State monitoring method of two-way liquid cooling energy storage system

Abstract

The invention discloses a state monitoring method for a two-way liquid cooling energy storage system, and belongs to the field of energy storage system monitoring. According to the method, the problem that the system state is difficult to accurately monitor in real time in the prior art is solved, the detailed operation state of the system can be mastered in real time through comprehensive data acquisition, the data quality is improved through filtering, denoising and normalization operation in the data processing link, a foundation can be laid for subsequent accurate evaluation, and the system reliability is improved. Potential faults can be found in time through state evaluation and abnormal early warning links, fault positions and reasons are accurately positioned in combination with a fault diagnosis algorithm, the maintenance time is effectively shortened, fault risks are reduced, system operation parameters are automatically adjusted according to evaluation and diagnosis results in an operation optimization link, and the system reliability is improved. And the cooling liquid flow, the temperature and the battery charging and discharging strategy are optimized, so that efficient and safe operation of the two-way liquid cooling energy storage system is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of energy storage system monitoring technology, specifically a status monitoring method for a dual-path liquid-cooled energy storage system. Background Technology

[0002] With the development of energy storage technology, liquid-cooled energy storage systems have been widely used due to their efficient heat dissipation performance. However, most existing liquid-cooled energy storage systems are single-channel liquid-cooled, which can easily lead to overheating and damage to the energy storage battery if the coolant leaks or the cooling system fails. Furthermore, it is difficult to accurately and in real-time monitor the system status, resulting in safety hazards and low operating efficiency. Therefore, these systems do not meet current requirements. To address this, we propose a status monitoring method for dual-channel liquid-cooled energy storage systems. Summary of the Invention

[0003] The purpose of this invention is to provide a status monitoring method for a dual-channel liquid-cooled energy storage system. Through comprehensive data acquisition, the detailed operating status of the system can be grasped in real time. The filtering, noise reduction, and normalization operations in the data processing stage improve data quality and lay the foundation for accurate subsequent assessment. Through the status assessment and anomaly early warning stages, potential faults can be detected in a timely manner. Combined with fault diagnosis algorithms, the fault location and cause can be accurately located, effectively shortening maintenance time and reducing fault risk. The operation optimization stage automatically adjusts the system operating parameters based on the assessment and diagnosis results, optimizing coolant flow, temperature, and battery charging and discharging strategies to ensure the efficient and safe operation of the dual-channel liquid-cooled energy storage system, thus solving the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a state monitoring method for a dual-path liquid-cooled energy storage system, the state monitoring method comprising the following steps: By deploying multiple sensors, the system collects real-time status data of the dual-channel liquid-cooled energy storage system, including but not limited to the temperature, voltage, and current of the battery pack, as well as the flow rate, pressure, and temperature of the coolant. The long-term performance trend of the dual-channel liquid-cooled energy storage system is analyzed, and the collected state data is analyzed using a preset evaluation model to evaluate the battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system. Set threshold ranges for each parameter. When any parameter in the evaluation results exceeds its corresponding threshold range, it is determined that the dual-path liquid-cooled energy storage system is abnormal. If an anomaly is detected, the fault diagnosis algorithm is used to determine the specific location and cause of the fault, and an early warning message is issued, while also notifying the operation and maintenance personnel. Based on the results of condition assessment and fault diagnosis, the operating parameters of the dual-channel liquid-cooled energy storage system are automatically adjusted, including adjusting the flow rate and temperature of the coolant, and optimizing the charging and discharging strategy of the energy storage battery.

[0005] Furthermore, the long-term performance trend analysis of the dual-channel liquid-cooled energy storage system involves the following specific steps: Establish a long-term performance trend database to store the results of each status assessment and fault diagnosis, as well as the corresponding operating parameters and environmental conditions; By using time series analysis algorithms to analyze long-term performance trend data, the performance change trend of the dual-channel liquid-cooled energy storage system can be predicted over a period of time, including battery life degradation trend and cooling system efficiency change trend. Based on the performance trend analysis results, develop preventative maintenance plans in advance, including battery replacement plans and cooling system maintenance plans.

[0006] Furthermore, the battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system are evaluated, and the specific steps are as follows: The collected status data is integrated into a unified data framework, ensuring timestamp alignment, and key features are extracted from the integrated status data, specifically: Battery health status characteristics: Extracting the average temperature, maximum temperature difference, voltage fluctuation range, and current fluctuation range of each battery cell from the status data; Cooling operation status characteristics: Extract the characteristics of the coolant system, such as average flow rate, maximum flow rate difference, average pressure, pressure fluctuation range, and temperature change rate, from the status data; An evaluation model is built based on machine learning algorithms. Historical data is used to train the evaluation model to ensure that the training data covers the battery status under different operating conditions. The hyperparameters of the evaluation model are optimized through cross-validation. The extracted battery health status features and cooling operation status features are input into the evaluation model, and the evaluation model outputs the evaluation results of the battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system.

