Intelligent cleaning robot battery thermal runaway and energy storage system optimization method

Abstract

The invention relates to the technical field of battery control, in particular to an intelligent cleaning robot battery thermal runaway and energy storage system optimization method. Through the technical means of multi-dimensional data acquisition, time sequence prediction analysis, a self-adaptive control algorithm, a smooth transition algorithm, a feedback learning mechanism and the like, accurate monitoring and dynamic adjustment of the temperature of the battery pack of the intelligent cleaning robot are achieved, and the thermal management efficiency and safety of an energy storage system are remarkably improved; and powerful technical support is provided for efficient operation of the intelligent cleaning robot.

Description

Technical Field

[0001] This invention relates to the field of battery control technology, specifically to a method for optimizing thermal runaway and energy storage systems in intelligent cleaning robots. Background Technology

[0002] As core equipment in modern homes and commercial environments, the thermal management technology of intelligent cleaning robots' energy storage systems directly affects their operational stability and lifespan. With the increasing workload and endurance requirements of robots, heat management during high-load operation of energy storage systems has become a key bottleneck restricting overall performance. Current thermal management solutions for energy storage systems mainly rely on passive cooling modes triggered by fixed thresholds. This approach shows significant inadequacy in adapting to the complex and ever-changing working environments of robots. Existing technologies typically employ control strategies with preset parameters, failing to adjust in real-time according to dynamic changes in the actual workload. This results in significant differences in the response efficiency of the thermal management system under different working conditions. Furthermore, traditional solutions lack the ability to predict future temperature trends, relying solely on reactive control based on the current state, which is insufficient to meet the high-efficiency thermal management needs of intelligent cleaning robots.

[0003] The core challenge in thermal management of energy storage systems lies in the temporal continuity of temperature control. When robots perform cleaning tasks, the battery pack's heating patterns exhibit a clear temporal correlation, with temperature states at different times influencing each other and showing continuity. This temporal correlation further complicates the smooth transition when switching control strategies. For example, when the robot switches from a low-power standby mode to a high-intensity cleaning mode, a sudden change in the thermal management system's control parameters can cause drastic fluctuations in battery pack temperature, affecting not only heat dissipation efficiency but also potentially impacting battery performance. This discontinuity in control strategy makes it difficult for the entire thermal management system to maintain a stable temperature environment, especially in scenarios with frequent switching of operating modes, where the stability issue of temperature control becomes even more prominent.

[0004] Furthermore, existing technologies have shortcomings in addressing the risk of battery thermal runaway. Due to a lack of accurate prediction and dynamic adjustment capabilities for temperature change trends, traditional thermal management systems struggle to effectively prevent battery performance degradation or safety issues caused by abnormal temperature increases. Therefore, how to optimize dynamic control strategies based on time-series characteristics during the thermal management process of energy storage systems, and ensure smooth transitions between different control stages to avoid temperature fluctuations caused by parameter mutations, has become a key issue in the development of thermal management technology for energy storage systems in intelligent cleaning robots. This invention aims to solve the above-mentioned technical challenges by introducing advanced technologies such as time-series prediction, adaptive control, and smooth transition algorithms, providing an efficient and stable battery thermal management solution for intelligent cleaning robots. Summary of the Invention

[0005] The purpose of this invention is to address the aforementioned shortcomings in the prior art by providing a method for optimizing thermal runaway and energy storage systems in intelligent cleaning robots.

[0006] The objective of this invention is achieved through the following technical solution: a method for optimizing the thermal runaway of a smart cleaning robot battery and its energy storage system, comprising the following steps: S1. Based on the real-time temperature data and power consumption data of the intelligent cleaning robot in different working modes, the temperature distribution information of each position of the battery pack is collected through the temperature sensor array, and the current cleaning task type and work intensity parameters are recorded to generate a multi-dimensional thermal management basic dataset. S2. Based on a multi-dimensional thermal management dataset, time series prediction analysis is used to analyze the temperature change trend of the battery pack, extract periodic and trend features, determine the direction and magnitude of temperature change in the future time period, and generate temperature prediction results and trend indicators. S3. Based on the temperature prediction results and trend indicators, if the future temperature rise trend exceeds the preset safety range, the adaptive control algorithm is activated to adjust the heat dissipation system parameters. The optimal heat dissipation power configuration is calculated based on the current workload intensity and the predicted peak temperature, and the heat dissipation parameter adjustment amount is generated. S4. Based on the adjustment amount of heat dissipation parameters, a smooth transition algorithm is used to generate a phased parameter adjustment path to avoid sudden jumps in heat dissipation control parameters and obtain the specific parameter values ​​at each time node. S5. Based on the generated parameter adjustment path, the parameter update operation of the heat dissipation system is executed step by step. At the same time, the temperature response and system stability indicators are monitored. If the temperature control effect deviates from the expected target, the subsequent parameter adjustment range is corrected in real time to generate a dynamically optimized control parameter sequence. S6. Based on the dynamically optimized control parameter sequence, a temperature control effect evaluation mechanism is used to quantitatively analyze the execution result of the current heat dissipation strategy. By comparing the deviation between the actual temperature change curve and the predicted target curve, the direction of control strategy adjustment is generated. S7. Adjust the direction based on the control strategy, update the weight parameters of the time series prediction model and the response sensitivity settings of the adaptive control algorithm, optimize the algorithm performance through feedback learning of historical control effect data, and generate an improved thermal management control model. S8. Based on the improved thermal management control model, the optimal heat dissipation strategy combination of the energy storage system under various working scenarios is recalculated, a dynamic mapping relationship between working mode and heat dissipation parameters is established, an intelligent thermal management strategy library covering the working state of the robot throughout its entire life cycle is formed, and a complete adaptive thermal management solution is generated.

