Power battery dual-circulation heat dissipation control device based on temperature measurement

Abstract

The present application provides a dual-circulation heat dissipation control device for power batteries based on temperature measurement, which relates to the field of battery heat dissipation control technology, including: receiving driving input information and performing battery power output demand analysis; obtaining real-time battery temperature through temperature measurement, and predicting battery temperature changes based on the battery discharge power sequence; optimizing heat dissipation control based on the predicted battery temperature change sequence to obtain a dual-circulation heat dissipation control sequence; collecting real-time temperature data of the target vehicle through temperature measurement while the driving system performs vehicle driving control and the heat dissipation system performs heat dissipation control synchronously; and performing compensation control based on the deviation between the real-time temperature data and the safe temperature of the power battery. This application can solve the technical problem in the prior art of poor battery heat dissipation efficiency due to the lack of flexibility in adjusting the heat dissipation control strategy when facing rapid temperature changes. The heat dissipation efficiency of the battery is improved through a dual-circulation heat dissipation system and real-time temperature control compensation.

Description

Technical Field

[0001] The present application relates to the technical field of battery heat dissipation control, and in particular to a power battery dual-circulation heat dissipation control device based on temperature measurement. Background Art

[0002] Power batteries are a core component of new energy vehicles and a key direction for future energy transformation. Power battery heat dissipation control primarily regulates battery temperature in real time based on factors such as the battery's charge and discharge power, ambient temperature, and vehicle speed. This prevents the battery temperature from being too high or too low, thus avoiding degradation in battery performance, shortened lifespan, and even safety accidents caused by overheating or overcooling. Existing power battery heat dissipation control methods have been able to ensure stable battery temperatures to a certain extent, but they still face some challenges. When the battery load fluctuates dramatically or the temperature changes rapidly (such as during acceleration, deceleration, or drastic changes in the external environment), the heat dissipation control strategy often cannot be adjusted in a timely manner, causing the battery temperature to exceed the safe range and affecting the battery's heat dissipation efficiency.

[0003] In summary, the prior art has a technical problem of low heat dissipation efficiency of the battery due to insufficient flexibility in adjusting the heat dissipation control strategy when facing rapid temperature changes. Summary of the Invention

[0004] The purpose of this application is to provide a dual-circulation heat dissipation control device for a power battery based on temperature measurement, so as to solve the technical problem in the prior art that the heat dissipation efficiency of the battery is low due to the inflexible adjustment of the heat dissipation control strategy when facing rapid temperature changes.

[0005] In view of the above problems, the present application provides a power battery dual-circulation heat dissipation control device based on temperature measurement, wherein the power battery dual-circulation heat dissipation control device based on temperature measurement includes: receiving driving input information, and performing battery power output demand analysis based on the driving input information to obtain a battery discharge power sequence; obtaining the real-time battery temperature of the power battery through temperature measurement, and taking the real-time battery temperature as the starting point, predicting the battery temperature change according to the battery discharge power sequence, and outputting the battery predicted temperature change time sequence; performing heat dissipation control optimization according to the battery predicted temperature change time sequence to obtain a dual-circulation heat dissipation control sequence; in the process where the driving system performs vehicle driving control based on the driving control sequence and the heat dissipation system synchronously performs heat dissipation control of the power battery based on the dual-circulation heat dissipation control sequence, real-time temperature data of the target vehicle is collected through temperature measurement; and compensation control of the dual-circulation heat dissipation control sequence is performed based on the deviation between the real-time temperature data and the safe temperature of the power battery.

[0006] The technical solution provided in this application has at least the following technical effects or advantages:

[0007] The system receives driving input information and analyzes battery power output requirements based on the driving input information to obtain a battery discharge power sequence. It also obtains the real-time battery temperature of the power battery through temperature measurement. Using the real-time battery temperature as a starting point, it predicts battery temperature changes based on the battery discharge power sequence and outputs a predicted battery temperature change time sequence. It then optimizes heat dissipation control based on the predicted battery temperature change time sequence to obtain a dual-cycle heat dissipation control sequence. While the driving system controls the vehicle based on the driving control sequence and the heat dissipation system simultaneously controls the power battery based on the dual-cycle heat dissipation control sequence, it collects real-time temperature data of the target vehicle through temperature measurement. Compensation control for the dual-cycle heat dissipation control sequence is performed based on the deviation between the real-time temperature data and the safe temperature of the power battery. In other words, the system predicts battery output based on the driving input information and the battery temperature, and performs dual-cycle heat dissipation control based on the output prediction. While dissipating heat in advance, it also compensates for heat dissipation based on the real-time battery temperature. This achieves temperature management of the power battery of the new energy vehicle, ensuring that the battery operates within an optimal temperature range and improving battery heat dissipation efficiency.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0010] Figure 1 This is a schematic diagram of the structure of the power battery dual-circulation heat dissipation control device based on temperature measurement in this application;

[0011] Figure 2 This is a flow chart of the predicted temperature change sequence of the output battery in the power battery dual-cycle heat dissipation control device based on temperature measurement in this application.

[0012] Description of the accompanying drawings: demand analysis module 11, temperature change prediction module 12, control optimization module 13, heat dissipation control module 14, temperature compensation module 15. DETAILED DESCRIPTION

[0013] This application provides a dual-circulation heat dissipation control device for power batteries based on temperature measurement, resolving the existing technical problem of low battery heat dissipation efficiency due to inflexible adjustment of heat dissipation control strategies in the face of rapid temperature changes. Battery output is predicted using driving input information and battery temperature, and dual-circulation heat dissipation control is performed based on the output prediction. While dissipating heat in advance, heat dissipation compensation is performed based on the battery's real-time temperature. This achieves temperature management of new energy vehicle power batteries, ensuring that the batteries operate within the optimal temperature range and improving battery heat dissipation efficiency.

[0014] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0015] For examples, please see the attached Figure 1 The present application provides a power battery dual-circulation heat dissipation control device based on temperature measurement, wherein the power battery dual-circulation heat dissipation control device based on temperature measurement includes:

[0016] The demand analysis module 11 is used to receive driving input information, and perform battery power output demand analysis based on the driving input information to obtain a battery discharge power sequence.

[0017] Specifically, driving input information is obtained through onboard sensors (such as GPS, speed sensors, and steering sensors) to determine the vehicle's starting point, destination, and specific travel path. Based on the vehicle's planned route, or route, which typically consists of a starting point, waypoints, and destination, traffic situation data is collected. This data includes information such as traffic flow, traffic density, and road conditions at a specific time, location, or road section. This includes information on traffic flow, speed limits, congestion, and traffic signals. Once the driving route is determined, traffic situation data is collected based on the road section structure. This data is collected from multiple sources, including traffic surveillance cameras, traffic sensors, and traffic management platforms, to obtain real-time information on traffic flow, vehicle speed, and road conditions for each section. For example, suppose a vehicle's route passes through City A and City B, encompassing a variety of highways and urban roads. Highway sections tend to have higher traffic volumes but faster speeds, while urban road sections may have more traffic lights and congestion. This information can be obtained in real time through a network-based traffic management system.

[0018] Based on traffic situation information (such as road section traffic flow and speed limits), driving behavior is predicted and analyzed, including control actions such as acceleration, braking, and steering. Based on the traffic situation and driving behavior prediction model, the vehicle's driving operation sequence, including acceleration, braking, and steering commands, is derived. The collected traffic situation information is used to analyze the driving environment (e.g., traffic congestion, road conditions, etc.) for each route, and based on this information, the vehicle's driving behavior is predicted. Appropriate driving control sequences are generated based on different road section characteristics (e.g., speed limits, traffic density, etc.).

