High-altitude energy storage monitoring system

Abstract

The invention provides a high-altitude energy storage monitoring system. The system comprises an environmental data acquisition module, an intelligent temperature control analysis module, an intelligent energy scheduling module, a health monitoring module, a self-adaptive adjustment module and a system optimization module. The invention provides an intelligent and environment-adaptive energy storage system monitoring and maintenance strategy, the temperature control strategy, the energy distribution and the maintenance plan can be dynamically adjusted according to the real-time change of the high-altitude environment, the efficient operation of the energy storage system is realized, and the service life of equipment is prolonged. A sensor technology is used for collecting multi-dimensional environment data, and an intelligent algorithm is combined to monitor the operation state of the equipment in real time, predict the health state of the equipment, optimize energy scheduling and formulate a self-adaptive maintenance strategy, so that the fault risk and the maintenance cost are reduced, and the stable operation of the system in a complex environment is ensured.

Description

Technical Field

[0001] The present invention belongs to the field of energy storage monitoring, and in particular relates to a high-altitude energy storage monitoring system. Background Art

[0002] The application of energy storage systems in high-altitude environments faces many challenges. High-altitude areas usually have low air pressure, drastic temperature fluctuations, strong solar radiation and high humidity, which have a significant impact on energy storage systems (especially batteries). First, low air pressure causes the air density to decrease, which reduces the heat dissipation performance of the battery and easily leads to overheating problems; secondly, drastic temperature changes may cause uneven temperature inside the battery, accelerate degradation, and affect the health of the battery; in addition, strong solar radiation and high humidity increase the heat dissipation burden of the battery. These environmental conditions significantly affect the life and performance of the energy storage system and increase the complexity of maintenance and management.

[0003] Existing energy storage system monitoring and maintenance technologies usually adopt static temperature control strategies and regular maintenance mechanisms when facing these extreme environments. However, static temperature control strategies cannot be adjusted according to real-time changes in the environment, which can easily lead to delayed temperature control response or excessive energy consumption; and regular maintenance strategies do not fully consider the real-time operating status and environmental pressure of the equipment, often causing the equipment to run for a long time in a non-optimal state, increasing the risk of system failure. Traditional maintenance and monitoring methods are difficult to adapt to the dynamic changes of high-altitude environments, and cannot effectively respond to the challenges brought by complex environments, ultimately leading to low operating efficiency of energy storage equipment, increased equipment losses, high maintenance costs, and even system crashes. Summary of the invention

[0004] The purpose of this invention is to propose a high-altitude energy storage monitoring system that dynamically adjusts temperature control strategies, energy distribution, and maintenance plans according to real-time changes in the high-altitude environment to achieve efficient operation of the energy storage system and extend the life of the equipment. This requires the use of sensor technology to collect multi-dimensional environmental data, and combined with intelligent algorithms to monitor the equipment operating status in real time, predict the equipment health status, optimize energy scheduling, and formulate adaptive maintenance strategies to reduce the risk of failures and maintenance costs, and ensure the stable operation of the system in a complex environment.

[0005] In order to achieve the above-mentioned object, the present invention provides a high-altitude energy storage monitoring system, characterized in that the system comprises: an environmental data acquisition module, an intelligent temperature control analysis module, an intelligent energy scheduling module, a health monitoring module, an adaptive adjustment module and a system optimization module; wherein,

[0006] The environmental data acquisition module is used to adaptively and dynamically collect environmental parameters in a high-altitude environment using a multi-dimensional sensor network, and pre-process them in an edge computing unit to obtain an environmental parameter data set;

[0007] The intelligent temperature control analysis module is used to generate a temperature control signal based on the environmental parameter data set analysis to determine whether the energy storage device needs temperature control intervention; the temperature control signal includes a heating signal and a cooling signal;

[0008] The intelligent energy scheduling module is used to optimize energy allocation according to the temperature control signal transmitted by the intelligent temperature control analysis module and in combination with the power demand of the energy storage device and the external environment data;

[0009] The health monitoring module is used to perform health analysis in advance based on monitoring real-time power data and environmental feedback and through intelligent prediction algorithms;

[0010] The adaptive adjustment module is used to receive the health analysis results of the health monitoring module and dynamically adjust the maintenance strategy of the energy storage device in combination with environmental factors;

[0011] The system optimization module is used to adaptively learn the system's operational feedback and optimize the maintenance strategy;

[0012] The specific analysis process of judging whether the energy storage device needs temperature control intervention according to the environmental parameter data set is as follows:

[0013] Performing basic temperature control determination on the environmental parameter data set acquired by the environmental data acquisition module according to the battery operating temperature range of the energy storage device;

[0014] The pressure correction factor, humidity correction term and solar radiation correction term are introduced to correct the battery operating temperature range and obtain the final temperature control judgment condition;

[0015] The basic temperature control judgment is compared with the final temperature control judgment result. If the basic temperature control judgment is less than the minimum value of the final temperature control judgment result, a heating signal is generated. If the basic temperature control judgment is greater than the maximum value of the final temperature control judgment result, a cooling signal is generated.

[0016] Preferably, the multidimensional data includes temperature, air pressure, humidity and solar radiation; the adaptive dynamic acquisition is that the sampling frequency is dynamically adjusted according to the change rate of the environmental parameters, which is expressed as follows:

[0017]

[0018] Among them, f i (t) is the sampling frequency, f0 is the basic sampling frequency; α is the adjustment coefficient, which controls the increase of the sampling frequency with the rate of change; is the environmental parameter X i,j (t) The rate of change at time t, that is,

[0019] Preferably, the battery operating temperature range of the energy storage device is set to [T min ,T max ];

[0020] The air pressure correction coefficient is expressed as follows:

[0021]

[0022] in, is the minimum value of the pressure correction factor. is the maximum value of the pressure correction factor, β(t is the pressure correction factor, which reflects the effect of pressure on heat dissipation efficiency and is defined as γ is the pressure-temperature correction factor, which is used to adjust the effect of pressure changes on the temperature range; is the current air pressure, P std is the standard atmospheric pressure;

[0023] Wherein, the air pressure correction coefficient enables the temperature control operation to be triggered in advance when the air pressure is lower than the standard air pressure;

[0024] The humidity correction term α H (t) and the solar radiation correction term α R (t), expressed as follows:

[0025]

[0026] in, is the humidity correction to the temperature threshold, δ H is the humidity-temperature correction coefficient, H std is the standard humidity, is the current humidity; is the correction of solar radiation to the temperature control threshold, δ R is the radiation correction factor, R std is the standard solar radiation value, is the current solar radiation value; is the minimum value of the final temperature threshold, is the maximum value of the final temperature threshold.

