A method for monitoring thermal power coupled battery data and optimizing safe operation

Abstract

A method for monitoring thermal power coupled battery data and optimizing safe operation provided by the present invention relates to the technical field of power monitoring optimization; it includes: establishing a combined dynamic simulation model by combining preprocessed historical operation data with real-time operation data, and simulating the coordinated operation characteristics of a thermal power unit and a battery pack under different load conditions through the combined dynamic simulation model; analyzing the coordinated operation characteristics of the thermal power unit and the battery pack based on the combined dynamic simulation model, determining power distribution, temperature control requirements and response time, and dynamically adjusting the output power of the thermal power unit and the charge and discharge power of the battery pack in combination with real-time load data. By integrating the real-time operation data and historical operation data of the thermal power unit and the battery pack, and using a dynamic simulation algorithm to construct a combined dynamic simulation model, the present invention realizes an accurate description of the coordinated operation characteristics of the thermal power unit and the battery pack under different load conditions, providing a basis for optimizing operation strategies.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy monitoring optimization, and specifically relates to a method for monitoring the data of a thermal power coupled battery and optimizing its safe operation. Background Art

[0002] With the growth of energy demand and the increasing penetration of renewable energy, the load fluctuation and energy efficiency management of the power system face severe challenges.

[0003] Currently, the coordinated operation technology of thermal power units and battery energy storage systems is still in the development stage, and there are mainly the following problems:

[0004] Firstly, the deficiencies in data fusion and simulation models. In the current coordinated operation system of thermal power units and battery energy storage, there is often a lack of effective means to integrate historical operation data and real-time operation data, making it difficult to establish an accurate dynamic simulation model, thus affecting the effectiveness of the coordinated operation strategy.

[0005] Secondly, the low efficiency of load fluctuation prediction and waste heat utilization. The existing prediction models have low prediction accuracy for power load fluctuations and waste heat demand, making it difficult to dynamically adjust the output power of thermal power units and the charge-discharge rate of battery packs.

[0006] Thirdly, the utilization rate of waste heat resources generated by thermal power units is relatively low, and an efficient heat energy recovery and dynamic regulation mechanism has not been formed. Summary of the Invention

[0007] The present invention provides a method for monitoring the data of a thermal power coupled battery and optimizing its safe operation, aiming to solve the technical problem of insufficient data fusion and simulation models in the related technology, and further avoid the subsequent problems of low load fluctuation prediction and waste heat utilization efficiency, and the practical problem of low utilization rate of waste heat resources generated by thermal power units.

[0008] To achieve the above object, the present invention provides a method for monitoring the data of a thermal power coupled battery and optimizing its safe operation, including the following steps:

[0009] Obtain the real-time operation data and historical operation data of the thermal power unit and the battery pack, and preprocess the historical operation data to obtain the preprocessed historical operation data.

[0010] Combine the preprocessed historical operation data with the real-time operation data to establish a joint dynamic simulation model, and simulate the coordinated operation characteristics of the thermal power unit and the battery pack under different load conditions through the joint dynamic simulation model.

[0011] Analyze the coordinated operation characteristics of the thermal power unit and the battery pack based on the joint dynamic simulation model, determine the power distribution, temperature control requirements and response time, and dynamically adjust the output power of the thermal power unit and the charge-discharge power of the battery pack in combination with the real-time load data.

[0012] Based on the combined dynamic simulation model, calculate the waste heat supply demand. By calculating and combining the operating temperature of the battery pack and the ambient temperature with real-time monitoring, dynamically adjust the waste heat supply; provide heating for the battery pack in low-temperature environments and drive the cooling device to cool the battery pack through a heat exchange device in high-temperature environments.

[0013] Based on the long-term analysis of the combined dynamic simulation model, combine with the machine learning model to predict future load fluctuations, waste heat utilization demands, and battery performance changes; optimize the operation strategy according to the prediction results, dynamically adjust the output power of the thermal power unit, the charge and discharge rate of the battery pack, and the temperature control parameters to achieve closed-loop control.

[0014] As a preferred solution of the present invention, obtain the real-time operation data and historical operation data of the thermal power unit and the battery pack, and preprocess the historical operation data to obtain the preprocessed historical operation data, which specifically includes:

[0015] The real-time operation data includes: the load output data and waste heat emission data of the thermal power unit, as well as the charge state data, temperature distribution data, and voltage balance data of the battery pack.

[0016] The historical operation data includes: the load output data and waste heat emission data of the thermal power unit in the historical operation stage, as well as the charge state data, temperature distribution data, and voltage balance data of the battery pack in the historical operation stage.

[0017] The preprocessing includes: data cleaning, feature extraction, data denoising, time series segmentation, and normalization processing.

[0018] As a preferred solution of the present invention, establish a combined dynamic simulation model by combining the preprocessed historical operation data with the real-time operation data. Simulate the coordinated operation characteristics of the thermal power unit and the battery pack under different load conditions through the combined dynamic simulation model. The specific steps are as follows:

[0019] Fuse the preprocessed historical operation data with the real-time operation data to generate a comprehensive data set. The comprehensive data set includes the load output data and waste heat emission data of the thermal power unit, as well as the charge state data, temperature distribution data, and voltage balance data of the battery pack. The comprehensive data set provides a data basis for subsequent analysis.

[0020] Based on the comprehensive data set, extract the key feature parameters of the historical operation data and the real-time operation data, perform feature matching according to the operation conditions, and generate a matched data set. The matched data set is used to ensure the temporal consistency and characteristic relevance of the data.

[0021] According to the matched data set, the operation data of the thermal power unit and the battery pack are divided into different working condition categories according to the load status and temperature control requirements, and the working condition categories are used to support the multi-scenario modeling of the combined dynamic simulation model.

