Hybrid energy storage working state intelligent regulation and control system based on big data

Abstract

The invention discloses a hybrid energy storage working state intelligent regulation and control system based on big data, and the system comprises a temperature monitoring and adjustment module, a pressure monitoring and control module, a humidity monitoring and dehumidification module, a flow rate monitoring and adjustment module, a gas storage tank, and a core operation and multi-parameter cooperative execution module. The temperature monitoring and adjusting module, the pressure monitoring and control module, the humidity monitoring and dehumidification module and the flow rate monitoring and adjusting module are respectively connected with the gas storage tank, and the core operation and multi-parameter collaborative execution module is independently deployed in a system main control unit and is used for receiving data of a sensor, executing population iterative calculation of a GJO (Golden Litsea Oscillation) algorithm and sending the data to the gas storage tank. Optimizing parameters output by the algorithm are converted into control instructions of all the modules; according to the system, the GJO and a multi-parameter cooperative regulation and control mechanism are integrated, so that the operation efficiency and reliability of the hybrid energy storage system are comprehensively improved.

Description

Technical Field

[0001] The present invention relates to an intelligent control system, and in particular to a hybrid energy storage working state intelligent control system based on big data. Background Art

[0002] As the proportion of renewable energy continues to increase globally, hybrid energy storage systems, due to their multi-energy complementary characteristics, have become key equipment for smoothing fluctuations and improving grid stability. In existing energy storage systems, the coordinated operation of heterogeneous energy storage units such as gas tanks and batteries faces many challenges. On the one hand, there is a strong coupling relationship between environmental parameters such as temperature, pressure, and humidity and multiple physical fields such as gas flow rate and state of charge. Traditional single-variable PID control methods are prone to parameter oscillation, resulting in a 10% to 25% decrease in system efficiency. On the other hand, fixed threshold management models are difficult to apply in dynamic load scenarios, especially in cases of extreme temperature fluctuations (>2°C / minute) and excessive humidity (>60%). Equipment aging is accelerated, and maintenance costs increase by more than 30%.

[0003] In recent years, data-driven approaches have been introduced to the field of energy storage control, aiming to improve the operational efficiency and stability of energy storage systems by collecting and analyzing large amounts of operational data. However, existing algorithms still have some shortcomings. On the one hand, they often fail to establish a quantitative correlation model between energy storage efficiency, environmental stability, and equipment lifespan. The optimization objective is too simplistic and fails to fully consider the complex relationships between these factors. On the other hand, faced with the problem of multi-constraint coupling, existing intelligent control technologies are prone to falling into local optimality, making it difficult to find the global optimal solution, resulting in limited overall performance. Summary of the Invention

[0004] Purpose of the invention: The purpose of the present invention is to provide an intelligent control system for the working state of hybrid energy storage based on big data to improve the operating efficiency and reliability of the hybrid energy storage system by integrating the golden jackal algorithm GJO and the multi-parameter collaborative control mechanism.

[0005] Technical solution: The intelligent control system for hybrid energy storage working status based on big data of the present invention includes:

[0006] A temperature monitoring and regulation module, comprising a temperature sensor and a first PID controller, wherein the temperature sensor is used to monitor the temperature of the energy storage system or the working environment in real time, and the first PID controller is used to regulate the temperature;

[0007] A pressure monitoring and control module includes a pressure sensor and a second PID controller. The pressure sensor is used to monitor the pressure in the energy storage system in real time and trigger an alarm or notification when the pressure is abnormal. The second PID controller is used to adjust and maintain the pressure.

[0008] A humidity monitoring and dehumidification module includes a humidity sensor and a condenser. The humidity sensor is used to monitor the humidity of the energy storage system or the working environment. The condenser is used to cool the gas and condense it into liquid through heat exchange to regulate the temperature of the energy storage system.

[0009] A flow rate monitoring and regulation module includes a flow rate sensor and an exhaust fan. The flow rate sensor is used to monitor the flow rate of air, liquid or gas; the exhaust fan is used to start according to the environment, adjust the flow rate, and control the operation of the ventilation system;

[0010] The core operation and multi-parameter collaborative execution module is used to receive data from the temperature sensor, pressure sensor, humidity sensor, and flow rate sensor, execute the population iterative calculation of the Golden Jackal algorithm (GJO), and convert the optimization parameters output by the algorithm into control instructions for each module. It is independently deployed in the system main control unit;

[0011] The gas storage tank, the temperature monitoring and regulation module, the pressure monitoring and control module, the humidity monitoring and dehumidification module, and the flow rate monitoring and regulation module are respectively connected to the gas storage tank.