[0027] Preferably, the energy is optimally allocated according to the temperature control signal transmitted by the intelligent temperature control analysis module in combination with the power demand of the energy storage device and the external environment data. The specific analysis process is as follows:

[0028] The total power demand of the set system is composed of the external load and the temperature control power demand;

[0029] The effective available power of the system is defined to represent the remaining power that the energy storage device can provide at the current moment. Then, a dynamic energy allocation strategy is designed to adjust the power allocation of the temperature control device in real time to maximize energy utilization, that is, to minimize the remaining power that the energy storage device can provide and the temperature control power demand, which is determined by environmental factors and temperature control signals.

[0030] An environmental feedback correction mechanism is introduced for high-altitude environments to dynamically adjust the power output of the temperature control equipment according to the dramatic fluctuations in environmental parameters. At the same time, an energy scheduling optimization algorithm is designed based on the adjusted power output to minimize the power loss of the energy storage equipment and ensure the normal operation of the temperature control equipment.

[0031] The final temperature control power is output by the energy scheduling optimization algorithm combined with the temperature control signal.

[0032] Preferably, the environmental feedback correction mechanism is a temperature control power after correction Add the environmental correction factor, expressed as follows:

[0033] P temp (t)'=P temp (t)·(1+θ(t))

[0034] Among them, P temp (t)' is the power required for heating or cooling in the temperature control device, θ9t) is the environmental correction factor, which reflects the impact of environmental factors on the temperature control power; the environmental correction factor θ(t0 is calculated as:

[0035]

[0036] Where κ is the temperature correction coefficient, which is used to adjust the difference between the ambient temperature and the set target temperature; is the ambient temperature, T set is the target temperature of the battery; λ is the air pressure correction factor, which is used to adjust the effect of air pressure on power demand; is the current air pressure, P std is the standard atmospheric pressure;

[0037] The energy scheduling optimization algorithm is expressed as follows:

[0038]

[0039] in, is the final temperature control power;

[0040] When Heating9t) is true, the heating power is executed

[0041] When Cooling(t) is true, the cooling power is executed

[0042] Preferably, the health analysis is performed in advance based on monitoring real-time power data and environmental feedback and through an intelligent prediction algorithm. The specific analysis process is as follows:

[0043] According to the status signal obtained by the intelligent energy scheduling module, the status signal includes the total power output, the available power, and the power consumption of the temperature control device, combined with the environmental data set, to form an operation data set, and the operation data set is monitored in real time;

[0044] Build an adaptive health status prediction model, using historical operation data sets and real-time operation data sets as input to predict the health of energy storage equipment;

[0045] Set a health threshold and determine whether the equipment has entered a high-risk zone for failure based on the predicted health status. If the health status is lower than the health threshold, the equipment will enter the accelerated degradation stage and will soon fail. Then, based on the changing trend of the health status, design a dynamic maintenance optimization model and dynamically adjust the maintenance strategy based on the current health status and environmental pressure.

[0046] Finally, the system generates maintenance signals based on health status prediction, fault assessment, and maintenance optimization results.

[0047] Preferably, the adaptive health status prediction model processes time series data through a long short-term memory network to predict future health status, which is expressed as follows:

[0048] H(t)=LSTM(M(t-Δt,t),∈(t))

[0049] Where H(t) represents the health status of the system at time t, with a value range of [0,1], 1 represents health, and 0 represents failure; ∈(t) is an environmental correction term, which is used to dynamically adjust health prediction; LSTM is a long short-term memory network for processing time series data; where the environmental correction term ∈(t) is expressed as follows:

[0050]

[0051] Among them, T opt is the optimal operating temperature of the battery, P std is the standard atmospheric pressure; H std is the standard humidity, R std is the standard radiation value; α1, α2, α3, α4 are correction coefficients, reflecting the weight of the impact of different environmental factors on the battery health status;

[0052] The dynamic maintenance optimization model is used to adjust the maintenance cycle, which is expressed as follows:

[0053]

[0054] Where T0 is the initial maintenance cycle; β is the adjustment coefficient based on the decline in equipment health; γ is the adjustment coefficient based on the environmental correction term ∈(t); H init Is the initial health status of the device.

[0055] Preferably, the health analysis result of the health monitoring module is received, and the maintenance strategy of the energy storage device is dynamically adjusted in combination with environmental factors. The specific analysis process is:

[0056] When the health status is lower than the threshold, maintenance is triggered immediately, and the adaptive maintenance strategy optimization model is used to dynamically adjust the maintenance cycle according to the health status and environmental correction items. At the same time, the priority and intensity of the maintenance task are adjusted according to the health status of the equipment and the environmental pressure. The final maintenance strategy is output, executed, and the maintenance signal is output.

[0057] Preferably, the adaptive maintenance strategy optimization model is expressed as follows:

[0058]

[0059] Where T0 is the initial maintenance period; H init is the initial health state of the equipment; β reflects the impact of changes in health state on the maintenance cycle; γ is the environmental correction coefficient, which adjusts the maintenance cycle in combination with environmental pressure; ∈(t) is the environmental correction term;

[0060] The priority and intensity of maintenance tasks are adjusted according to the health status of the equipment and the environmental pressure, as shown below:

[0061]

[0062] Among them, P maint (t) is the maintenance task priority; δ is the environmental correction factor, which reflects the impact of environmental pressure on the priority; H(t is the current health status of the equipment;

[0063]

[0064] Among them, S maint (t) is the maintenance intensity, S0 is the initial maintenance intensity; λ is the environmental correction coefficient, which reflects the impact of environmental pressure on maintenance intensity.

[0065] Preferably, the adaptive learning of the system operation feedback and the optimization of the maintenance strategy are carried out, and the specific analysis process is as follows:

[0066] Based on the equipment feedback data, a maintenance effect evaluation function is designed to quantify the improvement of equipment health caused by each maintenance, and it is adjusted in combination with the environmental pressure correction term. A dynamic adaptive learning model is designed to adjust the maintenance cycle and intensity according to the historical maintenance effect.

