Solar energy and stored energy combined power supply method and system suitable for mobile square cabin

Abstract

The invention provides a solar energy and energy storage combined power supply method and system suitable for a mobile square cabin. The method comprises the steps of collecting power demand data in a shelter, performing prediction processing on a future solar power generation amount and a load demand change trend, and generating an energy demand prediction report in a period of time in the future; generating an optimized energy distribution strategy based on the energy demand prediction report; when it is detected that the solar power generation amount is not enough to meet the instant load requirement, according to the optimized energy distribution strategy, a fuzzy logic control system is started to dynamically adjust the charging and discharging strategy of the energy storage battery, and an energy storage battery health condition report is generated; and obtaining an optimized energy management scheme based on the energy storage battery health condition report and the system operation data. According to the technical scheme provided by the invention, the future power demand and the solar power generation amount can be accurately predicted, and the system of the energy distribution strategy is dynamically adjusted, so that efficient operation under various conditions can be ensured.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of solar energy and energy storage combined power supply, and in particular, to a solar energy and energy storage combined power supply method and system suitable for a mobile cabin. Background Art

[0002] With the widespread use of renewable energy, especially the popularity of solar power generation systems, the demand for efficient and stable energy management systems for mobile or fixed facilities such as shelters is increasing. These facilities are usually located in remote areas or in harsh environmental conditions, and need to ensure the continuity and reliability of power supply under different weather and temperature conditions.

[0003] Currently, most energy management systems rely mainly on static energy allocation strategies and simple threshold controls. These systems usually manage the charging and discharging process of solar power generation and energy storage batteries through pre-set rules. For example, when solar power generation falls below a certain threshold, the system switches to energy storage batteries for power supply. In addition, some systems also combine basic weather forecast data to predict future electricity demand and solar power generation, but these predictions are often not accurate enough and lack dynamic adjustment capabilities.

[0004] Most existing energy management systems rely on simple weather forecasts and historical data for predictions, which cannot accurately reflect actual electricity demand and changes in solar power generation, resulting in unreasonable energy allocation and affecting the overall efficiency of the system; existing systems usually adopt fixed energy allocation strategies and cannot be dynamically adjusted according to real-time electricity demand and changes in solar power generation, resulting in unstable power supply and even power outages in some cases; existing systems rarely monitor the health status of energy storage batteries in real time, and cannot promptly detect and solve potential battery problems, affecting the battery life and system reliability. Summary of the invention

[0005] The embodiments of the present application provide a solar energy and energy storage combined power supply method and system suitable for a mobile cabin, which is used to solve the problem that the prior art cannot promptly discover and solve potential battery problems, affecting the battery life and system reliability.

[0006] In a first aspect, an embodiment of the present application provides a solar energy and energy storage combined power supply method applicable to a mobile cabin, comprising:

[0007] Collect the electricity demand data inside the shelter, combine it with weather forecast information, predict the future trend of solar power generation and load demand changes, and generate an energy demand forecast report for a period of time in the future;

[0008] Based on the energy demand forecast report, the energy allocation plan is optimized using a genetic algorithm, and the efficient operation of the system under extreme temperatures is ensured through thermodynamic analysis to generate an optimized energy allocation strategy;

[0009] When it is detected that the solar power generation is insufficient to meet the immediate load demand, the fuzzy logic control system is started to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy allocation strategy, and the health status of the energy storage battery is monitored by electrochemical impedance spectroscopy technology to generate a health status report of the energy storage battery;

[0010] Based on the energy storage battery health status report and system operation data, the system's energy consumption pattern and optimization opportunities are identified and processed, and the energy management strategy is continuously adjusted and improved using big data analysis technology to obtain an optimized energy management solution.

[0011] Optionally, based on the energy demand forecast report, the energy allocation scheme is optimized by using a genetic algorithm, and efficient operation of the system under extreme temperatures is ensured by thermodynamic analysis to generate an optimized energy allocation strategy, including:

[0012] Using the energy demand forecast report, matching the future electricity demand and solar power generation is performed to obtain an initial energy allocation model;

[0013] Based on the initial energy distribution model, a genetic algorithm is used to perform optimization processing to obtain an optimized energy distribution model;

[0014] According to the optimized energy distribution model, combined with the thermodynamic analysis method, the system operation efficiency under different temperature conditions is evaluated and processed to obtain the temperature adaptability analysis results;

[0015] Based on the temperature adaptability analysis results, the optimized energy allocation model is adjusted to ensure that the system can operate efficiently even at extreme temperatures, thereby generating an optimized energy allocation strategy.

[0016] Optionally, the optimization process based on the initial energy distribution model is performed using a genetic algorithm to obtain an optimized energy distribution model, including:

[0017] Before calculating the fitness function F(x), it is necessary to first match the future electricity demand and solar power generation to generate an initial energy allocation model. In this process, it is necessary to combine the energy demand forecast report and conduct a detailed analysis of the electricity demand and solar power generation in different time periods to ensure that the initial parameters of the model can reflect the actual demand.

[0018] Fitness function:

[0019]

[0020] Among them, x is the parameter vector of the energy allocation model, including the matching ratio of solar power generation and load demand in each time period, and the charging and discharging strategy of the energy storage battery; P 需求 is the future electricity demand, obtained from the energy demand forecast report; P 太阳能 is the future solar power generation, obtained from the energy demand forecast report; T i is the i-th temperature point, which is used to evaluate the operating efficiency of the system under different temperature conditions; E 损失 (T i ) is at temperature T i Energy loss under 总 is the total energy; C is the system operation cost; α is the weight coefficient of matching degree; β is the weight coefficient of system efficiency; γ is the weight coefficient of cost; η is the weight coefficient of additional cost; EP 损失 (T i ) is at temperature T i Additional energy loss under

[0021] After calculating the fitness function F(x), the generated initial energy allocation model needs to be optimized. In this step, the selection, crossover and mutation operations in the genetic algorithm are used. The crossover operation is used to combine the parameter vectors of two parent individuals to generate a new individual.

[0022] Crossover operation:

[0023]

[0024] x 新 is the parameter vector of the new individual generated by the crossover operation; θ is the crossover probability, which ranges from [0,1] and indicates the proportion of the characteristics inherited by the new individual from the parent individual; δ is the crossover coefficient of variation, which is used to introduce nonlinear variation and enhance the search capability; ζ is the Gaussian coefficient of variation, which is used to introduce random variation of Gaussian distribution and enhance the search diversity; σ is the standard deviation of Gaussian distribution, which controls the amplitude of Gaussian variation; x 1 is the energy allocation model parameter vector of the first parent individual; x 2 is the parameter vector of the energy allocation model of the second parent individual;

[0025] After calculating the new individual parameter vector x 新 Finally, the generated model is further verified and optimized, and the performance of the generated model is evaluated through simulation and actual operation data to obtain the optimized energy distribution model.

[0026] Optionally, the optimized energy allocation model is combined with a thermodynamic analysis method to evaluate the system operation efficiency under different temperature conditions to obtain a temperature adaptability analysis result, including:

[0027] According to the optimized energy distribution model, the working state of the system under different temperature conditions is simulated to obtain simulated operation data;

[0028] Combined with thermodynamic analysis methods, the simulation operation data is analyzed, the data of the system under different temperature conditions is evaluated, and a thermodynamic analysis report is obtained;

[0029] Based on the thermodynamic analysis report, identify the operation bottlenecks and potential problems of the system under extreme temperatures, and obtain temperature adaptability evaluation indicators;

[0030] The temperature adaptability evaluation index is used to comprehensively evaluate the system operation efficiency under different temperature conditions to generate temperature adaptability analysis results.

[0031] Optionally, based on the temperature adaptability analysis result, adjusting the optimized energy allocation model to ensure that the system can operate efficiently even at extreme temperatures, and generating an optimized energy allocation strategy, includes:

[0032] Based on the temperature adaptability analysis results, identify the operation bottlenecks and inefficient links of the system under extreme temperature conditions, and obtain a bottleneck analysis report;

[0033] According to the bottleneck analysis report, key parameters in the optimized energy allocation model are adjusted to obtain an energy allocation model;

[0034] Using the energy distribution model and combining it with actual operation data, simulation verification is performed to evaluate the operation effect of the adjusted model under extreme temperatures and generate a simulation verification report;

[0035] Based on the simulation verification report, the adjusted energy allocation model is further optimized to generate an optimized energy allocation strategy.

[0036] Optionally, when it is detected that the solar power generation is insufficient to meet the immediate load demand, the fuzzy logic control system is started to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy allocation strategy, and the health status of the energy storage battery is monitored by electrochemical impedance spectroscopy technology to generate a health status report of the energy storage battery, including:

[0037] When it is detected that the solar power generation is insufficient to meet the immediate load demand, the start-up condition of the fuzzy logic control system is triggered and a start-up signal is generated;

[0038] According to the start signal and the optimized energy allocation strategy, the fuzzy logic control system is started, and the charge and discharge rate of the energy storage battery is dynamically adjusted in combination with the PID control algorithm to generate a charge and discharge adjustment instruction;

[0039] Using the charge and discharge adjustment instructions, the health status of the energy storage battery is monitored in real time through electrochemical impedance spectroscopy technology, and the monitoring data is smoothed in combination with the Kalman filter algorithm to generate energy storage battery health monitoring data;

[0040] Based on the energy storage battery health monitoring data, a data analysis algorithm is used to identify the health status and potential faults of the energy storage battery, and generate an energy storage battery health status report.