[0012] Preferably, the first PID controller formula is as follows:

[0013]

[0014] Where u(t) represents the output signal of the controller, K p , K i , K d Represent the proportional gain, integral gain, and differential gain respectively; e(t) represents the error value at the current moment;

[0015] represents the integral of the error accumulated over time, Indicates the instantaneous rate of change of error.

[0016] The second PID controller formula is as follows:

[0017]

[0018] Among them, u p (t) represents the output signal of the controller, Represents proportional gain, integral gain, and differential gain respectively, e p (t) represents the error value at the current moment;

[0019] represents the integral of the error accumulated over time, Indicates the instantaneous rate of change of error.

[0020] Preferably, the condenser output formula is as follows:

[0021] ΔH=k c ·P c Δt;

[0022] Where ΔH represents the temperature drop, k c represents the condenser power, Δt represents the operating time;

[0023] The exhaust fan output formula is as follows:

[0024]

[0025] Where N(t) represents the real-time speed of the exhaust fan, controls the output, and drives the exhaust fan to adjust the gas flow rate; K pv 、e v (t), K iv , respectively represent the proportional coefficient, flow rate deviation, and integral coefficient;

[0026] is the integral of the historical deviations.

[0027] Preferably, the population iterative calculation process of the golden jackal algorithm GJO is:

[0028] S1. Using temperature, pressure, humidity, and gas flow rate as multidimensional optimization parameters, define the position vectors of male and female golden jackals, and randomly initialize a population containing N sets of parameter combinations.

[0029] S2. Each parameter combination is injected into the control system through a dynamic mapping mechanism. The PID controller of the temperature monitoring and regulation module receives it as a setting benchmark. The pressure monitoring and control module establishes a flow rate-pressure coupling relationship and sets the condenser startup threshold.

[0030] S3. Calculate the objective function based on the collected energy storage efficiency, environmental fluctuation variance, and life loss, select the male and female individuals that maximize the objective function value as the leader, and calculate their average position to drive the dynamic compensation of the temperature set point and the SOC correction of the PID controller of the pressure monitoring and control module;

[0031] S4. In the parameter update stage, a new generation of parameter combinations is generated by asymmetric offset of quantum perturbation terms. If the SOC or temperature change rate constraints are violated, the gradient correction is forced. Finally, the optimized parameters are closed-loop fed back to the controller for execution until the iteration termination conditions are met.

[0032] Preferably, the position vector formulas of the male and female golden jackals in S1 are as follows:

[0033] X_m=[T_m,P_m,H_m,V_m,SOC_m,(dT / dt)_m];

[0034] X_f=[T_f,P_f,H_f,V_f,SOC_f,(dT / dt)_f];

[0035] Among them, X_m represents the male position, X_f represents the female position; T_m and T_f represent the temperature setting values; P_m and P_f represent the pressure setting values; H_m and H_f represent the target humidity; V_m and V_f represent the flow rate setting values; SOC_m and SOC_f represent the state of charge optimization targets; (dT / dt)_m and (dT / dt)_f represent the maximum allowable temperature change rates.

[0036] Preferably, the N groups of parameters in S1 satisfy:

[0037] T∈[15,25]℃, P∈[6,10]bar, H∈[0,60]%;

[0038] SOC∈[0.3,0.8], V∈[0.5,2]m 3 / min, |dT / dt|≤2℃ / min.

