, which determines the learning speed, the discount factor refers to the discount rate of future rewards, and the Q-value function refers to a function used to estimate the expected cumulative reward of the motor under a given state and torque action.

[0157] The present invention uses the battery energy management data to establish a battery unsupervised management model for the battery to be managed, automatically discovers abnormal patterns during battery use, and predicts the remaining useful life (RUL) and state of health (SOH) of the battery, thereby achieving effective management and maintenance of the battery.

[0158] In detail, the step of establishing a battery unsupervised management model of the battery to be managed by using the battery energy management data includes:

[0159] Normalizing the battery energy management data to obtain normalized management data;

[0160] extracting energy management features of the normalized management data;

[0161] Calculating characteristic principal component coefficients of the energy management characteristic;

[0162] Extracting key energy management features of the energy management features according to the feature principal component coefficients, wherein the key energy management features include voltage change, current change, and temperature change;

[0163] Determining an unsupervised learning algorithm for the battery to be managed;

[0164] A battery unsupervised supervision model of the battery to be managed is constructed according to the key energy management features and the unsupervised learning algorithm.

[0165] Among them, the normalized management data refers to the data after the original data is normalized so that it is distributed between 0 and 1, and the energy management feature refers to the key features extracted from the battery energy management data, such as voltage change, current change and temperature change. For example, for the charge and discharge data of a battery, the voltage change can be the voltage difference during the charge and discharge process, the current change can be the current difference during the charge and discharge process, and the temperature change can be the temperature change during the charge and discharge process. The characteristic principal component coefficient is the coefficient used to represent the principal component of the data in the principal component analysis (PCA). The voltage change refers to the change in voltage during the charge and discharge process of the battery. For example, if the voltage of a battery changes from 3.7V to 3.8V during the charge and discharge process, then the voltage change is 0.1V, and the current change refers to the change in current during the charge and discharge process of the battery. For example, if the current of a battery changes from 0.2A to 0.3A during the charge and discharge process, then the current change is 0.1A, and the temperature change refers to the change in temperature during the charge and discharge process of the battery. For example, if the temperature of a battery changes from 25°C to 30°C during charging and discharging, the temperature change is 5°C. The unsupervised learning algorithm is a method used to discover hidden patterns and structures in data, such as autoencoders, cluster analysis and PCA. The battery unsupervised management model refers to a model built based on an unsupervised learning algorithm, which is used to predict the remaining useful life (RUL) and health state (SOH) of the battery.

[0166] S4, integrating the motor hybrid deep DRL model and the battery unmanaged supervision model into the edge computing network to obtain an integrated computing network, using the sensor network to collect real-time motor data and real-time battery data of the motor to be controlled and the battery to be managed, analyzing the motor state of the motor to be controlled through the real-time motor data, and analyzing the battery state of the battery to be managed according to the real-time battery data;

[0167] It should be explained that the integrated computing network refers to the integration of multiple models and algorithms into a unified computing framework for processing and analyzing real-time data from the sensor network. This network includes multiple edge computing nodes, each of which may contain one or more models for processing specific types of data. The real-time motor data refers to the motor operation data collected in real time from the sensor network, such as current, voltage, speed, temperature, etc. These data reflect the current working status of the motor, and the real-time battery data refers to the battery status data collected in real time from the sensor network, such as voltage, current, temperature, SOC (state-of-charge), SOH (state-of-health), etc. These data reflect the current operating status of the battery.

[0168] The present invention analyzes the motor state of the motor to be controlled through the real-time motor data, and analyzes the battery state of the battery to be managed according to the real-time battery data. The state analysis based on the real-time motor data and the real-time battery data is helpful to timely discover the abnormal conditions of the motor and the battery, and take corresponding measures to deal with them, thereby improving the reliability and safety of the system. Among them, the motor state refers to the various key performance indicators of the motor monitored by the system in real time through sensors, including parameters such as torque, current, voltage, and speed, and the battery state refers to the various key performance indicators of the battery monitored by sensors in real time, such as voltage, current, temperature, state-of-charge (SOC), and other indicators.