[0007] Furthermore, fault diagnosis algorithms are used to determine the specific location and cause of the fault. The specific steps are as follows: Pre-set the threshold range for each parameter, and adjust the threshold range regularly based on seasonal changes and load conditions of the dual-path liquid-cooled energy storage system. At the same time, optimize the threshold settings by combining historical data and actual operating conditions. If the threshold setting of a certain parameter is found to be unreasonable, adjust it in time. The evaluation results are compared with preset thresholds. If any parameter in the evaluation results exceeds its corresponding threshold range, the data is marked as abnormal data, and the time of the abnormality, sensor number, abnormal parameter value and threshold range are recorded. Based on the topology and working principle of the dual-channel liquid-cooled energy storage system, and using a pre-trained fault diagnosis model to further analyze the abnormal data, the fault diagnosis model outputs the specific location and cause of the fault based on the characteristics of the input abnormal data. Detailed early warning information is generated based on the fault diagnosis results, including fault description, scope of impact and recommended measures. At the same time, the early warning information is sent to the operation and maintenance personnel via SMS notification or remote push.

[0008] Furthermore, based on historical data and actual operational conditions, the threshold settings were optimized. The specific steps are as follows: Retrieve the values ​​of each parameter from historical data; Retrieve the peak and trough values ​​corresponding to each parameter from the historical data; Extract the timestamps corresponding to all peak and trough values ​​for each parameter; The threshold range corresponding to the peak and trough values ​​is determined based on the timestamps of all the peak and trough values ​​corresponding to the parameters, and is used as the target threshold range. Determine whether the target threshold range has undergone an optimization process; If the target threshold range has undergone an optimization process, then the optimized threshold range parameters are retrieved. The current threshold range is optimized using the optimized threshold range parameters and actual operating data.

[0009] Furthermore, the current threshold range is further optimized using the optimized threshold range parameters and actual operating data. The specific steps are as follows: Retrieve the values ​​of each parameter in the current actual operating data and their corresponding currently adjusted but not optimized threshold ranges; The values ​​of each parameter in the current actual operating data are used to obtain the values ​​that are within the threshold range that have been adjusted but not optimized. Retrieve the data difference between the value in the currently adjusted but unoptimized threshold range and the threshold value of that range; When the number of data differences below the preset data difference threshold is less than the preset number threshold, the current threshold range is optimized using only the optimized threshold range parameter. When the number of data differences that are lower than the preset data difference threshold is not lower than the preset number threshold, the current threshold range is optimized using the threshold range parameter and all data differences.

[0010] Furthermore, after the early warning information is issued, the results of the early warning are tracked and feedback is provided. The specific steps are as follows: Record the sending time and receiving status of early warning information to ensure that maintenance personnel receive early warning information in a timely manner; Set a warning response time threshold; if the maintenance personnel do not respond within the specified time, a second warning message will be automatically sent. Provide feedback channels so that maintenance personnel can provide feedback on the processing results; Based on feedback from maintenance personnel, update the status and fault records of the dual-path liquid-cooled energy storage system; Based on the early warning results and feedback from maintenance personnel, the effectiveness of the early warning mechanism is evaluated regularly. If the early warning information is found to be inaccurate or the response is not timely, the fault diagnosis algorithm and early warning notification method are optimized. The fault diagnosis model and rule base are updated based on new fault cases.

[0011] Furthermore, detailed early warning information is generated based on the fault diagnosis results, and graded early warnings are issued for abnormal states of the dual-path liquid-cooled energy storage system. The specific steps are as follows: Based on the type of abnormal parameters, the degree to which they exceed the threshold, and the degree of impact on the operation of the dual-path liquid-cooled energy storage system, the abnormal state is divided into several levels, including minor abnormality, moderate abnormality, and severe abnormality. For different levels of abnormal status, corresponding early warning information content and notification methods should be formulated; Minor anomalies are communicated to maintenance personnel via internal system prompts or emails; moderate anomalies are communicated to maintenance personnel via SMS; and severe anomalies are communicated to maintenance personnel and relevant management personnel simultaneously via SMS or telephone. Different response time thresholds are set according to the severity of the abnormal state. For severe abnormal states, maintenance personnel are required to respond and handle the situation in a shorter time.

[0012] Furthermore, based on the results of condition assessment and fault diagnosis, the operating parameters of the dual-path liquid-cooled energy storage system are automatically adjusted. The specific steps are as follows: By integrating the status assessment report and fault diagnosis results, the current operating status and existing problems of the dual-channel liquid-cooled energy storage system are clarified, and key parameters that need to be optimized are identified for automatic adjustment of the operating parameters of the dual-channel liquid-cooled energy storage system. After optimization, the operating status of the dual-channel liquid-cooled energy storage system is monitored in real time to verify the optimization effect and compare the battery temperature, coolant flow and temperature, and battery charging and discharging efficiency before and after optimization. If the optimization results are not satisfactory, analyze the reasons and adjust the optimization strategy.

[0013] Furthermore, if the optimization effect is not ideal, analyze the reasons and adjust the optimization strategy. The specific steps are as follows: If the optimization effect is not ideal, use deep learning algorithms to analyze the data during the optimization process and find the possible causes of the problem, including unreasonable selection of optimization algorithm, inaccurate allocation of parameter weights, and deviation between the model and actual operation. Based on the analysis results, the optimization strategy is dynamically adjusted, including changing the optimization algorithm, reallocating parameter weights, and modifying the model; Repeat the above optimization process until the optimization effect reaches the preset performance index; Meanwhile, a self-learning mechanism is introduced to automatically record the data and results of the optimization process after each optimization and adjustment. By continuously learning and accumulating experience, the operating parameters of the dual-path liquid-cooled energy storage system can be continuously optimized.