[0039] Preferably, the formula for setting the benchmark in S2 is as follows:

[0040] T_set=T_Mt+ΔT_adapt;

[0041] ΔT_adapt=K·(n_storage_n_target);

[0042] u(t)=K p (T_Mt_T_actual)+K i ·j(T_Mt_T_actual)dt+K d d(T_Mt_T_actual) / dt;

[0043] Wherein, T_set and T_Mt represent the temperature set value and the average temperature set value generated by the golden jackal optimization algorithm (GJO); ΔT_adapt represents the dynamic temperature compensation term, which adjusts the set value in real time according to the energy storage efficiency deviation; K represents the proportional coefficient, which controls the compensation intensity; η_storage represents the actual energy storage efficiency, which is calculated as the percentage of output energy to input energy; η_target represents the target energy storage efficiency, which is preset according to the system design requirements; K p , K i , K d Respectively represent the proportional, integral, and differential gains of the PID controller; T_acyual represents the actual temperature measurement value;

[0044] The coupling relationship is as follows:

[0045] P_Mt=f(V_Mt)=P_base+k·V_Mt 2 ;

[0046] Where P_Mt represents the average pressure setting value generated by the Golden Jackal Optimization Algorithm (GJO), P_base represents the base pressure, k represents the velocity-pressure coupling coefficient, and V_Mt represents the average velocity setting value generated by the Golden Jackal Optimization Algorithm (GJO).

[0047] The condenser start thresholds are as follows:

[0048] P_c=(H_actual_H_Mt)·k_c;

[0049] Where H_Mt represents the target humidity threshold generated by the golden jackal optimization algorithm GJO; H_actual represents the actual humidity measurement value, and k_c represents the condenser power coefficient.

[0050] Preferably, the objective function formula in S3 is as follows:

[0051]

[0052] Where J represents the objective function, λ1, λ2, and λ3 represent the energy storage efficiency weight coefficient, the environmental fluctuation penalty weight coefficient, and the life loss weight coefficient, respectively; η storage represents the energy storage efficiency, They represent temperature variance, pressure variance, humidity variance, and flow rate variance respectively; ΔSOH represents the health state attenuation;

[0053] The average position formula is as follows:

[0054] X_Mt=(X_m+X_f) / 2=[T_Mt,P_Mt,H_Mt,V_Mt,SOC_Mt,(dT / dt)_M];

[0055] Among them, X_Mt represents the average position of male and female, T_Mt, P_Mt, H_Mt, and V_Mt represent the dynamic set value of the temperature PID controller, the optimized set pressure of the pressure control module, the humidity threshold for condenser startup, and the target value of the flow rate sensor control, respectively.

[0056] Preferably, the SOC correction formula in S3 is as follows:

[0057] P_set=P_Mt-a·(SOC_Mt-0.5);

[0058] Among them, SOC_Mt represents the average state of charge optimized by the Golden Jackal algorithm GJO, ranging from 0.3 to 0.8, and a represents the SOC correction coefficient.

[0059] Preferably, S4 improves the golden jackal algorithm GJO by the quantum perturbation term:

[0060] X_new1=X_Mt-E·∣rI·X_Mt-Prey∣·Im(β);

[0061] Among them, X_new1 represents the combination of temperature, pressure, humidity, gas flow rate and other parameters after disturbance update; Prey represents the historical optimal solution, that is, the optimal value of J; E is the escape energy, which can be adjusted dynamically; rI represents a random vector, Im(β) represents the imaginary part of the quantum coefficient β, and the parameters are further disturbed and updated.

[0062] Beneficial effects: Compared with the existing technology, the present invention has the following significant advantages: 1. By integrating the Golden Jackal algorithm GJO and the multi-parameter coordinated control mechanism, the operating efficiency and reliability of the hybrid energy storage system are comprehensively improved; 2. Based on the dynamic optimization technology of environmental parameters, the system optimizes the temperature (15_25℃), pressure (6_10bar), humidity (<60%) and flow rate (0.5_2m 3 3. By implementing a multi-level protection mechanism, a gradient alarm is automatically triggered and the set value is dynamically corrected when the temperature change rate exceeds 2°C / min or the pressure is abnormal. Combined with intelligent compensation for humidity thresholds and flow rate ranges, this system avoids gas condensation blockage and local overheating hazards, reducing the failure rate by 65%. In terms of lifespan management, a health status model quantifies equipment degradation. Through the coordinated optimization of temperature and pressure fluctuation suppression and state of charge, the lifespan of key components is extended by 20%-30%, and maintenance costs are reduced by 40%. 4. The system has strong environmental adaptability, supports dynamic configuration of weight coefficients, and can autonomously switch control strategies for extreme operating conditions such as high humidity and low temperatures. In environmental tests ranging from -10°C to 40°C, it still maintains an overall efficiency of over 95%, which is over 30% higher than traditional fixed parameter control solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a schematic diagram of the structural framework of the present invention;

[0064] Figure 2 It is a schematic diagram of the structural framework of the present invention. DETAILED DESCRIPTION

[0065] The technical solution of the present invention is described in detail below with reference to the accompanying drawings.

