A military battery operation adjusting system based on extreme environment identification detection

Abstract

The application discloses a kind of based on extreme environment identification detection's military battery operation adjustment system, it is related to military power management technical field, the system includes: environment perception module, environment identification and decision module, thermal management execution module and battery management module;Environment perception module is used to real-time collection temperature, humidity, wind speed, dust concentration and solar radiation intensity etc.environmental data;Environment identification and decision module adopts BP neural network and fuzzy control logic to identify and classify working condition state, and joint PID regulation algorithm output control strategy;Thermal management execution module realizes heating, heat dissipation and sand prevention operation according to instruction;Battery management module dynamically adjusts charge-discharge strategy according to identification state.The application can realize the adaptive adjustment of battery temperature and energy management under extreme working condition, improve system stability and life, applicable to desert and other high temperature, low temperature, strong wind sand, high radiation and other severe environments battery management.

Description

Technical Field

[0001] This invention relates to the field of military power management technology, and in particular to a military battery operation regulation system based on extreme environment identification and detection. Background Technology

[0002] With the widespread deployment of military equipment in complex field environments, higher demands are placed on the operational reliability of battery systems in extreme environments such as high temperature, extreme cold, sandstorms, and radiation. As the core energy source of equipment, the performance of batteries directly affects the system's continuous combat capability and safety.

[0003] Existing military battery systems generally lack the ability to actively sense and intelligently adjust to the external environment, relying primarily on preset thresholds and passive response strategies. In situations involving drastic temperature changes between day and night or sudden sandstorms, traditional systems exhibit sluggish response and poor adjustment precision, easily leading to problems such as battery overheating, low-temperature start-up failure, overcharging and discharging, and system lifespan degradation. Furthermore, existing thermal management systems mostly employ fixed air-cooling / heating methods, making it difficult to adapt to multi-factor nonlinear disturbances and dynamic operating condition changes.

[0004] To address the aforementioned issues, this invention provides a military battery operation regulation system based on extreme environment identification and detection. Through multi-sensor fusion, neural network classification and recognition, fuzzy logic reasoning, and PID fine-tuning, it achieves closed-loop control of the entire process from environmental perception and intelligent judgment to strategy output and feedback execution. It possesses high adaptability and strong environmental adaptability, and is particularly suitable for the safe and stable operation of battery systems under extreme conditions such as deserts. Summary of the Invention

[0005] To address the above problems, this invention provides a military battery operation adjustment system based on extreme environment identification and detection, which solves the problems of slow response, poor temperature control accuracy, crude energy consumption management, and lack of intelligent adaptive adjustment capability in existing technologies under extreme environments.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a military battery operation adjustment system based on extreme environment identification and detection, comprising the following modules:

[0007] The environmental sensing module is used to collect environmental parameter information, including temperature, humidity, wind speed, dust concentration and solar radiation intensity, and to filter and limit the collected raw signals before outputting them to the next level module.

[0008] The environment identification and decision-making module is used to receive the information output by the environment perception module, identify and classify the environmental state based on the BP neural network and fuzzy logic algorithm, and output targeted adjustment strategies and control commands in combination with the fuzzy adaptive PID control algorithm.

[0009] a thermal management execution module for executing heat dissipation, heating or heat storage operation of the battery according to the control command output by the environment identification and decision module, the thermal management execution module comprising a fan, a heat pipe, a PTC resistance wire, a Peltier thermoelectric module and a phase change heat storage material;

[0010] a battery management module for dynamically adjusting a charging and discharging current, a voltage parameter and a safety protection strategy according to the state synchronization information of the environment identification and decision module and the state feedback of the thermal management execution module, and feeding back battery state information.