[0022] Extract key parameters from the data set after working condition division to generate the input parameters of the combined dynamic simulation model. The input parameters include: power distribution parameters, waste heat utilization efficiency parameters, and temperature control response time.

[0023] Based on the operation characteristics and operation mechanisms of the thermal power unit and the battery pack, a combined dynamic simulation model is constructed using dynamic simulation algorithms. The combined dynamic simulation model is used to describe the coordinated operation characteristics of the thermal power unit and the battery pack under different loads and temperature control requirements.

[0024] Use the fused real-time operation data and historical operation data to verify the established combined dynamic simulation model. By comparing the model output with the actual data, verify the accuracy of the model; adjust the model parameters according to the verification results.

[0025] Based on the verified combined dynamic simulation model, simulate the coordinated operation status of the thermal power unit and the battery pack under different loads and temperature control conditions, and output the power distribution scheme, waste heat utilization strategy, and temperature control response time to provide a reference basis for subsequent optimization and dynamic adjustment.

[0026] As a preferred solution of the present invention, analyze the coordinated operation characteristics of the thermal power unit and the battery pack based on the combined dynamic simulation model, determine the power distribution, temperature control requirements, and response time, and dynamically adjust the output power of the thermal power unit and the charge and discharge power of the battery pack in combination with the real-time load data. The specific steps are as follows:

[0027] Based on the real-time operation data, combined with the analysis of the coordinated operation characteristics output by the combined dynamic simulation model, calculate the load value in real time and judge whether the current load status is low or high.

[0028] When the load value is in the low state, according to the analysis results of the combined dynamic simulation model, preferentially reduce the output power of the thermal power unit and use the excess electric energy for charging the battery pack.

[0029] When the load value is in the high state, support the peak load demand through the discharge of the battery pack, reduce the load pressure of the thermal power unit, and supplement the output power of the thermal power unit according to the demand.

[0030] According to the change trend of the real-time load data, combined with the response time and operation characteristics predicted by the combined dynamic simulation model, dynamically adjust the power distribution scheme of the thermal power unit and the battery pack to smooth the load fluctuation.

[0031] As a preferred solution of the present invention, based on real-time operation data, combined with the collaborative operation characteristic analysis output by the joint dynamic simulation model, the load value is calculated in real time, and the current load state is judged to be low valley or peak. The specific steps are as follows:

[0032] According to the real-time operation data, calculate the current load value. The calculation formula is:

[0033]

[0034] In the formula, represents the current load value, is the current power generation of the thermal power unit, is the current load demand.

[0035] According to the dynamic change of the real-time load value, judge the current load state. The judgment rule is specifically:

[0036]

[0037]

[0038] In the formula, and are the preset low valley and peak thresholds of the load value respectively.

[0039] As a preferred solution of the present invention, based on the joint dynamic simulation model, calculate the waste heat supply demand, and calculate and dynamically adjust the waste heat supply by combining the real-time monitored operating temperature and ambient temperature of the battery pack; provide heating for the battery pack in low temperature environment, and drive the cooling device to cool the battery pack through the heat exchange device in high temperature environment. The specific steps are as follows:

[0040] The calculation formula for the waste heat supply demand of the joint dynamic simulation model is:

[0041]

[0042] In the formula, represents the required heat, represents the mass of the battery pack, represents the specific heat capacity of the battery pack, represents the target temperature, represents the current temperature.

[0043] Obtain the real-time operating temperature and external ambient temperature data of the battery pack, and dynamically adjust the waste heat supply of the thermal power unit according to the predicted temperature control demand and real-time temperature data; give priority to using waste heat as the temperature control energy source of the battery pack to reduce the consumption of other energy sources.

[0044] In a low temperature environment, provide heat for the battery pack by adjusting the waste heat supply, and raise the operating temperature of the battery pack to the preset range.

[0045] In a high-temperature environment, a waste heat-driven heat exchange device is adopted to reduce the temperature of the battery pack through a cooling device.

[0046] As a preferred solution of the present invention, based on the long-term analysis of the combined dynamic simulation model, combined with the machine learning model to predict future load fluctuations, waste heat utilization requirements and battery performance changes; optimize the operation strategy according to the prediction results, and dynamically adjust the output power of the thermal power unit, the charge and discharge rate of the battery pack and the temperature control parameters to achieve closed-loop control. The specific steps are as follows:

[0047] Based on the combined dynamic simulation model, by fusing historical operation data and real-time operation data, analyze the operation characteristic data of the thermal power unit and the battery pack under different load conditions, including the operation efficiency, waste heat utilization rate and battery life of the thermal power unit and the battery pack under different load conditions.

[0048] Adopt machine learning algorithms, use the analyzed operation characteristic data as training samples to construct a prediction model; use the trained prediction model to predict future load fluctuations, waste heat demand trends and battery performance changes, and provide a reference basis for strategy optimization.

[0049] Based on the prediction model, analyze the future load fluctuation trend, judge the occurrence time and duration of peak load and valley load, and provide data reference for power distribution adjustment.

[0050] According to the future load fluctuation prediction results, combined with the battery temperature control requirements, calculate the time distribution and demand of waste heat supply, and plan the waste heat utilization strategy in advance.

[0051] Analyze the charge and discharge cycle characteristics and service life trend of the battery pack, predict the future decay rate and remaining capacity of the battery performance, and provide support for the adjustment of the charge and discharge strategy.

[0052] Dynamically adjust the operation strategies of the thermal power unit and the battery pack according to the results of the prediction model.