[0007] The present invention is further configured such that the multi-dimensional thermal management basic dataset includes a battery pack temperature distribution map, power consumption trend analysis, and operating mode classification; the temperature prediction results and trend indicators include temperature rise rate assessment, future peak temperature prediction, and abnormal temperature rise warning; the heat dissipation parameter adjustment amounts specifically include fan speed adjustment values ​​and heat sink thermal conductivity adjustment values; the dynamically optimized control parameter sequence includes a phased parameter adjustment path and a real-time correction strategy; the control strategy adjustment direction includes temperature control accuracy improvement measures and response sensitivity optimization schemes; the improved thermal management control model includes prediction model weight optimization and control algorithm sensitivity calibration; and the intelligent thermal management strategy library includes an operating mode-heat dissipation parameter mapping table and a full life cycle thermal management strategy.

[0008] The present invention is further configured to generate a multi-dimensional thermal management basic dataset by collecting temperature distribution information at various locations of the battery pack through a temperature sensor array, based on real-time temperature data and power consumption data of the intelligent cleaning robot under different working modes, and recording the current cleaning task type and workload parameters. Based on the real-time operation data of the intelligent cleaning robot, the temperature distribution information of key points on the surface and inside of the battery pack is collected through a temperature sensor array. Combined with power consumption data, the energy consumption characteristics of each working mode are recorded to generate an initial temperature distribution dataset. Based on the initial temperature distribution dataset, multi-source data fusion technology is used to spatially and temporally synchronize temperature sensor data with robot working status parameters to generate a standardized multi-dimensional thermal management data set. Based on the standardized multidimensional thermal management data set, a classification algorithm is used to categorize cleaning task types and work intensity parameters, generating work mode classification labels with timestamps. Based on the aforementioned operating mode classification labels, temperature distribution data and power consumption data are integrated to generate a multi-dimensional thermal management basic dataset.

[0009] The present invention is further configured such that, based on the aforementioned multi-dimensional thermal management basic dataset, time series prediction analysis is used to analyze the temperature change trend of the battery pack, extract periodic and trend features, determine the direction and magnitude of temperature changes in future time periods, and generate temperature prediction results and trend indicators. The specific steps are as follows: Based on the aforementioned multi-dimensional thermal management dataset, the sliding time window technique is used to extract time series features of temperature changes, identify the periodicity and trend of temperature fluctuations, and generate temperature change feature analysis results. Based on the temperature change characteristic analysis results, a nonlinear dynamic modeling method is used to simulate the temperature change process of the battery pack over time, reveal the intrinsic driving factors of temperature change, and generate a temperature dynamic change model. Based on the aforementioned temperature dynamic change model, a trend decomposition algorithm is used to separate the long-term trend and short-term fluctuation components in temperature changes, generating a quantitative description of the direction and magnitude of temperature changes. Based on the quantitative description of the direction and magnitude of the temperature change, combined with future workload forecasts, temperature prediction results and trend indicators are generated.

[0010] The present invention is further configured such that, based on the temperature prediction results and trend indicators, if the future temperature rise trend exceeds a preset safety range, an adaptive control algorithm is activated to adjust the heat dissipation system parameters. The specific steps for calculating the optimal heat dissipation power configuration based on the current workload intensity and the predicted peak temperature, and generating the heat dissipation parameter adjustment amount, are as follows: Based on the temperature prediction results and trend indicators, if the future temperature rise trend is detected to exceed the preset safety range, the adaptive control algorithm is triggered to generate a heat dissipation demand signal. Based on the heat dissipation demand signal, combined with the current workload intensity and the predicted temperature peak, the optimal heat dissipation power configuration is calculated using dynamic programming, and a preliminary heat dissipation parameter adjustment scheme is generated. Based on the preliminary heat dissipation parameter adjustment scheme, the influence of the heat sink thermal conductivity and fan speed on temperature control is analyzed through a heat conduction model to generate heat dissipation parameter adjustment amounts. Based on the aforementioned heat dissipation parameter adjustment amount, the feasibility of the heat dissipation system parameters is verified, and the final heat dissipation parameter adjustment amount is generated.