[0019] The system uses the vehicle's driving control sequence to predict battery power output requirements and analyze the power required to support current driving behavior. This typically takes into account the impact of acceleration and deceleration on battery power. Using the driving control sequence (i.e., the predicted sequence of acceleration, braking, steering, and other behaviors) as input, the system uses a pre-built output power prediction model to predict the required battery power. By predicting the battery's power requirements in different driving situations based on driver control and environmental information, the system optimizes battery management and improves driving safety and efficiency.

[0020] The temperature change prediction module 12 is used to obtain the real-time battery temperature of the power battery through temperature measurement, and use the real-time battery temperature as a starting point to predict the battery temperature change according to the battery discharge power sequence, and output a battery predicted temperature change time series.

[0021] Specifically, the power battery's temperature is measured in real time using a temperature sensor or other monitoring device to obtain the real-time battery temperature. Battery temperature fluctuations are closely related to their power output. Higher power levels generate more heat within the battery, leading to higher temperatures. The target vehicle's standard heat dissipation status—that is, its normal heat dissipation—is determined. Using the standard heat dissipation status as a constraint, network data is retrieved to obtain multiple sample battery status data for multiple sample vehicles of the same model as the target vehicle. These sample battery status data include sample power output sequences and sample battery temperature sequences. The battery discharge power sequence represents the battery's power output at each moment or time period. This sequence is captured in real time by the battery management system and dynamically adjusted based on the vehicle's operating status, driving behavior, or external environmental factors. To predict battery temperature fluctuations, a battery temperature change prediction model is constructed using historical data.

[0022] The battery discharge power series and real-time battery temperature are fed into the battery temperature change prediction model to recursively predict battery temperature changes. Each prediction result output by the model is used as the input for the next prediction, forming a recursive prediction process that ultimately outputs a predicted battery temperature change time series. The temperature change prediction model generates a time series of battery temperature changes over a period of time. This is typically a dynamic prediction result that is continuously updated over time and with changes in power output. By combining real-time temperature and discharge power series, the battery temperature change trend can be predicted with high accuracy. Real-time monitoring of battery temperature effectively prevents battery overheating or overcooling, ensuring that the battery operates within a safe temperature range.

[0023] The control optimization module 13 is used to perform heat dissipation control optimization according to the battery predicted temperature change time sequence to obtain a dual-cycle heat dissipation control sequence.

[0024] Specifically, a battery temperature variation time series curve is drawn based on the predicted battery temperature variation time series, identifying temperature variation nodes—points where the temperature rise rate changes. As the temperature rise rate changes, the corresponding heat dissipation control should also change. Based on the predicted battery temperature variation time series, the heat dissipation control strategy is dynamically adjusted to ensure that the battery temperature is always maintained within a safe and ideal range. Through heat dissipation control optimization, the most appropriate heat dissipation method (air cooling, water cooling, or a combination of the two) and the optimal operating parameters for each method (such as air cooling cycle speed and water cooling cycle speed) can be selected.

[0025] In a dual-circulation cooling system, water cooling and air cooling typically work together. Water cooling systems remove heat generated by the battery through the flow of coolant. The circulation speed determines the coolant flow rate, which affects the cooling efficiency. Air cooling systems remove heat through the flow of air. The air cooling circulation speed determines the fan speed, which affects the air flow rate. Based on the predicted battery temperature changes, the temperature rise rate and target temperature are first determined, and then adjustments are made based on the characteristics of the water and air cooling systems. An optimization algorithm is used to adjust the circulation speeds of water and air cooling to balance their energy efficiency and ensure effective battery temperature control.

[0026] In the predicted temperature change time series, the system identifies periods of rapid battery temperature change based on the temperature rise rate, indicating the need for enhanced heat dissipation. Different heat dissipation control parameters (such as water cooling rate and air cooling rate) result in different energy consumption. During the optimization process, the system calculates the energy consumption of each control strategy and selects the solution that maximizes energy savings while ensuring stable battery temperature. During each period of battery temperature change, dual-loop heat dissipation control parameters are dynamically generated based on the temperature trend and the optimized results of the heat dissipation control parameters. The control sequence must consider the continuity of temperature changes and the temperature rise rate nodes to avoid excessive or insufficient heat dissipation caused by sudden temperature changes. The optimized dual-loop heat dissipation control sequence—a set of optimal water and air cooling control parameters—is used to control the operating state of the heat dissipation system. This includes all adjustment parameters throughout the entire temperature change process and enables real-time adjustments based on battery temperature fluctuations. This dual-loop heat dissipation control strategy precisely regulates battery temperature, preventing overheating or overcooling and improving battery safety and stability. Real-time monitoring and adjustment of the heat dissipation strategy ensures that the battery operates within the optimal operating temperature range.

[0027] The heat dissipation control module 14 is used to collect real-time temperature data of the target vehicle through temperature measurement when the driving system performs vehicle driving control based on the driving control sequence and the heat dissipation system synchronously performs heat dissipation control of the power battery based on the dual-loop heat dissipation control sequence.

[0028] Specifically, the driving control sequence is a sequence of control commands generated by the driving control system based on driving inputs (such as throttle, brake, and steering). It directs the vehicle's motion (such as speed and acceleration) under different road conditions. Generated by the vehicle's driving system, the driving control sequence typically includes outputs for control commands such as acceleration, braking, and steering. This sequence directly impacts battery power output, as the power output requirements of the power battery are closely related to the vehicle's driving behavior. Vehicle driving is controlled according to the driving control sequence. The cooling system makes real-time adjustments based on the dual-loop cooling control sequence. Based on the battery's power output requirements and predicted temperature changes, it adjusts the operating conditions of the water and air cooling systems (such as water flow and air speed) to maintain stable battery temperature. As the battery temperature changes, the cooling control system adjusts the cooling strategy to achieve optimal temperature management.

[0029] Real-time temperature data collection ensures effective battery operation during thermal control. Using temperature sensors, the system continuously measures the actual battery temperature and provides real-time feedback to the thermal control system. The thermal control system uses this data to determine whether to adjust its thermal control strategy. Through real-time temperature monitoring, battery temperature data is fed back into the thermal control system, achieving closed-loop temperature control. Within this closed-loop process, driving control sequences influence battery power output, and changes in battery temperature influence adjustments in the thermal control system, ensuring that the battery's operating temperature remains within a safe range. Real-time temperature data and the thermal control system work closely together to respond to temperature changes. When the battery temperature approaches a preset safety limit, the thermal control system immediately adjusts, such as increasing the intensity of water or air cooling. The synergistic effect of real-time temperature data collection and the thermal control strategy allows precise battery temperature management, avoiding battery performance degradation or safety issues caused by excessively high or low temperatures, and ensuring optimal thermal support for the battery under varying driving conditions. Dynamic adjustment of water and air cooling parameters ensures high energy efficiency for the thermal control system.

[0030] The temperature compensation module 15 is used to perform compensation control of the dual-cycle heat dissipation control sequence according to the real-time temperature data and the safety temperature deviation of the power battery.