[0067] In order to cope with the special impact of high-altitude environment on device health, a special environment regularization term is introduced to smooth out drastic changes in health status and avoid misjudgment caused by short-term environmental fluctuations;

[0068] Finally, a global optimization model is designed to achieve a balance between maintenance costs, equipment health, and environmental pressure in the long term.

[0069] Wherein, the maintenance effect evaluation function is expressed as follows:

[0070]

[0071] Among them, H(t+Δt) is the health status of the equipment after maintenance; S maint (t) is the current maintenance intensity; α is the weight coefficient, which represents the impact of environmental pressure on maintenance effect; ∈(t) is the environmental correction term, which is used to reflect the impact of the external environment on equipment degradation.

[0072] The beneficial technical effects of the present invention are at least as follows:

[0073] (1) The present invention proposes a multi-dimensional sensor network layout and dynamic acquisition strategy based on high-altitude environment. The system monitors key environmental parameters such as temperature, air pressure, humidity and solar radiation in real time through multiple sensor nodes, and uses an adaptive acquisition frequency adjustment mechanism to ensure that the sampling frequency is increased when the environment changes drastically and the sampling frequency is reduced when the environment is stable, thereby achieving accurate and real-time data collection. Through the multi-dimensional data fusion algorithm, the system can automatically correct sensor measurement errors to ensure the accuracy of environmental data. This dynamic and adaptive acquisition strategy greatly improves the real-time and accuracy of the data, providing a reliable foundation for subsequent temperature control and energy scheduling.

[0074] (2) In view of the impact of complex factors such as air pressure, temperature, humidity and solar radiation on the operation of the energy storage system in high-altitude environments, the present invention designs an intelligent temperature control judgment and energy scheduling system. The system not only dynamically adjusts the temperature control threshold through real-time environmental data, but also refines the calculation of temperature control requirements through environmental correction items. The temperature control judgment is based on the adaptive adjustment of environmental parameters to ensure that the system can respond in time to changes in factors such as temperature, air pressure, and humidity. In addition, the system optimizes energy scheduling based on the current energy storage situation, power demand and temperature control demand, and dynamically allocates power to ensure the rational use of energy and effective heat dissipation of equipment in high-altitude environments.

[0075] (3) The present invention proposes an adaptive health prediction model for energy storage equipment, which combines environmental correction items with historical operating data to dynamically predict the health status of the equipment. The system predicts the future health status of the equipment through intelligent algorithms (such as LSTM networks), and adjusts the weights in the prediction process based on real-time temperature, air pressure and other parameters in high-altitude environments, thereby achieving accurate prediction of equipment degradation trends. In addition, the system dynamically adjusts the maintenance cycle and maintenance intensity based on the prediction results of the health status, avoiding the waste of resources caused by the traditional regular maintenance model. The adaptive maintenance strategy enables the equipment to always maintain the best health status in a complex environment, thereby extending the equipment life, reducing the failure rate, and improving operating efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0077] Figure 1 This is a framework diagram of a high-altitude energy storage monitoring system of the present invention. DETAILED DESCRIPTION

[0078] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0079] like Figure 1 As shown, an embodiment of the present invention provides a high-altitude energy storage monitoring system, the system comprising: an environmental data acquisition module 101, an intelligent temperature control analysis module 102, an intelligent energy scheduling module 103, a health monitoring module 104, an adaptive adjustment module 105 and a system optimization module 106; wherein,

[0080] The environmental data acquisition module 101 is used to adaptively and dynamically collect environmental parameters in a high-altitude environment using a multi-dimensional sensor network, and pre-process them in an edge computing unit to obtain an environmental parameter data set;

[0081] The intelligent temperature control analysis module 102 is used to generate a temperature control signal according to the environmental parameter data set analysis to determine whether the energy storage device needs temperature control intervention; the temperature control signal includes a heating signal and a cooling signal;

[0082] The intelligent energy scheduling module 103 is used to optimize energy allocation according to the temperature control signal transmitted by the intelligent temperature control analysis module and in combination with the power demand of the energy storage device and the external environment data;

[0083] The health monitoring module 104 is used to perform health analysis in advance based on monitoring real-time power data and environmental feedback and through intelligent prediction algorithms;

[0084] The adaptive adjustment module 105 is used to receive the health analysis results of the health monitoring module and dynamically adjust the maintenance strategy of the energy storage device in combination with environmental factors;

[0085] The system optimization module 106 is used to perform adaptive learning on the system operation feedback and optimize the maintenance strategy.

[0086] Specifically, the multi-dimensional sensor network is used to adaptively and dynamically collect environmental parameters in a high-altitude environment, and pre-processed in an edge computing unit to obtain an environmental parameter data set. The specific analysis is as follows:

[0087] In order to accurately capture various key parameters in high-altitude environments, the present invention designs a multi-dimensional sensor network for real-time collection of data such as temperature, air pressure, humidity, and solar radiation. These sensor nodes are arranged outside and inside the energy storage device, especially in key parts of the device (such as around the battery) to ensure comprehensive monitoring. Each sensor node P i The set of environmental parameters collected at time t is:

[0088] X i,j (t) = {T i (t),P i (t),H i (t),R i (t)} (1)

[0089] Among them, T i (t) represents the sensor node P i The temperature collected at time t; P i (t) represents air pressure; H i (t) indicates humidity; R i (t represents solar radiation. These parameters reflect the real-time status of the energy storage system in a high-altitude environment and provide basic data for subsequent steps.

[0090] Due to the drastic climate change in high-altitude environments, environmental parameters such as temperature and air pressure may fluctuate significantly in a short period of time. Therefore, sensor nodes need to dynamically adjust the sampling frequency according to environmental changes. This paper designs an adaptive dynamic acquisition strategy with a sampling frequency f i (t) According to the rate of change of environmental parameters Dynamic Adjustment:

[0091]

[0092] Where f0 is the basic sampling frequency; α is the adjustment coefficient, which controls the increase of the sampling frequency with the rate of change; is the environmental parameter X i,j (t) The rate of change at time t, that is, This formula allows the sampling frequency to automatically increase when the environment changes rapidly, thereby ensuring the real-time nature of the data; when the environment is stable, the sampling frequency is reduced to save resources.