[0011] The present invention is further configured such that, based on the heat dissipation parameter adjustment amount, a phased parameter adjustment path is generated using a smooth transition algorithm to avoid sudden jumps in heat dissipation control parameters, and the specific parameter value at each time node is obtained as follows: Based on the aforementioned heat dissipation parameter adjustment amount, a smooth transition algorithm is used to design the parameter adjustment path to ensure that the changes in fan speed and heat sink thermal conductivity meet the continuity requirements, thereby generating a preliminary parameter adjustment path; Based on the initial parameter adjustment path, the parameter change rate is optimized by dynamically adjusting the step size to avoid temperature fluctuations caused by parameter abrupt changes, and a phased parameter adjustment path is generated. Based on the phased parameter adjustment path, and combined with the timestamp, specific parameter values ​​are allocated for each time node to generate a detailed parameter adjustment plan. Based on the detailed parameter adjustment plan, the stability and effectiveness of the parameter adjustment path are verified, and the final parameter adjustment path is generated.

[0012] The present invention is further configured to, based on the generated parameter adjustment path, progressively execute parameter update operations for the heat dissipation system, while simultaneously monitoring the temperature response and system stability indicators; if the temperature control effect deviates from the expected target, then the subsequent parameter adjustment magnitude is corrected in real time, and the steps for generating a dynamically optimized control parameter sequence are as follows: Based on the parameter adjustment path, the parameter update operation of the heat dissipation system is executed step by step, the battery pack temperature response and system stability indicators are monitored in real time, and an initial control parameter sequence is generated. Based on the initial control parameter sequence, if the temperature control effect deviates from the expected target, a real-time correction mechanism is activated to dynamically adjust the adjustment range of subsequent parameters and generate a corrected control parameter sequence. Based on the corrected control parameter sequence, the parameter adjustment strategy is optimized through a feedback control algorithm to ensure that the temperature control effect gradually approaches the expected target, and a dynamically optimized control parameter sequence is generated. Based on the dynamically optimized control parameter sequence, the stability and accuracy of temperature control are verified, and the final control parameter sequence is generated.

[0013] The present invention is further configured such that, based on the dynamically optimized control parameter sequence, a temperature control effect evaluation mechanism is used to quantitatively analyze the execution result of the current heat dissipation strategy, and the direction of control strategy adjustment is generated by comparing the deviation between the actual temperature change curve and the predicted target curve. Based on the dynamically optimized control parameter sequence, a temperature control effect evaluation mechanism is adopted. By comparing the deviation between the actual temperature change curve and the predicted target curve, a temperature control effect evaluation result is generated. Based on the temperature control effect evaluation results, the reasons for insufficient temperature control accuracy are analyzed, and the direction for adjusting the control strategy is generated. Based on the control strategy, the direction is adjusted, and combined with historical temperature control data, the temperature prediction model and adaptive control algorithm are optimized to generate an improved control strategy. Based on the improved control strategy, its applicability and effectiveness in different working scenarios are verified, and the final control strategy adjustment direction is generated.

[0014] The present invention is further configured such that, based on the control strategy, the direction is adjusted, the weight parameters of the time series prediction model and the response sensitivity settings of the adaptive control algorithm are updated, and the algorithm performance is optimized through feedback learning of historical control effect data to generate an improved thermal management control model. The specific steps are as follows: Based on the control strategy, the direction is adjusted, and the weight parameters of the time series prediction model are updated using a feedback learning mechanism to improve the model's prediction accuracy of future temperature change trends and generate an improved temperature prediction model. Based on the improved temperature prediction model, the response sensitivity setting of the adaptive control algorithm is adjusted to optimize the real-time response capability of the heat dissipation system to temperature changes, thereby generating the improved adaptive control algorithm. Based on the improved adaptive control algorithm, the algorithm performance is verified by combining historical control effect data, and an improved thermal management control model is generated. Based on the improved thermal management control model, its stability and reliability under complex working scenarios are verified, and the final thermal management control model is generated.