[0011] The environment perception module is composed of a plurality of environment sensors, including temperature sensors, humidity sensors, air pressure sensors, wind speed / wind direction sensors, dust concentration sensors and solar radiation intensity sensors; the temperature sensors are respectively installed inside the battery pack and outside the shell, for detecting the temperature of the battery cell and the surrounding environment in real time; the humidity and dust sensors are installed at the air inlet of the device, for monitoring the dryness degree and suspended particle concentration in the air; the radiation sensor is placed on the top of the battery shell, for collecting solar radiation intensity data;

[0012] Each sensor collects environmental parameters in real time and outputs an electrical signal; the temperature sensor measures the temperature of the environment and the battery cell; the humidity sensor monitors the air dryness; the wind speed sensor measures the wind speed; the dust sensor detects the concentration of sand and dust in the air based on the laser scattering principle, to cope with the sudden high wind speed and corrosive dust extreme factors in the desert; the radiation sensor collects the intensity of direct sunlight;

[0013] The environment perception module mainly performs signal preprocessing, including denoising filtering and amplitude limiting protection, and uses Kalman filtering to filter the sensor signals and eliminate transient impact and noise disturbance; for high-frequency interference signals such as wind and sand, simple threshold and fuzzy filtering are used to judge sudden events; the environment perception module does not directly output control commands, but inputs the processed environmental information as a perception result into the environment identification module; the module transmits the monitored temperature, humidity, wind speed, dust and radiation information to the environment identification and decision module through a data bus, forming a "perception→identification" path of the system.

[0014] The environment identification and decision module is composed of an embedded controller and its matching storage unit and communication interface; the controller is installed in a sealed aluminum alloy shell inside the battery system cabinet, the shell is filled with thermal insulation material and equipped with cooling fins to adapt to an environment of-40℃~+70℃; the controller is connected with the environment perception module, the thermal management execution module and the battery management module through CAN / LIN bus, can collect and process sensor data at high speed, and issue control commands;

[0015] The environment recognition and decision module comprehensively analyzes data from the environment perception module, recognizes the current environment condition using multi-sensor data fusion and artificial intelligence algorithm, classifies and predicts the collected temperature, humidity, wind speed, dust concentration and radiation intensity features using a BP neural network, and determines whether the current situation is "extremely hot during the day", "extremely cold at night", or "sandstorm approaching"; meanwhile, the uncertainty of the sensor data is processed by fuzzy logic, and a qualitative judgment of the current environment is obtained through fuzzy reasoning;

[0016] The environment recognition module issues corresponding control strategies according to the recognition results, and adopts a PID adjustment scheme based on BP neural network and fuzzy control for adaptive control in different scenarios; in the daytime high-temperature condition, the decision module issues a forced cooling command; in the nighttime low-temperature condition, a heating preheating command is issued; and in the sandstorm condition, the fresh air inlet is closed and the circulating fan is started to clean the filter screen;

[0017] In specific control, a fuzzy adaptive PID controller is used for temperature regulation: the PID controller is used for fast and stable temperature set value control, the BP neural network is used for online learning and adjustment of the PID gain parameters, and the fuzzy control eliminates the static error of the system in the mutation condition by defining the fuzzy rules between temperature and regulation, and the specific control process is as follows:

[0018] First, define the temperature deviation as shown in the following formula: ;

[0019] Wherein, is the temperature error at the current time, is the current detected battery temperature, is the set target temperature;

[0020] Based on this error, the output control quantity of the PID controller is as shown in the following formula:

[0021] ;

[0022] Wherein, is the controller output signal, , , are the proportional, integral and differential coefficients respectively;

[0023] Then, the BP neural network is introduced to dynamically adjust the above PID parameters, and the adaptive ability of the system is enhanced, and the update rule is as shown in the following formula: ;

[0024] Wherein, is the PID gain vector, is the learning rate, a gradient of the error function with respect to the weight;

[0025] When the environmental conditions change dramatically, i.e., the temperature difference between day and night changes abruptly or the nonlinear response is significant, a fuzzy logic adjustment factor is introduced, and the adjustment weight is generated according to the fuzzy membership of the current error and the error change rate, and the final control signal is specifically shown as follows: ;

[0026] wherein, is the final control signal, is the fuzzy logic adjustment factor, is the controller output signal.