[0041] Optionally, the use of the charge and discharge adjustment instructions to monitor the health status of the energy storage battery in real time through electrochemical impedance spectroscopy technology, and smoothing the monitoring data in combination with a Kalman filter algorithm to generate energy storage battery health monitoring data, including:

[0042] Before calculating the electrochemical impedance spectrum Z(f), it is necessary to conduct impedance testing and collect impedance data at different frequencies. At the same time, the data must be preprocessed to remove noise and outliers to ensure the accuracy and reliability of the data.

[0043] Electrochemical Impedance Spectroscopy:

[0044]

[0045] Where Z(f) is the impedance value at frequency f in electrochemical impedance spectroscopy; R 0 is the ohmic resistance; C 0 is the constant phase element capacitance; R k is the resistance corresponding to the kth time constant; C k is the capacitance corresponding to the kth time constant; M is the number of time constants; ω is the angular frequency, ω = 2πf; η is the additional impedance coefficient, used to introduce nonlinear correction; θ is the impedance correction coefficient, used to introduce nonlinear correction; j is the imaginary unit

[0046] After calculating Z(f), the impedance data is smoothed using the Kalman filter algorithm to reduce noise interference, improve data accuracy and real-time performance, and provide a basis for subsequent health monitoring.

[0047] Kalman filter smoothing:

[0048]

[0049] in, is the state estimate at time t; is the prior state estimate at time t; K t is the Kalman gain; y t is the measured value at time t; H is the observation matrix; is the state estimate at time t-1; u t is the control input at time t; A is the state transfer matrix; B is the control input matrix; Pt∣t-1 is the prior error covariance matrix at time t; R is the measurement noise covariance matrix; P t is the posterior error covariance matrix at time t; I is the identity matrix; λ is the nonlinear correction coefficient; σ y is the standard deviation of the measured value; μ is the control input correction factor; σ u is the standard deviation of the control input; φ is the measurement value correction coefficient; ψ is the control input nonlinear correction coefficient; v is the Kalman gain correction coefficient; ρ is the Kalman gain nonlinear correction coefficient; ξ is the error covariance correction coefficient; τ is the error covariance nonlinear correction coefficient; y represents the measured value of a certain state or parameter of the energy storage battery at a certain time t;

[0050] After the Kalman filter smoothing process is completed, feature extraction and pattern recognition are performed on the generated data to generate a detailed energy storage battery health status report.

[0051] Optionally, starting the fuzzy logic control system according to the start signal and the optimized energy allocation strategy, combining the PID control algorithm, dynamically adjusting the charge and discharge rate of the energy storage battery, and generating the charge and discharge adjustment instruction, includes:

[0052] Utilizing the start signal, activating the operating state of the fuzzy logic control system, receiving and processing the energy allocation strategy, and generating a control system activation signal;

[0053] Based on the optimized energy allocation strategy, the charging and discharging target values ​​of the energy storage battery are determined and used as inputs of the fuzzy logic control system to generate the charging and discharging target values;

[0054] Using the control system activation signal and the charge and discharge target value, combined with the real-time operation data of the system, the charge and discharge rate of the energy storage battery is dynamically adjusted through the fuzzy logic control system to generate preliminary charge and discharge adjustment instructions;

[0055] The preliminary charge and discharge adjustment instructions are compared with the actual charge and discharge rates, the error is calculated through the PID control algorithm, the control parameters are adjusted, and the final charge and discharge adjustment instructions are generated.

[0056] Optionally, based on the energy storage battery health status report and system operation data, the energy consumption mode and optimization opportunity points of the system are identified and processed, and the energy management strategy is continuously adjusted and improved by using big data analysis technology to obtain an optimized energy management solution, including:

[0057] Based on the energy storage battery health status report, extract key health parameters of the energy storage battery and generate a health parameter data set;

[0058] Analyze the energy consumption pattern of the system in combination with the system operation data, and generate an energy consumption pattern analysis report;

[0059] Using big data analysis technology, deeply mine the health parameter data set and the energy consumption pattern analysis report, identify energy consumption anomalies and optimization opportunities in the system, and generate an optimization opportunity report;

[0060] Based on the optimization opportunity point report, formulate specific optimization measures and generate optimization measure plans;

[0061] The optimization measures are applied to the system, the system operation status is continuously monitored, the effects of the optimization measures are evaluated, the energy management strategy is adjusted and improved, and an optimized energy management plan is generated.

[0062] In a second aspect, an embodiment of the present application provides a solar energy and energy storage combined power supply system suitable for a mobile cabin, comprising:

[0063] The collection module is used to collect the power demand data inside the shelter, and combine it with weather forecast information to predict the future trend of solar power generation and load demand changes, and generate an energy demand forecast report for a period of time in the future;

[0064] An allocation module is used to optimize the energy allocation plan based on the energy demand forecast report using a genetic algorithm, ensure the efficient operation of the system under extreme temperatures through thermodynamic analysis, and generate an optimized energy allocation strategy;

[0065] A monitoring module is used to start the fuzzy logic control system to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy allocation strategy when it is detected that the solar power generation is insufficient to meet the immediate load demand, monitor the health status of the energy storage battery through electrochemical impedance spectroscopy technology, and generate a health status report of the energy storage battery;

[0066] The adjustment module is used to identify and process the system's energy consumption pattern and optimization opportunities based on the energy storage battery health status report and system operation data, and to continuously adjust and improve the energy management strategy using big data analysis technology to obtain an optimized energy management solution.

[0067] In the embodiment of the present application, the power demand data inside the cabin is collected, and combined with the weather forecast information, the future solar power generation and load demand change trends are predicted and processed, and an energy demand forecast report for a period of time in the future is generated; based on the energy demand forecast report, a genetic algorithm is used to optimize the energy distribution plan, and the efficient operation of the system under extreme temperatures is ensured through thermodynamic analysis, and an optimized energy distribution strategy is generated; when it is detected that the solar power generation is insufficient to meet the immediate load demand, according to the optimized energy distribution strategy, the fuzzy logic control system is started to dynamically adjust the charging and discharging strategy of the energy storage battery, and the health status of the energy storage battery is monitored by electrochemical impedance spectroscopy technology, and an energy storage battery health status report is generated; based on the energy storage battery health status report and system operation data, the system's energy consumption mode and optimization opportunity points are identified and processed, and the energy management strategy is continuously adjusted and improved by big data analysis technology to obtain an optimized energy management plan.

[0068] The technical solution of this application has the following beneficial effects:

[0069] By collecting the power demand data inside the cabin and combining it with weather forecast information, the future solar power generation and load demand change trends are predicted and processed, and an energy demand forecast report for a period of time in the future is generated; this helps to plan and optimize energy distribution in advance, reduce energy waste, and improve the overall energy efficiency of the system; based on the energy demand forecast report, a genetic algorithm is used to optimize the energy distribution plan, and through thermodynamic analysis, the efficient operation of the system under extreme temperatures is ensured to generate an optimized energy distribution strategy; this not only improves the energy utilization rate of the system, but also enhances the adaptability and robustness of the system, so that it can maintain efficient operation under various environmental conditions; when it is detected that the solar power generation is insufficient to meet the immediate load demand, the fuzzy logic control system is started to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy distribution strategy. This enables the system to respond flexibly in a real-time changing environment and ensure the stability and reliability of power supply. At the same time, the health status of the energy storage battery is monitored by electrochemical impedance spectroscopy technology, and a health status report of the energy storage battery is generated, which helps to timely discover and solve potential battery problems and extend battery life. Based on the health status report of the energy storage battery and the system operation data, the energy consumption mode and optimization opportunity points of the system are identified and processed, and the energy management strategy is continuously adjusted and improved by big data analysis technology to obtain an optimized energy management solution. This not only improves the operating efficiency of the system, but also reduces operating costs and achieves the optimal configuration and utilization of resources. Through the above series of optimization measures, the system can better cope with various uncertainties and emergencies and ensure stable operation under different working conditions. This not only improves the reliability and safety of the system, but also enhances user satisfaction and trust. Through accurate energy demand prediction and optimized energy allocation schemes, the system can more effectively utilize renewable energy, reduce dependence on fossil fuels, reduce carbon emissions, and achieve the goal of green environmental protection. Using big data analysis technology, the system can provide rich data support to help managers make more scientific and reasonable decisions and improve the overall management level and operational efficiency.