[0015] The present invention is further configured to, based on the improved thermal management control model, recalculate the optimal heat dissipation strategy combination of the energy storage system under various working scenarios, establish a dynamic mapping relationship between working modes and heat dissipation parameters, form an intelligent thermal management strategy library covering the entire life cycle working states of the robot, and generate a complete adaptive thermal management solution. The specific steps are as follows: Based on the improved thermal management control model, the optimal heat dissipation strategy combination of the energy storage system under various working scenarios is recalculated, and an optimized heat dissipation strategy scheme is generated. Based on the aforementioned heat dissipation strategy optimization scheme, a dynamic mapping relationship between working modes and heat dissipation parameters is established, and a mapping table between working modes and heat dissipation parameters is generated. Based on the mapping table between the working mode and the heat dissipation parameters, the thermal management strategies under the entire life cycle working state are integrated to generate an intelligent thermal management strategy library. Based on the aforementioned intelligent thermal management strategy library, its comprehensive performance in practical applications is verified, and a complete adaptive thermal management solution is generated.

[0016] The beneficial effects of this invention are as follows: This invention achieves precise monitoring and dynamic adjustment of the battery pack temperature of intelligent cleaning robots through multi-dimensional data acquisition, time series prediction analysis, adaptive control algorithms, smooth transition algorithms, and feedback learning mechanisms. This significantly improves the thermal management efficiency and safety of energy storage systems and provides strong technical support for the efficient operation of intelligent cleaning robots. Attached Figure Description

[0017] The invention will be further illustrated with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the invention. For those skilled in the art, other drawings can be obtained based on the following drawings without any creative effort.

[0018] Figure 1 This is a process flow diagram of the present invention. Detailed Implementation

[0019] The present invention will be further described in conjunction with the following embodiments.

[0020] Depend on Figure 1 As can be seen, the intelligent cleaning robot battery thermal runaway and energy storage system optimization method described in this embodiment uses an intelligent cleaning robot equipped with a temperature sensor array, a heat dissipation system and a control module. Through multi-dimensional data acquisition, time series prediction analysis, adaptive control algorithms and smooth transition algorithms, it achieves precise monitoring and dynamic adjustment of battery pack temperature, and finally forms an intelligent thermal management strategy library covering the entire life cycle working state.

[0021] The overall process starts with data acquisition and gradually completes time series forecast analysis, heat dissipation parameter adjustment, smooth transition path design, dynamic optimization control parameter generation, temperature control effect evaluation, model optimization, and intelligent thermal management strategy library construction.

[0022] In actual operation, step S1 first requires collecting temperature distribution information at various locations within the battery pack using a temperature sensor array, and recording the current cleaning task type and workload parameters. The intelligent cleaning robot's battery pack consists of multiple individual lithium batteries distributed in the central area of ​​the robot's chassis. To achieve comprehensive temperature monitoring, this embodiment employs a set of high-precision temperature sensors, including surface temperature sensors and internally embedded temperature sensors. These sensors are positioned at key locations within the battery pack, such as the center point, edge areas, and near the heat sink, ensuring comprehensive capture of temperature change information. Simultaneously, power consumption data is collected in real-time using built-in current and voltage sensors, recording energy consumption characteristics under different operating modes. After spatial and temporal synchronization processing, this data generates a standardized multidimensional thermal management dataset, providing a foundation for subsequent analysis.

[0023] In step S2, based on a multi-dimensional thermal management dataset, time series prediction analysis is used to analyze the battery pack temperature change trend, extract periodic and trend features, and determine the direction and magnitude of temperature changes in future time periods. Specifically, a sliding time window technique is first used to extract the time series features of temperature changes. The width of the sliding time window is set to 10 seconds, and the step size is 1 second. By statistically analyzing the temperature data within each time window, the periodic and trend patterns of temperature fluctuations are identified. For example, in one experiment, it was found that when the robot performed a high-intensity cleaning task, the battery pack temperature showed a significant upward trend, with an increase of approximately 2°C per minute. Based on this, a nonlinear dynamic modeling method is used to simulate the change process of battery pack temperature over time. The formula for the nonlinear dynamic model is as follows: In this model, T(t) represents the temperature at time t, P(t) represents the power consumption at time t, Q(t) represents the heat dissipation power at time t, and α and β are the influence coefficients of power consumption and heat dissipation power on temperature change, respectively. This model can reveal the intrinsic driving factors of temperature change and generate a dynamic temperature change model. Furthermore, a trend decomposition algorithm is used to separate the long-term trend and short-term fluctuation components in temperature change, resulting in a quantitative description of the direction and magnitude of temperature change. For example, for a specific operating mode, the prediction results show that the temperature will rise by 6°C within the next 5 minutes, reaching a peak of 45°C.