[0169] S5. Based on the motor state and the battery state, construct an integrated computing model of the integrated computing network, and establish an AI multi-objective algorithm of the integrated computing model through the performance indicators and management objectives. Through the AI ​​multi-objective algorithm, analyze the integrated control instructions of the motor to be controlled and the battery to be managed, and perform integrated control of the motor to be controlled and the battery to be managed based on the integrated control instructions.

[0170] It should be explained that the integrated computing model integrates multiple models and algorithms into a unified computing framework for processing and analyzing real-time data from the sensor network. They work together to achieve precise control of motor torque and effective management of battery energy. The AI ​​multi-objective algorithm refers to an algorithm used to simultaneously optimize multiple objective functions, such as genetic algorithms, particle swarm optimization algorithms, etc. In the integrated system of motor torque control and battery energy management, the AI ​​multi-objective algorithm is used to optimize the goals of motor torque control and battery energy management, such as maximizing motor efficiency, extending battery life, and optimizing system energy efficiency.

[0171] The present invention uses the AI ​​multi-objective algorithm to analyze the integrated control instructions of the motor to be controlled and the battery to be managed to achieve coordinated optimization of motor torque control and battery energy management, which helps to improve the overall performance and efficiency of the system, and can also improve the intelligence level of the system.

[0172] In detail, the integrated control instructions of the motor to be controlled and the battery to be managed are analyzed by the AI ​​multi-objective algorithm, including:

[0173] According to the performance indicators and management objectives corresponding to the motor to be controlled and the battery to be managed, using the integrated calculation model corresponding to the motor to be controlled and the battery to be managed to analyze the initial optimization parameter group of the motor to be controlled and the battery to be managed;

[0174] Calculate the parameter group response value of the initial optimization parameter group corresponding to the initial optimization parameter group by using the AI ​​multi-objective algorithm;

[0175] Determining a target optimized parameter group in the initial optimized parameter group based on the parameter group response value;

[0176] According to the target optimization parameter group, integrated control instructions for the motor to be controlled and the battery to be managed are determined.

[0177] Among them, the initial optimization parameter group refers to the set of all possible parameter combinations in the multi-objective optimization problem, the parameter group response value refers to the contribution of each parameter group to the objective function in the multi-objective optimization problem, the target optimization parameter group refers to the parameter group that can achieve the best performance indicators and management objectives in the multi-objective optimization problem, and the integrated control instruction refers to the control instruction for the motor and battery determined according to the target optimization parameter group in the multi-objective optimization problem.

[0178] The present invention constructs a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and management objectives, thereby constructing an efficient and reliable sensor network to provide accurate data support for motor torque control and battery energy management; the present invention provides real-time data processing and analysis capabilities for the sensor network by constructing edge computing nodes of the sensor network; further, the present invention configures redundant computing nodes of the edge computing nodes, and constructs an edge computing network of the motor to be controlled and the battery to be managed through the edge computing nodes and redundant computing nodes, thereby improving the reliability and real-time performance of the system and ensuring the stable operation of the integrated system of motor torque control and battery energy management; further, the present invention constructs a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, thereby constructing a model that adapts to different motor control tasks, thereby improving the effect of motor control; further, the present invention Through the battery energy management data, a battery unsupervised management model of the battery to be managed is established to automatically discover abnormal patterns during battery use, predict the remaining service life (RUL) and health state (SOH) of the battery, thereby realizing effective management and maintenance of the battery. The present invention analyzes the motor state of the motor to be controlled through the real-time motor data, and analyzes the battery state of the battery to be managed according to the real-time battery data. The state analysis based on the real-time motor data and the real-time battery data helps to timely discover abnormal conditions of the motor and the battery, and take corresponding measures to deal with them, thereby improving the reliability and safety of the system. Finally, the present invention analyzes the integrated control instructions of the motor to be controlled and the battery to be managed through the AI ​​multi-objective algorithm to realize the coordinated optimization of motor torque control and battery energy management, which helps to improve the overall performance and efficiency of the system, and also can improve the intelligence level of the system. Therefore, the present invention can improve the integrated coordinated optimization effect of motor torque control and battery energy management.

[0179] like Figure 2As shown, it is a functional module diagram of an AI-based motor torque control and battery energy management integrated system provided by one embodiment of the present invention.