[0053] As a preferred solution of the present invention, dynamically adjust the operation strategies of the thermal power unit and the battery pack according to the results of the prediction model, specifically including:

[0054] According to the predicted future load fluctuation trend, reduce the output power of the thermal power unit during valley load; increase the output power during peak load, and dynamically adjust the response time to meet the rapid change demand of the load.

[0055] Charge the battery pack preferentially during valley load to reserve energy; support the load demand by discharging the battery pack during peak load, and dynamically adjust the discharge rate to extend the service life of the battery pack; the charge and discharge power calculation formula of the battery pack is:

[0056]

[0057] In the formula, represents the charge and discharge power of the battery pack, represents the available energy storage capacity, represents the load duration.

[0058] Combined with the temperature control requirements of the battery pack, dynamically optimize the waste heat supply strategy, and verify the dynamically optimized waste heat supply strategy by calculating the comprehensive efficiency. The calculation formula is:

[0059]

[0060] In the formula, represents the comprehensive efficiency, represents the effective power output, represents the total input power.

[0061] As a preferred solution of the present invention, after dynamically adjusting the operation strategies of the thermal power unit and the battery pack according to the results of the prediction model, it further includes:

[0062] After dynamically adjusting the operation strategy, verify the dynamically adjusted operation strategy through the combined dynamic simulation model, and evaluate the impact of the adjustment strategy on power distribution, waste heat utilization efficiency, and battery pack life by combining real-time operation data and prediction data.

[0063] According to the feedback results of the simulation model, calculate the load response times of the thermal power unit and the battery pack, and optimize the load distribution strategy. The optimization formula is:

[0064]

[0065] In the formula, represents the response time of the thermal power unit, the response time of the battery pack.

[0066] Combined with the feedback of the waste heat utilization effect from the simulation model, optimize the operation parameters of the heat exchange equipment.

[0067] According to the long-term data of the battery pack operation status, introduce a health state evaluation model, dynamically adjust the charge and discharge strategy of the battery pack, and extend the service life of the battery pack. The health state evaluation formula is expressed as:

[0068]

[0069] In the formula, represents the health state of the battery pack, represents the cumulative discharge amount of the battery, represents the total discharge capacity of the battery.

[0070] A closed-loop control is formed during the verification and optimization process. By continuously adjusting the strategy through the real-time feedback of the combined dynamic simulation model, the stable operation of the thermal power unit and the battery pack under various load conditions is achieved, and the model input parameters are dynamically updated to enhance the prediction accuracy of the simulation model.

[0071] The beneficial effects of the present invention are as follows:

[0072] 1. By integrating the real-time operation data and historical operation data of the thermal power unit and the battery pack, a combined dynamic simulation model is constructed using a dynamic simulation algorithm, achieving an accurate description of the collaborative operation characteristics of the thermal power unit and the battery pack under different load conditions, and providing a basis for optimizing the operation strategy.

[0073] 2. Using machine learning algorithms to predict future load fluctuations, waste heat demands, and battery performance changes, providing accurate load distribution and waste heat utilization strategies, and improving the response efficiency of the thermal power unit and the waste heat utilization rate.

[0074] 3. Dynamically adjusting the charge and discharge rate of the battery pack, optimizing the charge and discharge cycle characteristics, slowing down the battery performance degradation rate, extending the battery life, and enhancing the economy of long-term operation.

[0075] 4. Through the combined dynamic simulation model and real-time feedback, a closed-loop control mechanism is formed to optimize the operation strategies of the thermal power unit and the battery pack in real time, achieving stable operation under various load conditions, and dynamically updating the model input parameters to improve the accuracy of prediction and optimization effects.

[0076] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments of the present invention. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0078] Figure 1 It is a flowchart of a method for monitoring thermal power coupled battery data and optimizing safe operation provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0079] The following will describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention.

[0080] Please refer to Figure 1 , Figure 1 which is the flowchart provided by an embodiment of the present invention.

[0081] In this embodiment, a method for monitoring thermal power coupled battery data and optimizing safe operation includes step S100, step S200, step S300, step S400, and step S500.

[0082] Step S100: Obtain the real-time operation data and historical operation data of the thermal power unit and the battery pack, and preprocess the historical operation data to obtain the preprocessed historical operation data. Specifically, it includes:

[0083] The real-time operation data includes: the load output data of the thermal power unit, the waste heat emission data, as well as the charging state data, temperature distribution data, and voltage balance data of the battery pack.

[0084] It should be noted that through the operation monitoring devices of the thermal power unit and the battery pack, the following parameters are obtained:

[0085] The load output data of the thermal power unit: It is collected in real time by a power generation sensor, and the data unit is MW.

[0086] The waste heat emission data: The real-time waste heat emission power is obtained through a heat flow sensor, and the data unit is kW.

[0087] The charging state data of the battery pack: The real-time charging current and voltage are collected through a battery management system, and the SOC is calculated.

[0088] The temperature distribution data of the battery pack: The temperature distribution of each unit in the battery pack is obtained through a battery module temperature sensor, and the data unit is degrees Celsius;

[0089] The voltage balance data of the battery pack: The voltage difference of each single battery is obtained through a voltage acquisition module, and the data unit is V.

[0090] The historical operation data includes: the load output data of the thermal power unit and the waste heat emission data in the historical operation stage, as well as the charging state data, temperature distribution data, and voltage balance data of the battery pack in the historical operation stage.

[0091] It should be noted that the specific way to obtain the historical operation data is as follows:

[0092] The historical load output data of the thermal power unit is based on the time series data extracted from the power generation record log.

[0093] The waste heat emission data is obtained through the historical waste heat power record.