[0024] In step S3, if the temperature prediction results and trend indicators show that the future temperature rise exceeds a preset safety range, the adaptive control algorithm is activated to adjust the heat dissipation system parameters. Specifically, when a future temperature rise exceeding a preset safety range (e.g., 40°C) is detected, the adaptive control algorithm is triggered to generate a heat dissipation demand signal. Subsequently, combining the current workload intensity and the predicted peak temperature, a dynamic programming method is used to calculate the optimal heat dissipation power configuration. The objective function of the dynamic programming is to minimize the sum of temperature deviation and heat dissipation energy consumption, as shown in the following formula: Where T(t) represents the actual temperature at time t, T_target represents the target temperature, E(t) represents the heat dissipation energy consumption at time t, and w1 and w2 are the weighting coefficients for temperature deviation and heat dissipation energy consumption, respectively. After generating a preliminary heat dissipation parameter adjustment scheme using this method, the influence of the heat sink's thermal conductivity and fan speed on temperature control is further analyzed using a heat conduction model; the heat conduction model formula is: Where Q represents heat dissipation power, k represents the thermal conductivity of the heat sink, A represents the heat dissipation area, ΔT represents the temperature difference, and d represents the thickness of the heat sink. Based on this model, specific fan speed adjustment values ​​and heat sink thermal conductivity adjustment values ​​are calculated, and the feasibility of the heat dissipation system parameters is verified to generate the final heat dissipation parameter adjustment values.

[0025] In step S4, based on the adjustment amount of the heat dissipation parameters, a smooth transition algorithm is used to generate a phased parameter adjustment path to avoid sudden jumps in the heat dissipation control parameters. First, the parameter adjustment path is designed to ensure that the changes in fan speed and heat sink thermal conductivity meet the continuity requirements. The core idea of ​​the smooth transition algorithm is to introduce a transition function. The parameter changes are smoothed, where a, b, and c are undetermined coefficients, and x represents the time variable. The rate of parameter change is optimized by dynamically adjusting the step size to avoid temperature fluctuations caused by abrupt parameter changes. For example, in one experiment, the fan speed was gradually increased from an initial value of 3000 rpm to a target value of 5000 rpm. The entire process was divided into 5 stages, each lasting 10 seconds. After assigning specific parameter values ​​for each time node based on timestamps, a detailed parameter adjustment plan was generated, and the stability and effectiveness of the parameter adjustment path were verified.

[0026] In step S5, based on the generated parameter adjustment path, the parameters of the heat dissipation system are updated step by step, while the temperature response and system stability indicators are monitored. First, the heat dissipation system parameters are updated step by step according to the parameter adjustment path, and the battery pack temperature response and system stability indicators are monitored in real time. For example, in one experiment, when the fan speed was adjusted to 4000 rpm, the battery pack temperature dropped by 2°C, and the system stability indicators remained within the normal range. However, when the temperature control effect deviates from the expected target, a real-time correction mechanism is activated to dynamically adjust the subsequent parameter adjustment range; for example, if the actual temperature drop rate is lower than expected, the fan speed adjustment range is appropriately increased. The parameter adjustment strategy is optimized through a feedback control algorithm to ensure that the temperature control effect gradually approaches the expected target. The feedback control algorithm formula is as follows: , where u(t) represents the control output, e(t) represents the error signal, and Kp, Ki and Kd are the proportional, integral and derivative coefficients, respectively.

[0027] In step S6, based on the dynamically optimized control parameter sequence, a temperature control effect evaluation mechanism is used to quantitatively analyze the execution result of the current heat dissipation strategy. The temperature control effect evaluation result is generated by comparing the deviation between the actual temperature change curve and the predicted target curve; for example, in a certain experiment, the maximum deviation between the actual temperature change curve and the predicted target curve was 1℃, and the average deviation was 0.5℃. Based on the evaluation result, the reasons for insufficient temperature control accuracy are analyzed, and the direction for adjusting the control strategy is generated; for example, if it is found that the insufficient temperature control accuracy is mainly due to the low thermal conductivity of the heat sink, the thermal conductivity of the heat sink is appropriately increased. The temperature prediction model and adaptive control algorithm are optimized by combining historical temperature control data to generate an improved control strategy.

[0028] In step S7, the direction is adjusted based on the control strategy, and the weight parameters of the time series prediction model and the response sensitivity settings of the adaptive control algorithm are updated. A feedback learning mechanism is used to update the weight parameters of the time series prediction model, improving the model's prediction accuracy for future temperature change trends; for example, by adjusting the α and β coefficients in the nonlinear dynamic model, the model is made to better reflect actual temperature changes. Simultaneously, the response sensitivity settings of the adaptive control algorithm are adjusted to optimize the real-time response capability of the heat dissipation system to temperature changes; for example, by appropriately increasing the Kp and Kd coefficients in the feedback control algorithm, the system response speed is improved. The algorithm performance is verified using historical control effect data, generating an improved thermal management control model.