[0180] The AI-based motor torque control and battery energy management integrated system 200 of the present invention can be installed in an electronic device. According to the functions implemented, the AI-based motor torque control and battery energy management integrated system 200 may include a sensor network construction module 201, an edge computing network construction module 202, a battery management model construction module 203, an integrated computing network construction module 204 and a motor and battery integrated control module 205. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0181] In this embodiment, the functions of each module / unit are as follows:

[0182] The sensor network construction module 201 is used to determine the performance indicators of the motor to be controlled, define the management objectives of the battery to be managed, and construct the sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and the management objectives;

[0183] The edge computing network construction module 202 is used to calculate the instantaneous coefficient of the sensor network, and when the instantaneous coefficient meets the preset instantaneous coefficient threshold, construct the edge computing node of the sensor network, and configure the redundant computing node of the edge computing node, and construct the edge computing network of the motor to be controlled and the battery to be managed through the edge computing node and the redundant computing node;

[0184] The battery management model building module 203 is used to obtain the motor control data and battery energy management data of the motor to be controlled and the battery to be managed, and to build a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, and to establish a battery unsupervised management model of the battery to be managed through the battery energy management data;

[0185] The integrated computing network construction module 204 is used to integrate the motor hybrid deep DRL model and the battery unmanaged supervision model into the edge computing network to obtain an integrated computing network, collect real-time motor data and real-time battery data of the motor to be controlled and the battery to be managed by using the sensor network, analyze the motor state of the motor to be controlled through the real-time motor data, and analyze the battery state of the battery to be managed according to the real-time battery data;

[0186] The motor and battery integrated control module 205 is used to construct an integrated computing model of the integrated computing network based on the motor status and the battery status, and to establish an AI multi-objective algorithm of the integrated computing model through the performance indicators and management objectives. Through the AI ​​multi-objective algorithm, the integrated control instructions of the motor to be controlled and the battery to be managed are analyzed, and the integrated control of the motor to be controlled and the battery to be managed is performed based on the integrated control instructions.

[0187] In detail, the modules described in the AI-based motor torque control and battery energy management integrated system 200 described in the embodiment of the present invention adopt the same technical means as the AI-based motor torque control and battery energy management integrated method described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0188] An embodiment of the present invention provides an electronic device for implementing an AI-based integrated method for motor torque control and battery energy management.

[0189] See also Figure 3 As shown, the electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as an AI-based motor torque control and battery energy management integrated method program.

[0190] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor is the control core (Control Unit) of the electronic device, which uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes programs or modules stored in the memory (for example, executing an AI-based motor torque control and battery energy management integrated program, etc.), and calls the data stored in the memory to execute various functions of the electronic device and process data.

[0191] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory may also include both an internal storage unit of the electronic device and an external storage device. The memory can be used not only to store application software and various types of data installed in the electronic device, such as the code of the integrated program of motor torque control and battery energy management based on AI, but also to temporarily store data that has been output or is to be output.

[0192] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0193] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0194] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0195] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0196] The AI-based motor torque control and battery energy management integrated program stored in the memory of the electronic device is a combination of multiple instructions, and when running in the processor, it can achieve:

[0197] Determine the performance indicators of the motor to be controlled, define the management objectives of the battery to be managed, and build a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and the management objectives;

[0198] Calculate the instantaneous coefficient of the sensor network, and when the instantaneous coefficient meets the preset instantaneous coefficient threshold, construct an edge computing node of the sensor network, configure a redundant computing node of the edge computing node, and construct an edge computing network of the motor to be controlled and the battery to be managed through the edge computing node and the redundant computing node;

[0199] Acquire motor control data and battery energy management data of the motor to be controlled and the battery to be managed, construct a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, and establish a battery unsupervised management model of the battery to be managed through the battery energy management data;

[0200] Integrate the motor hybrid deep DRL model and the battery unmanaged supervision model into the edge computing network to obtain an integrated computing network, use the sensor network to collect real-time motor data and real-time battery data of the motor to be controlled and the battery to be managed, analyze the motor state of the motor to be controlled through the real-time motor data, and analyze the battery state of the battery to be managed according to the real-time battery data;

[0201] Based on the motor state and the battery state, an integrated computing model of the integrated computing network is constructed, and through the performance indicators and management objectives, an AI multi-objective algorithm of the integrated computing model is established, and through the AI ​​multi-objective algorithm, the integrated control instructions of the motor to be controlled and the battery to be managed are analyzed, and based on the integrated control instructions, integrated control of the motor to be controlled and the battery to be managed is performed.