[0031] Specifically, the current temperature of the battery is monitored in real time based on the temperature sensor. The safe temperature deviation refers to the difference between the real-time temperature and the safe operating temperature. Generally, the power battery has a temperature range within which the battery can operate safely. When the real-time temperature of the battery exceeds this range, a temperature deviation occurs, and measures may need to be taken to adjust it. When the battery temperature deviation exceeds the set threshold, the heat dissipation control system activates compensation control. Compensation control compensates for temperature deviation by adjusting the control parameters of the heat dissipation system (such as water cooling circulation speed, air cooling speed, etc.) to ensure that the battery temperature does not exceed the safe range. If the battery temperature is high, the water cooling circulation speed will be increased. If the temperature deviation is large, the air cooling speed will also be increased to enhance the heat dissipation effect.

[0032] Based on real-time temperature deviations, the system calculates compensation requirements and generates corresponding compensation control strategies, such as increasing the flow rate or air speed of the water and air cooling systems to improve heat dissipation efficiency. During the compensation control process, the system continuously adjusts cooling control parameters based on changes in battery temperature to ensure the temperature returns to a safe range. Real-time temperature data is continuously fed back to the system during this compensation control process. As the cooling control strategy executes, the battery temperature gradually decreases or stabilizes. When the temperature returns to the set safe range, the intensity of water and air cooling is reduced to avoid overcooling and save energy. Compensation control is not just a simple adjustment; it is a dynamic optimization process. As battery temperature and power output change, the cooling system continuously optimizes operating parameters based on the compensation control sequence. For example, if the battery temperature remains high, the cooling system will adopt stronger water cooling control; conversely, if the temperature returns to the normal range, the cooling system will reduce the intensity of air and water cooling. By monitoring battery temperature in real time and implementing compensation control based on temperature deviations, the battery temperature can be precisely controlled to prevent overheating or overcooling, ensuring the battery remains within the optimal operating temperature range and maintaining a stable battery temperature under various operating conditions, ensuring normal vehicle operation.

[0033] Furthermore, the demand analysis module 11 in the power battery dual-circulation heat dissipation control device based on temperature measurement is also used for:

[0034] A driving route is generated based on the driving input information; traffic situation data is collected based on the road segment composition of the driving route to obtain multiple traffic situation information for multiple sections of the driving route; driving control analysis is performed based on the multiple traffic situation information to output the driving control sequence; an output power prediction model is pre-constructed, and battery power output demand analysis is performed by inputting the driving control sequence into the output power prediction model to obtain the battery discharge power sequence.

[0035] Specifically, based on vehicle or driver input, including the vehicle's current driving mode, starting and ending points, speed, acceleration and braking operations, a specific driving route is generated. This is the path the vehicle is scheduled to travel over a period of time, including multiple sections between multiple starting and ending points, such as highways, urban roads, rural roads, and other different types of sections. Based on the road segment composition of the driving route, namely the different types of sections the vehicle needs to pass through, such as main roads, secondary roads, and highways, traffic situation data is collected to collect traffic condition information for each section along the route. Traffic situation data refers to the real-time collection and recording of information such as traffic flow, traffic signals, and traffic congestion on the road, including factors such as vehicle volume, road capacity, traffic accidents, and weather conditions.

[0036] Through on-board sensors or connections to road network systems, real-time traffic information is collected from multiple traversing sections, resulting in multiple traffic situation information for each traversing section along the driving route. This information includes traffic flow, traffic accidents, traffic light cycles, congestion, and weather conditions. Driving control analysis is performed on each of the multiple traffic situation information for each traversing section. By analyzing the driving input information and traffic situation information, corresponding driving behavior control strategies are formulated, including optimized decisions regarding acceleration, deceleration, lane changes, and steering, to improve driving efficiency or conserve energy. Taking any one of the multiple traversing sections as an example, namely, the first traversing section, the first traversing section is divided into multiple first one-dimensional sections based on the variation in section shape. Specifically, the sections are divided into sections with a single driving direction or shape (e.g., straight roads, one-way roads, etc.). First traffic situation information corresponding to the first traversing section is extracted from the multiple traffic situation information. Multiple first one-dimensional section features are also extracted for each of the multiple first one-dimensional sections, including section length features, section undulation features, section shape features, and section speed limit features.

[0037] The first driving direction vector from the first traffic situation information is obtained, i.e., the direction vector of the vehicle traveling on the first traversed road section. This vector is usually represented as a vector with a certain direction and angle, which determines the vehicle's direction of travel on the road section. The first driving direction vector and multiple first one-dimensional road section features are synchronized to the driving control prediction model, and the driver's behavior is analyzed and predicted to obtain multiple first driving control parameters, including speed, turning angle, acceleration, and braking. The driving control prediction model is a mathematical model for predicting driving behavior. It is constructed based on a knowledge graph and predicts the driver's control behavior (such as acceleration, deceleration, steering, etc.) based on the input road section features and driving direction information. The specific construction process is explained in detail in the corresponding steps below.

[0038] The multiple first driving control parameters are sorted based on the connections between the various road sections to ensure a smooth transition of the vehicle's driving behavior on each road section, thereby obtaining first driving control information. Similarly, the above analysis is performed on the multiple traffic situation information for the multiple traversed road sections to obtain multiple driving control information. The multiple driving control information is then sorted based on the connections between the multiple traversed road sections to obtain a final driving control sequence, which includes the driving behavior control instructions for each road section calculated based on the traffic situation and road section characteristics.

[0039] An output power prediction model is constructed based on multiple sample driving control data and multiple sample battery output powers. This model predicts the battery's output power based on driving control sequences (such as acceleration and braking). The detailed construction is explained in detail in the corresponding steps below and is not detailed here. The driving control sequence is input into the output power prediction model to analyze the battery's power output requirements. This model considers the impact of acceleration and deceleration on battery power and analyzes the power required by the battery to support the current driving behavior. Using the driving control sequence (i.e., the predicted sequence of acceleration, braking, steering, etc.) as input, the pre-built output power prediction model predicts the required battery power. The power output required is predicted based on the driving behavior at each moment, providing the battery management system with accurate power demand information. A battery discharge power sequence is a sequence of battery power output over time. It describes the battery's power output requirements at different time points and is typically directly related to the vehicle's driving behavior. For example, a vehicle accelerates for 1 second with an output power of 200W; for the next 3 seconds, the vehicle maintains a constant speed with an output power of 150W; and for the next 5 seconds, the vehicle brakes with an output power of 50W. By combining traffic situation data, driving control sequences and output power prediction models, the battery power demand can be accurately predicted, and the battery power output demand can be dynamically adjusted according to the real-time driving environment (such as traffic flow, road conditions, vehicle speed, etc.), thereby optimizing battery energy efficiency. This not only improves the utilization efficiency of the power battery, but also effectively extends the battery life.

[0040] Furthermore, the demand analysis module 11 in the power battery dual-circulation heat dissipation control device based on temperature measurement is also used for:

[0041] Interactively obtaining multiple sample driving control data and multiple sample battery output powers; performing power change correlation analysis on the multiple sample driving control data and the multiple sample battery output powers to obtain N power-related control indicators; using the N power-related control indicators to filter the multiple sample driving control data to obtain multiple sample related control data; completing the construction of the output power prediction model by performing multiple linear regression analysis based on the multiple sample related control data and the multiple sample battery output powers; after performing data preprocessing on the driving control sequence using the N power-related control indicators, performing battery power output demand analysis via the output power prediction model to obtain the battery discharge power sequence.