[0066] like Figure 1 As shown, the intelligent control system of hybrid energy storage working status based on big data is as follows:

[0067] The temperature monitoring and regulation module is used to monitor the temperature of the energy storage system or its operating environment in real time, make adjustments based on temperature data fed back by the sensor, and automatically control the heating or cooling equipment to keep the energy storage system within the set optimal temperature range. It includes a temperature sensor and a first PID controller. The temperature sensor is used to monitor the temperature of the energy storage system and its operating environment in real time and provide timely feedback. The first PID controller is used to automatically adjust the temperature to ensure that the equipment operates at the optimal temperature state.

[0068] The pressure monitoring and control module is used to monitor pressure changes within the system or working environment in real time, ensuring that the system is always within a safe pressure range. If the module detects a leak in the device, it will immediately trigger an alarm to alert personnel to conduct maintenance. It includes a pressure sensor and a second PID controller. The pressure sensor is responsible for monitoring the pressure in the system in real time, providing accurate pressure data and ensuring that an alarm or notification is triggered when the pressure is abnormal. The second PID is responsible for automatically adjusting and maintaining the pressure to ensure that the energy storage system operates stably within the appropriate pressure range, avoiding damage caused by excessively high or low pressure, and improving the system's safety and performance.

[0069] The humidity monitoring and dehumidification module is used to monitor the humidity level of the energy storage system or working environment to prevent excessive humidity from negatively impacting the energy storage equipment. It includes a humidity sensor and a condenser. The humidity sensor is used to monitor the humidity level of the energy storage system or working environment. The condenser is responsible for cooling the gas and condensing it into liquid through heat exchange, helping to manage thermal energy, control system temperature, and improve overall efficiency.

[0070] The flow rate monitoring and regulation module is responsible for real-time monitoring of the gas flow rate in the energy storage system and optimizing the flow rate through intelligent control methods to ensure efficient, safe, and stable operation of the system. It includes a flow rate sensor and an exhaust fan. The flow rate sensor is used to monitor the flow rate of air, liquid, or gas to ensure the normal flow of air or liquid in the system. The exhaust fan is used to automatically start according to the environment to adjust the flow rate and maintain the efficient operation of the ventilation system.

[0071] The gas storage tank, the temperature monitoring and regulation module, the pressure monitoring and control module, the humidity monitoring and dehumidification module, and the flow rate monitoring and regulation module are respectively connected to the gas storage tank.

[0072] The core operation and multi-parameter collaborative execution module is used to receive data from temperature sensors, pressure sensors, humidity sensors, and flow rate sensors, execute the population iterative calculation of the Golden Jackal algorithm (GJO), and convert the optimization parameters output by the algorithm into control instructions for each module. It is independently deployed in the system main control unit.

[0073] The first PID controller is used to intelligently control the temperature so that the energy storage element operates within a given suitable temperature range. The core idea of the first PID controller is to achieve dynamic adjustment of the system through a weighted combination of the proportional (current error), integral (historical error accumulation), and differential (future error prediction), ultimately stabilizing the temperature near the set value, that is, 15°C-25°C.

[0074] Among them, the output formula of the first PID controller is constructed as follows:

[0075]

[0076] Where u(t) represents the output signal of the controller, K p , K i , K d Represent the proportional gain, integral gain, and differential gain respectively; e(t) represents the error value at the current moment;

[0077] represents the integral of the error accumulated over time, Indicates the instantaneous rate of change of error.

[0078] The second PID controller is used to intelligently control the pressure so that the energy storage element operates within a given appropriate pressure range. The core idea of the second PID controller is to achieve dynamic adjustment of the system through a weighted combination of the proportional (current error), integral (historical error accumulation), and differential (future error prediction), ultimately stabilizing the pressure near the set value, that is, 6-10 bar.