[0202] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0203] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0204] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0205] Determine the performance indicators of the motor to be controlled, define the management objectives of the battery to be managed, and build a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and the management objectives;

[0206] Calculate the instantaneous coefficient of the sensor network, and when the instantaneous coefficient meets the preset instantaneous coefficient threshold, construct an edge computing node of the sensor network, configure a redundant computing node of the edge computing node, and construct an edge computing network of the motor to be controlled and the battery to be managed through the edge computing node and the redundant computing node;

[0207] Acquire motor control data and battery energy management data of the motor to be controlled and the battery to be managed, construct a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, and establish a battery unsupervised management model of the battery to be managed through the battery energy management data;

[0208] Integrate the motor hybrid deep DRL model and the battery unmanaged supervision model into the edge computing network to obtain an integrated computing network, use the sensor network to collect real-time motor data and real-time battery data of the motor to be controlled and the battery to be managed, analyze the motor state of the motor to be controlled through the real-time motor data, and analyze the battery state of the battery to be managed according to the real-time battery data;

[0209] Based on the motor state and the battery state, an integrated computing model of the integrated computing network is constructed, and through the performance indicators and management objectives, an AI multi-objective algorithm of the integrated computing model is established, and through the AI ​​multi-objective algorithm, the integrated control instructions of the motor to be controlled and the battery to be managed are analyzed, and based on the integrated control instructions, integrated control of the motor to be controlled and the battery to be managed is performed.

[0210] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0211] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0212] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0213] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0214] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0215] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0216] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0217] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An AI-based integrated method for motor torque control and battery energy management, characterized in that: The method comprises: Determine the performance indicators of the motor to be controlled, define the management objectives of the battery to be managed, and build a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and the management objectives; Calculate the instantaneous coefficient of the sensor network, and when the instantaneous coefficient meets the preset instantaneous coefficient threshold, construct an edge computing node of the sensor network, configure a redundant computing node of the edge computing node, and construct an edge computing network of the motor to be controlled and the battery to be managed through the edge computing node and the redundant computing node; Acquire motor control data and battery energy management data of the motor to be controlled and the battery to be managed, construct a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, and establish a battery unsupervised management model of the battery to be managed through the battery energy management data; Integrate the motor hybrid deep DRL model and the battery unmanaged supervision model into the edge computing network to obtain an integrated computing network, use the sensor network to collect real-time motor data and real-time battery data of the motor to be controlled and the battery to be managed, analyze the motor state of the motor to be controlled through the real-time motor data, and analyze the battery state of the battery to be managed according to the real-time battery data; Based on the motor state and the battery state, an integrated computing model of the integrated computing network is constructed, and through the performance indicators and management objectives, an AI multi-objective algorithm of the integrated computing model is established, and through the AI ​​multi-objective algorithm, the integrated control instructions of the motor to be controlled and the battery to be managed are analyzed, and based on the integrated control instructions, integrated control of the motor to be controlled and the battery to be managed is performed.

2. The AI-based motor torque control and battery energy management integrated method according to claim 1, characterized in that: The step of constructing a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and management objectives includes: Identifying the working environment of the motor to be controlled and the battery to be managed; Determine the sensor equipment of the motor to be controlled and the battery to be managed according to the performance indicators, management objectives and working environment; Analyzing the device performance of the sensing device, wherein the device performance includes sensitivity, linearity, repeatability, and durability; When the device performance meets a preset device performance threshold, analyzing the coordinate location of the sensor device; Constructing a star topology of the sensor device through the coordinate locations; According to the star topology, a data transmission protocol of the sensor device is defined; Based on the data transmission protocol, a sensor network of the motor to be controlled and the battery to be managed is constructed.