[0070] Furthermore, based on the energy demand forecast report, the energy allocation scheme is optimized using a genetic algorithm, and the system is ensured to operate efficiently under extreme temperatures through thermodynamic analysis to generate an optimized energy allocation strategy. The specific steps include: using the energy demand forecast report to match future electricity demand and solar power generation to obtain an initial energy allocation model; based on the initial energy allocation model, the genetic algorithm is used for optimization to obtain an optimized energy allocation model; based on the optimized energy allocation model, the system operating efficiency under different temperature conditions is evaluated in combination with thermodynamic analysis methods to obtain temperature adaptability analysis results; based on the temperature adaptability analysis results, the optimized energy allocation model is adjusted to ensure that the system can operate efficiently under extreme temperatures and generate an optimized energy allocation strategy. Accurate energy demand matching: By using the energy demand forecast report to match the future electricity demand and solar power generation, the initial energy allocation model is generated, which improves the prediction accuracy and energy efficiency of the system; the genetic algorithm is used to optimize the initial energy allocation model to generate an optimized energy allocation model, which improves the energy utilization efficiency and operation stability of the system; combined with the thermodynamic analysis method, the system operation efficiency under different temperature conditions is evaluated to ensure that the system can still operate efficiently under extreme temperatures, thereby enhancing the environmental adaptability and reliability of the system; based on the temperature adaptability analysis results, the optimized energy allocation model is adjusted to generate the final optimized energy allocation strategy to ensure that the system can maintain optimal performance under various environmental conditions; through the above optimization measures, the system can better cope with various uncertainties and emergencies, ensure stable operation under different working conditions, and improve the reliability and safety of the system; the optimized energy allocation strategy effectively utilizes renewable energy, reduces dependence on fossil fuels, reduces carbon emissions, and achieves the goal of green environmental protection; using big data analysis technology, the system can provide rich data support to help managers make more scientific and reasonable decisions and improve the overall management level and operational efficiency.

[0071] Furthermore, when it is detected that the solar power generation is insufficient to meet the immediate load demand, the fuzzy logic control system is started according to the optimized energy allocation strategy to dynamically adjust the charging and discharging strategy of the energy storage battery, and the health status of the energy storage battery is monitored through the electrochemical impedance spectroscopy technology to generate a health status report of the energy storage battery. The specific steps include: when it is detected that the solar power generation is insufficient, the starting condition of the fuzzy logic control system is triggered to generate a starting signal; according to the starting signal and the optimized energy allocation strategy, the fuzzy logic control system is started, and the charging and discharging rate of the energy storage battery is dynamically adjusted in combination with the PID control algorithm to generate a charging and discharging adjustment instruction; using the charging and discharging adjustment instruction, the health status of the energy storage battery is monitored in real time through the electrochemical impedance spectroscopy technology, and the monitoring data is smoothed in combination with the Kalman filter algorithm to generate energy storage battery health monitoring data; based on the energy storage battery health monitoring data, a data analysis algorithm is used to identify the health status and potential faults of the energy storage battery, and a health status report of the energy storage battery is generated; through the fuzzy logic control system and the PID control algorithm, the system can respond to changes in solar power generation in real time, dynamically adjust the charging and discharging strategy of the energy storage battery, and ensure the stability and reliability of the power supply; Electrochemical impedance spectroscopy technology and Kalman filtering algorithm are used to monitor the health status of energy storage batteries in real time, generate smoothed monitoring data, and improve the accuracy and reliability of the data; based on the health monitoring data of energy storage batteries, data analysis algorithms are used to identify the health status and potential faults of energy storage batteries, and generate energy storage battery health status reports, which help to timely discover and solve battery problems and extend battery life; through the above optimization measures, the system can better cope with various uncertainties and emergencies, ensure stable operation under different working conditions, and improve the reliability and safety of the system; dynamically adjust the charging and discharging strategies of energy storage batteries, combined with health monitoring data, to achieve optimal management and utilization of energy and improve the overall energy efficiency of the system; using big data analysis technology, the system can provide rich data support to help managers make more scientific and reasonable decisions and improve the overall management level and operational efficiency.

[0072] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0074] Figure 1 A flow chart of a solar energy and energy storage combined power supply method applicable to a mobile cabin provided in an embodiment of the present application;

[0075] Figure 2 A schematic diagram of the structure of a solar energy and energy storage combined power supply system suitable for a mobile cabin provided in an embodiment of the present application;

[0076] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0077] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0078] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0079] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0080] Figure 1 A flowchart of a solar energy and energy storage combined power supply method applicable to a mobile cabin is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0081] 101. Collect the power demand data inside the shelter, combine it with weather forecast information, predict the future trend of solar power generation and load demand changes, and generate an energy demand forecast report for a period of time in the future;

[0082] In this step, the power demand data includes the historical power consumption, power consumption time, power consumption pattern and other data of each power-consuming equipment in the cabin, which is used to understand and predict future power demand.

[0083] Weather forecast information includes future meteorological data such as solar radiation intensity, sunshine hours, and temperature, which are used to predict future solar power generation.

[0084] The energy demand forecast report integrates electricity demand data and weather forecast information to generate a forecast report on electricity demand and solar power generation in the future, which is used to guide the formulation of energy allocation strategies.

[0085] In the embodiment of the present application, the power demand data inside the cabin is collected through sensors and a monitoring system, including the historical power consumption and power consumption time of each electrical equipment; the weather station or weather forecast website obtains weather forecast information for the next few days, including solar radiation intensity, sunshine time and temperature, etc.; the collected power demand data and weather forecast information are cleaned and preprocessed to remove noise and outliers to ensure the accuracy and reliability of the data; time series analysis, machine learning and other methods are used to establish a prediction model for power demand and solar power generation; based on the prediction model, an energy demand forecast report for a period of time in the future is generated, and the report contains the changing trends of future power demand and solar power generation.

[0086] Assume that there are multiple electrical devices in the cabin, including air conditioning, lighting, communication equipment, etc. The electricity consumption data for the past month is collected through the smart meters installed on each device. At the same time, the weather forecast information for the next week is obtained from the local weather station. The Autoregressive Integrated Moving Average Model (ARIMA) and the random forest algorithm are used to combine historical electricity consumption data and weather forecast information to predict the electricity demand and solar power generation for the next week. The generated forecast report lists in detail the daily electricity demand and solar power generation, as well as the possible supply and demand gap.

[0087] 102. Based on the energy demand forecast report, use a genetic algorithm to optimize the energy allocation plan, ensure the efficient operation of the system under extreme temperatures through thermodynamic analysis, and generate an optimized energy allocation strategy;

[0088] In this step, a genetic algorithm, an optimization algorithm that simulates natural selection and genetic mechanisms, is used to find the optimal energy allocation solution.

[0089] Thermodynamic analysis uses the principles of thermodynamics to analyze the operating efficiency of a system under different temperature conditions to ensure that the system can still operate efficiently under extreme temperatures.

[0090] The optimized energy allocation strategy is generated based on genetic algorithm and thermodynamic analysis, and can operate efficiently under different environmental conditions.

[0091] In an embodiment of the present application, an initial energy allocation model is generated based on an energy demand forecast report, including the matching ratio of solar power generation and load demand in each time period, the charging and discharging strategy of the energy storage battery, etc.; a genetic algorithm is used to optimize the initial energy allocation model through selection, crossover and mutation operations to generate multiple candidate solutions; a thermodynamic analysis is performed on each candidate solution to evaluate the operating efficiency of the system under different temperature conditions to ensure efficient operation even at extreme temperatures; based on the results of the thermodynamic analysis, the optimal energy allocation solution is selected to generate an optimized energy allocation strategy.

[0092] Optionally, in step 102, based on the energy demand forecast report, a genetic algorithm is used to optimize the energy allocation scheme, and efficient operation of the system under extreme temperatures is ensured through thermodynamic analysis to generate an optimized energy allocation strategy, including:

[0093] The energy demand forecast report is used to match future electricity demand and solar power generation to obtain an initial energy allocation model; based on the initial energy allocation model, a genetic algorithm is used to perform optimization processing to obtain an optimized energy allocation model; based on the optimized energy allocation model, combined with a thermodynamic analysis method, the system operation efficiency under different temperature conditions is evaluated and processed to obtain a temperature adaptability analysis result; based on the temperature adaptability analysis result, the optimized energy allocation model is adjusted to ensure that the system can operate efficiently even at extreme temperatures, thereby generating an optimized energy allocation strategy.

[0094] Wherein, based on the temperature adaptability analysis result, the optimized energy allocation model is adjusted to ensure that the system can operate efficiently even at extreme temperatures, and an optimized energy allocation strategy is generated, including:

[0095] Based on the temperature adaptability analysis results, the operating bottlenecks and inefficient links of the system under extreme temperature conditions are identified to obtain a bottleneck analysis report; according to the bottleneck analysis report, the key parameters in the optimized energy distribution model are adjusted to obtain an energy distribution model; using the energy distribution model, combined with actual operating data, simulation verification is performed to evaluate the operating effect of the adjusted model under extreme temperatures, and a simulation verification report is generated; based on the simulation verification report, the adjusted energy distribution model is further optimized to generate an optimized energy distribution strategy.

[0096] Wherein, the system operation efficiency under different temperature conditions is evaluated and processed according to the optimized energy distribution model in combination with the thermodynamic analysis method to obtain the temperature adaptability analysis results, including:

[0097] According to the optimized energy distribution model, the working state of the system under different temperature conditions is simulated to obtain simulated operation data; in combination with the thermodynamic analysis method, the simulated operation data is analyzed, the data of the system under different temperature conditions is evaluated, and a thermodynamic analysis report is obtained; based on the thermodynamic analysis report, the operating bottlenecks and potential problems of the system under extreme temperatures are identified to obtain temperature adaptability evaluation indicators; using the temperature adaptability evaluation indicators, the system operating efficiency under different temperature conditions is comprehensively evaluated to generate temperature adaptability analysis results.