[0094] The historical charging state data, temperature distribution data, and voltage balance data of the battery pack are obtained through the log data of the battery management system.

[0095] The preprocessing includes: data cleaning, feature extraction, data denoising, time series segmentation, and normalization processing.

[0096] It should be noted that data cleaning is to remove incorrect data through missing value processing and outlier detection, and fill in the missing values using linear interpolation.

[0097] Feature extraction is to extract key feature parameters from the data. The key feature parameters include the load change rate of the thermal power unit, the temperature gradient of the battery pack, and the voltage fluctuation range.

[0098] Data denoising is to use the moving average algorithm to denoise the real-time data and historical data, and remove the interference signals.

[0099] Time series segmentation is to classify and segment the historical data according to the load status, waste heat output, and battery operating conditions for subsequent analysis.

[0100] Data normalization processes data with different dimensions in a unified standardized manner to ensure the comparability between different characteristic parameters.

[0101] Step S200: Establish a combined dynamic simulation model by combining the preprocessed historical operation data with the real-time operation data, and simulate the collaborative operation characteristics of the thermal power unit and the battery pack under different load conditions through the combined dynamic simulation model. The specific steps are as follows:

[0102] Fuse the preprocessed historical operation data with the real-time operation data to generate a comprehensive data set. The comprehensive data set includes the load output data of the thermal power unit, the waste heat emission data, as well as the charge state data, temperature distribution data, and voltage balance data of the battery pack. The comprehensive data set provides a data basis for subsequent analysis.

[0103] Based on the comprehensive data set, extract the key feature parameters of the historical operation data and the real-time operation data, perform feature matching according to the operation conditions, and generate a matched data set. The matched data set is used to ensure the temporal consistency and characteristic relevance of the data.

[0104] It should be noted that the operation conditions refer to the key working condition parameters that affect the collaborative operation characteristics of the thermal power unit and the battery pack, including the following:

[0105] Load status: The real-time load output level of the thermal power unit and the charge and discharge status of the battery pack.

[0106] Temperature control requirement: The difference between the operating temperature of the battery pack and the ambient temperature, corresponding to the waste heat heating requirement or cooling requirement of the battery pack.

[0107] Waste heat availability: The real-time waste heat emission of the thermal power unit, which affects the battery temperature control and energy distribution strategy.

[0108] Furthermore, it should be noted that feature matching is achieved through the following steps to generate the matched dataset:

[0109] A1. Feature extraction: Extract the following feature parameters from the comprehensive dataset:

[0110] The real-time load output data and waste heat emission data of the thermal power unit.

[0111] The SOC, temperature distribution data, and voltage balance data of the battery pack.

[0112] A2. Operating condition screening: According to the definition of operating conditions, which includes load status, temperature control requirements, and waste heat availability, filter out the data segments that meet the conditions.

[0113] A3. Time series alignment: Match the timestamps of historical data and real-time data to ensure the temporal consistency of the two.

[0114] A4. Feature correlation check: Verify the physical correlation of the data. For example, the matching degree between the waste heat emission and the battery temperature control requirements; finally, generate the matched dataset for subsequent input.

[0115] According to the matched dataset, divide the operating data of the thermal power unit and the battery pack into different operating condition categories according to the load status and temperature control requirements. The operating condition categories are used to support the multi-scenario modeling of the combined dynamic simulation model.

[0116] It should be noted that the operating condition categories are obtained based on the operating states of the thermal power unit and the battery pack, including the following types:

[0117] Low load condition: The output power of the thermal power unit is low and the battery pack is in the charging state.

[0118] High load condition: The output power of the thermal power unit is high and the battery pack is in the discharging state.

[0119] Insufficient waste heat condition: The waste heat emission of the thermal power unit cannot meet the battery temperature control requirements.

[0120] Excessive waste heat condition: The waste heat emission of the thermal power unit far exceeds the battery temperature control requirements.

[0121] Heating condition: The battery pack needs to use waste heat for heating.

[0122] Cooling condition: The battery pack needs to be cooled through a heat exchange device.

[0123] According to the matched dataset, divide the data into the above categories, specifically:

[0124] For the real-time load data, conduct operating condition division according to the load value judgment result in S300.

[0125] Compare the relationship between the waste heat emission and the battery temperature control requirements to divide the waste heat state.

[0126] Determine the heating or cooling condition according to the difference between the real-time temperature of the battery pack and the target temperature.

[0127] Extract key parameters from the dataset after condition division to generate the input parameters of the combined dynamic simulation model. The input parameters include: power distribution parameters, waste heat utilization efficiency parameters, and temperature control response time.

[0128] It should be noted that the key parameters include: the power distribution ratio between the thermal power unit and the battery pack; the efficiency of converting waste heat into battery temperature control energy; the time required for the battery pack to adjust from the current temperature to the target temperature.

[0129] Based on the operating characteristics and mechanisms of the thermal power unit and the battery pack, a combined dynamic simulation model is constructed using a dynamic simulation algorithm. The combined dynamic simulation model is used to describe the collaborative operating characteristics of the thermal power unit and the battery pack under different loads and temperature control requirements.

[0130] It should be noted that a dynamic simulation algorithm based on state-space modeling is selected to describe the dynamic behavior of the simulation object through state variables, including the power distribution, temperature control response, and waste heat utilization of the thermal power unit and the battery pack.

[0131] First, define the variables of the combined dynamic simulation model, and the specific definitions are as follows:

[0132] State variables, including: Represents the output power of the thermal power unit, Represents the charging and discharging power of the battery pack, Represents the waste heat supply power, Represents the operating temperature of the battery pack.

[0133] Input variables, including: real-time operating data and condition classification results.