[0014] Compared with the prior art, the beneficial effects of the present invention are: This invention, through comprehensive data acquisition, enables real-time monitoring of the system's detailed operating status, ensuring accurate monitoring of key parameters of the battery pack and cooling system. The data processing stage improves data quality through filtering, noise reduction, and normalization, laying the foundation for accurate subsequent assessments. The status assessment and anomaly warning stages promptly identify potential faults, and combined with fault diagnosis algorithms, accurately pinpoint the fault location and cause, effectively shortening repair time and reducing fault risks. The operation optimization stage automatically adjusts system operating parameters based on assessment and diagnosis results, optimizing coolant flow, temperature, and battery charging and discharging strategies. This improves the operating efficiency and stability of the dual-channel liquid-cooled energy storage system, extends battery life, and ensures the efficient and safe operation of the dual-channel liquid-cooled energy storage system, providing reliable support for energy storage and utilization. Attached Figure Description

[0015] Figure 1 This is a flowchart of the status monitoring method for the dual-channel liquid-cooled energy storage system of the present invention; Figure 2 This is a flowchart of the hierarchical early warning and feedback mechanism of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] To address the technical issues of existing liquid-cooled energy storage systems, which are mostly single-channel liquid-cooled, making them prone to overheating and damage to the energy storage battery in case of coolant leakage or cooling system failure, and which pose safety hazards and low operating efficiency due to the difficulty in accurately and in real-time monitoring of system status, please refer to [link to relevant documentation]. Figures 1-2This embodiment provides the following technical solution: A method for monitoring the condition of a dual-channel liquid-cooled energy storage system includes the following steps: By deploying multiple sensors, the system collects real-time status data of the dual-channel liquid-cooled energy storage system, including but not limited to the temperature, voltage, and current of the battery pack, as well as the flow rate, pressure, and temperature of the coolant. The long-term performance trend of the dual-channel liquid-cooled energy storage system is analyzed, and the collected state data is analyzed using a preset evaluation model to evaluate the battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system. Set threshold ranges for each parameter. When any parameter in the evaluation results exceeds its corresponding threshold range, it is determined that the dual-path liquid-cooled energy storage system is abnormal. If an anomaly is detected, the fault diagnosis algorithm is used to determine the specific location and cause of the fault, and an early warning message is issued, while also notifying the operation and maintenance personnel. Based on the results of condition assessment and fault diagnosis, the operating parameters of the dual-channel liquid-cooled energy storage system are automatically adjusted, including adjusting the flow rate and temperature of the coolant, and optimizing the charging and discharging strategy of the energy storage battery.

[0018] The technical effects of the above solution are as follows: By deploying multiple sensors to collect system status data in real time and combining this with long-term performance trend analysis, it helps to detect potential performance degradation problems in advance and take timely measures for maintenance or adjustment, thereby extending the service life of the battery pack and cooling system. A preset evaluation model is used to analyze the collected data to assess the battery health and cooling operation status. By setting threshold ranges for each parameter, when any parameter exceeds the threshold, the system is judged to have malfunctioned. A fault diagnosis algorithm is used to determine the fault location and cause, issue an early warning, and notify maintenance personnel, facilitating rapid problem location and reducing troubleshooting time, further improving system safety. Based on the status assessment and fault diagnosis results, operating parameters are automatically adjusted, preventing the battery pack and cooling system from operating under adverse conditions for extended periods and reducing equipment wear and tear.

[0019] The specific steps for analyzing the long-term performance trend of a dual-channel liquid-cooled energy storage system are as follows: Establish a long-term performance trend database to store the results of each status assessment and fault diagnosis, as well as the corresponding operating parameters and environmental conditions; By using time series analysis algorithms to analyze long-term performance trend data, the performance change trend of the dual-channel liquid-cooled energy storage system in the future is predicted, including the battery life degradation trend and the cooling system efficiency change trend. Based on the performance trend analysis results, develop preventative maintenance plans in advance, including battery replacement plans and cooling system maintenance plans.

[0020] The technical effects of the above solution are as follows: long-term performance trend analysis of the dual-path liquid-cooled energy storage system can achieve accurate prediction and optimized management of system performance. By establishing a long-term performance trend database to store the results of each state assessment and fault diagnosis, as well as the corresponding operating parameters and environmental conditions, and using time series analysis algorithms to analyze the data to predict future performance changes such as battery life decay trends and cooling system efficiency changes, preventive maintenance plans can be formulated in advance based on the analysis results, thereby effectively extending equipment service life, reducing maintenance costs, and reducing the risk of sudden failures.