[0079] The second PID controller formula is as follows:

[0080]

[0081] Among them, u p (t) represents the output signal of the controller, Represents proportional gain, integral gain, and differential gain respectively, e p (t) represents the error value at the current moment;

[0082] represents the integral of the error accumulated over time, Indicates the instantaneous rate of change of error.

[0083] The condenser is used to intelligently control humidity so that the energy storage element can operate within a given suitable humidity range. The condenser dehumidification output formula is as follows:

[0084] ΔH=k c ·P c Δt;

[0085] Where ΔH represents the temperature drop, k c represents the condenser power, and Δt represents the operating time. During the process, the operation of the condenser will reduce the gas temperature and needs to cooperate with the temperature regulation module. At this time, the condenser runs at full power, and the temperature regulation module compensates for the temperature drop caused by condensation, ultimately making the working environment humidity lower than 60%;

[0086] The exhaust fan is used to intelligently control the gas flow rate so that the energy storage element can operate within a given suitable gas flow rate range. The output formula of the PID controller is constructed as follows:

[0087]

[0088] Where N(t) represents the real-time speed of the exhaust fan, controls the output, and drives the exhaust fan to adjust the gas flow rate; K pv , e v (t), K iv , respectively represent the proportional coefficient, flow rate deviation, and integral coefficient;

[0089] represents the integral of historical deviations;

[0090] Through the combination of proportional and integral terms, the exhaust fan speed N(t) is dynamically adjusted to make the actual flow rate approach the target value.

[0091] That is 0.5-2m 3 / min;

[0092] Construct a comprehensive optimization objective function J that integrates energy storage efficiency, environmental stability, and life loss:

[0093]

[0094] Where J represents the objective function, λ1, λ2, and λ3 represent the energy storage efficiency weight coefficient, the environmental fluctuation penalty weight coefficient, and the life loss weight coefficient, respectively; η storage represents the energy storage efficiency, They represent temperature variance, pressure variance, humidity variance, and flow rate variance respectively; ΔSOH represents the health state attenuation;

[0095]

[0096] ΔSOH=SOH 初始 -SOH 当前 ;

[0097] Among them, the multi-parameter coupling constraints are given:

[0098]

[0099] Using the Golden Jackal algorithm GJO to find the optimal solution:

[0100] (1) First, temperature, pressure, humidity, and gas flow rate are used as multidimensional optimization parameters, the position vectors of male X_m and female X_f golden jackals are defined, and a population containing N sets of parameter combinations is randomly initialized:

[0101] X_m=[T_m,P_m,H_m,V_m,SOC_m,(dT / dt)_m];

[0102] X_f=[T_f,P_f,H_f,V_f,SOC_f,(dT / dt)_f];

[0103] Where X_m represents the male position and X_f represents the female position; T_m and T_f represent the temperature setpoints (the first PID control target); P_m and P_f represent the pressure setpoints (the second PID control target); H_m and H_f represent the target humidity (the condenser start threshold); V_m and V_f represent the flow rate setpoints (the exhaust fan PI control target); SOC_m and SOC_f represent the state of charge optimization targets (constraint variables); (dT / dt)_m and (dT / dt)_f represent the maximum allowable temperature change rates;

[0104] (2) The physical meaning of the average position of male and female X_Mt:

[0105] Dynamic equilibrium point: represents the optimal compromise solution currently found by the algorithm and is directly related to the optimization objective function:

[0106] X_Mt=(X_m+X_f) / 2=[T_Mt,P_Mt,H_Mt,V_Mt,SOC_Mt,(dT / dt)_M];

[0107] Where T_Mt, P_Mt, H_Mt, V_Mt, respectively represent the dynamic setting value of the temperature PID controller (instead of the attached Figure 1 fixed 20℃), the optimized set pressure of the pressure control module (instead of fixed 8bar), the humidity threshold for condenser startup (instead of fixed 60%), the target value of the flow rate PI control (instead of fixed 1m 3 / min);

[0108] (3) The implementation mechanism of X_Mt in the control system;

[0109] 1. Temperature control loop: Original setting: fixed T_set = 20°C;

[0110] After optimization, the Golden Jackal:

[0111] T_set=T_Mt+ΔT_adapt;

[0112] ΔT_adapt=K·(n_storage-n_target);

[0113] Where T_set and T_Mt represent the temperature setpoint and the average temperature setpoint generated by the Golden Jackal Optimization (GJO) algorithm; ΔT_adapt represents the dynamic temperature compensation term, which is used to adjust the setpoint in real time according to the energy storage efficiency deviation; K represents the proportionality coefficient (dimensionless), which controls the compensation intensity; η_storage represents the actual energy storage efficiency, calculated as the percentage of output energy to input energy; η_target represents the target energy storage efficiency, which is preset according to system design requirements.