3. The AI-based motor torque control and battery energy management integrated method according to claim 2, characterized in that: The analyzing the device performance of the sensing device includes: Performing a performance test on the sensor device to obtain a performance test parameter; By means of the performance test parameters, the final output value, the initial output value, the final input value and the initial input value of the sensor device are analyzed, The sensitivity of the sensor device is calculated using the following formula using the final output value, the initial output value, the final input value and the initial input value: σ=Δ(O_fR_f) / Δ(D_f-U_f) Wherein, σ represents the sensitivity of the sensor device, Δ(O_f-R_f) represents the output change of the f-th measurement point of the sensor device, Δ(D_f-U_f) represents the input change of the f-th measurement point of the sensor device, O_f represents the final output value of the f-th measurement point of the sensor device, R_f represents the initial output value of the f-th measurement point of the sensor device, D_f represents the final input value of the f-th measurement point of the sensor device, and U_f represents the initial input value of the f-th measurement point of the sensor device; According to the final output value, the linearity of the sensor device is calculated using the following formula: Wherein, L represents the linearity of the sensor device, O_f represents the final output value of the f-th measurement point of the sensor device, O_f,th ​​represents the theoretical output value of the f-th measurement point of the sensor device, and N represents the number of corresponding measurement points of the sensor device; Analyzing the coefficient of consistency and the number of cycles of the sensing device based on the final output value, the initial output value, the final input value, and the initial input value; Determining the repeatability of the sensing device based on the coefficient of consistency; Determining the durability of the sensing device through the number of cycles; The device performance of the sensing device is analyzed based on the sensitivity, linearity, repeatability and durability.

4. The AI-based motor torque control and battery energy management integrated method as claimed in claim 3, characterized in that: The edge computing node of the sensor network is constructed, including: Analyzing the data processing requirements of the sensor network, wherein the data processing requirements include: data real-time requirements, computational complexity, and storage requirements; Based on the data processing requirements, determining edge computing requirement resources of the sensor network; Determining edge computing hardware components of the sensor network according to the edge computing demand resources; Based on the edge computing hardware components, establishing an edge computing software architecture of the sensor network; Constructing an initial edge computing node of the sensor network according to the edge computing software architecture and edge computing hardware components; Calculating a collaboration coefficient of the initial edge computing node; When the cooperation coefficient meets a preset cooperation coefficient threshold, the initial edge computing node is used as an edge computing node of the sensor network.

5. The AI-based motor torque control and battery energy management integration method according to claim 4, characterized in that: The analyzing the data processing requirements of the sensor network includes: Analyzing preset data collection time requirements and preset data processing time requirements of the sensor network; Determining the data real-time requirement of the sensor network through the preset data collection time requirement and the preset data processing time requirement; Identifying a preset data volume and data size of the sensor network, and determining a storage requirement of the sensor network based on the preset data volume and data size; Defining the data algorithm complexity and data preprocessing times of the sensor network; Based on the data algorithm complexity and the number of data preprocessing times, the computational complexity of the sensor network is calculated using the following formula: C_complexity=m*∑(C_algorithm_i*m_i) Wherein, C_complexity represents the computational complexity of the sensor network, m represents the number of data preprocessing times of the sensor network, C_algorithm_i represents the data algorithm complexity of data point i in the sensor network, and m_i represents the number of preprocessing times of data point i in the number of data preprocessing times of the sensor network; The data processing requirements of the sensor network are determined according to the data real-time requirements, computational complexity and storage requirements.

6. The AI-based motor torque control and battery energy management integration method according to claim 5, characterized in that: The step of constructing a motor hybrid deep DRL model of the motor to be controlled based on the motor control data includes: Defining the state space, torque action space and reward mechanism of the motor to be controlled; Analyzing a Q value data set of the motor to be controlled based on the motor control data, the state space, the torque action space, and the reward mechanism, wherein the Q value data set includes a current state, a torque action, a next state, and a reward; Calculating the motor Q value of the motor to be controlled by using the Q value data set; According to the motor Q value, construct an initialization Q table of the motor to be controlled; Using a preset experience replay pool, the initialized Q table is updated to obtain an updated Q table; Calculating the expected value of the updated Q table; When the expected value meets the preset expected standard value, the motor hybrid depth DRL model of the motor to be controlled is constructed using the updated Q table.