[0098] Assume that there is a shelter equipped with a solar power generation system and energy storage batteries. It is necessary to generate an efficient energy distribution strategy based on future power demand and solar power generation to ensure that the system can operate stably under various environmental conditions, especially extreme temperatures. The specific steps are as follows:

[0099] According to the energy demand forecast report, collect the power demand data and solar power generation data for the next week. For example, suppose the power demand on a certain day is 100kWh and the solar power generation is 80kWh; based on these data, generate an initial energy allocation model, which includes the matching ratio of solar power generation and load demand in each time period, the charging and discharging strategy of the energy storage battery, etc. For example, the initial model is set to charge 20kWh during the day and discharge 20kWh at night; generate 100 initial energy allocation models as a population, each model is a possible solution;

[0100] According to the fitness function, select the 30 models with the highest fitness to enter the next generation; combine the parameter vectors of the two parent models to generate a new child model. For example, assuming that the two parent models are 1x1 and 2x2, a new model newxnew is generated through crossover operation; perform random mutations on some child models to introduce new mutation features to enhance the diversity and robustness of the search;

[0101] According to the optimized energy allocation model, simulate the working state of the system under different temperature conditions (such as 40℃ and -10℃) to obtain simulated operation data. For example, simulate the charging and discharging efficiency of the system at 40℃, battery temperature change and other data;

[0102] Combined with thermodynamic analysis methods, the simulated operation data is analyzed to evaluate the system performance under different temperature conditions and generate a thermodynamic analysis report. For example, the charging and discharging efficiency of the energy storage battery at 40°C decreases by 10%, and the charging and discharging efficiency at -10°C increases by 5%. Based on the thermodynamic analysis report, the operating bottlenecks and potential problems of the system at extreme temperatures are identified, and the temperature adaptability evaluation index is obtained. For example, it is found that the charging and discharging efficiency of the energy storage battery decreases at high temperatures, which may lead to a decrease in the overall efficiency of the system.

[0103] Using the temperature adaptability evaluation index, the system operating efficiency under different temperature conditions is comprehensively evaluated to generate temperature adaptability analysis results. For example, the evaluation results show that the system efficiency is 85% at 40°C and 90% at -10°C; the final generated temperature adaptability analysis results include comprehensive performance evaluation and improvement suggestions for the system at different temperatures. For example, it is recommended to appropriately reduce the charging rate of the energy storage battery under high temperature conditions to avoid overheating, and appropriately increase the charging rate under low temperature conditions to maintain the activity of the battery.

[0104] Through the above steps, the temperature adaptability analysis results were successfully generated to ensure that the system can operate efficiently under various environmental conditions, especially under extreme temperatures.

[0105] This application considers that in an energy management system, optimizing the energy allocation model is the key to ensure the efficient operation of the system. Genetic algorithm is an optimization algorithm that simulates natural selection and genetic mechanisms and is widely used in complex optimization problems. By optimizing the energy allocation model through genetic algorithm, the system can be ensured to operate efficiently under different environmental conditions, especially extreme temperatures.

[0106] Optionally, the optimization process based on the initial energy distribution model is performed using a genetic algorithm to obtain an optimized energy distribution model, including:

[0107] Before calculating the fitness function F(x), it is necessary to first match the future electricity demand and solar power generation to generate an initial energy allocation model. In this process, it is necessary to combine the energy demand forecast report and conduct a detailed analysis of the electricity demand and solar power generation in different time periods to ensure that the initial parameters of the model can reflect the actual demand.

[0108] Fitness function:

[0109]

[0110] Among them, x is the parameter vector of the energy allocation model, including the matching ratio of solar power generation and load demand in each time period, and the charging and discharging strategy of the energy storage battery; P 需求 is the future electricity demand, obtained from the energy demand forecast report; P 太阳能 is the future solar power generation, obtained from the energy demand forecast report; T i is the i-th temperature point, which is used to evaluate the operating efficiency of the system under different temperature conditions; E 损失 (T i ) is at temperature T i Energy loss under 总is the total energy; C is the system operation cost; α is the weight coefficient of matching degree; β is the weight coefficient of system efficiency; γ is the weight coefficient of cost; η is the weight coefficient of additional cost; EP 损失 (T i ) is at temperature T i Additional energy loss under

[0111] After calculating the fitness function F(x), the generated initial energy allocation model needs to be optimized. In this step, the selection, crossover and mutation operations in the genetic algorithm are used. The crossover operation is used to combine the parameter vectors of two parent individuals to generate a new individual.

[0112] Crossover operation:

[0113]

[0114] x 新 is the parameter vector of the new individual generated by the crossover operation; θ is the crossover probability, which ranges from [0,1] and indicates the proportion of the characteristics inherited by the new individual from the parent individual; δ is the crossover coefficient of variation, which is used to introduce nonlinear variation and enhance the search capability; ζ is the Gaussian coefficient of variation, which is used to introduce random variation of Gaussian distribution and enhance the search diversity; σ is the standard deviation of Gaussian distribution, which controls the amplitude of Gaussian variation; x 1 is the energy allocation model parameter vector of the first parent individual; x 2 is the parameter vector of the energy allocation model of the second parent individual;

[0115] After calculating the new individual parameter vector x 新 Finally, the generated model needs to be further verified and optimized. In this step, the performance of the new model is evaluated through simulation and actual operation data to ensure its effectiveness and stability in practical applications, and to obtain an optimized energy distribution model.

[0116] The formula aims to consider the matching degree, system efficiency and operating cost of the energy allocation model at the same time. Therefore, when designing the fitness function, it is necessary to balance these factors; the operating efficiency of the system is different under different temperature conditions, so it is necessary to consider the impact of temperature on energy loss; the selection, crossover and mutation operations in the genetic algorithm can enhance the diversity and robustness of the search and ensure that the global optimal solution is found.

[0117] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0118]

[0119] In the fitness function F(x), the matching term It is used to measure the matching degree between solar power generation and power demand, ensuring that the system can effectively meet the load demand; system efficiency Used to evaluate the operating efficiency of the system under different temperature conditions, reduce energy loss, and improve the overall efficiency of the system; cost items Used to consider system operating costs, including direct costs and additional costs, to ensure that the optimization plan is economically feasible;

[0120] The following is a brief introduction to how to obtain the parameters of the formula:

[0121] T i is obtained from the thermodynamic analysis report and represents the i-th temperature point; P 需求 is obtained from the energy demand forecast report and represents future electricity demand; C is obtained from the system operation data and represents the system operation cost; α is set according to the system demand and represents the weight coefficient of matching degree; β is set according to the system demand and represents the weight coefficient of system efficiency; γ is set according to the system demand and represents the weight coefficient of cost; η is set according to the system demand and represents the weight coefficient of additional cost; EP 损失 (T i ) is calculated by thermodynamic analysis method, indicating that at temperature T i Additional energy loss under 总 Obtained from system operation data, representing total energy; P 太阳能 is obtained from the energy demand forecast report and represents the future solar power generation; E 损失 (T i ) is calculated by thermodynamic analysis method, indicating that at temperature T i Energy loss under

[0122] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0123]

[0124] Linear combination term: (1-θ)·x 1 +θ·x 2 ; This term is obtained by linearly combining the parameter vectors x of the two parent individuals 1 and x 2 , generating a new individual. The parameter θ is the crossover probability, which ranges from [0,1] and indicates the proportion of characteristics inherited by the new individual from the parent individual. In this way, the advantages of the parent individual can be retained to a certain extent while exploring new solution spaces; ensuring that the new individual inherits the excellent characteristics of the parent individual to a certain extent, while introducing certain variations and increasing the diversity of the search

[0125] Nonlinear variation: This term enhances the search capability by introducing nonlinear variation. The periodicity and boundedness of the sine function enable this term to introduce directional variation to a certain extent, which helps to jump out of the local optimal solution and explore a wider solution space; through nonlinear variation, the diversity and flexibility of the search are increased, which helps to find the global optimal solution.

[0126] Gaussian variation: This term enhances the diversity of the search by introducing random mutations of the Gaussian distribution. The nature of the Gaussian distribution makes the size of the mutation increase with x. 1 and x 2 The distance between them increases and decreases, which helps to perform fine search in a local range and coarse search in a larger range; through Gaussian mutation, the robustness and diversity of the search are increased, which helps to balance the capabilities of global and local searches at different search stages.

[0127] The following is a brief introduction to how to obtain the parameters of the formula:

[0128] x 1 is the energy allocation model parameter vector of the first parent individual, selected from the population of the genetic algorithm; x 2 is the parameter vector of the energy allocation model of the second parent individual, which is selected from the population of the genetic algorithm; θ is the crossover probability, which ranges from [0,1] and indicates the proportion of characteristics inherited by the new individual from the parent individual, which is determined according to the parameter setting of the genetic algorithm; δ is the crossover coefficient of variation, which is used to introduce nonlinear variation and enhance the search capability, and is calibrated according to experimental data; ζ is the Gaussian coefficient of variation, which is used to introduce random variation of the Gaussian distribution and enhance the search diversity, and is calibrated according to experimental data; σ is the standard deviation of the Gaussian distribution, which controls the amplitude of the Gaussian variation and is calibrated according to experimental data.