[0021] The battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system are evaluated through the following steps: The collected status data is integrated into a unified data framework, ensuring timestamp alignment, and key features are extracted from the integrated status data, specifically: Battery health status characteristics: Extracting the average temperature, maximum temperature difference, voltage fluctuation range, and current fluctuation range of each battery cell from the status data; Cooling operation status characteristics: Extract the characteristics of the coolant system, such as average flow rate, maximum flow rate difference, average pressure, pressure fluctuation range, and temperature change rate, from the status data; An evaluation model is built based on machine learning algorithms. Historical data is used to train the evaluation model to ensure that the training data covers the battery status under different operating conditions. The hyperparameters of the evaluation model are optimized through cross-validation. The extracted battery health status features and cooling operation status features are input into the evaluation model, and the evaluation model outputs the evaluation results of the battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system.

[0022] The technical effects of the above solution are as follows: by integrating and extracting key features from the collected status data, including battery health status features and cooling operation status features, and building an evaluation model based on machine learning algorithms, the battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system can be accurately evaluated, providing a scientific basis for the operation monitoring and fault early warning of the dual-channel liquid-cooled energy storage system, and improving the operation reliability and maintenance efficiency of the dual-channel liquid-cooled energy storage system.

[0023] The specific steps for determining the exact location and cause of a fault using a fault diagnosis algorithm are as follows: Pre-set the threshold range for each parameter, and adjust the threshold range regularly based on seasonal changes and load conditions of the dual-path liquid-cooled energy storage system. At the same time, optimize the threshold settings by combining historical data and actual operating conditions. If the threshold setting of a certain parameter is found to be unreasonable, adjust it in time. The evaluation results are compared with preset thresholds. If any parameter in the evaluation results exceeds its corresponding threshold range, the data is marked as abnormal data, and the time of the abnormality, sensor number, abnormal parameter value and threshold range are recorded. Based on the topology and working principle of the dual-channel liquid-cooled energy storage system, and using a pre-trained fault diagnosis model to further analyze the abnormal data, the fault diagnosis model outputs the specific location and cause of the fault based on the characteristics of the input abnormal data. Detailed early warning information is generated based on the fault diagnosis results, including fault description, scope of impact and recommended measures. At the same time, the early warning information is sent to the operation and maintenance personnel via SMS notification or remote push.

[0024] The technical effects of the above solution are as follows: By using fault diagnosis algorithms to determine the specific location and cause of the fault, dynamically adjusting the threshold range to adapt to seasonal changes and load conditions, and optimizing the threshold settings by combining historical data, the accuracy and timeliness of fault detection can be ensured. Abnormal data is marked and recorded to facilitate subsequent analysis and tracing. Furthermore, by using the fault diagnosis model to accurately locate the fault location and analyze the cause, the source of the fault can be quickly identified, and detailed early warning information can be generated and notified to operation and maintenance personnel through various means. This helps to respond to and handle faults in a timely manner, thereby effectively improving the fault handling efficiency of the dual-path liquid-cooled energy storage system, reducing the impact of faults on system operation, enhancing the reliability and stability of the system, and thus improving the level of intelligent operation and maintenance management.

[0025] Specifically, based on historical data and actual operational conditions, the threshold settings are optimized. The specific steps are as follows: Retrieve the values ​​of each parameter from historical data; Retrieve the peak and trough values ​​corresponding to each parameter from the historical data; Extract the timestamps corresponding to all peak and trough values ​​for each parameter; The threshold range corresponding to the peak and trough values ​​is determined based on the timestamps of all the peak and trough values ​​corresponding to the parameters, and is used as the target threshold range. Determine whether the target threshold range has undergone an optimization process; If the target threshold range has undergone an optimization process, then the optimized threshold range parameters are retrieved. The current threshold range is optimized using the optimized threshold range parameters and actual operating data.

[0026] The technical effect of the above solution is as follows: By extracting the peak and trough values ​​and corresponding timestamps of each parameter from historical data, the determination of the target threshold range no longer relies on static empirical values, but is based on the extreme value fluctuation characteristics that occur in the actual operation of the system. Peaks and troughs themselves reflect the boundary states of parameters under different operating conditions (such as high load, low load, changes in ambient temperature, etc.). The threshold range based on this can more accurately cover the normal fluctuation range of the system, avoiding false alarms (such as misjudging normal peak values ​​as faults) or missed alarms (such as not covering abnormal troughs) caused by static thresholds.

[0027] The operating parameters of a dual-channel liquid-cooled energy storage system will slowly drift due to factors such as equipment aging, environmental changes, and load mode adjustments (e.g., the liquid cooling pump flow rate decreases after long-term operation, and battery heat dissipation requirements change as SOH decreases). The step in the solution to "optimize the current threshold using optimized threshold range parameters and actual operating data" achieves dynamic threshold updates—inheriting historical optimization results (retrieving optimized parameters) and combining real-time status (actual operating data), enabling the threshold to continuously adapt to the dynamic changes of the system and avoiding monitoring failures caused by threshold "fixation".

[0028] Meanwhile, the solution constructs a "memory mechanism" for threshold optimization by "determining whether the target threshold has undergone an optimization process" and retrieving "optimized threshold range parameters." This means that each optimization does not start from scratch, but rather iterates based on historical optimization results, continuously accumulating knowledge of system characteristics (such as parameter patterns under specific seasons and loads). As the running time increases, the threshold range will gradually converge to the system's true safety boundary, and the monitoring accuracy will continuously improve.