7. The AI-based motor torque control and battery energy management integrated method according to claim 6, characterized in that: The step of calculating the motor Q value of the motor to be controlled by using the Q value data set includes: Constructing a Q value function of the motor to be controlled; Determining a learning rate and a discount factor of the Q-value function; Based on the learning rate, discount factor and Q value data set, the motor Q value of the motor to be controlled is calculated using the Q value function: Q(s,a)=(1-α)*Q(s,a)+α*[ρ+ε*max_a'Q(s',α)-Q(s,a)] Among them, Q(s,a) represents the motor Q value of the motor to be controlled in the Q value dataset corresponding to the current state s and torque action a, Q(s',a') represents the motor Q value of the motor to be controlled in the Q value dataset corresponding to the next state s' and torque action a', α represents the learning rate of the Q value function, ε represents the discount factor of the Q value function, ρ represents the reward corresponding to the Q value dataset, and max_a' represents the maximum value of the torque action in the Q value dataset.

8. The AI-based motor torque control and battery energy management integrated method according to claim 7, characterized in that: The step of establishing a battery unsupervised management model of the battery to be managed by using the battery energy management data includes: Normalizing the battery energy management data to obtain normalized management data; extracting energy management features of the normalized management data; Calculating characteristic principal component coefficients of the energy management characteristic; Extracting key energy management features of the energy management features according to the feature principal component coefficients, wherein the key energy management features include voltage change, current change, and temperature change; Determining an unsupervised learning algorithm for the battery to be managed; A battery unsupervised supervision model of the battery to be managed is constructed according to the key energy management features and the unsupervised learning algorithm.

9. The AI-based motor torque control and battery energy management integrated method according to claim 8, characterized in that: The step of analyzing the integrated control instructions of the motor to be controlled and the battery to be managed by the AI ​​multi-objective algorithm includes: According to the performance indicators and management objectives corresponding to the motor to be controlled and the battery to be managed, using the integrated calculation model corresponding to the motor to be controlled and the battery to be managed to analyze the initial optimization parameter group of the motor to be controlled and the battery to be managed; Calculate the parameter group response value of the initial optimization parameter group corresponding to the initial optimization parameter group by using the AI ​​multi-objective algorithm; Determining a target optimized parameter group in the initial optimized parameter group based on the parameter group response value; According to the target optimization parameter group, integrated control instructions for the motor to be controlled and the battery to be managed are determined.

10. An AI-based motor torque control and battery energy management integrated system, characterized in that: The system is used to execute the AI-based motor torque control and battery energy management integrated method as described in any one of claims 1 to 9, the system comprising: A sensor network construction module, used to determine the performance indicators of the motor to be controlled, define the management objectives of the battery to be managed, and construct a sensor network of the motor to be controlled and the battery to be managed based on the performance indicators and the management objectives; An edge computing network construction module is used to calculate the instantaneous coefficient of the sensor network, and when the instantaneous coefficient meets the preset instantaneous coefficient threshold, construct an edge computing node of the sensor network, and configure a redundant computing node of the edge computing node, and construct an edge computing network of the motor to be controlled and the battery to be managed through the edge computing node and the redundant computing node; A battery management model building module is used to obtain the motor control data and battery energy management data of the motor to be controlled and the battery to be managed, and to build a motor hybrid deep DRL model of the motor to be controlled based on the motor control data, and to establish a battery unsupervised management model of the battery to be managed through the battery energy management data; An integrated computing network building module is used to integrate the motor hybrid deep DRL model and the battery unmanaged supervision model into the edge computing network to obtain an integrated computing network, and use the sensor network to collect real-time motor data and real-time battery data of the motor to be controlled and the battery to be managed, analyze the motor state of the motor to be controlled through the real-time motor data, and analyze the battery state of the battery to be managed according to the real-time battery data; The motor and battery integrated control module is used to construct an integrated computing model of the integrated computing network based on the motor state and the battery state, and to establish an AI multi-objective algorithm of the integrated computing model through the performance indicators and management objectives, analyze the integrated control instructions of the motor to be controlled and the battery to be managed through the AI ​​multi-objective algorithm, and perform integrated control of the motor to be controlled and the battery to be managed based on the integrated control instructions.

Images