[0134] Output variables, including: power distribution ratio, temperature control response time, and operating efficiency.

[0135] Use the fused real-time operating data and historical operating data to verify the established combined dynamic simulation model. By comparing the output of the combined dynamic simulation model with the actual data, verify the accuracy of the combined dynamic simulation model; adjust the parameters of the combined dynamic simulation model according to the verification results.

[0136] The combined dynamic simulation model describes the collaborative changes of the thermal power unit and the battery pack in the time series based on difference equations, and its mathematical representation formula is:

[0137]

[0138]

[0139]

[0140] In the formula,

[0141] respectively represent the dynamic change rates of the output power of the thermal power unit, the power of the battery pack, and the temperature of the battery pack;

[0142] respectively represent the non-linear functions of the power distribution of the thermal power unit, the power adjustment of the battery pack, and the temperature control dynamic response.

[0143] Subsequently, combining historical data with real-time data, initialize the parameters of the joint dynamic simulation model; initialize the rated power ranges of the thermal power unit and the battery pack; initialize the temperature control target interval; initialize the initial value of the waste heat utilization efficiency; the initialization processing basis is obtained by statistically analyzing the key parameters using the matched data set.

[0144] After initialization, use numerical methods to solve the equations of the joint dynamic simulation model, and use the Runge-Kutta method to perform iterative calculations on the non-linear equations of the joint dynamic simulation model to simulate the coordinated changes in the power output and temperature control response of the thermal power unit and the battery pack.

[0145] It should be further noted that the simulation steps of the joint dynamic simulation model are as follows:

[0146] B1. At each time step, input the real-time operating data and the predicted operating conditions parameters.

[0147] B2. Calculate the state variables of the next time step according to the equations of the joint dynamic simulation model.

[0148] B3. Output the current power distribution plan, waste heat utilization strategy, and battery pack temperature control data.

[0149] Based on the verified joint dynamic simulation model, simulate the coordinated operating states of the thermal power unit and the battery pack under different loads and temperature control conditions, and output the power distribution plan, waste heat utilization strategy, and temperature control response time, providing a reference basis for subsequent optimization and dynamic adjustment.

[0150] It should be noted that the verification is to compare the simulation output with the actual operating data, and the comparison conditions are: the power distribution ratio error between the thermal power unit and the battery pack is less than 5%; the battery temperature control response time error is less than 10%.

[0151] It should be further noted that the joint dynamic simulation model adjusts its structure and parameters according to the verification results, including: improving the prediction accuracy of the temperature control response time; enhancing the fitting degree of the waste heat utilization efficiency; optimizing the dynamic adjustment ability of the power distribution plan.

[0152] Step S300: Analyze the coordinated operation characteristics of the thermal power unit and the battery pack based on the joint dynamic simulation model, determine the power distribution, temperature control requirements, and response time, and dynamically adjust the output power of the thermal power unit and the charge-discharge power of the battery pack in combination with the real-time load data. The specific steps are as follows:

[0153] Based on the real-time operation data, combined with the analysis of the coordinated operation characteristics output by the joint dynamic simulation model, calculate the load value in real time and determine whether the current load state is low or high.

[0154] It should be noted that according to the real-time operation data, calculate the current load value, and the calculation formula is:

[0155]

[0156] In the formula, represents the current load value, is the current power generation of the thermal power unit, is the current load demand;

[0157] According to the dynamic change of the real-time load value, judge the current load state, and the judgment rule is specifically:

[0158]

[0159]

[0160] In the formula, and are the preset low and high load value thresholds respectively.

[0161] In the low load value state, according to the analysis result of the joint dynamic simulation model, preferentially reduce the output power of the thermal power unit and use the excess electric energy for charging the battery pack.

[0162] It should be noted that according to the analysis result of the joint dynamic simulation model, determine the current reducible power of the thermal power unit ; and calculate the charge power acceptable to the battery pack , so that it satisfies the following constraints:

[0163]

[0164] In the formula,

[0165] represents the maximum charge power of the battery pack,

[0166] represents the current charge power of the battery pack.

[0167] Adjust the power output of the thermal power unit to At the same time, trigger the battery pack to charge.

[0168] When the load value is at its peak, the battery pack discharges to support the peak load demand, reducing the load pressure on the thermal power units. At the same time, the output power of the thermal power units is supplemented according to the demand.

[0169] It should be noted that according to the power distribution plan predicted by the combined dynamic simulation model, the discharge power of the battery pack is determined :

[0170]

[0171] In the formula, represents the currently available discharge capacity of the battery pack.

[0172] Supplement the output power of the thermal power unit to meet the remaining load demand.

[0173] According to the change trend of real-time load data, combined with the response time and operating characteristics predicted by the combined dynamic simulation model, the power distribution plan between the thermal power unit and the battery pack is dynamically adjusted to smooth the load fluctuation.

[0174] It should be noted that the short-term load change trend is predicted, the load status classification standard is adjusted, and dynamic allocation is achieved:

[0175]

[0176] In the formula, represents the power distribution ratio of the thermal power unit, represents the power distribution ratio of the battery pack, is the current load demand, represents the adjusted output power, represents the adjusted battery discharge power.

[0177] Step S400: Calculate the waste heat supply demand based on the combined dynamic simulation model. By calculating and combining the operating temperature of the battery pack and the ambient temperature monitored in real time, the waste heat supply is dynamically adjusted; heating is provided for the battery pack in a low-temperature environment, and in a high-temperature environment, a cooling device is driven by a heat exchange device to cool the battery pack. The specific steps are as follows:

[0178] The calculation formula for the waste heat supply demand of the combined dynamic simulation model is:

[0179]

[0180] ]>In the formula, represents the required heat, represents the mass of the battery pack, represents the specific heat capacity of the battery pack, represents the target temperature, represents the current temperature.