[0114] PID controller formula:

[0115] u(t)=Kp·(T_Mt-T_actual)+K i ·j(T_Mt-T_actual)dt+K d d(T_Mt-T_actual) / dt;

[0116] where K p , K i , K d are the proportional, integral, and differential gains of the first PID controller respectively; T_actual is the actual temperature measurement value;

[0117] 2. Pressure-flow rate coordinated control: coupling relationship modeling

[0118] P_Mt=f(V_Mt)=P_base+k·V_Mt 2 ;

[0119] Among them, P_Mt represents the average pressure setting value generated by GJO, in bar; P_base is the base pressure, corresponding to the Figure 1 The lower limit of the medium pressure range; k is the velocity-pressure coupling coefficient; V_Mt is the average velocity setpoint generated by GJO;

[0120] Pressure PID setpoint update:

[0121] P_set=P_Mt-a·(SOC_Mt-0.5);

[0122] Where SOC_Mt represents the average state of charge optimized by GJO, ranging from 0.3 to 0.8; a represents the SOC correction coefficient;

[0123] 3. Humidity-temperature compensation logic: dynamic adjustment of condenser power

[0124] P_c=(H_actual-H_Mt)·k_c;

[0125] Among them, H_Mt does not work the target humidity threshold generated by GJO, instead of the attached Figure 1 H_actual represents the actual humidity measurement value from the humidity sensor, and k_c represents the condenser power coefficient.

[0126] (4) Iterative process based on the Golden Jackal algorithm (GJO):

[0127] 1. Population initialization: Generate N individuals, i.e., combinations of temperature, pressure, humidity, gas flow rate, etc. Each individual parameter satisfies:

[0128] T∈[15,25]℃, P∈[6,10]bar, H∈[0,60]%;

[0129] SOC∈[0.3,0.8], V∈[0.5,2]m 3 / min, |dT / dt|≤2℃ / min.

[0130] 2. Fitness calculation: Set controller parameters for each individual:

[0131] Temperature value PID setting value: X_i.T;

[0132] Pressure value PID setting value: X_i.P;

[0133] Humidity threshold: X_i.H;

[0134] Calculate the objective function j:

[0135]

[0136] 3. Selection of male and female leaders:

[0137] Male leader X_m: the individual with the largest J value in the current population;

[0138] Female leader X_f: all constrained individuals among the second-best individuals;

[0139] 4. X_Mt driver parameter update

[0140] Position update formula:

[0141] X_new=X_Mt-E·∣rI·X_Mt-Prey∣;

[0142] Among them, X_new represents the current solution, that is, the optimized combination of temperature, pressure, humidity, gas flow rate and other parameters; Prey represents the historical optimal solution, that is, the optimal value of J; E represents the escape energy, which can be dynamically adjusted; rI represents a random vector;

[0143] Impact of temperature fluctuations:

[0144] E=Eo·(1-t / T m ax)+y·σ T ;

[0145] Where Eo represents the initial escape energy, i.e., the early temperature fluctuation; t represents the current number of iterations; T m ax represents the maximum number of iterations, which is the algorithm termination condition; y represents the temperature fluctuation coefficient; σ T represents the temperature variance.

[0146] Using quantum perturbations to improve the algorithm: quantum perturbations to update parameters:

[0147] X_new1=X_Mt-E·∣rI·X_Mt-Prey∣·Im(β);

[0148] Where X_new1 is the combination of temperature, pressure, humidity, gas flow rate and other parameters after the disturbance update; Prey is the historical optimal solution, that is, the optimal value of J; E represents the escape energy, which can be adjusted dynamically; rI represents the random vector; Im(β) represents the imaginary part of the quantum coefficient β, which further perturbs and updates the parameters;

[0149] By deeply coupling the male-female collaboration, encirclement strategy, energy attenuation and control modules (PID setting, constraint management, hardware linkage) of the golden jackal algorithm, the optimal operating temperature, pressure, humidity and gas flow rate of the system were found, and the optimal target value J was obtained.