[0029] In step S8, based on the improved thermal management control model, the optimal heat dissipation strategy combination for the energy storage system under various working scenarios is recalculated, establishing a dynamic mapping relationship between working modes and heat dissipation parameters. First, the optimal heat dissipation strategy combination for the energy storage system under various working scenarios is recalculated, generating optimized heat dissipation strategy schemes; for example, in low-intensity cleaning tasks, a lower fan speed and heat sink thermal conductivity are recommended; while in high-intensity cleaning tasks, a higher fan speed and heat sink thermal conductivity are recommended. Then, a dynamic mapping relationship between working modes and heat dissipation parameters is established, generating a working mode-heat dissipation parameter mapping table; for example, the carpet cleaning mode corresponds to a fan speed of 4000 rpm and a heat sink thermal conductivity of 200 W / m·K, while the hard floor cleaning mode corresponds to a fan speed of 3000 rpm and a heat sink thermal conductivity of 150 W / m·K. The thermal management strategies under all working states throughout the entire lifecycle are integrated to generate an intelligent thermal management strategy library; for example, the strategy library contains all working modes and their corresponding heat dissipation parameter combinations from the robot's initial use to its scrapping. Finally, the comprehensive performance of the intelligent thermal management strategy library in practical applications is verified, generating a complete adaptive thermal management solution.

[0030] In summary, this invention achieves precise monitoring and dynamic adjustment of the battery pack temperature of intelligent cleaning robots through multi-dimensional data acquisition, time series predictive analysis, adaptive control algorithms, smooth transition algorithms, and feedback learning mechanisms. This significantly improves the thermal management efficiency and safety of energy storage systems and provides strong technical support for the efficient operation of intelligent cleaning robots.

[0031] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the essence and scope of the technical solutions of the present invention.

Claims

1. A method for optimizing the thermal runaway of a battery and the energy storage system of an intelligent cleaning robot, characterized in that: Includes the following steps: S1. Based on the real-time temperature data and power consumption data of the intelligent cleaning robot in different working modes, the temperature distribution information of each position of the battery pack is collected through the temperature sensor array, and the current cleaning task type and work intensity parameters are recorded to generate a multi-dimensional thermal management basic dataset. S2. Based on a multi-dimensional thermal management dataset, time series prediction analysis is used to analyze the temperature change trend of the battery pack, extract periodic and trend features, determine the direction and magnitude of temperature change in the future time period, and generate temperature prediction results and trend indicators. S3. Based on the temperature prediction results and trend indicators, if the future temperature rise trend exceeds the preset safety range, the adaptive control algorithm is activated to adjust the heat dissipation system parameters. The optimal heat dissipation power configuration is calculated based on the current workload intensity and the predicted peak temperature, and the heat dissipation parameter adjustment amount is generated. S4. Based on the adjustment amount of heat dissipation parameters, a smooth transition algorithm is used to generate a phased parameter adjustment path to avoid sudden jumps in heat dissipation control parameters and obtain the specific parameter values ​​at each time node. S5. Based on the generated parameter adjustment path, the parameter update operation of the heat dissipation system is executed step by step. At the same time, the temperature response and system stability indicators are monitored. If the temperature control effect deviates from the expected target, the subsequent parameter adjustment range is corrected in real time to generate a dynamically optimized control parameter sequence. S6. Based on the dynamically optimized control parameter sequence, a temperature control effect evaluation mechanism is used to quantitatively analyze the execution result of the current heat dissipation strategy. By comparing the deviation between the actual temperature change curve and the predicted target curve, the direction of control strategy adjustment is generated. S7. Adjust the direction based on the control strategy, update the weight parameters of the time series prediction model and the response sensitivity settings of the adaptive control algorithm, optimize the algorithm performance through feedback learning of historical control effect data, and generate an improved thermal management control model. S8. Based on the improved thermal management control model, the optimal heat dissipation strategy combination of the energy storage system under various working scenarios is recalculated, a dynamic mapping relationship between working mode and heat dissipation parameters is established, an intelligent thermal management strategy library covering the working state of the robot throughout its entire life cycle is formed, and a complete adaptive thermal management solution is generated.

2. The method for optimizing the thermal runaway and energy storage system of an intelligent cleaning robot battery according to claim 1, characterized in that: The multi-dimensional thermal management basic dataset includes battery pack temperature distribution maps, power consumption trend analysis, and operating mode classification. The temperature prediction results and trend indicators include temperature rise rate assessment, future peak temperature prediction, and abnormal temperature rise warning. The heat dissipation parameter adjustment amounts specifically include fan speed adjustment values ​​and heat sink thermal conductivity adjustment values. The dynamically optimized control parameter sequence includes staged parameter adjustment paths and real-time correction strategies. The control strategy adjustment directions include temperature control accuracy improvement measures and response sensitivity optimization schemes. The improved thermal management control model includes prediction model weight optimization and control algorithm sensitivity calibration. The intelligent thermal management strategy library includes an operating mode-heat dissipation parameter mapping table and full life cycle thermal management strategies.