[0093] The data collected by each sensor node may generate noise due to measurement errors or external interference. In order to improve the accuracy of the data, this paper proposes a multidimensional data fusion algorithm to process the data by weighted summation and introducing regularization terms. i The parameter X collected at time t i,j (t), the fused parameters Calculated by the following formula:

[0094]

[0095] Among them, w i is the sensor node P i The weight is adjusted adaptively based on the historical accuracy of the node and the current environmental changes to satisfy ∑w i =1; λ is the coefficient of the regularization term; Reg(X i,j (t)) is a regular term used to smooth data fluctuations, and its form is:

[0096]

[0097] This regularization term controls the second-order derivative of the data, suppressing drastic fluctuations in the data, especially short-term abnormal fluctuations in air pressure and temperature, to ensure data stability.

[0098] Furthermore, in order to reduce data transmission delay and ensure that the system can respond quickly in high-altitude environments, the present invention introduces an edge computing unit (EPU). The EPU is responsible for local data processing and compression, reducing the amount of transmitted data and ensuring high-frequency transmission at critical moments. The data set after adaptive fusion processing It will be further processed by the EPU and output a complete environmental data set D(t), including temperature, air pressure, humidity and radiation:

[0099]

[0100] These fused and processed environmental data D(t) will become the input for subsequent temperature control and energy scheduling, ensuring that the system can be optimized and adjusted based on accurate and real-time data in high-altitude environments.

[0101] Specifically, the temperature control signal is generated according to the environmental parameter data set analysis to determine whether the energy storage device needs temperature control intervention; the temperature control signal includes a heating signal and a cooling signal, and the specific analysis is as follows:

[0102] First, according to the battery operating temperature range [T min ,T max ] to make a basic temperature control judgment. The present invention needs to ensure that the energy storage device maintains efficient operation within this temperature range. The preliminary judgment formula is:

[0103]

[0104] Among them, T min and T max are the minimum and maximum operating temperatures of the energy storage device, respectively; It is the current temperature after data fusion processing outputted in step 1. This judgment provides the basic trigger condition for temperature control, but it is not sufficient to make temperature control judgment based on temperature alone, especially in high altitude environment, where factors such as air pressure, humidity and radiation have a significant impact on temperature control requirements. Therefore, the present invention further performs dynamic correction.

[0105] Furthermore, at high altitudes, changes in air pressure will affect the density of the air and the heat dissipation efficiency of the battery. In particular, when the air pressure is lower, heat dissipation becomes more difficult. Therefore, making temperature control decisions based solely on the temperature threshold may be inaccurate. The present invention introduces an air pressure correction coefficient β(t) to dynamically adjust the temperature threshold of temperature control. Temperature range after air pressure correction The calculation formula is:

[0106]

[0107] Among them, β(t) is the air pressure correction coefficient, which reflects the effect of air pressure on heat dissipation efficiency and is defined as γ is the pressure-temperature correction factor, which is used to adjust the effect of pressure changes on the temperature range; is the current air pressure, P std It is the standard air pressure. The air pressure correction makes the temperature control threshold more stringent when the air pressure is lower than the standard air pressure, triggering the temperature control operation in advance. For example, in a low-pressure environment, the battery is prone to overheating. The lower the air pressure, the narrower the temperature threshold.

[0108] Furthermore, under conditions of high humidity and strong solar radiation, the heat dissipation efficiency of the battery is further reduced. Therefore, the temperature control system needs to comprehensively consider humidity. and solar radiation To this end, the present invention introduces a humidity correction term α H (t) and the solar radiation correction term α R(t) is used to fine-tune the temperature control threshold. The adjusted temperature range is:

[0109]

[0110] in, is the humidity correction to the temperature threshold, δ H is the humidity-temperature correction coefficient, H std is the standard humidity; is the correction of solar radiation to the temperature control threshold, δ R is the radiation correction factor, R std is the standard solar radiation value. These correction items ensure that the temperature control system can adjust its operation more sensitively according to environmental changes under high humidity and strong radiation conditions. For example, under strong solar radiation, the external temperature of the system may rise rapidly, and the temperature control system needs to start the cooling device in advance.

[0111] Furthermore, combining the above air pressure, humidity and solar radiation corrected temperature thresholds, the final temperature control judgment formula is:

[0112]

[0113] This means that when the current temperature Below the minimum temperature after multiple corrections When the temperature is higher than These judgment conditions are adjusted according to real-time environmental changes to ensure that the energy storage equipment can obtain temperature control support in a timely manner under any climatic conditions.

[0114] Furthermore, according to the final temperature control determination result, the system generates a temperature control trigger signal:

[0115] like Generate a heating signal Heating(t);

[0116] like A cooling signal Cooling(t) is generated.

[0117] These trigger signals will be used as inputs to the subsequent intelligent energy scheduling system to determine the reasonable allocation and management of energy during heating or cooling. The output of this step ensures that the energy storage system maintains the optimal operating temperature of the battery through precise temperature control strategies in extreme environments at high altitudes.

[0118] Through the above-mentioned intelligent temperature control judgment scheme, the present invention extracts the current temperature, air pressure, humidity, radiation and other information from the environmental data set D(t), and realizes accurate judgment of temperature control requirements by dynamically adjusting the temperature control threshold. This scheme ensures that the system can respond quickly and take appropriate temperature control measures in high-altitude environments through multiple corrections of air pressure, humidity and radiation. All judgment signals serve as the basic input for subsequent energy scheduling, ensuring the close integration of temperature control operations and energy management, forming an efficient temperature control-energy integrated management solution.

[0119] Specifically, the energy is optimally allocated according to the temperature control signal transmitted by the intelligent temperature control analysis module and combined with the power demand of the energy storage device and the external environment data. The specific analysis is as follows:

[0120] Since the energy storage device has limited energy, the system must dynamically schedule between external load power supply and internal temperature control requirements. total (t) by external load P sys (t) and temperature control power requirement P temp (t) are jointly determined. The expression of the preliminary power requirement is:

[0121] P total (t) = P sys 9t)+P temp (t) (11)

[0122] Among them, P sys (t) is the current external load demand; P temp (t) is the power required by the temperature control device (heating or cooling), which is adaptively calculated based on the environmental data when the temperature control signal Heating(t) or Cooling(t) is activated.