[0129] Assume that there is a shelter equipped with a solar power generation system and energy storage batteries. It is necessary to generate an efficient energy allocation strategy based on future power demand and solar power generation to ensure that the system can operate efficiently under various environmental conditions. The specific steps are as follows:

[0130] Before calculating the fitness function F(x), it is first necessary to match the future electricity demand and solar power generation to generate an initial energy allocation model. In this process, it is necessary to combine the energy demand forecast report and conduct a detailed analysis of the electricity demand and solar power generation in different time periods to ensure that the initial parameters of the model can reflect the actual demand.

[0131] For example, if electricity demand on a particular day is 100kWh and solar generation is 80kWh, the initial model might set the storage battery to charge 20kWh during the day and discharge 20kWh at night.

[0132] P 需求 =100kWh, obtained from the energy demand forecast report; P 太阳能 = 80 kWh, obtained from the energy demand forecast report; T 1 =40℃, obtained from the temperature sensor; T 2 =-10℃, obtained from the temperature sensor; E 损失 (T 1 )=10kWh, obtained through experimental data; E 损失 (T 2 )=5kWh, obtained through experimental data; E 总 =100kWh, obtained from system operation data; C = 1000 yuan, obtained from financial reports; α = 0.5, set according to system requirements; β = 0.3, set according to system requirements; γ = 0.2, set according to system requirements; η = 0.1, set according to system requirements; EP 损失 (T 1 )=5kWh, obtained through experimental data; EP 损失 (T 2 )=2kWh, obtained through experimental data.

[0133] Calculate the fitness function F(x):

[0134]

[0135] F(x)=0.5·0.8+0.3·0.85-0.2·(1000+0.1·log(1.07))

[0136] F(x)=0.4+0.255-0.2·(1000+0.1·0.02956)

[0137] F(x)=0.655-0.2·1000.002956

[0138] F(x)=0.655-200.0005912

[0139] F(x)=-199.3455912

[0140] Generate 100 initial energy allocation models as a population, each model is a possible solution; select the 30 models with the highest fitness to enter the next generation; combine the parameter vectors of the two parent models to generate a new child model. For example, suppose the two parent models are x 1 =[0.8,0.2,0.15] and x 2 =[0.7,0.3,0.2], generate a new model x through crossover operation 新 :

[0141]

[0142] x 新 =[0.75,0.25,0.175]+0.1·[0.599,-0.599,-0.300]+0.05·0.326

[0143] x 新 =[0.75,0.25,0.175]+[0.0599,-0.0599,-0.0300]+[0.0163,0.0163,0.0163]

[0144] x 新 =[0.8262,0.2064,0.1613]

[0145] The new individual parameter vector x generated 新 The simulation and actual operation data are used to evaluate the performance of the new model, ensure its effectiveness and stability in practical applications, and obtain the optimized energy distribution model. For example, through simulation verification, it is found that the new model improves the system efficiency by 10% in high temperature environment and 5% in low temperature environment.

[0146] Through the above steps, an optimized energy allocation model was successfully generated to ensure that the system can operate efficiently under various environmental conditions. The final optimized energy allocation model includes new energy allocation strategies, energy storage battery management strategies, etc., to ensure that the system can operate efficiently under various environmental conditions.

[0147] 103. When it is detected that the solar power generation is insufficient to meet the immediate load demand, the fuzzy logic control system is started to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy allocation strategy, and the health status of the energy storage battery is monitored by electrochemical impedance spectroscopy technology to generate a health status report of the energy storage battery;

[0148] Fuzzy logic control system is a control system based on fuzzy logic, which is used to dynamically adjust the charging and discharging strategy of energy storage batteries.

[0149] PID control algorithm is a commonly used feedback control algorithm used to accurately control the charge and discharge rate of energy storage batteries.

[0150] Electrochemical impedance spectroscopy technology reflects the internal state of energy storage batteries by measuring impedance values ​​at different frequencies and is used to monitor the health of batteries. The energy storage battery health status report is generated based on electrochemical impedance spectroscopy technology and Kalman filtering algorithm, and is a report reflecting the health status and potential faults of energy storage batteries.

[0151] In the embodiment of the present application, the solar power generation and the load demand are monitored in real time. When it is detected that the solar power generation is insufficient to meet the immediate load demand, the start condition of the fuzzy logic control system is triggered and a start signal is generated; according to the start signal and the optimized energy allocation strategy, the fuzzy logic control system is started, and the charge and discharge rates of the energy storage battery are dynamically adjusted in combination with the PID control algorithm to generate a charge and discharge adjustment instruction; the charge and discharge adjustment instruction is used to monitor the health status of the energy storage battery in real time through the electrochemical impedance spectroscopy technology, and the monitoring data is smoothed in combination with the Kalman filter algorithm to generate energy storage battery health monitoring data; based on the energy storage battery health monitoring data, a data analysis algorithm is used to identify the health status and potential faults of the energy storage battery, and generate an energy storage battery health status report.

[0152] Optionally, in step 103, when it is detected that the solar power generation is insufficient to meet the immediate load demand, the fuzzy logic control system is started to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy allocation strategy, and the health status of the energy storage battery is monitored by electrochemical impedance spectroscopy technology to generate a health status report of the energy storage battery, including:

[0153] When it is detected that the solar power generation is insufficient to meet the immediate load demand, the start-up condition of the fuzzy logic control system is triggered and a start-up signal is generated; according to the start-up signal and the optimized energy allocation strategy, the fuzzy logic control system is started, and the charge and discharge rates of the energy storage battery are dynamically adjusted in combination with the PID control algorithm to generate a charge and discharge adjustment instruction; the charge and discharge adjustment instruction is used to monitor the health status of the energy storage battery in real time through the electrochemical impedance spectroscopy technology, and the monitoring data is smoothed in combination with the Kalman filter algorithm to generate energy storage battery health monitoring data; based on the energy storage battery health monitoring data, a data analysis algorithm is used to identify the health status and potential faults of the energy storage battery and generate an energy storage battery health status report.

[0154] The method of starting the fuzzy logic control system according to the start signal and the optimized energy allocation strategy, combining the PID control algorithm, dynamically adjusting the charge and discharge rate of the energy storage battery, and generating the charge and discharge adjustment instruction includes:

[0155] The start signal is used to activate the operating state of the fuzzy logic control system, receive and process the energy allocation strategy, and generate a control system activation signal; based on the optimized energy allocation strategy, the charge and discharge target value of the energy storage battery is determined, and the charge and discharge target value is generated as the input of the fuzzy logic control system; the control system activation signal and the charge and discharge target value are used, combined with the real-time operation data of the system, and the charge and discharge rate of the energy storage battery is dynamically adjusted through the fuzzy logic control system to generate a preliminary charge and discharge adjustment instruction; the preliminary charge and discharge adjustment instruction is compared with the actual charge and discharge rate, the error is calculated through the PID control algorithm, the control parameter is adjusted, and the final charge and discharge adjustment instruction is generated.

[0156] Assume that there is a shelter equipped with a solar power generation system and energy storage batteries. It is necessary to generate an efficient energy distribution strategy based on future power demand and solar power generation to ensure that the system can operate stably under various environmental conditions, especially extreme temperatures. The specific steps are as follows:

[0157] Real-time monitoring of solar power generation and load demand. For example, assuming that the solar power generation is 50kWh at a certain moment, and the immediate load demand is 70kWh; when it is detected that the solar power generation is insufficient to meet the immediate load demand, the start-up condition of the fuzzy logic control system is triggered and a start-up signal is generated. For example, when the solar power generation is 50kWh and the load demand is 70kWh, the system generates a start-up signal; using the start-up signal, the operating state of the fuzzy logic control system is activated, the energy allocation strategy is received and processed, and a control system activation signal is generated. For example, after the start signal is triggered, the fuzzy logic control system enters the working state and is ready to receive and process the energy allocation strategy; based on the optimized energy allocation strategy, the charge and discharge target value of the energy storage battery is determined as the input of the fuzzy logic control system to generate the charge and discharge target value. For example, the optimized energy allocation strategy indicates that 20kWh needs to be discharged from the energy storage battery at this moment, so the charge and discharge target value is 20kWh; using the control system activation signal and the charge and discharge target value, combined with the real-time operation data of the system, the charge and discharge rate of the energy storage battery is dynamically adjusted through the fuzzy logic control system to generate a preliminary charge and discharge adjustment instruction. For example, the fuzzy logic control system preliminarily sets the energy storage battery discharge rate to 10kW based on the current solar power generation and load demand; compares the preliminary charge and discharge adjustment instructions with the actual charge and discharge rate, calculates the error through the PID control algorithm, adjusts the control parameters, and generates the final charge and discharge adjustment instructions. For example, if the actual charge and discharge rate is 8kW, the PID control algorithm calculates the error to 2kW, and adjusts the control parameters so that the final charge and discharge rate reaches 10kW; generates the final charge and discharge adjustment instructions to ensure that the energy storage battery is charged and discharged according to the optimized energy allocation strategy. For example, the final generated charge and discharge adjustment instructions are a discharge rate of 10kW and a duration of 2 hours to meet the load demand.

[0158] Through the above steps, the final charge and discharge adjustment instructions are successfully generated to ensure that the system can operate efficiently under various environmental conditions, especially under extreme temperatures.