[0029] Specifically, the current threshold range is optimized using the optimized threshold range parameters and actual operating data. The specific steps are as follows: Retrieve the values ​​of each parameter in the current actual operating data and their corresponding currently adjusted but not optimized threshold ranges; The values ​​of each parameter in the current actual operating data are used to obtain the values ​​that are within the threshold range that have been adjusted but not optimized. Retrieve the data difference between the value in the currently adjusted but unoptimized threshold range and the threshold value of that range; When the number of data differences below the preset data difference threshold is less than the preset number threshold, the current threshold range is optimized using only the optimized threshold range parameter. The optimized threshold range is obtained using the following formula:

[0030] Where D represents the boundary value corresponding to the threshold range after optimization; D0 represents the boundary value corresponding to the threshold range before optimization; n represents the total number of parameters for the optimized threshold range; P i Let P represent the magnitude ratio of the i-th optimized threshold range parameter to the unoptimized threshold range parameter, and P i A negative value for P indicates that the optimized threshold range parameter is narrowed; i A positive number indicates that the optimized threshold range parameter is expanded; When the number of data differences that are lower than the preset data difference threshold is not lower than the preset number threshold, the current threshold range is optimized using the threshold range parameter and all data differences. The optimized threshold range is obtained using the following formula:

[0031] Where D represents the boundary value corresponding to the threshold range after optimization; D0 represents the boundary value corresponding to the threshold range before optimization; n represents the total number of parameters for the optimized threshold range; P i Let P represent the magnitude ratio of the i-th optimized threshold range parameter to the unoptimized threshold range parameter, and P i A negative value for P indicates that the optimized threshold range parameter is narrowed; i A positive number indicates that the optimized threshold range parameter is expanded; m represents the number of data differences lower than the preset data difference threshold; C i C represents the data difference value of the i-th data difference value that is lower than the preset data difference threshold; p This indicates the span value corresponding to the threshold range that has been adjusted but not optimized.

[0032] The technical effects of the above solution are as follows: In actual operation, the parameter fluctuations of the system are not constant but exhibit different characteristics due to various factors. When the number of data differences below the preset data difference threshold is small, it means that the system is currently operating relatively smoothly, and the parameter fluctuations are within a small range. In this case, using only the optimized threshold range parameters for optimization can fully leverage the value of historical optimization experience. Because during the stable operation phase of the system, the parameter adjustment patterns accumulated through historical optimization can often adapt well to the current state, avoiding unnecessary fluctuations that may be caused by introducing too much real-time data, ensuring the stability and reliability of the threshold range, and preventing misjudgments due to frequent threshold adjustments during stable system operation. However, when the number of data differences below the preset data difference threshold is large, it indicates that the system may be in a phase of significant changes in operating conditions, and the parameter fluctuations are more pronounced. In this case, combining the threshold range parameters with all data differences to optimize the current threshold range allows the threshold range to reflect the real-time operating status of the system more promptly and accurately. This strategy of flexibly selecting optimization methods according to different scenarios allows the adjustment of the threshold range to closely match the actual operation of the system. Whether in a stable period or a period of fluctuation, effective threshold optimization can be achieved, greatly enhancing the system's adaptability to various operating scenarios.

[0033] Meanwhile, quantifying the fusion optimization effect of "historical experience + real-time feedback" provides a scientific and precise calculation basis for threshold range optimization, achieving an organic integration of historical optimization experience and real-time operational data. In the formula that only uses the optimized threshold range parameters, the total number n of optimized threshold range parameters and the magnitude P of each parameter compared to the unoptimized value are introduced. i This quantifies the adjustment trends and magnitudes accumulated during historical optimization. This makes historical experience no longer a vague concept, but rather something that can be reflected in the optimized threshold range through specific numerical calculations, ensuring that historical optimization results can be effectively inherited and applied. Furthermore, in the formula that combines threshold range parameters and data differences for optimization, in addition to the quantified parameters of historical experience, it also introduces the number m of data differences below the preset data difference threshold, and C for each data difference. i And the span value C corresponding to the currently adjusted but not optimized threshold range. pThis design incorporates the proximity of parameters reflected in real-time operational data to the threshold values ​​into the calculation, allowing real-time feedback to quantitatively influence the optimization results of the threshold range. This formula design fully utilizes valuable experience gained from historical optimization processes, ensuring the continuity and stability of threshold optimization, while also promptly incorporating the current system state reflected in real-time operational data. This enables dynamic adjustments to the threshold range based on actual conditions, achieving a close integration of historical and current real-world data, and significantly improving the accuracy and scientific rigor of threshold optimization.