[0042] Specifically, multiple sample driving control data and corresponding sample battery output power are obtained from actual driving or simulated driving data. Driving control data refers to control information generated by the driving system (such as the autonomous driving system or the driver), typically including behavioral data such as acceleration, braking, and steering, reflecting the vehicle's operating instructions. Battery output power refers to the amount of electrical energy provided by the battery over a certain period of time, usually expressed in watts (W). The battery's output power is closely related to factors such as the vehicle's power requirements, driving style, and road conditions.

[0043] The relationship between multiple sample driving control data and multiple sample battery output powers is analyzed to identify the correlation between driving behavior (such as acceleration, braking, and steering) and battery power output. Power-related control indicators refer to the key control factors that can affect power output extracted from the correlation between driving control behavior and battery output power. For example, acceleration may directly affect the battery's output power, while driving direction (turning left or right) may only affect driving speed control and have no significant impact on power output. Through power change correlation analysis, N power-related control indicators are extracted, including acceleration level is proportional to battery power output, braking intensity is inversely proportional to battery power output, and steering angle has no direct impact on battery power output.

[0044] Using N power-related control indicators, multiple sample driving control data are screened for driving control data that are significantly correlated with battery power output. This results in multiple sample correlated control data, including driving control behaviors that are closely related to battery power changes. The purpose of this screening is to reduce unnecessary input features, thereby simplifying the model calculation process and improving prediction accuracy. Multiple linear regression analysis is performed on the multiple sample correlated control data and multiple sample battery output powers to construct an output power prediction model. Multiple linear regression analysis is a statistical method used to model the relationship between multiple independent variables and dependent variables. Driving control data (such as acceleration and braking intensity) are the independent variables, and battery output power is the dependent variable. Multiple linear regression learns the relationship between these independent and dependent variables based on the sample data and uses the resulting model to predict future power demand. Multiple sample driving control data (such as acceleration intensity and braking intensity) are input into the multiple linear regression model along with the corresponding battery power output (dependent variable). The model then identifies the coefficients (weights) that influence acceleration and braking intensity on battery output power, thereby predicting the battery power demand corresponding to new driving behaviors.

[0045] Regression analysis generates a regression equation describing the relationship between driving control behaviors (such as acceleration and braking) and battery output power. By repeatedly performing regression analysis on sample data, the model gradually adjusts the coefficients to ensure that the predicted power value is as close as possible to the actual battery output power, thereby improving model accuracy. The final optimized model is used as the output power prediction model.

[0046] N power-related control indicators are applied to the data preprocessing of the driving control sequence. Key data, such as acceleration and braking intensity, are extracted from the driving control sequence and input into the output power prediction model for analysis. The output power prediction model predicts the battery's power requirements at different time points based on the driving control sequence, resulting in a battery discharge power sequence. Power change correlation analysis accurately identifies which driving behaviors have a significant impact on battery power output, thereby improving the accuracy of power predictions. Key control indicators are screened to reduce interference from irrelevant data, making the model simpler, faster to calculate, and more accurate in predictions. Through precise power change correlation analysis and multivariate linear regression analysis, the system can effectively predict the battery's power requirements and optimize them based on the driving control sequence, thereby achieving efficient battery management and more accurate energy distribution.

[0047] Furthermore, the demand analysis module 11 in the power battery dual-circulation heat dissipation control device based on temperature measurement is also used for:

[0048] Divide a first passing road segment into a plurality of first one-dimensional road segments according to changes in road segment shape; extract a plurality of first one-dimensional road segment features of the plurality of first one-dimensional road segments from first traffic situation information, wherein the first one-dimensional road segment features include road segment length features, road segment undulation features, road segment shape features, and road segment speed limit features; extract a first driving direction vector of the first passing road segment from the first traffic situation information; pre-construct a driving control prediction model, and perform driving behavior analysis by synchronizing the first driving direction vector and the plurality of first one-dimensional road segment features to the driving control prediction model to obtain a plurality of first driving control parameters; map and sort the plurality of first driving control parameters according to the connection relationship of the plurality of first one-dimensional road segments in the first passing road segment to obtain first driving control information; and so on, perform driving control analysis based on the plurality of traffic situation information, and after obtaining a plurality of driving control information of the plurality of passing road segments, sort the plurality of driving control information according to the connection relationship of the plurality of passing road segments in the driving route, and output the driving control sequence.

[0049] Specifically, a road segment is randomly selected from multiple traversed road segments as the first traversed road segment, such as an urban road, a highway, or a rural road. Each traversed road segment has different characteristics such as traffic conditions, road surface types, and road morphology. Similarly, first traffic situation information corresponding to the first traversed road segment is obtained from the multiple traffic situation information, namely, relevant information such as traffic flow, traffic lights, traffic accidents, and weather conditions on the first traversed road segment. This information is used to analyze road conditions and assess their impact on driving behavior.

[0050] Based on the shape variations of the road segment, the first route segment is divided into multiple first one-dimensional segments. Each one-dimensional segment represents a relatively simple road segment with consistent control parameters (such as a straight road or a single turn). For example, a straight line plus a curve is a two-dimensional feature segment, which is then split into two one-dimensional segments: a straight line segment and a curve. The one-dimensionality implies the consistency of the control parameters. Multiple first one-dimensional segment features associated with each first one-dimensional segment are extracted from the first traffic situation information, including segment length (physical length of the segment), undulation (high and low undulation of the segment), segment shape (morphological characteristics of the segment, such as curves, straight roads, uphill and downhill slopes), and speed limit. For example, the features of the two one-dimensional segments are: the straight line segment has a length of 500 meters, an undulation of flatness, a shape of straightness, and a speed limit of 60 km / h; the curve segment has a length of 100 meters, an undulation of flatness, a shape of curves, and a speed limit of 30 km / h.

[0051] A first driving direction vector for the first traversed road segment is extracted from the first traffic situation information to describe the vehicle's travel direction on the segment. For example, the vehicle may be traveling north or southeast. The first driving direction vector refers to the vehicle's direction on a specific road segment, typically represented as a vector with a certain direction and angle, which determines the vehicle's direction on the segment. The driving control prediction model is a mathematical model used to predict driving behavior based on road segment characteristics and driving direction. Based on the data structure of a knowledge graph, it stores and associates different types of information (such as road segment characteristics, driving direction vectors, and driving behavior data). Multiple first one-dimensional road segment characteristics are input into the driving control prediction model and combined with the first driving direction vector to perform driving behavior analysis. This predicts possible driving control behaviors on the specific road segment and obtains multiple first driving control parameters, including those for maintaining speed, slight acceleration, deceleration, and turning angles. Driving control parameters refer to control parameters that require adjustment for a vehicle on a specific road segment, such as acceleration, braking, and steering wheel angle, which affect the vehicle's power output and driving state.

[0052] Multiple first driving control parameters are sorted based on the connections between road sections to ensure a smooth transition of the vehicle's driving behavior on each road section. Assuming the driving route includes multiple road sections, each control parameter is sorted based on the starting and ending locations of each road section, as well as its shape change (e.g., from a straight road to a curve). This sorting process yields first driving control information, i.e., a driving control sequence for the entire driving route. This information includes driving behavior control instructions for each first traversed road section, calculated based on the first traffic situation information and multiple first unidimensional road section features.