[0159] This application takes into account that in the health monitoring of energy storage batteries, electrochemical impedance spectroscopy (EIS) technology is a commonly used method for evaluating the internal state of the battery. The Kalman filter algorithm is used to smooth the collected impedance data, reduce noise interference, and improve the accuracy and real-time performance of the data. Through these technologies, a detailed energy storage battery health status report can be generated to ensure the efficient operation of the system.

[0160] Optionally, the use of the charge and discharge adjustment instructions to monitor the health status of the energy storage battery in real time through electrochemical impedance spectroscopy technology, and smoothing the monitoring data in combination with a Kalman filter algorithm to generate energy storage battery health monitoring data, including:

[0161] Before calculating the electrochemical impedance spectrum Z(f), it is necessary to conduct impedance testing and collect impedance data at different frequencies. At the same time, the data must be preprocessed to remove noise and outliers to ensure the accuracy and reliability of the data.

[0162] Electrochemical Impedance Spectroscopy:

[0163]

[0164] Where Z(f) is the impedance value at frequency f in electrochemical impedance spectroscopy; R 0 is the ohmic resistance; C 0 is the constant phase element capacitance; R k is the resistance corresponding to the kth time constant; C k is the capacitance corresponding to the kth time constant; M is the number of time constants; ω is the angular frequency, ω = 2πf; η is the additional impedance coefficient, used to introduce nonlinear correction; θ is the impedance correction coefficient, used to introduce nonlinear correction; j is the imaginary unit

[0165] After calculating Z(f), the impedance data is smoothed using the Kalman filter algorithm to reduce noise interference, improve data accuracy and real-time performance, and provide a basis for subsequent health monitoring.

[0166] Kalman filter smoothing:

[0167]

[0168] in, is the state estimate at time t; is the prior state estimate at time t; K t is the Kalman gain; y t is the measured value at time t; H is the observation matrix; is the state estimate at time t-1; u t is the control input at time t; A is the state transfer matrix; B is the control input matrix; P t∣t-1 is the prior error covariance matrix at time t; R is the measurement noise covariance matrix; P t is the posterior error covariance matrix at time t; I is the identity matrix; λ is the nonlinear correction coefficient; σ y is the standard deviation of the measured value; μ is the control input correction factor; σ u is the standard deviation of the control input; φ is the measurement value correction coefficient; ψ is the control input nonlinear correction coefficient; v is the Kalman gain correction coefficient; ρ is the Kalman gain nonlinear correction coefficient; ξ is the error covariance correction coefficient; τ is the error covariance nonlinear correction coefficient; y represents the measured value of a certain state or parameter of the energy storage battery at a certain time t;

[0169] After the Kalman filter smoothing process is completed, feature extraction and pattern recognition are performed on the generated data to generate a detailed energy storage battery health status report.

[0170] The formula is designed to enable electrochemical impedance spectroscopy (EIS) technology to comprehensively evaluate the internal state of the energy storage battery, including parameters such as ohmic resistance and capacitance, thereby reflecting the health of the battery; the Kalman filter algorithm can smooth the collected impedance data, reduce noise interference, improve data accuracy and real-time performance, and provide a basis for subsequent health monitoring.

[0171] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0172]

[0173] Ohmic resistance term R 0 Used to evaluate the ohmic resistance of the battery, reflecting the contact resistance and electrolyte resistance inside the battery; constant phase element capacitance Used to evaluate the interfacial capacitance of the battery, reflecting the charge storage capacity of the battery surface; time constant term Used to evaluate multiple time constants of the battery, reflecting the complex electrochemical reactions inside the battery; nonlinear correction term Used to introduce nonlinear corrections to improve the accuracy of the model;

[0174] The following is a brief introduction to how to obtain the parameters of the formula:

[0175] Z(f) is the electrochemical impedance spectroscopy, the impedance value at frequency f, collected by an impedance test instrument; R 0 is the ohm resistance, collected by the impedance test instrument; C 0 is the capacitance of the constant-phase element, which is collected by the impedance test instrument; R k is the resistance corresponding to the kth time constant, which is collected by the impedance test instrument; C k is the capacitance corresponding to the kth time constant, collected by the impedance test instrument; M is the number of time constants, determined according to the impedance test results; ω is the angular frequency, calculated by the formula ω = 2πf; η is the additional impedance coefficient, calibrated according to experimental data; θ is the impedance correction coefficient, calibrated according to experimental data; j is the imaginary unit, with a fixed value of

[0176] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0177]

[0178] State Estimate Update Used to update state estimation and reduce noise interference; prior state estimation Used to predict the state of the next time step; Kalman gain Used to calculate the Kalman gain and adjust the weight of the state estimate; error covariance update: Used to update the error covariance to reflect the uncertainty of state estimation.

[0179] The following is a brief introduction to how to obtain the parameters of the formula:

[0180] is the state estimate at time t, calculated by the Kalman filter algorithm; is the prior state estimate at time t, calculated by the Kalman filter algorithm; K t is the Kalman gain, calculated by the Kalman filter algorithm; y t is the measurement value at time t, collected by the sensor; H is the observation matrix, determined according to the system model; is the state estimate at time t-1, calculated by the Kalman filter algorithm; u t is the control input at time t, determined according to the system control strategy; A is the state transfer matrix, determined according to the system model; B is the control input matrix, determined according to the system model; P t∣t-1 is the prior error covariance matrix at time t, calculated by the Kalman filter algorithm; R is the measurement noise covariance matrix, determined according to the sensor characteristics; P t is the a posteriori error covariance matrix at time t, calculated by the Kalman filter algorithm; I is the unit matrix, and the fixed value is a matrix with all diagonal 1s; λ is the nonlinear correction coefficient, calibrated according to experimental data; σ y is the standard deviation of the measured value, which is determined according to the sensor characteristics; μ is the control input correction factor, which is calibrated according to experimental data; σ u is the standard deviation of the control input, which is determined according to the system control strategy; φ is the measurement value correction coefficient, which is calibrated according to the experimental data; ψ is the control input nonlinear correction coefficient, which is calibrated according to the experimental data; ν is the Kalman gain correction coefficient, which is calibrated according to the experimental data; ρ is the Kalman gain nonlinear correction coefficient, which is calibrated according to the experimental data; ξ is the error covariance correction coefficient, which is calibrated according to the experimental data; τ is the error covariance nonlinear correction coefficient, which is calibrated according to the experimental data.

[0181] Suppose there is an energy storage battery, and its health status needs to be monitored in real time through electrochemical impedance spectroscopy technology and Kalman filtering algorithm. The specific steps are as follows: perform impedance testing and collect impedance data at different frequencies, such as collecting impedance data at 10Hz, 100Hz, 1kHz, 10kHz, and 100kHz; preprocess the data to remove noise and outliers to ensure the accuracy and reliability of the data. For example, the collected impedance data is

[0182] Z(10Hz)=0.5+0.1jΩ, Z(100Hz)=0.4+0.05jΩ, Z(1kHz)=0.3+0.02jΩ

[0183] Z(10kHz)=0.2+0.01jΩ, Z(100kHz)=0.1+0.005jΩ.

[0184] Calculate the electrochemical impedance spectroscopy Z(f): R 0 =0.5Ω,C 0 =100μF,R 1 =0.3Ω,C 1 =50μF,R 2 =0.2Ω,C 2 =20μF, M=2, eta=0.1, θ=0.2.

[0185] Calculate Z(f):

[0186] Z(10Hz)=0.5+159.155+0.299-0.00282j+0.199-0.00050j+0.00025+0.2·0.5878

[0187] Z(10Hz)=0.5+159.155+0.299+0.199+0.00025+0.11756-0.00282j-0.00050j

[0188] Z(10Hz)=160.27081-0.00332j

[0189] Kalman filter smoothing: λ=0.1,σ y =0.01,μ=0.1,σ u =0.01, φ=0.1, ψ=0.1, ν=0.1, ρ=0.1, ξ=0.1, τ=0.1.

[0190] calculate

[0191]

[0192] Calculate K 1 :

[0193]

[0194] K 1 =[0.99]+0.1·1+0.1·log(15967.081)

[0195] K 1 =[0.99]+0.1+0.1·4.204

[0196] K 1 =[1.01204]

[0197] calculate

[0198]

[0199] After the Kalman filter smoothing process is completed, the generated data is subjected to feature extraction and pattern recognition to generate a detailed report on the health status of the energy storage battery. For example, the report points out that the ohmic resistance of the battery has increased, indicating that the battery may be aging and recommends maintenance inspection.

[0200] Through the above steps, a detailed energy storage battery health report was successfully generated to ensure that the system can operate efficiently under various environmental conditions. The final report includes key parameters such as the battery's ohmic resistance and capacitance, as well as recommended maintenance measures.

[0201] 104. Based on the energy storage battery health status report and system operation data, the system's energy consumption pattern and optimization opportunity points are identified and processed, and the energy management strategy is continuously adjusted and improved using big data analysis technology to obtain an optimized energy management solution.

[0202] System operation data includes energy storage battery charging and discharging data, power demand data, solar power generation data, etc., which are used to analyze the system's energy consumption pattern.

[0203] Big data analysis technology refers to the use of big data analysis technology to conduct in-depth mining of system operation data to identify the system's energy consumption patterns and optimization opportunities.

[0204] An optimized energy management solution refers to continuously adjusting and improving energy management strategies based on big data analysis results to generate optimized energy management solutions.