[0027] The thermal management execution module is composed of heating and heat dissipation two-part execution devices, the heat dissipation part includes battery pack heat dissipation fins, heat pipes and fans; the heating part includes PTC resistance wire and Peltier thermoelectric pile; the heat dissipation fins and heat pipes are directly attached to the surface of the battery module and are in close contact with the battery cells through heat-conducting materials; the fan and the cooling liquid path are installed in the battery shell, the fan blowing port and the cooling liquid path inlet are located in the shell air vent and are equipped with a dustproof filter screen, and the heating element is arranged in the battery interior close to the battery cell, so as to ensure the rapid heating of the battery at low temperature start, the whole module is sealed in the shell with a multi-layer heat insulation structure, and a light-reflecting coating is covered on the shell;

[0028] The thermal management execution module realizes the functions of heat dissipation and heating respectively under extreme temperature conditions, when the daytime temperature is as high as 70 DEG C, the fan is started and the heat dissipation fins are heat-conducted to quickly conduct the battery heat and discharge through forced air convection and liquid cooling circulation; at the same time, the phase change material is used to store heat to flatten the transient temperature rise;

[0029] At night, when it is extremely cold, the heating element is powered on to heat the battery pack and raise the temperature of the battery cell to the safe working interval, since the best working temperature of the lithium battery is 15-35 DEG C, the heat dissipation / heating intensity is dynamically adjusted according to the actual battery temperature;

[0030] For the sandstorm environment, the strong wind and floating particles will reduce the heat dissipation efficiency, the module automatically closes the shell air inlet fan and only circulates internally to prevent sand and dust from entering when the sandstorm state is identified; at the same time, the filter screen cleaning function is periodically started to filter out the accumulated dust;

[0031] The thermal management execution module responds to the control unit instructions and implements the adjustment, adopts a PID closed-loop control algorithm, takes the difference between the actual temperature of the battery and the target temperature as the input, controls the fan speed and the heater power through the incremental PID algorithm, so as to quickly make the temperature converge to the set value; the BP neural network is used for online optimization of the PID parameters, the PID gain is optimized in real time through learning the historical environment and temperature response characteristics; the fuzzy control is used for processing the nonlinear change in the extreme case, in the case of the dramatic change of the ambient temperature and the cold start, the fuzzy logic intelligently adjusts the PID output according to the temperature gradient, so as to avoid the temperature overshoot and oscillation;

[0032] In the running time, the thermal management execution module receives the control instructions from the decision unit and feeds back the execution state, when the decision unit detects the daytime high temperature, the "full-speed heat dissipation" command is sent to the module, the fan is driven to run at full speed and the liquid pump is activated to circulate, and at the same time the heater is closed; when the low temperature or the battery preheating requirement is detected, the "heating" command is issued by the decision unit, the heating element controls the power supply according to the PID output on-off control, the fan speed and the heater power are monitored in real time by the temperature sensor during the execution process and are fed back to the control unit, so as to realize the closed-loop control.

[0033] The battery management module is mainly composed of a battery management system BMS and a battery state sensor, the aging degree and the internal resistance change of the battery are detected, and the charging and discharging strategy is dynamically optimized according to the recognized temperature, humidity and radiation intensity, the BMS communicates data with the environment recognition and decision module through the CAN bus, realizes the bidirectional information interaction of the running state and the environment state, and the detailed functions of the module are introduced from the following three aspects:

[0034] In the high-temperature environment, if the external temperature is detected to be high, the BMS actively limits the charging current and the charging power to reduce the heat generation rate; in the low-temperature environment, the cell heating unit is preferentially activated, the temperature compensation is made to make it reach the appropriate charging temperature zone, and then the constant-current charging is started;

[0035] In the intelligent control aspect, the fuzzy controller and the BP neural network algorithm are integrated, the fuzzy controller takes the SOC and the temperature as the core input variables, adjusts the charging strategy in real time according to the preset rules, the BP neural network learns and trains the aging characteristics and the temperature behavior based on the long-term data in the battery operation process, and is used for predicting the capacity attenuation trend under different working conditions;

[0036] In the system aspect, the BMS synchronously uploads the real-time state of all monomer batteries to the environment recognition and decision module, the real-time state includes the voltage, the current, the temperature and the SOC; after the module issues the instructions, the BMS performs the task according to the set control logic, if the BMS detects the abnormal state, the alarm information or the emergency stop instruction is immediately issued through the bus.

[0037] Compared with the prior art, the present application has the beneficial effects that:

[0038] The present application can accurately identify and classify typical extreme working conditions in real time by introducing a multi-source environmental perception device, cooperating with an environmental recognition model constructed by a BP neural network and a fuzzy logic algorithm, so that the system has the ability to switch the heat regulation and battery operation strategy in a targeted manner, which is different from the extensive design of the prior art which is driven and controlled by only a single temperature threshold.