[0181] Obtain the real-time operating temperature of the battery pack and the ambient temperature data. According to the predicted temperature control requirements and the real-time temperature data, dynamically adjust the supply of waste heat from the thermal power unit; prioritize using waste heat as the temperature control energy for the battery pack to reduce the consumption of other energy sources.

[0182] In a low-temperature environment, provide heat for the battery pack by adjusting the waste heat supply, and raise the operating temperature of the battery pack to the preset range.

[0183] It should be noted that in a low-temperature environment, the waste heat supply is preferentially allocated to the battery pack, and the temperature is quickly raised by adjusting the supply path and flow rate to ensure the stable operation of the battery pack.

[0184] Furthermore, it should be noted that the preset range is 15°C to 40°C.

[0185] In a high-temperature environment, use waste heat to drive a heat exchange device, and reduce the temperature of the battery pack through a cooling device.

[0186] It should be noted that in a high-temperature environment, use waste heat to drive a cooling device to reduce the temperature of the battery pack, and optimize the cooling path and power distribution in combination with the real-time cooling efficiency data.

[0187] It should be noted that the combined dynamic simulation model calculates the waste heat demand based on the real-time temperature of the battery pack and the ambient temperature, dynamically adjusts the supply power ratio, prioritizes meeting the temperature control target, and ensures the efficient use of waste heat.

[0188] Step S500: Based on the long-term analysis of the combined dynamic simulation model, combine the machine learning model to predict future load fluctuations, waste heat utilization requirements, and battery performance changes; optimize the operation strategy according to the prediction results, dynamically adjust the output power of the thermal power unit, the charge and discharge rate of the battery pack, and the temperature control parameters to achieve closed-loop control. The specific steps are as follows:

[0189] Based on the combined dynamic simulation model, by integrating historical operation data and real-time operation data, analyze the operation characteristic data of the thermal power unit and the battery pack under different load conditions, including the operation efficiency, waste heat utilization rate, and battery life of the thermal power unit and the battery pack under different load conditions.

[0190] Adopt machine learning algorithms, use the analyzed operation characteristic data as training samples to build a prediction model; use the trained prediction model to predict future load fluctuations, waste heat demand trends, and battery performance changes to provide a reference basis for strategy optimization.

[0191] Based on the prediction model, analyze the future load fluctuation trend, judge the occurrence time and duration of peak load and valley load, and provide data reference for power distribution adjustment.

[0192] According to the predicted results of future load fluctuations and combined with the battery temperature control requirements, calculate the time distribution and demand of waste heat supply, and plan the waste heat utilization strategy in advance.

[0193] Analyze the charge and discharge cycle characteristics and service life trend of the battery pack, predict the future decay rate of battery performance and remaining capacity, and provide support for the adjustment of charge and discharge strategies.

[0194] It should be noted that an LSTM is selected to construct a prediction model to process the time series characteristics of the operating characteristic data of thermal power units and battery packs, and predict the future waste heat demand and battery performance changes through support vector regression; after preprocessing the historical operating data, the data with characteristics in the historical operating data are used as training samples to train the prediction model.

[0195] Furthermore, it should be noted that based on the output of the prediction model, analyze the future load fluctuation trend, including the occurrence time and duration of peak load and valley load, and provide reference data for power distribution adjustment; and according to the predicted battery temperature control requirements, calculate the time distribution and demand of waste heat supply, and plan the waste heat utilization strategy in advance.

[0196] Furthermore, it should be noted that use the prediction model to estimate the charge and discharge cycle characteristics of the battery pack, analyze the battery life trend, calculate the battery performance decay rate and remaining capacity; according to the battery performance prediction results, dynamically adjust the charge and discharge strategy to ensure the maximization of battery life.

[0197] Furthermore, it should be noted that combine the predicted waste heat demand and temperature control demand results, dynamically adjust the supply priority of waste heat from thermal power units, and plan the operation time and efficiency distribution of heat exchange equipment.

[0198] Dynamically adjust the operating strategies of thermal power units and battery packs according to the results of the prediction model.

[0199] It should be noted that according to the predicted future load fluctuation trend, reduce the output power of thermal power units during valley load; increase the output power during peak load, and dynamically adjust the response time to meet the rapid change demand of the load.

[0200] Charge the battery pack preferentially during valley load to reserve energy; support the load demand through the discharge of the battery pack during peak load, and dynamically adjust the discharge rate to extend the service life of the battery pack; the charge and discharge power calculation formula of the battery pack is:

[0201]

[0202] In the formula, represents the charge and discharge power of the battery pack, represents the available energy storage capacity, represents the load duration.

[0203] Combined with the temperature control requirements of the battery pack, dynamically optimize the waste heat supply strategy, and verify the dynamically optimized waste heat supply strategy by calculating the comprehensive efficiency. The calculation formula is as follows:

[0204]

[0205] In the formula, represents the comprehensive efficiency, represents the effective power output, represents the total input power.

[0206] Further, it should be noted that after the execution of step S500, it also includes:

[0207] After dynamically adjusting the operation strategy, verify the dynamically adjusted operation strategy through the combined dynamic simulation model, and evaluate the impact of the adjustment strategy on power distribution, waste heat utilization efficiency, and battery pack life by combining real-time operation data and prediction data.

[0208] According to the feedback results of the combined dynamic simulation model, calculate the load response time of the thermal power unit and the battery pack, and optimize the load distribution strategy. The optimization formula is:

[0209]

[0210] In the formula, represents the response time of the thermal power unit, the response time of the battery pack.