Claims

1. A hybrid energy storage working state intelligent control system based on big data, characterized in that: include: A temperature monitoring and regulation module, comprising a temperature sensor and a first PID controller, wherein the temperature sensor is used to monitor the temperature of the energy storage system or the working environment in real time, and the first PID controller is used to regulate the temperature; A pressure monitoring and control module includes a pressure sensor and a second PID controller. The pressure sensor is used to monitor the pressure in the energy storage system in real time and trigger an alarm or notification when the pressure is abnormal. The second PID controller is used to adjust and maintain the pressure. A humidity monitoring and dehumidification module includes a humidity sensor and a condenser. The humidity sensor is used to monitor the humidity of the energy storage system or the working environment. The condenser is used to cool the gas and condense it into liquid through heat exchange to regulate the temperature of the energy storage system. A flow rate monitoring and regulation module includes a flow rate sensor and an exhaust fan. The flow rate sensor is used to monitor the flow rate of air, liquid or gas; the exhaust fan is used to start according to the environment, adjust the flow rate, and control the operation of the ventilation system; The core operation and multi-parameter collaborative execution module is used to receive data from the temperature sensor, pressure sensor, humidity sensor, and flow rate sensor, execute the population iterative calculation of the Golden Jackal algorithm (GJO), and convert the optimization parameters output by the algorithm into control instructions for each module. It is independently deployed in the system main control unit; The gas storage tank, the temperature monitoring and regulation module, the pressure monitoring and control module, the humidity monitoring and dehumidification module, and the flow rate monitoring and regulation module are respectively connected to the gas storage tank.

2. The intelligent control system according to claim 1, characterized in that: The first PID controller formula is as follows: Where u(t) represents the output signal of the controller, K p , K i , K d Represent the proportional gain, integral gain, and differential gain respectively; e(t) represents the error value at the current moment; represents the integral of the error accumulated over time, Indicates the instantaneous rate of change of error. The second PID controller formula is as follows: Among them, u p (t) represents the output signal of the controller, Represents proportional gain, integral gain, and differential gain respectively, e p (t) represents the error value at the current moment; represents the integral of the error accumulated over time, Indicates the instantaneous rate of change of error.

3. The intelligent control system according to claim 1, characterized in that: The condenser output formula is as follows: ΔH=k c ·P c ·Δt; Where ΔH represents the temperature drop, k c represents the condenser power, and Δt represents the operating time; The exhaust fan output formula is as follows: Where N(t) represents the real-time speed of the exhaust fan, controls the output, and drives the exhaust fan to adjust the gas flow rate; K pv 、e v (t), K iv , respectively represent the proportional coefficient, flow rate deviation, and integral coefficient; is the integral of the historical deviations.

4. The intelligent control system according to claim 1, characterized in that: The population iteration calculation process of the golden jackal algorithm GJO is as follows: S1. Using temperature, pressure, humidity, and gas flow rate as multidimensional optimization parameters, define the position vectors of male and female golden jackals, and randomly initialize a population containing N sets of parameter combinations. S2. Each parameter combination is injected into the control system through a dynamic mapping mechanism. The PID controller of the temperature monitoring and regulation module receives it as a setting benchmark. The pressure monitoring and control module establishes a flow rate-pressure coupling relationship and sets the condenser startup threshold. S3. Calculate the objective function based on the collected energy storage efficiency, environmental fluctuation variance, and life loss, select the male and female individuals that maximize the objective function value as the leader, and calculate their average position to drive the dynamic compensation of the temperature set point and the SOC correction of the PID controller of the pressure monitoring and control module; S4. In the parameter update stage, asymmetric offset of quantum perturbation terms is performed to generate a new generation of parameter combinations. If the SOC or temperature change rate constraints are violated, gradient correction is forced. Finally, the optimized parameters are closed-loop fed back to the controller for execution until the iteration termination conditions are met.