[0053] Similarly, the above steps are applied to each segment along the entire driving route, and driving control analysis is performed on multiple traffic situation information for multiple segments. The above steps are repeated to obtain multiple driving control information for each segment. The characteristics and connectivity of each segment are analyzed, and the multiple driving control information is sorted to generate a driving control sequence for the entire driving route, which is used to guide the vehicle's autonomous driving system or assisted driving system to perform specific driving operations. A connectivity relationship refers to the connection or connection method between different segments. For example, the end of one segment may have a certain connectivity relationship with the beginning of the next segment, which may affect the continuity of driving behavior. By combining segment characteristics, driving direction, and connectivity relationships, the driver's driving behavior on different segments is accurately predicted. By analyzing the connectivity of the control information for each segment, the coherence of the driving control sequence is ensured. Ultimately, a complete driving control sequence is output, providing decision-making basis for the autonomous driving system, thereby achieving a smoother and safer driving experience.

[0054] Furthermore, the demand analysis module 11 in the power battery dual-circulation heat dissipation control device based on temperature measurement is also used for:

[0055] Interactively obtain multiple sample feature information, multiple sample driving direction vectors and multiple sample driving behavior data of multiple sample road sections; use the road section feature as the first attribute, the driving direction vector as the second attribute, and the behavior data as the third attribute, and store the multiple sample feature information, multiple sample driving direction vectors and multiple sample driving behavior data based on the knowledge graph to complete the construction of the driving control prediction model; synchronize the first one-dimensional road section feature to the driving control prediction model, perform feature comparison based on the Pearson correlation coefficient, and obtain the first alternative behavior data of the first sample direction and the second alternative behavior data of the second sample direction through primary screening; obtain the first driving control parameter through secondary screening of the first alternative behavior data and the second alternative behavior data according to the first driving direction vector; and so on, obtain multiple first driving control parameters by synchronizing the first driving direction vector and multiple first one-dimensional road section features to the driving control prediction model for driving behavior analysis.

[0056] Specifically, relevant information of multiple sample road sections is collected from multiple actual roads or simulated environments, including multiple sample feature information, multiple sample driving direction vectors and multiple sample driving behavior data. Multiple sample feature information refers to the road section length characteristics, road section undulation characteristics, road section shape characteristics and road section speed limit characteristics corresponding to each sample road section. Multiple sample driving direction vectors represent the driving direction of the vehicle on multiple sample road sections, described by angle and speed, and are usually a mathematical representation of the vehicle's driving path, reflecting the vehicle's heading and motion state while driving. Multiple sample driving behavior data refer to the driving control parameters made by the driver or the automatic driving system during the vehicle driving process, as well as the duration of the control parameters, such as speed, turning angle, acceleration and braking, etc.

[0057] This sample data is stored in an associative manner within a knowledge graph, with each sample's road segment features as a node, and the driving direction vector and behavior data as additional nodes. Nodes are connected by edges (i.e., relationships), establishing connections between the data. A knowledge graph is a technology that uses a graph structure (nodes and edges) to store and represent multiple data types, capturing and expressing the relationships between different data elements. Sample road segment features, driving direction vectors, and driving behavior data are stored in an associative manner, establishing their interrelationships. Using road segment features as the primary attribute, driving direction vectors as the secondary attribute, and behavior data as the tertiary attribute, the knowledge graph associates and stores multiple sample feature information, multiple sample driving direction vectors, and multiple sample driving behavior data, establishing connections between the data and building a driving control prediction model that understands the relationship between road segment features and driving behavior. The knowledge graph can link each road segment feature to specific driving behavior data (such as acceleration, braking, steering, etc.).

[0058] First-dimensional road segment features (such as road segment length, undulation, and speed limit) are synchronized with the driving control prediction model. The Pearson correlation coefficient is used to compare these features with those stored in the knowledge graph to identify the behavioral data most relevant to these features. The Pearson correlation coefficient measures the correlation between the input first-dimensional road segment features and existing road segment features in the knowledge graph, determining which road segment features have a greater impact on driving behavior. Driving behaviors that match the current road segment features are automatically screened to obtain the most relevant driving behaviors, namely the first candidate behavioral data for the first sample direction and the second candidate behavioral data for the second sample direction. The Pearson correlation coefficient is a statistic that measures the linear relationship between two variables. Its value range is [-1, 1], with 0 indicating no correlation, 1 indicating perfect positive correlation, and -1 indicating perfect negative correlation. This first-level screening selects the most relevant behavioral data from a large number of possible behaviors, retaining the driving behaviors most likely to occur on the road segment.

[0059] From all possible driving behavior data, the two most relevant driving behaviors for the current road segment are selected. These are referred to as the first candidate behavior data and the second candidate behavior data. Combined with the first driving direction vector (the vehicle's direction of travel), a secondary screening process is performed on the first and second candidate behavior data to select the most appropriate driving control parameters. The driving direction vector can provide additional contextual information, such as whether the vehicle is about to enter an uphill, downhill, or curve. Secondary screening involves further rigorous screening of the candidate data based on the primary screening process, selecting the most appropriate driving control parameters based on the driving direction vector.

[0060] Similarly, multiple first-dimensional road segment features are synchronized with the driving control prediction model for screening. Then, further screening is performed based on the first driving direction vector to obtain the first driving control parameter corresponding to each first-dimensional road segment feature. This results in multiple driving control parameters, forming a complete driving control sequence. By combining road segment features, driving direction vectors, and driving behavior data, the system accurately predicts the driver's behavior on a specific road segment. Primary and secondary screening ensure that the system can select the most appropriate control strategy for the current road segment from multiple driving behaviors, thereby optimizing the driving experience and safety.

[0061] Further, as attached Figure 2 As shown, the temperature change prediction module 12 in the power battery dual-circulation heat dissipation control device based on temperature measurement is also used for:

[0062] Interactively obtain the standard heat dissipation state of the target car; use the standard heat dissipation state as a constraint to call network data to obtain multiple sample battery status data of multiple sample cars with the same model as the target car, wherein the sample battery status data includes a sample power output sequence and a sample battery temperature sequence; preset a power fluctuation threshold, and use the power fluctuation threshold to traverse multiple sample power output sequences to obtain multiple sample power fluctuation nodes; synchronously split multiple sample power output sequences and multiple sample battery temperature sequences according to the multiple sample power fluctuation nodes to obtain multiple groups of sample steady-state temperature change data, wherein the Among the multiple groups of sample steady-state temperature change data, each group of sample steady-state temperature change data includes a sample starting temperature, a sample stable power mean, a sample stable time and a sample end temperature; the multiple groups of sample steady-state temperature change data are used to train a battery temperature change prediction model; the battery discharge power sequence is split using the power fluctuation threshold to obtain multiple real-time stable power means and multiple real-time stable time periods; with the real-time battery temperature as the starting point, according to the connection relationship between the multiple real-time stable power means in the battery discharge power sequence, the battery temperature change prediction model is used to recursively predict the battery temperature change, and the battery predicted temperature change time series is output.

[0063] Specifically, the system interacts with the vehicle network to obtain the target vehicle's standard thermal state parameters during normal operation. This refers to the ideal thermal state that the target vehicle's battery system can maintain under normal operating conditions. This state is defined based on vehicle type, environmental conditions, and standard operating procedures. Using the standard thermal state as a constraint, the system retrieves data from multiple sample vehicles of the same model as the target vehicle through network access. The system obtains multiple sample battery state data sets for each sample vehicle, including battery power output sequences and battery temperature sequences. The sample power output sequences record the duration of different power levels over a period of time, forming a series of time series data that describes battery power variations. The sample battery temperature sequences record the time-varying battery temperature at corresponding power outputs. By accessing data from multiple sample vehicles of the same model over the network, the system collects the battery power output and battery temperature sequences for each vehicle and uses them to train a battery temperature variation prediction model.