[0211] Combined with the feedback of the waste heat utilization effect of the combined dynamic simulation model, optimize the operation parameters of the heat exchange equipment.

[0212] According to the long-term data of the battery pack operation status, introduce a health state evaluation model, dynamically adjust the charge and discharge strategy of the battery pack, and extend the service life of the battery pack. The health state evaluation formula is expressed as:

[0213]

[0214] In the formula, represents the health state of the battery pack, represents the cumulative discharge amount of the battery, represents the total discharge capacity of the battery.

[0215] During the verification and optimization process, form a closed-loop control, continuously adjust the strategy through the real-time feedback of the combined dynamic simulation model, realize the stable operation of the thermal power unit and the battery pack under various load conditions, and dynamically update the input parameters of the combined dynamic simulation model to enhance the prediction accuracy.

[0216] Thus, a method for monitoring the data of the thermal power coupled battery and optimizing the safe operation is completed.

[0217] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the embodiments of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the embodiments of the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the embodiments of the present invention. Therefore, the protection scope of the embodiments of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for monitoring thermal power coupled battery data and optimizing safe operation, characterized in that, Including the following steps: Obtain the real-time operation data and historical operation data of the thermal power unit and the battery pack, preprocess the historical operation data, and obtain the preprocessed historical operation data; Establish a joint dynamic simulation model by combining the preprocessed historical operation data with the real-time operation data, and simulate the coordinated operation characteristics of the thermal power unit and the battery pack under different load conditions through the joint dynamic simulation model; Analyze the coordinated operation characteristics of the thermal power unit and the battery pack based on the joint dynamic simulation model, determine the power distribution, temperature control requirements and response time, and dynamically adjust the output power of the thermal power unit and the charge and discharge power of the battery pack in combination with the real-time load data. The specific steps are as follows: Based on the real-time operation data, combined with the analysis of the coordinated operation characteristics output by the joint dynamic simulation model, calculate the load value in real time, and judge whether the current load state is low or high, specifically including: Calculate the current load value according to the real-time operation data, and the calculation formula is: ， In the formula, represents the current load value, is the current power generation of the thermal power unit, is the current load demand; Judge the current load state according to the dynamic change of the real-time load value, and the judgment rule is specifically: ， ， In the formula, and are respectively the preset low and high threshold values of the load value; In the low-load state of the load value, according to the analysis results of the joint dynamic simulation model, preferentially reduce the output power of the thermal power unit, and use the excess electric energy for charging the battery pack; In the high-load state of the load value, support the high-load demand through the discharge of the battery pack, reduce the load pressure of the thermal power unit, and supplement the output power of the thermal power unit according to the demand; According to the change trend of the real-time load data, combined with the response time and operation characteristics predicted by the joint dynamic simulation model, dynamically adjust the power distribution scheme of the thermal power unit and the battery pack to smooth the load fluctuation; Calculate the waste heat supply demand based on the joint dynamic simulation model, and dynamically adjust the waste heat supply by calculating and combining the operating temperature of the battery pack and the ambient temperature monitored in real time; provide heating for the battery pack in a low-temperature environment, and drive the cooling device to cool the battery pack through the heat exchange device in a high-temperature environment; Based on the long-term analysis of the joint dynamic simulation model, combined with the machine learning model, predict the future load fluctuation, waste heat utilization demand and battery performance change; optimize the operation strategy according to the prediction results, and dynamically adjust the output power of the thermal power unit, the charge and discharge rate of the battery pack and the temperature control parameters to achieve closed-loop control; After dynamically adjusting the operation strategy, verify the dynamically adjusted operation strategy through the joint dynamic simulation model, and evaluate the impact of the adjustment strategy on power distribution, waste heat utilization efficiency and battery pack life in combination with the real-time operation data and prediction data; According to the feedback results of the simulation model, calculate the load response time of the thermal power unit and the battery pack, and optimize the load distribution strategy. The optimization formula is: ， In the formula, represents the response time of the thermal power unit, represents the response time of the battery pack; Optimize the operation parameters of the heat exchange device in combination with the feedback of the waste heat utilization effect of the simulation model; According to the long-term data of the operation state of the battery pack, introduce a health state evaluation model, dynamically adjust the charge and discharge strategy of the battery pack, and extend the service life of the battery pack. The health state evaluation formula is expressed as: ， Wherein, represents the state of health of the battery pack, represents the cumulative discharge amount of the battery, represents the total discharge capacity of the battery; Form a closed-loop control during the verification and optimization process, continuously adjust the strategy through the real-time feedback of the joint dynamic simulation model, realize the stable operation of the thermal power unit and the battery pack under various load conditions, and dynamically update the model input parameters to enhance the prediction accuracy of the simulation model.

2. The data monitoring and safety operation optimization method of a thermal power coupled battery according to claim 1, characterized in that Obtain the real-time operation data and historical operation data of the thermal power unit and the battery pack, preprocess the historical operation data to obtain the preprocessed historical operation data, specifically including: The real-time operation data includes: the load output data and waste heat emission data of the thermal power unit, as well as the charge state data, temperature distribution data, and voltage equalization data of the battery pack; The historical operation data includes: the load output data and waste heat emission data of the thermal power unit in the historical operation stage, as well as the charge state data, temperature distribution data, and voltage equalization data of the battery pack in the historical operation stage; The preprocessing includes: data cleaning, feature extraction, data denoising, time series segmentation, and normalization processing.