3. The method for optimizing the thermal runaway and energy storage system of an intelligent cleaning robot battery according to claim 1, characterized in that: Based on real-time temperature and power consumption data of the intelligent cleaning robot under different working modes, the steps to collect temperature distribution information at various locations of the battery pack through a temperature sensor array, and record the current cleaning task type and workload parameters to generate a multi-dimensional thermal management basic dataset are as follows: Based on the real-time operation data of the intelligent cleaning robot, the temperature distribution information of key points on the surface and inside of the battery pack is collected through a temperature sensor array. Combined with power consumption data, the energy consumption characteristics of each working mode are recorded to generate an initial temperature distribution dataset. Based on the initial temperature distribution dataset, multi-source data fusion technology is used to spatially and temporally synchronize temperature sensor data with robot working status parameters to generate a standardized multi-dimensional thermal management data set. Based on the standardized multidimensional thermal management data set, a classification algorithm is used to categorize cleaning task types and work intensity parameters, generating work mode classification labels with timestamps. Based on the aforementioned operating mode classification labels, temperature distribution data and power consumption data are integrated to generate a multi-dimensional thermal management basic dataset.

4. The method for optimizing the thermal runaway and energy storage system of an intelligent cleaning robot battery according to claim 1, characterized in that: Based on the aforementioned multi-dimensional thermal management dataset, the specific steps for using time series prediction analysis to analyze the battery pack temperature change trend, extracting periodic and trend features, determining the direction and magnitude of temperature changes in future time periods, and generating temperature prediction results and trend indicators are as follows: Based on the aforementioned multi-dimensional thermal management dataset, the sliding time window technique is used to extract time series features of temperature changes, identify the periodicity and trend of temperature fluctuations, and generate temperature change feature analysis results. Based on the temperature change characteristic analysis results, a nonlinear dynamic modeling method is used to simulate the temperature change process of the battery pack over time, reveal the intrinsic driving factors of temperature change, and generate a temperature dynamic change model. Based on the aforementioned temperature dynamic change model, a trend decomposition algorithm is used to separate the long-term trend and short-term fluctuation components in temperature changes, generating a quantitative description of the direction and magnitude of temperature changes. Based on the quantitative description of the direction and magnitude of the temperature change, combined with future workload forecasts, temperature prediction results and trend indicators are generated.

5. The method for optimizing the thermal runaway and energy storage system of an intelligent cleaning robot battery according to claim 1, characterized in that: Based on the temperature prediction results and trend indicators, if the future temperature rise trend exceeds the preset safety range, an adaptive control algorithm is activated to adjust the heat dissipation system parameters. The specific steps for calculating the optimal heat dissipation power configuration and generating the heat dissipation parameter adjustment amount based on the current workload intensity and the predicted peak temperature are as follows: Based on the temperature prediction results and trend indicators, if the future temperature rise trend is detected to exceed the preset safety range, the adaptive control algorithm is triggered to generate a heat dissipation demand signal. Based on the heat dissipation demand signal, combined with the current workload intensity and the predicted temperature peak, the optimal heat dissipation power configuration is calculated using dynamic programming, and a preliminary heat dissipation parameter adjustment scheme is generated. Based on the preliminary heat dissipation parameter adjustment scheme, the influence of the heat sink thermal conductivity and fan speed on temperature control is analyzed through a heat conduction model to generate heat dissipation parameter adjustment amounts. Based on the aforementioned heat dissipation parameter adjustment amount, the feasibility of the heat dissipation system parameters is verified, and the final heat dissipation parameter adjustment amount is generated.

6. The method for optimizing the thermal runaway and energy storage system of an intelligent cleaning robot battery according to claim 1, characterized in that: Based on the aforementioned heat dissipation parameter adjustment amount, a smooth transition algorithm is used to generate a phased parameter adjustment path to avoid sudden jumps in heat dissipation control parameters. The specific steps for obtaining the specific parameter values ​​at each time node are as follows: Based on the aforementioned heat dissipation parameter adjustment amount, a smooth transition algorithm is used to design the parameter adjustment path to ensure that the changes in fan speed and heat sink thermal conductivity meet the continuity requirements, thereby generating a preliminary parameter adjustment path; Based on the initial parameter adjustment path, the parameter change rate is optimized by dynamically adjusting the step size to avoid temperature fluctuations caused by parameter abrupt changes, and a phased parameter adjustment path is generated. Based on the phased parameter adjustment path, and combined with the timestamp, specific parameter values ​​are allocated for each time node to generate a detailed parameter adjustment plan. Based on the detailed parameter adjustment plan, the stability and effectiveness of the parameter adjustment path are verified, and the final parameter adjustment path is generated.