[0064] The preset power fluctuation threshold is a value used to identify fluctuations in the power sequence. When the power fluctuation reaches this threshold, a fluctuation is considered to have occurred. Using the power fluctuation threshold, multiple sample power output sequences are traversed to obtain multiple sample power fluctuation nodes. These are the time points in the power output sequence where the power change exceeds the preset threshold. Nodes with large power fluctuations (i.e., power fluctuation nodes) are identified and marked, indicating significant fluctuations in battery power output.

[0065] Based on multiple sample power fluctuation nodes, multiple sample power output sequences and multiple sample battery temperature sequences are synchronously split according to time periods, so that each segment of data can reflect the relationship between battery power and temperature at the same time. Steady-state temperature change data refers to the stability data of battery temperature changes under certain power output and temperature conditions. Each set of data will record the starting temperature, stable power average, stable time and end temperature. The sample starting temperature refers to the temperature value at the beginning of the battery temperature, the sample stable power average refers to the average value of the battery power during this period, indicating the power when the battery power output is stable; the sample stable time refers to the duration of time the battery power remains stable; the sample end temperature refers to the temperature value at the end of the battery temperature during this period.

[0066] Using multiple sets of collected steady-state temperature change data, the model is trained using machine learning methods (such as regression analysis, decision trees, and neural networks). By inputting stable power and starting temperature, the battery temperature change over a given period of time is predicted. Data preprocessing is performed on the multiple sets of steady-state temperature change data to extract several key features, which are used as input for model training. The starting temperature, stable power mean, and stable duration serve as input variables, and the end temperature serves as the target output variable. A machine learning model is selected, such as a regression model, decision tree, or neural network. If multivariate linear regression is used for training, temperature prediction is performed by learning the linear relationship between the input features and the target variable.

[0067] The dataset of multiple sets of steady-state temperature change data is split into a training set and a test set, typically 80% training and 20% test. The training data is input into a linear regression model to calculate the model parameters (i.e., regression coefficients). The training goal is to minimize the error between the predicted value and the actual target value, typically using an error function such as mean squared error. By minimizing the error function, the regression coefficients (i.e., weights) are adjusted to find the best fitting line (or hyperplane). The model learns how each feature affects the battery's temperature change. After model training is complete, the model is evaluated using the test set, and the R² value (coefficient of determination) is used to measure the model fit. The closer the value is to 1, the better the model. The trained model is used as the battery temperature change prediction model to predict the battery's temperature change based on the current battery power output and starting temperature.

[0068] The battery discharge power sequence is segmented using a power fluctuation threshold, identifying each period of stable power. The average power value and duration of each period are then calculated, resulting in multiple real-time stable power averages and multiple real-time stable durations. The real-time stable power average refers to the average value of the battery's power output, indicating the battery's power stability during that period. The real-time stable duration refers to the length of time the battery maintains a stable state. Using the real-time battery temperature as a starting point and combining multiple stable power averages within the battery discharge power sequence, a trained battery temperature change prediction model is used to recursively predict battery temperature changes. Each prediction result serves as input for the next prediction, until a complete temperature change time series is predicted. Each prediction result is combined based on the relationship between multiple real-time stable power averages to form a predicted battery temperature change time series. By analyzing the battery power and temperature data of multiple sample vehicles, a battery temperature change prediction model is established and used to recursively predict real-time battery temperature changes. By segmenting the battery using a power fluctuation threshold and calculating the stable power average, the relationship between battery temperature and power output is captured, resulting in more accurate temperature prediction.

[0069] Furthermore, the control optimization module 13 in the power battery dual-circulation heat dissipation control device based on temperature measurement is further used for:

[0070] A battery temperature variation timing curve is drawn according to the predicted battery temperature variation timing; temperature variation nodes of the battery temperature variation timing curve are identified based on differential approximation to divide the predicted battery temperature variation timing into multiple temperature variation timing sub-intervals; heat dissipation control optimization is performed on the multiple temperature variation timing sub-intervals to obtain multiple dual-loop heat dissipation control parameters; the multiple dual-loop heat dissipation control parameters are smoothly connected according to the temperature variation timing to obtain the dual-loop heat dissipation control sequence.

[0071] Specifically, the predicted battery temperature change time series is a time series of future battery temperature changes derived from the battery's real-time temperature and discharge power predictions. It reflects the battery's temperature fluctuation trend over a certain period of time. A battery temperature change time series curve is drawn based on the predicted battery temperature change time series. This curve plots the predicted battery temperature change over time, typically with time on the horizontal axis and battery temperature on the vertical axis. This provides an intuitive understanding of the battery temperature change trend over time.

[0072] Using differential approximation, the rate of temperature change—that is, the amount of temperature change at each moment—is calculated. Differential approximation approximates the temperature change rate by calculating the difference between the temperature changes at two adjacent moments. Differential approximation is a mathematical method typically used to determine the amount of change or rate of change of a particular item in a sequence. It is used to calculate the temperature change rate of a temperature-dependent time series curve, thereby identifying key temperature change nodes. A temperature change node is a point where the temperature change rate changes significantly, such as a point where the battery temperature rises or falls rapidly. By identifying these nodes, it is possible to determine when to adjust the cooling strategy.

[0073] After identifying key temperature change nodes, the predicted battery temperature change time series is divided into multiple temperature change sub-intervals. Within each sub-interval, the battery temperature change rate is relatively stable, allowing for different heat dissipation control methods to be applied to each sub-interval. Based on the temperature rise characteristics of each temperature change sub-interval, corresponding standard heat dissipation control parameters are applied, including standard water cooling cycle speeds and standard air cooling cycle speeds. Water cooling control decomposition is performed using the standard water cooling cycle speed (1 / K) as the adjustment scale to obtain multiple alternative water cooling cycle speeds. Air cooling control simulation is then performed to obtain multiple alternative air cooling cycle speeds. Energy consumption is calculated for these alternative water cooling cycle speeds and multiple alternative air cooling cycle speeds to obtain multiple dual-cycle heat dissipation energy consumptions. The minimum energy consumption among these multiple dual-cycle heat dissipation energy consumptions is selected as the dual-cycle heat dissipation control parameter. Heat dissipation control optimization involves using an algorithm to optimize heat dissipation control parameters, including water cooling flow rate and air cooling speed, based on battery temperature fluctuations, to maintain the battery temperature within the optimal range.

[0074] Dual-loop cooling control parameters refer to the control parameters used when both water and air cooling are used simultaneously. These parameters may include the water cooling loop flow rate and the air cooling wind speed, helping to improve cooling efficiency. After obtaining multiple cooling control parameters, they need to be smoothly connected. Smooth connection means maintaining a smooth transition between cooling control parameters in different sub-ranges to avoid sudden changes. For example, if a transition from a lower wind speed to a higher wind speed is required between two sub-ranges, an interpolation algorithm can be used to smooth the transition and avoid drastic fluctuations in temperature control. Common smoothing methods include linear interpolation (smoothing control parameters using simple linear relationships) and spline interpolation (using curve interpolation to provide smooth transitions). The resulting dual-loop cooling control sequence will contain cooling control instructions for different time periods, reflecting the cooling requirements throughout the entire temperature change process. By identifying the key nodes and change rates of battery temperature changes, the dynamic changes in battery temperature can be more accurately captured. Identifying each node enables targeted optimization of the cooling control strategy at different temperature stages, ensuring the most appropriate cooling strategy for each temperature stage, thereby improving cooling efficiency and system response speed.