[0034] The dual improvement in threshold accuracy and system adaptability is the culmination of the combined effects of the first two technologies, and is crucial for the efficient and stable operation of the dual-path liquid-cooled energy storage system. Improved threshold accuracy means the system can more accurately distinguish between normal fluctuations and abnormal changes in parameters. Through layered processing and scientific formula design, the optimized threshold range can more precisely define the range of parameter changes during normal system operation, effectively reducing false alarms and missed alarms caused by unreasonable threshold settings. For example, when system parameters fluctuate within the normal range, the optimized threshold will not easily classify it as a fault, avoiding unnecessary downtime for inspection and maintenance; while when parameters deviate significantly from normal parameters, the threshold can issue an alarm in a timely manner, ensuring that faults are detected and addressed promptly. Improved system adaptability allows the threshold range to better adapt to the characteristic changes of the dual-path liquid-cooled energy storage system under different operating stages and conditions. Whether it's equipment aging and performance degradation due to long-term system operation, or drastic changes in external environmental temperature and load, the optimized threshold range can be dynamically adjusted to match these changes, maintaining effective monitoring of the system status at all times. This combination of high precision and high adaptability not only improves the reliability of system status monitoring and provides a more accurate basis for fault diagnosis, but also reduces the system's operation and maintenance costs and improves the operating efficiency and safety of the entire dual-path liquid-cooled energy storage system.

[0035] After the early warning information is issued, the results of the early warning will be tracked and feedback will be provided. The specific steps are as follows: Record the sending time and receiving status of early warning information to ensure that maintenance personnel receive early warning information in a timely manner; Set a warning response time threshold; if the maintenance personnel do not respond within the specified time, a second warning message will be automatically sent. Provide feedback channels so that maintenance personnel can provide feedback on the processing results; Based on feedback from maintenance personnel, update the status and fault records of the dual-path liquid-cooled energy storage system; Based on the early warning results and feedback from maintenance personnel, the effectiveness of the early warning mechanism is evaluated regularly. If the early warning information is found to be inaccurate or the response is not timely, the fault diagnosis algorithm and early warning notification method are optimized. The fault diagnosis model and rule base are updated based on new fault cases.

[0036] The technical effects of the above solution are as follows: By recording the sending time and receiving status of early warning information, it ensures that maintenance personnel receive early warning information in a timely manner. Simultaneously, by setting an early warning response time threshold and automatically sending a second early warning message, it effectively guarantees timely response to faults by maintenance personnel, avoiding delays in fault handling due to information delays. Providing a feedback channel and updating system status and fault records based on feedback from maintenance personnel helps achieve closed-loop management of fault handling, ensuring the accuracy of system status and the completeness of fault handling. Regularly evaluating the effectiveness of the early warning mechanism and optimizing the fault diagnosis algorithm and early warning notification method based on the evaluation results, along with updating the fault diagnosis model and rule base with new fault cases, continuously improves the accuracy and reliability of the early warning system. This further enhances the fault handling efficiency and maintenance management level of the dual-path liquid-cooled energy storage system, strengthens system stability and security, and provides strong support for the long-term reliable operation of the system.

[0037] Detailed early warning information is generated based on the fault diagnosis results. At the same time, graded early warnings are issued for abnormal states of the dual-path liquid-cooled energy storage system. The specific steps are as follows: Based on the type of abnormal parameters, the degree to which they exceed the threshold, and the degree of impact on the operation of the dual-path liquid-cooled energy storage system, the abnormal state is divided into several levels, including minor abnormality, moderate abnormality, and severe abnormality. For different levels of abnormal status, corresponding early warning information content and notification methods should be formulated; Minor anomalies are communicated to maintenance personnel via internal system prompts or emails; moderate anomalies are communicated to maintenance personnel via SMS; and severe anomalies are communicated to maintenance personnel and relevant management personnel simultaneously via SMS or telephone. Different response time thresholds are set according to the severity of the abnormal state. For severe abnormal states, maintenance personnel are required to respond and handle the situation in a shorter time.

[0038] The technical effects of the above solution are as follows: Detailed early warning information is generated based on the fault diagnosis results, and a graded early warning mechanism for abnormal states of the dual-path liquid-cooled energy storage system is established. This mechanism can accurately distinguish the severity of different abnormalities, thereby formulating targeted early warning information content and notification methods. This can effectively improve the operation and maintenance response speed, ensure that the dual-path liquid-cooled energy storage system can be quickly handled when abnormalities occur, and minimize the impact of abnormalities on the operation of the dual-path liquid-cooled energy storage system.

[0039] Based on the results of condition assessment and fault diagnosis, the operating parameters of the dual-path liquid-cooled energy storage system are automatically adjusted. The specific steps are as follows: By integrating the status assessment report and fault diagnosis results, the current operating status and existing problems of the dual-channel liquid-cooled energy storage system are clarified, and key parameters that need to be optimized are identified for automatic adjustment of the operating parameters of the dual-channel liquid-cooled energy storage system. After optimization, the operating status of the dual-channel liquid-cooled energy storage system is monitored in real time to verify the optimization effect and compare the battery temperature, coolant flow and temperature, and battery charging and discharging efficiency before and after optimization. If the optimization results are not ideal, analyze the reasons and adjust the optimization strategy accordingly, specifically: If the optimization effect is not ideal, use deep learning algorithms to analyze the data during the optimization process and find the possible causes of the problem, including unreasonable selection of optimization algorithm, inaccurate allocation of parameter weights, and deviation between the model and actual operation. Based on the analysis results, the optimization strategy is dynamically adjusted, including changing the optimization algorithm, reallocating parameter weights, and modifying the model; Repeat the above optimization process until the optimization effect reaches the preset performance index; Meanwhile, a self-learning mechanism is introduced to automatically record the data and results of the optimization process after each optimization and adjustment. By continuously learning and accumulating experience, the operating parameters of the dual-path liquid-cooled energy storage system can be continuously optimized.