[0123] At this time, it is necessary to calculate the energy reserve E of the system. avail 9t) is dispatched to ensure that the power output does not exceed the energy limit of the energy storage system.

[0124] Furthermore, in order to cope with the dynamic changes in the energy of energy storage equipment in high-altitude environments (such as changes in heat dissipation performance caused by drastic temperature differences or air pressure fluctuations), the present invention introduces a dynamic energy allocation strategy, which adjusts the power allocation of temperature control equipment in real time to ensure maximum energy utilization.

[0125] Define the effective available power P of the system avail (t), represents the remaining power that the energy storage device can provide at the current moment. The dynamic allocation strategy will optimize the energy distribution between the temperature control device and the external load:

[0126] P temp (t) = min(P avail(t),P req (t)) (12)

[0127] Among them, P avail 9t) represents the remaining power that the energy storage device can provide; P req 9t) is the required power of the temperature control equipment, which is determined by environmental factors and temperature control signals.

[0128] Furthermore, in order to adapt to the complex environment of high altitude areas, the system also needs to perform adaptive energy scheduling according to environmental changes. External factors such as temperature, air pressure, humidity, radiation, etc. directly affect the temperature control requirements. Therefore, the present invention designs an environmental feedback correction mechanism to enable the system to dynamically adjust the power of the temperature control device. The environmental correction coefficient θ(t) is introduced to dynamically adjust the power output of the temperature control device according to the drastic fluctuations in environmental parameters. The corrected temperature control power The expression is:

[0129]

[0130] Among them, θ9t) is the environmental correction coefficient, which reflects the impact of environmental factors on temperature control power; the calculation formula of θ(t) is:

[0131]

[0132] Where κ is the temperature correction coefficient, which is used to adjust the difference between the ambient temperature and the set target temperature; is the ambient temperature, T set is the target temperature of the battery; λ is the air pressure correction factor, which is used to adjust the effect of air pressure on power demand; is the current air pressure, P std is the standard atmospheric pressure. The correction factor θ(t) provides an adaptive power regulation method based on real-time environmental feedback, which enables the temperature control device to adjust the power output more flexibly according to environmental changes. For example, when the temperature drops suddenly or the air pressure drops suddenly, the power output will increase accordingly to ensure the stable operation of the energy storage system.

[0133] Furthermore, in order to ensure that the entire system maintains efficient energy utilization in a complex environment, the present invention designs an energy scheduling optimization algorithm to minimize the power loss of the energy storage system and ensure the normal operation of the temperature control equipment. The energy scheduling goal is to maximize the temperature control efficiency while minimizing the excessive consumption of the energy storage equipment. The final temperature control power The calculation formula is:

[0134]

[0135] This formula ensures that the temperature control power does not exceed the available power P of the energy storage device. avail(t), and adaptively adjusts the power output in combination with the environmental correction coefficient θ(t). This optimization algorithm calculates the temperature control power in real time, and ensures that the temperature control device can operate efficiently in extreme environments based on the current environmental data and the remaining power of the energy storage device.

[0136] Furthermore, according to the final calculated power distribution, the system will execute the power output of the temperature control device:

[0137] When Heating(t) is true, the heating power is executed

[0138] When Cooling(t) is true, the cooling power is executed

[0139] The system also outputs the current power status signal S status (t), including total power output, available energy, temperature control power consumption, etc., for subsequent system health management and further optimization.

[0140] Specifically, the real-time power data and environmental feedback are monitored and health analysis is performed in advance through intelligent prediction algorithms. The specific analysis is as follows:

[0141] The power status signal S obtained from the above module status (t), including the total power output of the energy storage system P total (t), available power P avail (t), power consumption of temperature control equipment These data are combined with the environmental dataset provided in step 1 Combined, they form the operation data set M(t) of the energy storage device. This data set is used to monitor the performance and health status of the device in real time. Define the operation monitoring data set:

[0142]

[0143] This dataset covers the power distribution and environmental data of the device, which can provide sufficient input for subsequent health status prediction. It not only reflects the current performance status of the device, but also dynamically adjusts the weight of health assessment according to changes in the external environment.

[0144] Furthermore, the performance of energy storage devices (especially batteries) gradually deteriorates over time, and environmental pressure (such as low air pressure at high altitudes and drastic temperature changes) will accelerate this degradation. Therefore, it is necessary to build a dynamic prediction model by combining historical data with real-time status to determine the health status of the energy storage system. The present invention designs an adaptive health status prediction model (AHSPM) that dynamically adjusts the prediction process based on the historical operating data and real-time input of the energy storage device. The model corrects the degradation rate of the energy storage device through environmental parameters to make the health prediction more accurate. The input of the model is time series data M(t-Δt, t), and the output is the health status H(t) at the current time t. The model processes time series data through a long short-term memory network (LSTM) to predict the future health status H(t). The formula is as follows:

[0145] H(t)=LSTM(M(t-Δt,t),∈(t)) (17)

[0146] Among them, H(t) represents the health status of the system at time t, with a value range of [0,1], 1 represents health, and 0 represents failure; ∈(t is an environmental correction term used to dynamically adjust health prediction; LSTM is a long short-term memory network that processes time series data.

[0147] The innovation of this invention lies in the environmental correction term ∈(t), which is used to dynamically adjust the health prediction of the energy storage device according to the different weights of environmental pressure. The environment in high-altitude areas fluctuates violently, and the temperature difference, air pressure, etc. have a greater impact on the battery. Therefore, the correction term ∈(t depends on the environmental data:

[0148]

[0149] Among them, T opt is the optimal operating temperature of the battery; P std is the standard atmospheric pressure; H std is the standard humidity, R std is the standard radiation value; α1, α2, α3, α4 are correction coefficients, reflecting the weight of the impact of different environmental factors on the health status of the battery. The environmental correction term ∈(t) will be dynamically adjusted as the environment changes. By introducing environmental influences in the health prediction process, it ensures that the model can accurately reflect the true health status of the energy storage device in extreme environments.