[0075] Furthermore, the control optimization module 13 in the power battery dual-circulation heat dissipation control device based on temperature measurement is further used for:

[0076] The temperature rise characteristics of the first temperature change time series sub-interval are used as local data call constraints to obtain standard heat dissipation control parameters, wherein the standard heat dissipation control parameters include a standard water cooling cycle speed and a standard air cooling cycle speed; the standard water cooling cycle speed 1 / K is used as an adjustment scale to perform water cooling control solution expansion to obtain multiple spare water cooling cycle speeds; air cooling control simulation is performed based on the first temperature change time series sub-interval and the multiple spare water cooling cycle speeds to obtain multiple spare air cooling cycle speeds; energy consumption of the multiple spare water cooling cycle speeds and the multiple spare air cooling cycle speeds is calculated based on the first temperature change duration of the first temperature change time series sub-interval to obtain multiple dual-cycle heat dissipation energy consumptions; the multiple dual-cycle heat dissipation energy consumptions are serialized, and the first dual-cycle heat dissipation control parameters are located among the multiple spare water cooling cycle speeds and the multiple spare air cooling cycle speeds according to the sequence minimum; and so on, heat dissipation control optimization is performed on the multiple temperature change time series sub-intervals to obtain the multiple dual-cycle heat dissipation control parameters.

[0077] Specifically, one is randomly selected from multiple temperature change time series sub-intervals as the first temperature change time series sub-interval. The temperature rise characteristics of the first temperature change time series sub-interval are used as local data call constraints. The temperature rise characteristics refer to the temperature rise trend of the battery temperature in the first sub-interval in the temperature change time series curve, which usually includes the speed of temperature rise, duration of temperature rise and other characteristics. The standard heat dissipation control parameters are heat dissipation parameters adjusted according to the temperature change characteristics of the battery and preset standards, usually including the water cooling cycle speed and the air cooling cycle speed. The standard heat dissipation control parameters are the default operating parameters of the battery heat dissipation system in the absence of external disturbances.

[0078] The standard water cooling cycle speed, 1 / K, is used as the adjustment scale. This is the inverse of the temperature change rate and is used to adjust the water cooling system's cycle speed to meet the needs of battery temperature fluctuations. K represents the speed of temperature change. By expanding the adjustment scale of the standard water cooling cycle speed, multiple backup water cooling cycle speeds are generated. These backup water cooling cycle speeds are adjusted based on the standard water cooling cycle speed and are used to adjust the water cooling system's cycle speed under different temperature conditions, providing a flexible adjustment solution based on the changing needs of battery temperature.

[0079] An air cooling control simulation is performed based on the backup water cooling cycle speed. The air cooling cycle speed typically works in conjunction with the water cooling control speed. Therefore, the air cooling control system adjusts accordingly based on the water cooling speed, generating multiple backup air cooling cycle speeds. Similar to the backup water cooling cycle speed, the backup air cooling cycle speed is a cooling control parameter derived from the water cooling control simulation. The air cooling control simulation takes into account the output of the water cooling system and generates corresponding air cooling cycle speeds based on battery temperature fluctuations. After determining multiple backup water cooling cycle speeds and multiple backup air cooling cycle speeds based on the duration of the first temperature change subinterval in the first temperature change time series, energy consumption calculation is performed to evaluate the energy consumption of each water-cooling and air-cooling combination. The power consumption of each combination is evaluated, including the power consumption of the water cooling cycle and the power consumption of the air cooling system. By calculating the energy consumption of each combination, the cooling control parameters with the lowest energy consumption are selected to improve cooling efficiency and reduce energy consumption. Dual-cycle cooling energy consumption refers to the total energy consumed under dual-cycle cooling control (when both the water cooling and air cooling systems are operating simultaneously).

[0080] Arrange the energy consumption of multiple dual-loop heat dissipation in a certain order, select the combination with the lowest energy consumption, and finally locate the first dual-loop heat dissipation control parameter, that is, the heat dissipation parameter with the lowest energy consumption within the current temperature change timing sub-interval. Similarly, repeat the above steps, perform heat dissipation control optimization on multiple temperature change timing sub-intervals, and obtain multiple dual-loop heat dissipation control parameters. The temperature rise characteristics of each sub-interval are different, so the corresponding heat dissipation control strategy will also be different. By optimizing the heat dissipation control for each sub-interval, a set of optimal dual-loop heat dissipation control parameters is finally obtained. By performing detailed analysis and heat dissipation control optimization on different temperature change timing sub-intervals, the combination of water cooling and air cooling can be accurately adjusted to provide a targeted heat dissipation solution to ensure that the battery temperature remains within the optimal range.

[0081] In summary, the power battery dual-circulation heat dissipation control device based on temperature measurement provided by this application has the following technical effects:

[0082] The system receives driving input information and analyzes battery power output requirements based on the driving input information to obtain a battery discharge power sequence. It also obtains the real-time battery temperature of the power battery through temperature measurement. Using the real-time battery temperature as a starting point, it predicts battery temperature changes based on the battery discharge power sequence and outputs a predicted battery temperature change time sequence. It then optimizes heat dissipation control based on the predicted battery temperature change time sequence to obtain a dual-cycle heat dissipation control sequence. While the driving system controls the vehicle based on the driving control sequence and the heat dissipation system simultaneously controls the power battery based on the dual-cycle heat dissipation control sequence, it collects real-time temperature data of the target vehicle through temperature measurement. Compensation control for the dual-cycle heat dissipation control sequence is performed based on the deviation between the real-time temperature data and the safe temperature of the power battery. In other words, the system predicts battery output based on the driving input information and the battery temperature, and performs dual-cycle heat dissipation control based on the output prediction. While dissipating heat in advance, it also compensates for heat dissipation based on the real-time battery temperature. This achieves temperature management of the power battery of the new energy vehicle, ensuring that the battery operates within an optimal temperature range and improving battery heat dissipation efficiency.