[0205] Collect energy storage battery health status reports and system operation data, including energy storage battery charging and discharging data, power demand data, solar power generation data, etc.

[0206] In the embodiments of the present application, big data analysis technology is used to deeply mine the collected data to identify the energy consumption patterns and optimization opportunities of the system; based on the data analysis results, the energy allocation strategy is adjusted, the charging and discharging strategy of the energy storage battery is optimized, and the overall energy efficiency of the system is improved; an optimized energy management solution is generated, including a new energy allocation strategy, an energy storage battery management strategy, etc., to ensure that the system can operate efficiently under various environmental conditions.

[0207] Optionally, in step 104, based on the energy storage battery health status report and system operation data, the energy consumption mode and optimization opportunity points of the system are identified and processed, and the energy management strategy is continuously adjusted and improved by using big data analysis technology to obtain an optimized energy management solution, including:

[0208] Based on the health status report of the energy storage battery, the key health parameters of the energy storage battery are extracted to generate a health parameter data set; in combination with the system operation data, the energy consumption pattern of the system is analyzed to generate an energy consumption pattern analysis report; using big data analysis technology, the health parameter data set and the energy consumption pattern analysis report are deeply mined to identify energy consumption anomalies and optimization opportunity points in the system, and an optimization opportunity point report is generated; based on the optimization opportunity point report, specific optimization measures are formulated and an optimization measure plan is generated; the optimization measure plan is applied to the system, the system operation status is continuously monitored, the effect of the optimization measures is evaluated, the energy management strategy is adjusted and improved, and an optimized energy management plan is generated.

[0209] Assume that there is a shelter equipped with a solar power generation system and energy storage batteries. It is necessary to generate an efficient energy management plan based on the health status report of the energy storage batteries and the system operation data to ensure that the system can operate efficiently under various environmental conditions. The specific steps are as follows:

[0210] Collect the health status report of the energy storage battery, which includes the key health parameters of the battery, such as the internal resistance, temperature, and charge and discharge efficiency. For example, the report points out that the internal resistance of the battery has increased by 10%, and the temperature rises rapidly in a high temperature environment; collect system operation data, including the charge and discharge data of the energy storage battery, power demand data, and solar power generation data. For example, the charge and discharge rate, daily power demand, and solar power generation in the past week are recorded; based on the health status report of the energy storage battery, extract the key health parameters of the energy storage battery and generate a health parameter data set. For example, extract parameters such as battery internal resistance, temperature, and charge and discharge efficiency to form a structured data set; combine the system operation data, analyze the energy consumption mode of the system, and generate an energy consumption mode analysis report. For example, the analysis found that the battery charge and discharge efficiency of the system decreased in a high temperature environment, resulting in a decrease in overall energy efficiency; use big data analysis technology to deeply mine the health parameter data set and energy consumption mode analysis report, identify energy consumption anomalies and optimization opportunities in the system, and generate an optimization opportunity report. For example, big data analysis found that the internal resistance of the battery increased in a high temperature environment, resulting in a decrease in charging and discharging efficiency. It is recommended to reduce the charging rate in a high temperature environment; based on the optimization opportunity point report, specific optimization measures are formulated and an optimization measure plan is generated. For example, the optimization measure plan includes reducing the charging rate of the energy storage battery in a high temperature environment from 20kWh to 15kWh, and appropriately increasing the charging rate in a low temperature environment from 20kWh to 25kWh; applying the optimization measure plan to the system, continuously monitoring the system operation status, evaluating the effect of the optimization measures, adjusting and improving the energy management strategy, and generating an optimized energy management plan. For example, after implementing the optimization measures, the overall energy efficiency of the system in a high temperature environment increased by 10%, and the energy efficiency in a low temperature environment increased by 5%.

[0211] Through the above steps, an optimized energy management solution was successfully generated to ensure that the system can operate efficiently under various environmental conditions. The final optimized energy management solution includes new energy allocation strategies, energy storage battery management strategies, etc., to ensure that the system can operate efficiently under various environmental conditions.

[0212] Figure 2 A schematic diagram of a solar energy and energy storage combined power supply system suitable for a mobile cabin is provided for an embodiment of the present application. Figure 2 As shown, the device comprises:

[0213] The collection module 21 is used to collect the power demand data inside the shelter, and combine it with the weather forecast information to predict the future trend of solar power generation and load demand changes, and generate an energy demand forecast report for a period of time in the future;

[0214] The allocation module 22 is used to optimize the energy allocation plan based on the energy demand forecast report using a genetic algorithm, ensure the efficient operation of the system under extreme temperatures through thermodynamic analysis, and generate an optimized energy allocation strategy;

[0215] The monitoring module 23 is used to start the fuzzy logic control system to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy allocation strategy when it is detected that the solar power generation is insufficient to meet the immediate load demand, monitor the health status of the energy storage battery through the electrochemical impedance spectroscopy technology, and generate a health status report of the energy storage battery;

[0216] The adjustment module 24 is used to identify and process the system's energy consumption pattern and optimization opportunities based on the energy storage battery health status report and system operation data, and to continuously adjust and improve the energy management strategy using big data analysis technology to obtain an optimized energy management solution.

[0217] Figure 2 The solar energy and energy storage combined power supply system suitable for mobile cabins can be implemented Figure 1 The implementation principle and technical effect of the solar energy and energy storage combined power supply method suitable for mobile cabins described in the embodiment shown are not repeated here. The specific way in which each module and unit performs the operation of the solar energy and energy storage combined power supply system suitable for mobile cabins in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0218] In one possible design, Figure 2 A solar energy and energy storage combined power supply system suitable for a mobile cabin in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0219] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0220] The processing component 32 is used to: collect the power demand data inside the cabin, combine it with weather forecast information, predict and process the future solar power generation and load demand change trends, and generate an energy demand forecast report for a period of time in the future; based on the energy demand forecast report, use genetic algorithms to optimize the energy distribution plan, ensure the efficient operation of the system under extreme temperatures through thermodynamic analysis, and generate an optimized energy distribution strategy; when it is detected that the solar power generation is insufficient to meet the immediate load demand, according to the optimized energy distribution strategy, start the fuzzy logic control system to dynamically adjust the charging and discharging strategy of the energy storage battery, monitor the health status of the energy storage battery through electrochemical impedance spectroscopy technology, and generate an energy storage battery health status report; based on the energy storage battery health status report and system operation data, identify and process the system's energy consumption mode and optimization opportunity points, and use big data analysis technology to continuously adjust and improve the energy management strategy to obtain an optimized energy management plan.

[0221] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0222] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0223] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0224] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0225] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0226] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0227] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a method for combining solar energy and energy storage to supply power to a mobile cabin.

[0228] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0229] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0230] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0231] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A solar energy and energy storage combined power supply method suitable for a mobile cabin, characterized in that: include: Collect the electricity demand data inside the shelter, combine it with weather forecast information, predict the future trend of solar power generation and load demand changes, and generate an energy demand forecast report for a period of time in the future; Based on the energy demand forecast report, the energy allocation plan is optimized using a genetic algorithm, and the efficient operation of the system under extreme temperatures is ensured through thermodynamic analysis to generate an optimized energy allocation strategy; When it is detected that the solar power generation is insufficient to meet the immediate load demand, the fuzzy logic control system is started to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy allocation strategy, and the health status of the energy storage battery is monitored by electrochemical impedance spectroscopy technology to generate a health status report of the energy storage battery; Based on the energy storage battery health status report and system operation data, the system's energy consumption pattern and optimization opportunities are identified and processed, and the energy management strategy is continuously adjusted and improved using big data analysis technology to obtain an optimized energy management solution.

2. The method according to claim 1, characterized in that Based on the energy demand forecast report, the energy allocation scheme is optimized by using a genetic algorithm, and the efficient operation of the system under extreme temperatures is ensured by thermodynamic analysis, so as to generate an optimized energy allocation strategy, including: Using the energy demand forecast report, matching the future electricity demand and solar power generation is performed to obtain an initial energy allocation model; Based on the initial energy distribution model, a genetic algorithm is used to perform optimization processing to obtain an optimized energy distribution model; According to the optimized energy distribution model, combined with the thermodynamic analysis method, the system operation efficiency under different temperature conditions is evaluated and processed to obtain the temperature adaptability analysis results; Based on the temperature adaptability analysis results, the optimized energy allocation model is adjusted to ensure that the system can operate efficiently even at extreme temperatures, thereby generating an optimized energy allocation strategy.