[0150] Furthermore, based on the predicted health status H(t), the system determines whether the device has entered a high-risk area for failure. thresh When H(t) is lower than the threshold, it means that the device has entered the accelerated degradation stage and may be about to fail. Failure risk determination formula:

[0151] IfH(t) <H thresh, trigger maintenance alert. (19)

[0152] Among them, H thresh It is the health threshold that is adaptively adjusted based on the historical data of the device and the current operating status; when H(t) <H thresh When the system is faulty, it issues a maintenance alert, prompting the need for equipment inspection and possible replacement.

[0153] In addition, the failure risk assessment is also combined with the temperature-controlled power consumption Long-term high-load temperature control operation will accelerate battery degradation, so the system will further correct the health status of the device based on the fluctuations in temperature control power.

[0154] Furthermore, when the health status of the equipment is lower than the set threshold, the system will adjust the maintenance strategy according to the changing trend of the health status. In order to extend the life of the equipment and reduce the failure rate, the present invention introduces a dynamic maintenance optimization model (DMOM), which can adjust the frequency and intensity of maintenance according to the current health status and environmental pressure. Maintenance cycle T maint (t) is dynamically adjusted by the following formula:

[0155]

[0156] Where T0 is the initial maintenance cycle; β is the adjustment coefficient based on the decline in equipment health; γ is the adjustment coefficient based on the environmental correction term ∈(t); H init Is the initial health status of the device.

[0157] When the health status H(t) drops significantly, or the environmental pressure is high (∈(t) is high), the system will automatically shorten the maintenance cycle to arrange maintenance operations in advance; when the equipment is in good condition and the environmental impact is small, the maintenance cycle will be appropriately extended to reduce unnecessary maintenance.

[0158] Finally, the system generates a maintenance signal S based on the health status prediction, fault assessment and maintenance optimization results. maint (t). This signal contains maintenance suggestions, estimated maintenance time and operation instructions to help the system perform adaptive maintenance. The maintenance signal is expressed as:

[0159] S maint (t)={H(t),T maint (t),Maintenance Alert} (21)

[0160] This signal is used to remind the operator or automatically trigger the maintenance procedure and provide data support for subsequent maintenance feedback links.

[0161] Specifically, the health analysis result of the health monitoring module is received, and the maintenance strategy of the energy storage device is dynamically adjusted in combination with environmental factors. The specific analysis is as follows:

[0162] According to the received health status signal S maint (t) includes the current health status of the equipment H(t), maintenance cycle T maint (t) and maintenance alarm. First, the system determines whether H(t) is lower than the maintenance threshold H thresh If it is lower than that, maintenance will be triggered immediately.

[0163] IfH(t) <H thresh , trigger immediate maintenance. (22)

[0164] Where H(t) is the current health status of the device, and its value range is [0,1], where 1 indicates health and 0 indicates failure. thresh Represents the health status threshold, which is determined based on the historical data of the device. When H(t)≥H thresh When the maintenance cycle is started, dynamic optimization is started.

[0165] Furthermore, the maintenance cycle T is dynamically adjusted according to the health status H(t) and the environmental correction term ∈(t) through the adaptive maintenance strategy optimization model (AMSO). maint (t).

[0166]

[0167] Wherein, T0 represents the initial maintenance cycle; H init It represents the initial health status of the equipment; β represents the impact of changes in health status on the maintenance cycle; γ represents the environmental correction coefficient, which adjusts the maintenance cycle in combination with the environmental pressure; ∈(t) represents the environmental correction term, which takes into account external factors such as temperature, air pressure, humidity, etc.

[0168]

[0169] in, Indicates the current ambient temperature, T opt is the best working temperature; Indicates the current air pressure, P std is the standard atmospheric pressure; Indicates the current humidity, H std is the standard humidity; represents the current solar radiation, R std is the standard radiation; α1, α2, α3, α4 represent the environmental weight coefficients.

[0170] The system further adjusts the priority and intensity of maintenance tasks according to the equipment health status H(t) and environmental pressure ∈(t). Maintenance priority P maint (t):

[0171]

[0172] Among them, P maint (t) represents the maintenance task priority; δ represents the environmental correction coefficient, which reflects the impact of environmental pressure on the priority; H(t) represents the current health status of the equipment.

[0173] Maintenance intensity S maint (t):

[0174]

[0175] Among them, S0 represents the initial maintenance intensity; λ represents the environmental correction coefficient, which reflects the impact of environmental pressure on maintenance intensity.

[0176] Furthermore, according to the optimization result, the system outputs a maintenance signal S maint (t), used to perform actual maintenance operations and record maintenance results.

[0177]

[0178] This signal feedback is used to optimize subsequent maintenance cycles.

[0179] Specifically, the adaptive learning of the system's operational feedback and the optimization of the maintenance strategy are analyzed as follows:

[0180] According to the maintenance signal S maint (t), combined with the equipment health status H(t) and the environmental correction term ∈(t), constitutes the feedback data set:

[0181]

[0182] Among them, H(t) represents the current health status of the device, and its value range is [0,1], where 1 indicates that the device is healthy and 0 indicates that the device is close to failure; Indicates the adjusted maintenance cycle; P maint (t) indicates the current maintenance priority; S maint (t) represents the maintenance intensity, which indicates the resource input for current maintenance; ∈(t) represents the environmental pressure correction term, which reflects the impact of high altitude environment on equipment degradation. These feedback data are the core input of system optimization learning and are used for subsequent maintenance strategy adjustments.

[0183] Furthermore, the system uses the maintenance effect evaluation function E maint(t) to quantify the improvement in equipment health caused by each maintenance and adjust it with the environmental pressure correction term:

[0184]

[0185] Among them, H(t+Δt) represents the health status of the equipment after maintenance; S maint (t) represents the current maintenance intensity; α represents the weight coefficient, which indicates the influence of environmental pressure on the maintenance effect; ∈(t) represents the environmental correction term, which is used to reflect the influence of the external environment on equipment degradation.

[0186] This formula is used to evaluate the efficiency of maintenance operations and ensure that maintenance in high altitude environments can offset the effects of environmental pressure. maint (t) to determine whether the maintenance has achieved the expected effect.