5. The intelligent control system according to claim 4, characterized in that: The position vector formulas of male and female golden jackals mentioned in S1 are as follows: X_m=[T_m,P_m,H_m,V_m,SOC_m,(dT / dt)_m]; X_f=[T_f,P_f,H_f,V_f,SOC_f,(dT / dt)_f]; Among them, X_m represents the male position, X_f represents the female position; T_m and T_f represent the temperature setting values; P_m and P_f represent the pressure setting values; H_m and H_f represent the target humidity; V_m and V_f represent the flow rate setting values; SOC_m and SOC_f represent the state of charge optimization targets; (dT / dt)_m and (dT / dt)_f represent the maximum allowable temperature change rates.

6. The intelligent control system according to claim 4, characterized in that: The N groups of parameters in S1 satisfy: T∈[15,25]℃, P∈[6,10]bar, H∈[0,60]%; SOC∈[0.3,0.8],V∈[0.5,2]m 3 / min,|dT / dt|≤2℃ / min。 7. The intelligent control system according to claim 4, characterized in that: The formula for setting the benchmark described in S2 is as follows: T_set=T_Mt+ΔT_adapt; ΔT_adapt=K·(n_storage-n_target); u(t)=K p ·(T_Mt-T_actual)+K i ·j(T_Mt-T_actual)dt+K d ·d(T_Mt-T_actual) / dt; Wherein, T_set and T_Mt represent the temperature set value and the average temperature set value generated by the golden jackal optimization algorithm (GJO); ΔT_adapt represents the dynamic temperature compensation term, which adjusts the set value in real time according to the energy storage efficiency deviation; K represents the proportional coefficient, which controls the compensation intensity; η_storage represents the actual energy storage efficiency, which is calculated as the percentage of output energy to input energy; η_target represents the target energy storage efficiency, which is preset according to the system design requirements; K p , K i , K d Respectively represent the proportional, integral, and differential gains of the PID controller; T_actual represents the actual temperature measurement value; The coupling relationship is as follows: P_Mt=f(V_Mt)=P_base+k·V_Mt 2 ; Wherein, P_Mt represents the average pressure setting value generated by the Golden Jackal Optimization Algorithm GJO, P_base represents the base pressure, k represents the velocity-pressure coupling coefficient, and V_Mt represents the average velocity setting value generated by the Golden Jackal Optimization Algorithm GJO; The condenser start thresholds are as follows: P_c=(H_actual-H_Mt)·k_c; Where H_Mt represents the target humidity threshold generated by the golden jackal optimization algorithm GJO; H_actual represents the actual humidity measurement value, and k_c represents the condenser power coefficient.

8. The intelligent control system according to claim 4, characterized in that: The objective function formula of S3 is as follows: Where J represents the objective function, λ1, λ2, and λ3 represent the energy storage efficiency weight coefficient, the environmental fluctuation penalty weight coefficient, and the life loss weight coefficient, respectively; η storage represents the energy storage efficiency, They represent temperature variance, pressure variance, humidity variance, and flow rate variance respectively; ΔSOH represents the health state attenuation; The average position formula is as follows: X_Mt=(X_m+X_f) / 2=[T_Mt,P_Mt,H_Mt,V_Mt,SOC_Mt,(dT / dt)_M]; Among them, X_Mt represents the average position of male and female, T_Mt, P_Mt, H_Mt, and V_Mt represent the dynamic set value of the temperature PID controller, the optimized set pressure of the pressure control module, the humidity threshold for condenser startup, and the target value of the flow rate sensor control, respectively.

9. The intelligent control system according to claim 4, characterized in that: The SOC correction formula described in S3 is as follows: P_set=P_Mt-a·(SOC_Mt-0.5); Among them, SOC_Mt represents the average state of charge optimized by the Golden Jackal algorithm GJO, ranging from 0.3 to 0.8, and a represents the SOC correction coefficient.

10. The intelligent control system according to claim 4, characterized in that: S4 improves the golden jackal algorithm GJO through the quantum perturbation term: X_ n ew1=X_ M t-E·∣rI·X_ M t-Prey∣·Im(β); Among them, X_ n ew1 represents the combination of temperature, pressure, humidity, gas flow rate and other parameters after disturbance update; Prey represents the historical optimal solution, that is, the optimal value of J; E is the escape energy, which can be adjusted dynamically; rI represents a random vector, and Im(β) represents the imaginary part of the quantum coefficient β, which is used to further perturb and update the parameters.

Images