[0040] The technical effects of the above solution are as follows: The operating parameters of the dual-channel liquid-cooled energy storage system are automatically adjusted based on the results of condition assessment and fault diagnosis, enabling precise optimization of the system's operating status. By integrating condition assessment reports and fault diagnosis results, the current operating status and existing problems of the system are clearly identified, and key parameters requiring optimization are identified, allowing for targeted adjustment of operating parameters. After optimization, the system's operating status is monitored in real time, and the optimization effect is verified. Comparing key indicators before and after optimization ensures the effectiveness of the optimization measures. When the optimization effect is unsatisfactory, deep learning algorithms are used to analyze the data during the optimization process, uncover potential causes of problems, and dynamically adjust the optimization strategy until the optimization effect reaches the preset performance indicators. Simultaneously, a self-learning mechanism is introduced to automatically record data and results during the optimization process. Through continuous learning and experience accumulation, the operating parameters of the dual-channel liquid-cooled energy storage system are continuously optimized, thereby significantly improving the operating efficiency and stability of the dual-channel liquid-cooled energy storage system.

[0041] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0042] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention.

Claims

1. A method for monitoring the status of a dual-channel liquid-cooled energy storage system, characterized in that, Includes the following steps: By deploying multiple sensors, the system collects real-time status data of the dual-channel liquid-cooled energy storage system, including but not limited to the temperature, voltage, and current of the battery pack, as well as the flow rate, pressure, and temperature of the coolant. The long-term performance trend of the dual-channel liquid-cooled energy storage system is analyzed, and the collected state data is analyzed using a preset evaluation model to evaluate the battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system. Set threshold ranges for each parameter. When any parameter in the evaluation results exceeds its corresponding threshold range, it is determined that the dual-path liquid-cooled energy storage system is abnormal. If an anomaly is detected, the fault diagnosis algorithm is used to determine the specific location and cause of the fault, and an early warning message is issued, while also notifying the operation and maintenance personnel. Based on the results of condition assessment and fault diagnosis, the operating parameters of the dual-channel liquid-cooled energy storage system are automatically adjusted, including adjusting the flow rate and temperature of the coolant, and optimizing the charging and discharging strategy of the energy storage battery.

2. The status monitoring method for a dual-path liquid-cooled energy storage system according to claim 1, characterized in that, The specific steps for analyzing the long-term performance trend of a dual-channel liquid-cooled energy storage system are as follows: Establish a long-term performance trend database to store the results of each status assessment and fault diagnosis, as well as the corresponding operating parameters and environmental conditions; By using time series analysis algorithms to analyze long-term performance trend data, the performance change trend of the dual-channel liquid-cooled energy storage system can be predicted over a period of time, including battery life degradation trend and cooling system efficiency change trend. Based on the performance trend analysis results, develop preventative maintenance plans in advance, including battery replacement plans and cooling system maintenance plans.

3. The status monitoring method for a dual-path liquid-cooled energy storage system according to claim 1, characterized in that, The battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system are evaluated through the following steps: The collected status data is integrated into a unified data framework, ensuring timestamp alignment, and key features are extracted from the integrated status data, specifically: Battery health status characteristics: Extracting the average temperature, maximum temperature difference, voltage fluctuation range, and current fluctuation range of each battery cell from the status data; Cooling operation status characteristics: Extract the characteristics of the coolant system, such as average flow rate, maximum flow rate difference, average pressure, pressure fluctuation range, and temperature change rate, from the status data; An evaluation model is built based on machine learning algorithms. Historical data is used to train the evaluation model to ensure that the training data covers the battery status under different operating conditions. The hyperparameters of the evaluation model are optimized through cross-validation. The extracted battery health status features and cooling operation status features are input into the evaluation model, and the evaluation model outputs the evaluation results of the battery health status and cooling operation status of the dual-channel liquid-cooled energy storage system.

4. The status monitoring method for a dual-path liquid-cooled energy storage system according to claim 1, characterized in that, The specific steps for determining the exact location and cause of a fault using a fault diagnosis algorithm are as follows: Pre-set the threshold range for each parameter, and adjust the threshold range regularly based on seasonal changes and load conditions of the dual-path liquid-cooled energy storage system. At the same time, optimize the threshold settings by combining historical data and actual operating conditions. If the threshold setting of a certain parameter is found to be unreasonable, adjust it in time. The evaluation results are compared with preset thresholds. If any parameter in the evaluation results exceeds its corresponding threshold range, the data is marked as abnormal data, and the time of the abnormality, sensor number, abnormal parameter value and threshold range are recorded. Based on the topology and working principle of the dual-channel liquid-cooled energy storage system, and using a pre-trained fault diagnosis model to further analyze the abnormal data, the fault diagnosis model outputs the specific location and cause of the fault based on the characteristics of the input abnormal data. Detailed early warning information is generated based on the fault diagnosis results, including fault description, scope of impact and recommended measures. At the same time, the early warning information is sent to the operation and maintenance personnel via SMS notification or remote push.