[0083] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0084] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A dual-circulation heat dissipation control device for power batteries based on temperature measurement, characterized in that: include: a demand analysis module, the demand analysis module being configured to receive driving input information and perform battery power output demand analysis based on the driving input information to obtain a battery discharge power sequence; a temperature change prediction module, the temperature change prediction module being used to obtain the real-time battery temperature of the power battery through temperature measurement, and using the real-time battery temperature as a starting point, predict the battery temperature change according to the battery discharge power sequence, and output a battery predicted temperature change time series; a control optimization module, the control optimization module being used to optimize heat dissipation control according to the predicted temperature change time sequence of the battery to obtain a dual-cycle heat dissipation control sequence; a heat dissipation control module configured to collect real-time temperature data of a target vehicle through temperature measurement while the driving system performs vehicle driving control based on the driving control sequence and the heat dissipation system synchronously performs heat dissipation control of the power battery based on the dual-loop heat dissipation control sequence; a temperature compensation module, configured to perform compensation control of the dual-cycle heat dissipation control sequence according to a deviation between the real-time temperature data and a safe temperature of the power battery; The method of obtaining the real-time battery temperature of the power battery by temperature measurement, and using the real-time battery temperature as a starting point, predicting the battery temperature change according to the battery discharge power sequence, and outputting the battery predicted temperature change time series includes: interactively obtaining a standard heat dissipation state of the target vehicle; Performing online data call based on the standard heat dissipation state as a constraint to obtain a plurality of sample battery status data of a plurality of sample vehicles of the same model as the target vehicle, wherein the sample battery status data includes a sample power output sequence and a sample battery temperature sequence; Presetting a power fluctuation threshold, and using the power fluctuation threshold to traverse multiple sample power output sequences to obtain multiple sample power fluctuation nodes; Synchronously splitting multiple sample power output sequences and multiple sample battery temperature sequences according to the multiple sample power fluctuation nodes to obtain multiple groups of sample steady-state temperature change data, wherein each group of sample steady-state temperature change data includes a sample starting temperature, a sample stable power average, a sample stable time, and a sample end temperature; A battery temperature change prediction model is obtained by training the plurality of groups of sample steady-state temperature change data; The battery discharge power sequence is split by using the power fluctuation threshold to obtain multiple real-time stable power averages and multiple real-time stable durations; Taking the real-time battery temperature as a starting point, recursively predicting the battery temperature change using the battery temperature change prediction model according to the connection relationship between the multiple real-time stable power averages in the battery discharge power sequence, and outputting the battery predicted temperature change time series; The heat dissipation control optimization is performed according to the battery predicted temperature change time sequence to obtain a dual-cycle heat dissipation control sequence, including: Draw a battery temperature change time series curve according to the battery predicted temperature change time series; Identifying temperature change nodes of the battery temperature change time series curve based on differential approximation to divide the battery predicted temperature change time series into a plurality of temperature change time series subintervals; Performing heat dissipation control optimization on the multiple temperature variation time sequence sub-intervals to obtain multiple dual-loop heat dissipation control parameters; The plurality of dual-loop heat dissipation control parameters are smoothly connected according to the temperature change time sequence to obtain the dual-loop heat dissipation control sequence.

2. The power battery dual-circulation heat dissipation control device based on temperature measurement according to claim 1, characterized in that: Optimizing heat dissipation control for the multiple temperature variation time sequence subintervals to obtain multiple dual-loop heat dissipation control parameters, including: Using the temperature rise characteristic of the first temperature change time series subinterval as a local data call constraint, the standard heat dissipation control parameters are obtained by calling, wherein the standard heat dissipation control parameters include a standard water cooling circulation speed and a standard air cooling circulation speed; Using 1 / K of the standard water cooling cycle speed as the adjustment scale to perform water cooling control solution expansion, multiple standby water cooling cycle speeds are obtained, where K is a parameter indicating the speed of temperature change; Performing air cooling control simulation according to the first temperature variation time sequence sub-interval and a plurality of standby water cooling cycle speeds to obtain a plurality of standby air cooling cycle speeds; Calculate the energy consumption of the multiple standby water cooling cycle speeds and the multiple standby air cooling cycle speeds according to the first temperature change duration of the first temperature change time sequence subinterval to obtain multiple dual-cycle heat dissipation energy consumptions; Sequencing the plurality of dual-cycle heat dissipation energy consumptions, and locating a first dual-cycle heat dissipation control parameter at the plurality of standby water cooling cycle speeds and the plurality of standby air cooling cycle speeds according to a minimum value of the sequence; Similarly, heat dissipation control optimization is performed on the multiple temperature change time sequence sub-intervals to obtain the multiple dual-loop heat dissipation control parameters.

3. The power battery dual-circulation heat dissipation control device based on temperature measurement according to claim 1, characterized in that: Receiving driving input information, and performing battery power output demand analysis based on the driving input information to obtain a battery discharge power sequence, including: generating a driving route according to the driving input information; Collecting traffic situation data according to the road segment composition of the driving route to obtain multiple traffic situation information of multiple road segments in the driving route; Performing driving control analysis based on the plurality of traffic situation information and outputting the driving control sequence; An output power prediction model is pre-built, and the battery power output demand analysis is performed by inputting the driving control sequence into the output power prediction model to obtain the battery discharge power sequence.

4. The power battery dual-circulation heat dissipation control device based on temperature measurement according to claim 3, characterized in that: Pre-building an output power prediction model, inputting the driving control sequence into the output power prediction model to perform battery power output demand analysis to obtain the battery discharge power sequence, including: interactively obtaining a plurality of sample driving control data and a plurality of sample battery output powers; performing power change correlation analysis on the plurality of sample driving control data and the plurality of sample battery output powers to obtain N power correlation control indicators; Using the N power-related control indicators to filter the plurality of sample driving control data to obtain a plurality of sample-related control data; The output power prediction model is constructed by performing a multivariate linear regression analysis based on the plurality of sample associated control data and the plurality of sample battery output powers; After preprocessing the data of the driving control sequence using the N power-related control indicators, the battery power output demand analysis is performed via the output power prediction model to obtain the battery discharge power sequence.

5. The power battery dual-circulation heat dissipation control device based on temperature measurement according to claim 3, characterized in that: Performing driving control analysis based on the plurality of traffic situation information and outputting the driving control sequence includes: Dividing the first passing road segment into a plurality of first one-dimensional road segments according to the change of the road segment shape; Extracting a plurality of first one-dimensional road segment features of the plurality of first one-dimensional road segments from the first traffic situation information, wherein the first one-dimensional road segment features include a road segment length feature, a road segment undulation feature, a road segment shape feature, and a road segment speed limit feature; Extracting and obtaining a first driving direction vector of the first passing road segment from the first traffic situation information; Pre-building a driving control prediction model, performing driving behavior analysis by synchronizing the first driving direction vector and a plurality of first one-dimensional road segment features to the driving control prediction model to obtain a plurality of first driving control parameters; The first driving control parameters are mapped and sorted according to the connection relationship between the first one-dimensional road segments and the first passing road segment to obtain first driving control information; Similarly, driving control analysis is performed based on the multiple traffic situation information to obtain multiple driving control information of the multiple passing sections. The multiple driving control information is sorted according to the connection relationship between the multiple passing sections in the driving route, and the driving control sequence is output.

6. The power battery dual-circulation heat dissipation control device based on temperature measurement according to claim 5, characterized in that: A driving control prediction model is pre-built, and driving behavior analysis is performed by synchronizing the first driving direction vector and a plurality of first one-dimensional road segment features to the driving control prediction model to obtain a plurality of first driving control parameters, including: Interactively obtain multiple sample feature information, multiple sample driving direction vectors and multiple sample driving behavior data of multiple sample road sections; Taking the road segment feature as the first attribute, the driving direction vector as the second attribute, and the behavior data as the third attribute, the plurality of sample feature information, the plurality of sample driving direction vectors, and the plurality of sample driving behavior data are associated and stored based on the knowledge graph to complete the construction of the driving control prediction model; Synchronizing the first unidimensional road segment feature to the driving control prediction model, performing feature comparison based on the Pearson correlation coefficient, and obtaining first candidate behavior data for the first sample direction and second candidate behavior data for the second sample direction through primary screening; Obtaining a first driving control parameter by secondary screening of the first candidate behavior data and the second candidate behavior data according to the first driving direction vector; Similarly, by synchronizing the first driving direction vector and a plurality of first one-dimensional road section features to the driving control prediction model to perform driving behavior analysis, a plurality of first driving control parameters are obtained.

Images