[0187] Furthermore, the system uses a dynamic adaptive learning model (DALM) to calculate the historical maintenance effect E maint (t) Adjust the maintenance cycle and intensity. The adaptive maintenance cycle adjustment formula is:

[0188]

[0189] in, Indicates the optimal cycle for the next maintenance; represents the adjustment period after the current maintenance; κ represents the learning rate, which controls the adjustment range of the period; E maint (t) represents the current maintenance effect evaluation; E target Indicates the expected maintenance effect.

[0190] When E maint (t) greater than E target When , it indicates that the maintenance effect is good and the system can extend the maintenance cycle; otherwise, shorten the cycle.

[0191] The maintenance intensity adjustment formula is:

[0192]

[0193] in, It represents the optimal intensity of the next maintenance; μ represents the learning step size, which controls the intensity adjustment amplitude.

[0194] When the maintenance effect is lower than expected, the system will increase the maintenance intensity; when the maintenance effect is higher than expected, the maintenance intensity will be reduced to save resources.

[0195] Furthermore, in order to cope with the special impact of high altitude environment on equipment health, the present invention introduces a special environment regularization term λ env(t), which is used to smooth out drastic changes in health status and avoid misjudgments caused by short-term environmental fluctuations.

[0196]

[0197] Among them, λ env (t) represents the special environment regularization term; β i Indicates the weight coefficient of environmental factors, reflecting the impact of different environmental factors; The second-order derivative of the health status of the equipment reflects the accelerated change of the health status. This regularization term is used to smooth the drastic changes in the health status and avoid misjudgment and excessive maintenance caused by short-term environmental fluctuations.

[0198] Finally, through the global optimization model G(t), the system achieves a balance between maintenance cost, equipment health, and environmental pressure in the long term. The global optimization objective function is:

[0199]

[0200] Among them, C maint (t) represents the maintenance cost, which varies with the maintenance intensity S maint (t) increases; λ represents the health state loss weight, reflecting the impact of the health state on the long-term benefits of the system; λ env (t) represents the special environment regularization term, which is used to smooth the impact of environmental fluctuations on the health status. This global optimization model ensures the optimal maintenance strategy and energy utilization efficiency in harsh environments by considering the system's operating cost and health management in the long term.

[0201] Unless otherwise specifically stated, the relative steps, numerical expressions and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present application.

[0202] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0203] In the description of the present application, it should be noted that the terms "upper", "lower", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or the orientations or positional relationships in which the inventive product is usually placed when in use. These are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0204] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0205] 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 replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A high altitude energy storage monitoring system, characterized in that: The system includes: an environmental data acquisition module, an intelligent temperature control analysis module, an intelligent energy scheduling module, a health monitoring module, an adaptive adjustment module and a system optimization module; wherein, The environmental data acquisition module is used to adaptively and dynamically collect environmental parameters in a high-altitude environment using a multi-dimensional sensor network, and pre-process them in an edge computing unit to obtain an environmental parameter data set; The intelligent temperature control analysis module is used to generate a temperature control signal based on the environmental parameter data set analysis to determine whether the energy storage device needs temperature control intervention; the temperature control signal includes a heating signal and a cooling signal; The intelligent energy scheduling module is used to optimize energy allocation according to the temperature control signal transmitted by the intelligent temperature control analysis module and in combination with the power demand of the energy storage device and the external environment data; The health monitoring module is used to perform health analysis in advance based on monitoring real-time power data and environmental feedback and through intelligent prediction algorithms; The adaptive adjustment module is used to receive the health analysis results of the health monitoring module and dynamically adjust the maintenance strategy of the energy storage device in combination with environmental factors; The system optimization module is used to adaptively learn the system's operational feedback and optimize the maintenance strategy; The specific analysis process of judging whether the energy storage device needs temperature control intervention according to the environmental parameter data set is as follows: Performing basic temperature control determination on the environmental parameter data set acquired by the environmental data acquisition module according to the battery operating temperature range of the energy storage device; The pressure correction factor, humidity correction term and solar radiation correction term are introduced to correct the battery operating temperature range and obtain the final temperature control judgment condition; The basic temperature control judgment is compared with the final temperature control judgment result. If the basic temperature control judgment is less than the minimum value of the final temperature control judgment result, a heating signal is generated. If the basic temperature control judgment is greater than the maximum value of the final temperature control judgment result, a cooling signal is generated.

2. A high altitude energy storage monitoring system according to claim 1, characterized in that: The multidimensional data includes temperature, air pressure, humidity and solar radiation; the adaptive dynamic acquisition is that the sampling frequency is dynamically adjusted according to the change rate of the environmental parameters, which is expressed as follows: Among them, f i (t) is the sampling frequency, f0 is the basic sampling frequency; α is the adjustment coefficient, which controls the increase of the sampling frequency with the rate of change; is the environmental parameter X i,j (t) The rate of change at time t, that is, 3. A high altitude energy storage monitoring system according to claim 1, characterized in that: The battery operating temperature range of the energy storage device is set to [T min ,T max ]; The air pressure correction coefficient is expressed as follows: in, is the minimum value of the pressure correction factor. is the maximum value of the pressure correction factor, β(t is the pressure correction factor, which reflects the effect of pressure on heat dissipation efficiency and is defined as γ is the pressure-temperature correction factor, which is used to adjust the effect of pressure changes on the temperature range; is the current air pressure, P std is the standard atmospheric pressure; Wherein, the air pressure correction coefficient enables the temperature control operation to be triggered in advance when the air pressure is lower than the standard air pressure; The humidity correction term α H (t) and the solar radiation correction term α R (t), expressed as follows: in, is the humidity correction to the temperature threshold, δ H is the humidity-temperature correction factor, H std is the standard humidity, is the current humidity; is the correction of the temperature control threshold by solar radiation, δ R is the radiation correction factor, R std is the standard solar radiation value, is the current solar radiation value; is the minimum value of the final temperature threshold, is the maximum value of the final temperature threshold.