3. The method according to claim 2, characterized in that The optimization process based on the initial energy distribution model is performed by using a genetic algorithm to obtain an optimized energy distribution model, including: Before calculating the fitness function F(x), it is necessary to first match the future electricity demand and solar power generation to generate an initial energy allocation model. In this process, it is necessary to combine the energy demand forecast report and conduct a detailed analysis of the electricity demand and solar power generation in different time periods to ensure that the initial parameters of the model can reflect the actual demand. Fitness function: Among them, x is the parameter vector of the energy allocation model, including the matching ratio of solar power generation and load demand in each time period, and the charging and discharging strategy of the energy storage battery; P 需求 is the future electricity demand, obtained from the energy demand forecast report; P 太阳能 is the future solar power generation, obtained from the energy demand forecast report; T i is the i-th temperature point, which is used to evaluate the operating efficiency of the system under different temperature conditions; E 损失 (T i ) is at temperature T i Energy loss under 总 is the total energy; C is the system operation cost; α is the weight coefficient of matching degree; β is the weight coefficient of system efficiency; γ is the weight coefficient of cost; η is the weight coefficient of additional cost; EP 损失 (T i ) is at temperature T i Additional energy loss under After calculating the fitness function F(x), the generated initial energy allocation model needs to be optimized. In this step, the selection, crossover and mutation operations in the genetic algorithm are used. The crossover operation is used to combine the parameter vectors of two parent individuals to generate a new individual. Crossover operation: x 新 is the parameter vector of the new individual generated by the crossover operation; θ is the crossover probability, which ranges from [0,1] and indicates the proportion of the characteristics inherited by the new individual from the parent individual; δ is the crossover coefficient of variation, which is used to introduce nonlinear variation and enhance the search capability; ζ is the Gaussian coefficient of variation, which is used to introduce random variation of Gaussian distribution and enhance the search diversity; σ is the standard deviation of Gaussian distribution, which controls the amplitude of Gaussian variation; x1 is the parameter vector of the energy allocation model of the first parent individual; x2 is the parameter vector of the energy allocation model of the second parent individual; After calculating the new individual parameter vector x 新 Finally, the generated model is further verified and optimized, and the performance of the generated model is evaluated through simulation and actual operation data to obtain the optimized energy distribution model.

4. The method according to claim 2, characterized in that: According to the optimized energy distribution model, combined with the thermodynamic analysis method, the system operation efficiency under different temperature conditions is evaluated and processed to obtain the temperature adaptability analysis results, including: According to the optimized energy distribution model, the working state of the system under different temperature conditions is simulated to obtain simulated operation data; Combined with thermodynamic analysis methods, the simulation operation data is analyzed, the data of the system under different temperature conditions is evaluated, and a thermodynamic analysis report is obtained; Based on the thermodynamic analysis report, identify the operation bottlenecks and potential problems of the system under extreme temperatures, and obtain temperature adaptability evaluation indicators; The temperature adaptability evaluation index is used to comprehensively evaluate the system operation efficiency under different temperature conditions to generate temperature adaptability analysis results.

5. The method according to claim 2, characterized in that: Based on the temperature adaptability analysis result, the optimized energy allocation model is adjusted to ensure that the system can operate efficiently even at extreme temperatures, and an optimized energy allocation strategy is generated, including: Based on the temperature adaptability analysis results, identify the operation bottlenecks and inefficient links of the system under extreme temperature conditions, and obtain a bottleneck analysis report; According to the bottleneck analysis report, key parameters in the optimized energy allocation model are adjusted to obtain an energy allocation model; Using the energy distribution model and combining it with actual operation data, simulation verification is performed to evaluate the operation effect of the adjusted model under extreme temperatures and generate a simulation verification report; Based on the simulation verification report, the adjusted energy allocation model is further optimized to generate an optimized energy allocation strategy.

6. The method according to claim 1, characterized in that When it is detected that the solar power generation is insufficient to meet the immediate load demand, the fuzzy logic control system is started to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy allocation strategy, and the health status of the energy storage battery is monitored by electrochemical impedance spectroscopy technology to generate a health status report of the energy storage battery, including: When it is detected that the solar power generation is insufficient to meet the immediate load demand, the start-up condition of the fuzzy logic control system is triggered and a start-up signal is generated; According to the start signal and the optimized energy allocation strategy, the fuzzy logic control system is started, and the charge and discharge rate of the energy storage battery is dynamically adjusted in combination with the PID control algorithm to generate a charge and discharge adjustment instruction; Using the charge and discharge adjustment instructions, the health status of the energy storage battery is monitored in real time through electrochemical impedance spectroscopy technology, and the monitoring data is smoothed in combination with the Kalman filter algorithm to generate energy storage battery health monitoring data; Based on the energy storage battery health monitoring data, a data analysis algorithm is used to identify the health status and potential faults of the energy storage battery, and generate an energy storage battery health status report.

7. The method according to claim 6, characterized in that The use of the charge and discharge adjustment instructions to monitor the health status of the energy storage battery in real time through electrochemical impedance spectroscopy technology, and smoothing the monitoring data in combination with the Kalman filter algorithm to generate energy storage battery health monitoring data, including: Before calculating the electrochemical impedance spectrum Z(f), it is necessary to conduct impedance testing and collect impedance data at different frequencies. At the same time, the data must be preprocessed to remove noise and outliers to ensure the accuracy and reliability of the data. Electrochemical Impedance Spectroscopy: Where Z(f) is the impedance value at the frequency f in the electrochemical impedance spectrum; R0 is the ohmic resistance; C0 is the capacitance of the constant phase element; R k is the resistance corresponding to the kth time constant; C k is the capacitance corresponding to the kth time constant; M is the number of time constants; ω is the angular frequency, ω = 2πf; η is the additional impedance coefficient, used to introduce nonlinear correction; θ is the impedance correction coefficient, used to introduce nonlinear correction; j is the imaginary unit After calculating Z(f), the impedance data is smoothed using the Kalman filter algorithm to reduce noise interference, improve data accuracy and real-time performance, and provide a basis for subsequent health monitoring. Kalman filter smoothing: in, is the state estimate at time t; is the prior state estimate at time t; K t is the Kalman gain; y t is the measured value at time t; H is the observation matrix; is the state estimate at time t-1; u t is the control input at time t; A is the state transfer matrix; B is the control input matrix; P t∣t-1 is the prior error covariance matrix at time t; R is the measurement noise covariance matrix; P t is the posterior error covariance matrix at time t; I is the identity matrix; λ is the nonlinear correction coefficient; σ y is the standard deviation of the measured value; μ is the control input correction factor; σ u is the standard deviation of the control input; φ is the measurement value correction coefficient; ψ is the control input nonlinear correction coefficient; v is the Kalman gain correction coefficient; ρ is the Kalman gain nonlinear correction coefficient; ξ is the error covariance correction coefficient; τ is the error covariance nonlinear correction coefficient; y represents the measured value of a certain state or parameter of the energy storage battery at a certain time t; After the Kalman filter smoothing process is completed, feature extraction and pattern recognition are performed on the generated data to generate a detailed energy storage battery health status report.

8. The method according to claim 6, characterized in that The method of starting the fuzzy logic control system according to the start signal and the optimized energy allocation strategy, combining the PID control algorithm, dynamically adjusting the charge and discharge rate of the energy storage battery, and generating the charge and discharge adjustment instruction includes: Utilizing the start signal, activating the operating state of the fuzzy logic control system, receiving and processing the energy allocation strategy, and generating a control system activation signal; Based on the optimized energy allocation strategy, the charging and discharging target values ​​of the energy storage battery are determined and used as inputs of the fuzzy logic control system to generate the charging and discharging target values; Using the control system activation signal and the charge and discharge target value, combined with the real-time operation data of the system, the charge and discharge rate of the energy storage battery is dynamically adjusted through the fuzzy logic control system to generate preliminary charge and discharge adjustment instructions; The preliminary charge and discharge adjustment instruction is compared with the actual charge and discharge rate, the error is calculated through the PID control algorithm, the control parameters are adjusted, and the final charge and discharge adjustment instruction is generated.

9. The method according to claim 1, characterized in that: Based on the energy storage battery health status report and system operation data, the energy consumption mode and optimization opportunity points of the system are identified and processed, and the energy management strategy is continuously adjusted and improved by using big data analysis technology to obtain an optimized energy management solution, including: Based on the energy storage battery health status report, extract key health parameters of the energy storage battery and generate a health parameter data set; Analyze the energy consumption pattern of the system in combination with the system operation data, and generate an energy consumption pattern analysis report; Using big data analysis technology, deeply mine the health parameter data set and the energy consumption pattern analysis report, identify energy consumption anomalies and optimization opportunities in the system, and generate an optimization opportunity report; Based on the optimization opportunity point report, formulate specific optimization measures and generate optimization measure plans; The optimization measures are applied to the system, the system operation status is continuously monitored, the effects of the optimization measures are evaluated, the energy management strategy is adjusted and improved, and an optimized energy management plan is generated.

10. A solar energy and energy storage combined power supply system suitable for a mobile cabin, characterized in that: include: The collection module is used to collect the power demand data inside the shelter, and combine it with weather forecast information to predict the future trend of solar power generation and load demand changes, and generate an energy demand forecast report for a period of time in the future; An allocation module is used to optimize the energy allocation plan based on the energy demand forecast report using a genetic algorithm, ensure the efficient operation of the system under extreme temperatures through thermodynamic analysis, and generate an optimized energy allocation strategy; A monitoring module is used to start the fuzzy logic control system to dynamically adjust the charging and discharging strategy of the energy storage battery according to the optimized energy allocation strategy when it is detected that the solar power generation is insufficient to meet the immediate load demand, monitor the health status of the energy storage battery through electrochemical impedance spectroscopy technology, and generate a health status report of the energy storage battery; The adjustment module is used to identify and process the system's energy consumption pattern and optimization opportunities based on the energy storage battery health status report and system operation data, and to continuously adjust and improve the energy management strategy using big data analysis technology to obtain an optimized energy management solution.

Images