7. The method for optimizing the thermal runaway and energy storage system of an intelligent cleaning robot battery according to claim 1, characterized in that: Based on the generated parameter adjustment path, the parameter update operation of the heat dissipation system is executed step by step, while monitoring the temperature response and system stability indicators. If the temperature control effect deviates from the expected target, the subsequent parameter adjustment range is adjusted in real time. The specific steps for generating a dynamically optimized control parameter sequence are as follows: Based on the parameter adjustment path, the parameter update operation of the heat dissipation system is executed step by step, the battery pack temperature response and system stability indicators are monitored in real time, and an initial control parameter sequence is generated. Based on the initial control parameter sequence, if the temperature control effect deviates from the expected target, a real-time correction mechanism is activated to dynamically adjust the adjustment range of subsequent parameters and generate a corrected control parameter sequence. Based on the corrected control parameter sequence, the parameter adjustment strategy is optimized through a feedback control algorithm to ensure that the temperature control effect gradually approaches the expected target, and a dynamically optimized control parameter sequence is generated. Based on the dynamically optimized control parameter sequence, the stability and accuracy of temperature control are verified, and the final control parameter sequence is generated.

8. The method for optimizing the thermal runaway and energy storage system of a smart cleaning robot battery according to claim 1, characterized in that: Based on the dynamically optimized control parameter sequence, a temperature control effect evaluation mechanism is used to quantitatively analyze the execution result of the current heat dissipation strategy. The specific steps for generating the control strategy adjustment direction by comparing the deviation between the actual temperature change curve and the predicted target curve are as follows: Based on the dynamically optimized control parameter sequence, a temperature control effect evaluation mechanism is adopted. By comparing the deviation between the actual temperature change curve and the predicted target curve, a temperature control effect evaluation result is generated. Based on the temperature control effect evaluation results, the reasons for insufficient temperature control accuracy are analyzed, and the direction for adjusting the control strategy is generated. Based on the control strategy, the direction is adjusted, and combined with historical temperature control data, the temperature prediction model and adaptive control algorithm are optimized to generate an improved control strategy. Based on the improved control strategy, its applicability and effectiveness in different working scenarios are verified, and the final control strategy adjustment direction is generated.

9. The method for optimizing the thermal runaway and energy storage system of an intelligent cleaning robot battery according to claim 1, characterized in that: The specific steps for adjusting the direction based on the control strategy, updating the weight parameters of the time series prediction model and the response sensitivity settings of the adaptive control algorithm, and optimizing the algorithm performance through feedback learning from historical control performance data to generate an improved thermal management control model are as follows: Based on the control strategy, the direction is adjusted, and the weight parameters of the time series prediction model are updated using a feedback learning mechanism to improve the model's prediction accuracy of future temperature change trends and generate an improved temperature prediction model. Based on the improved temperature prediction model, the response sensitivity setting of the adaptive control algorithm is adjusted to optimize the real-time response capability of the heat dissipation system to temperature changes, thereby generating the improved adaptive control algorithm. Based on the improved adaptive control algorithm, the algorithm performance is verified by combining historical control effect data, and an improved thermal management control model is generated. Based on the improved thermal management control model, its stability and reliability under complex working scenarios are verified, and the final thermal management control model is generated.

10. The method for optimizing the thermal runaway and energy storage system of an intelligent cleaning robot battery according to claim 1, characterized in that: Based on the improved thermal management control model, the optimal heat dissipation strategy combination of the energy storage system under various working scenarios is recalculated, a dynamic mapping relationship between working modes and heat dissipation parameters is established, and an intelligent thermal management strategy library covering the entire life cycle working states of the robot is formed. The specific steps for generating a complete adaptive thermal management solution are as follows: Based on the improved thermal management control model, the optimal heat dissipation strategy combination of the energy storage system under various working scenarios is recalculated, and an optimized heat dissipation strategy scheme is generated. Based on the aforementioned heat dissipation strategy optimization scheme, a dynamic mapping relationship between working modes and heat dissipation parameters is established, and a mapping table between working modes and heat dissipation parameters is generated. Based on the mapping table between the working mode and the heat dissipation parameters, the thermal management strategies under the entire life cycle working state are integrated to generate an intelligent thermal management strategy library. Based on the aforementioned intelligent thermal management strategy library, its comprehensive performance in practical applications is verified, and a complete adaptive thermal management solution is generated.

Images