4. A high altitude energy storage monitoring system according to claim 1, characterized in that: The energy is optimally allocated according to the temperature control signal transmitted by the intelligent temperature control analysis module and combined with the power demand of the energy storage device and the external environment data. The specific analysis process is as follows: The total power demand of the set system is composed of the external load and the temperature control power demand; The effective available power of the system is defined to represent the remaining power that the energy storage device can provide at the current moment. Then, a dynamic energy allocation strategy is designed to adjust the power allocation of the temperature control device in real time to maximize energy utilization, that is, to minimize the remaining power that the energy storage device can provide and the temperature control power demand, which is determined by environmental factors and temperature control signals. An environmental feedback correction mechanism is introduced for high-altitude environments to dynamically adjust the power output of the temperature control equipment according to the dramatic fluctuations in environmental parameters. At the same time, an energy scheduling optimization algorithm is designed based on the adjusted power output to minimize the power loss of the energy storage equipment and ensure the normal operation of the temperature control equipment. The final temperature control power output by the energy scheduling optimization algorithm is executed in combination with the temperature control signal.

5. A high altitude energy storage monitoring system according to claim 4, characterized in that: The environmental feedback correction mechanism is the temperature control power after correction Add the environmental correction factor, expressed as follows: P temp (t)'=P temp (t)·(1+θ(t)) Among them, P temp (t)' is the power required for heating or cooling in the temperature control device, θ(t) is the environmental correction factor, which reflects the impact of environmental factors on the temperature control power; the environmental correction factor θ(t) is calculated as follows: Where κ is the temperature correction coefficient, which is used to adjust the difference between the ambient temperature and the set target temperature; is the ambient temperature, T set is the target temperature of the battery; λ is the air pressure correction factor, which is used to adjust the effect of air pressure on power demand; is the current air pressure, P std is the standard atmospheric pressure; The energy scheduling optimization algorithm is expressed as follows: in, is the final temperature control power; When Heating(t) is true, the heating power is executed When Cooling(t) is true, the cooling power is executed 6. A high altitude energy storage monitoring system according to claim 1, characterized in that: According to the monitoring of real-time power data and environmental feedback, and through the intelligent prediction algorithm, health analysis is performed in advance. The specific analysis process is as follows: According to the status signal obtained by the intelligent energy scheduling module, the status signal includes the total power output, the available power, and the power consumption of the temperature control device, combined with the environmental data set, to form an operation data set, and the operation data set is monitored in real time; Build an adaptive health status prediction model, using historical operation data sets and real-time operation data sets as input to predict the health of energy storage equipment; Set a health threshold and determine whether the equipment has entered a high-risk zone for failure based on the predicted health status. If the health status is lower than the health threshold, the equipment will enter the accelerated degradation stage and will soon fail. Then, based on the changing trend of the health status, design a dynamic maintenance optimization model and dynamically adjust the maintenance strategy based on the current health status and environmental pressure. Finally, the system generates maintenance signals based on health status prediction, fault assessment, and maintenance optimization results.

7. A high altitude energy storage monitoring system according to claim 6, characterized in that: The adaptive health status prediction model processes time series data through a long short-term memory network to predict future health status, which is expressed as follows: H(t)=LSTM(M(t-Δt,t),∈(t)) Where H(t) represents the health status of the system at time t, with a value range of [0,1], 1 represents health, and 0 represents failure; ∈(t) is an environmental correction term, which is used to dynamically adjust health prediction; LSTM is a long short-term memory network for processing time series data; where the environmental correction term ∈(t) is expressed as follows: Among them, T opt is the optimal operating temperature of the battery, P std is the standard atmospheric pressure; H std is the standard humidity, R std is the standard radiation value; α1, α2, α3, α4 are correction coefficients, reflecting the weight of the impact of different environmental factors on the battery health status; The dynamic maintenance optimization model is used to adjust the maintenance cycle, which is expressed as follows: Where T0 is the initial maintenance cycle; β is the adjustment coefficient based on the decline in equipment health; γ is the adjustment coefficient based on the environmental correction term ∈(t); H init Is the initial health status of the device.

8. A high altitude energy storage monitoring system according to claim 7, characterized in that: The health analysis result of the health monitoring module is received, and the maintenance strategy of the energy storage device is dynamically adjusted in combination with environmental factors. The specific analysis process is as follows: When the health status is lower than the threshold, maintenance is triggered immediately, and the adaptive maintenance strategy optimization model is used to dynamically adjust the maintenance cycle according to the health status and environmental correction items. At the same time, the priority and intensity of the maintenance task are adjusted according to the health status of the equipment and the environmental pressure. The final maintenance strategy is output, executed, and the maintenance signal is output.

9. A high altitude energy storage monitoring system according to claim 8, characterized in that: The adaptive maintenance strategy optimization model is expressed as follows: Where T0 is the initial maintenance period; H init is the initial health state of the equipment; β reflects the impact of changes in health state on the maintenance cycle; γ is the environmental correction coefficient, which adjusts the maintenance cycle in combination with environmental pressure; ∈(t) is the environmental correction term; The priority and intensity of maintenance tasks are adjusted according to the health status of the equipment and the environmental pressure, as shown below: Among them, P maint (t) is the maintenance task priority; δ is the environmental correction factor, which reflects the impact of environmental pressure on the priority; H(t is the current health status of the equipment; Among them, S maint (t) is the maintenance intensity, S0 is the initial maintenance intensity; λ is the environmental correction coefficient, which reflects the impact of environmental pressure on maintenance intensity.

10. A high altitude energy storage monitoring system according to claim 1, characterized in that: The adaptive learning of the system's operational feedback and the optimization of the maintenance strategy are carried out. The specific analysis process is as follows: Based on the equipment feedback data, a maintenance effect evaluation function is designed to quantify the improvement of equipment health caused by each maintenance, and it is adjusted in combination with the environmental pressure correction term. A dynamic adaptive learning model is designed to adjust the maintenance cycle and intensity according to the historical maintenance effect. In order to cope with the special impact of high-altitude environment on device health, a special environment regularization term is introduced to smooth out drastic changes in health status and avoid misjudgment caused by short-term environmental fluctuations; Finally, a global optimization model is designed to achieve a balance between maintenance costs, equipment health, and environmental pressure in the long term. Wherein, the maintenance effect evaluation function is expressed as follows: Among them, H(t+Δt) is the health status of the equipment after maintenance; S maint (t) is the current maintenance intensity; α is the weight coefficient, which represents the impact of environmental pressure on maintenance effect; ∈(t) is the environmental correction term, which is used to reflect the impact of the external environment on equipment degradation.

Images