3. A method for monitoring thermal power coupled battery data and optimizing safe operation according to claim 1, characterized in that, Establish a joint dynamic simulation model by combining the preprocessed historical operation data with the real-time operation data, and simulate the coordinated operation characteristics of the thermal power unit and the battery pack under different load conditions through the joint dynamic simulation model. The specific steps are as follows: Fuse the preprocessed historical operation data with the real-time operation data to generate a comprehensive data set. The comprehensive data set includes the load output data and waste heat emission data of the thermal power unit, as well as the charge state data, temperature distribution data, and voltage equalization data of the battery pack. The comprehensive data set provides a data basis for subsequent analysis; Based on the comprehensive data set, extract the key feature parameters of the historical operation data and the real-time operation data, perform feature matching according to the operation conditions, and generate a matched data set. The matched data set is used to ensure the time series consistency and characteristic relevance of the data; According to the matched data set, divide the operation data of the thermal power unit and the battery pack into different working condition categories according to the load state and temperature control requirements. The working condition categories are used to provide support for the multi-scenario modeling of the joint dynamic simulation model; Extract the key parameters from the data set after working condition division to generate the input parameters of the joint dynamic simulation model. The input parameters include: power distribution parameters, waste heat utilization efficiency parameters, and temperature control response time; Based on the operation characteristics and operation mechanism of the thermal power unit and the battery pack, adopt a dynamic simulation algorithm to construct a joint dynamic simulation model. The joint dynamic simulation model is used to describe the coordinated operation characteristics of the thermal power unit and the battery pack under different loads and temperature control requirements; Use the fused real-time operation data and historical operation data to verify the established joint dynamic simulation model. Verify the accuracy of the model by comparing the model output with the actual data; adjust the model parameters according to the verification results; Based on the verified joint dynamic simulation model, simulate the coordinated operation states of the thermal power unit and the battery pack under different loads and temperature control conditions, and output the power distribution scheme, waste heat utilization strategy, and temperature control response time, providing a reference basis for subsequent optimization and dynamic adjustment.

4. A method for monitoring thermal power coupled battery data and optimizing safe operation according to claim 1, characterized in that, Calculate the waste heat supply demand based on the joint dynamic simulation model, and dynamically adjust the waste heat supply by calculating and combining the operating temperature of the battery pack and the ambient temperature monitored in real time; provide heating for the battery pack in a low-temperature environment, and drive the cooling device to cool the battery pack through a heat exchange device in a high-temperature environment. The specific steps are as follows: The calculation formula for the waste heat supply demand of the joint dynamic simulation model is: ， In the formula, represents the required heat, represents the mass of the battery pack, represents the specific heat capacity of the battery pack, represents the target temperature, represents the current temperature; Obtain the real-time operating temperature and ambient temperature data of the battery pack, and dynamically adjust the supply of waste heat from the thermal power unit according to the predicted temperature control requirements and real-time temperature data; prioritize using waste heat as the temperature control energy source for the battery pack to reduce the consumption of other energy sources; In a low-temperature environment, provide heat for the battery pack by adjusting the waste heat supply to raise the operating temperature of the battery pack to the preset range; In a high-temperature environment, use waste heat to drive the heat exchange equipment and reduce the temperature of the battery pack through the cooling device.

5. The method for monitoring thermal power coupled battery data and optimizing safe operation according to claim 1, characterized in that Based on the long-term analysis of the combined dynamic simulation model, combined with the machine learning model to predict future load fluctuations, waste heat utilization requirements, and battery performance changes; optimize the operating strategy according to the prediction results, dynamically adjust the output power of the thermal power unit, the charge and discharge rate of the battery pack, and the temperature control parameters to achieve closed-loop control. The specific steps are as follows: Based on the combined dynamic simulation model, by integrating historical operating data and real-time operating data, analyze the operating characteristic data of the thermal power unit and the battery pack under different load conditions, including the operating efficiency, waste heat utilization rate, and battery life of the thermal power unit and the battery pack under different load conditions; Adopt machine learning algorithms, use the analyzed operating characteristic data as training samples to construct a prediction model; use the trained prediction model to predict future load fluctuations, waste heat demand trends, and battery performance changes to provide a reference basis for strategy optimization; Based on the prediction model, analyze the future load fluctuation trend, judge the occurrence time and duration of peak load and valley load, and provide data reference for power distribution adjustment; According to the future load fluctuation prediction results, combined with the battery temperature control requirements, calculate the time distribution and demand of waste heat supply, and plan the waste heat utilization strategy in advance; Analyze the charge and discharge cycle characteristics and service life trend of the battery pack, predict the future decay rate and remaining capacity of the battery performance, and provide support for the adjustment of the charge and discharge strategy; Dynamically adjust the operating strategies of the thermal power unit and the battery pack according to the results of the prediction model.

6. The method for monitoring thermal power coupled battery data and optimizing safe operation according to claim 5, wherein The dynamically adjusting the operating strategies of the thermal power unit and the battery pack according to the results of the prediction model specifically includes: According to the predicted future load fluctuation trend, reduce the output power of the thermal power unit during valley load; increase the output power during peak load, and dynamically adjust the response time to respond to the rapid change demand of the load; Give priority to charging the battery pack during valley load to reserve energy; support the load demand through the discharge of the battery pack during peak load, and dynamically adjust the discharge rate to extend the service life of the battery pack; the calculation formula for the charge and discharge power of the battery pack is: ， In the formula, represents the charge and discharge power of the battery pack, represents the available energy storage capacity, represents the load duration; Combined with the battery pack temperature control requirements, dynamically optimize the waste heat supply strategy, and verify the dynamically optimized waste heat supply strategy by calculating the comprehensive efficiency. The calculation formula is: ， In the formula, represents the comprehensive efficiency, represents the effective power output, represents the total input power.

Images