5. The status monitoring method for a dual-path liquid-cooled energy storage system according to claim 4, characterized in that, Based on historical data and actual operational conditions, the threshold settings were optimized. The specific steps are as follows: Retrieve the values ​​of each parameter from historical data; Retrieve the peak and trough values ​​corresponding to each parameter from the historical data; Extract the timestamps corresponding to all peak and trough values ​​for each parameter; The threshold range corresponding to the peak and trough values ​​is determined based on the timestamps of all the peak and trough values ​​corresponding to the parameters, and is used as the target threshold range. Determine whether the target threshold range has undergone an optimization process; If the target threshold range has undergone an optimization process, then the optimized threshold range parameters are retrieved. The current threshold range is optimized using the optimized threshold range parameters and actual operating data.

6. The status monitoring method for a dual-path liquid-cooled energy storage system according to claim 5, characterized in that, The current threshold range is optimized using the optimized threshold range parameters and actual operating data. The specific steps are as follows: Retrieve the values ​​of each parameter in the current actual operating data and their corresponding currently adjusted but not optimized threshold ranges; The values ​​of each parameter in the current actual operating data are used to obtain the values ​​that are within the threshold range that have been adjusted but not optimized. Retrieve the data difference between the value in the currently adjusted but unoptimized threshold range and the threshold value of that range; When the number of data differences below the preset data difference threshold is less than the preset number threshold, the current threshold range is optimized using only the optimized threshold range parameter. When the number of data differences that are lower than the preset data difference threshold is not lower than the preset number threshold, the current threshold range is optimized using the threshold range parameter and all data differences.

7. The status monitoring method for a dual-path liquid-cooled energy storage system according to claim 4, characterized in that, After the early warning information is issued, the results of the early warning will be tracked and feedback will be provided. The specific steps are as follows: Record the sending time and receiving status of early warning information to ensure that maintenance personnel receive early warning information in a timely manner; Set a warning response time threshold; if the maintenance personnel do not respond within the specified time, a second warning message will be automatically sent. Provide feedback channels so that maintenance personnel can provide feedback on the processing results; Based on feedback from maintenance personnel, update the status and fault records of the dual-path liquid-cooled energy storage system; Based on the early warning results and feedback from maintenance personnel, the effectiveness of the early warning mechanism is evaluated regularly. If the early warning information is found to be inaccurate or the response is not timely, the fault diagnosis algorithm and early warning notification method are optimized. The fault diagnosis model and rule base are updated based on new fault cases.

8. The status monitoring method for a dual-path liquid-cooled energy storage system according to claim 4, characterized in that, Detailed early warning information is generated based on the fault diagnosis results. At the same time, graded early warnings are issued for abnormal states of the dual-path liquid-cooled energy storage system. The specific steps are as follows: Based on the type of abnormal parameters, the degree to which they exceed the threshold, and the degree of impact on the operation of the dual-path liquid-cooled energy storage system, the abnormal state is divided into several levels, including minor abnormality, moderate abnormality, and severe abnormality. For different levels of abnormal status, corresponding early warning information content and notification methods should be formulated; Minor anomalies are communicated to maintenance personnel via internal system prompts or emails; moderate anomalies are communicated to maintenance personnel via SMS; and severe anomalies are communicated to maintenance personnel and relevant management personnel simultaneously via SMS or telephone. Different response time thresholds are set according to the severity of the abnormal state. For severe abnormal states, maintenance personnel are required to respond and handle the situation in a shorter time.

9. The status monitoring method for a dual-path liquid-cooled energy storage system according to claim 1, characterized in that, Based on the results of condition assessment and fault diagnosis, the operating parameters of the dual-path liquid-cooled energy storage system are automatically adjusted. The specific steps are as follows: By integrating the status assessment report and fault diagnosis results, the current operating status and existing problems of the dual-channel liquid-cooled energy storage system are clarified, and key parameters that need to be optimized are identified for automatic adjustment of the operating parameters of the dual-channel liquid-cooled energy storage system. After optimization, the operating status of the dual-channel liquid-cooled energy storage system is monitored in real time to verify the optimization effect and compare the battery temperature, coolant flow and temperature, and battery charging and discharging efficiency before and after optimization. If the optimization results are not satisfactory, analyze the reasons and adjust the optimization strategy.

10. The status monitoring method for a dual-path liquid-cooled energy storage system according to claim 9, characterized in that, If the optimization results are not satisfactory, analyze the reasons and adjust the optimization strategy. The specific steps are as follows: If the optimization effect is not ideal, use deep learning algorithms to analyze the data during the optimization process and find the possible causes of the problem, including unreasonable selection of optimization algorithm, inaccurate allocation of parameter weights, and deviation between the model and actual operation. Based on the analysis results, the optimization strategy is dynamically adjusted, including changing the optimization algorithm, reallocating parameter weights, and modifying the model; Repeat the above optimization process until the optimization effect reaches the preset performance index; Meanwhile, a self-learning mechanism is introduced to automatically record the data and results of the optimization process after each optimization and adjustment. By continuously learning and accumulating experience, the operating parameters of the dual-path liquid-cooled energy storage system can be continuously optimized.

Images