[0039] The environmental recognition and decision module of the present application constructs a composite controller based on fuzzy logic + PID control + BP neural network, can learn the environmental temperature change trend and battery temperature response characteristics online, and adaptively adjusts the PID parameters to realize accurate control of the battery temperature, so that the system responds faster, has smaller error and stronger robustness, and is particularly suitable for the high-frequency temperature control requirements in nonlinear disturbance environments such as deserts.

[0040] The thermal management execution module of the present application combines various functional components such as resistance wire heating, Peltier thermoelectric module, fan / heat pipe heat dissipation, phase change material heat storage and release, supports a dual mode of "daytime strong heat dissipation + night temperature control and heat preservation", and can cope with the dual extreme requirements of-40℃ low temperature cold start and 70℃ high temperature over-temperature inhibition. Compared with the prior art which only has a single heating or air cooling mechanism, it has stronger environmental adaptability and temperature control flexibility.

[0041] The present application can make the battery management module dynamically adjust parameters such as charging current, cutoff voltage, start-stop strategy, etc., to avoid safety risks caused by overcharging, low-temperature charging, etc., effectively prolong the life of the battery cell, and reduce the degradation rate under extreme conditions.

[0042] The present application constructs a complete closed-loop self-adjusting system, from environmental data acquisition to working condition recognition, to thermal control and BMS execution adjustment, and then back to state feedback, forming a multi-level nested logic control closed loop, which has the advantages of strong system stability, high regulation efficiency, high intelligence, etc. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments, and understand that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0044] Figure 1 It is a system architecture diagram of the present application. DETAILED DESCRIPTION

[0045] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only for selected embodiments of the present application.

[0046] Please refer to Figure 1 , Figure 1 is a kind of military battery operation regulation system architecture based on extreme environment identification detection provided by the embodiment of the present application, comprising the following modules:

[0047] Environment perception module, environment identification and decision module, thermal management execution module, battery management module, each module cooperates to realize the closed-loop control process of "perception-identification-decision-execution", the following will be described in conjunction with typical desert application scene, i.e. daytime extreme heat, extremely cold at night and accompanied by sandstorm, each module is described.

[0048] Environment perception module, the module is composed of multiple environment sensors, including temperature sensor, humidity sensor, barometric pressure sensor, wind speed / direction sensor, dust concentration sensor and solar radiation intensity sensor;Temperature sensor is installed in the battery pack and the shell outside, for real-time detection of battery and ambient temperature;Humidity and dust sensor is installed at the air inlet of the equipment, for monitoring the dryness of air and suspended particle concentration;Radiation sensor is placed on the top of the battery shell to collect solar radiation intensity data. All sensors use industrial components, with wide operating temperature range and high protection level, can withstand sandstorm, dust and ultraviolet radiation in desert environment;

[0049] Each sensor real-time collects environmental parameters and outputs electrical signal, temperature sensor measures environment and battery temperature;Humidity sensor monitors air dryness;Wind speed sensor measures wind speed;Dust sensor detects dust concentration in air based on laser scattering principle to cope with sudden high wind speed and corrosive dust in desert and other extreme factors;Radiation sensor collects solar direct intensity.

[0050] The environmental perception module mainly performs signal preprocessing, including denoising filtering and amplitude limiting protection. Kalman filtering is used to filter the sensing signals to eliminate transient impact and noise disturbance. For high-frequency interference signals such as wind and sand, simple threshold and fuzzy filtering are used to judge sudden events. This module does not directly output control commands, but inputs the processed environmental information as perception results to the environmental recognition module. This module transmits the monitored temperature, humidity, wind speed, dust and radiation information to the environmental recognition and decision module through the data bus, forming the "perception → recognition" path of the system. Specifically, the sensor collects the environmental state in real time and sends the digitized information to the central control unit for analysis and judgment, without directly controlling other hardware.

[0051] It should be noted that, in view of the influence of direct sunlight on the sensor, a sunshade and a filter can be installed outside each sensor. When the temperature is low at night, the temperature and humidity sensors are equipped with a self-heating or anti-freezing circuit to prevent the sensing element from dewing or icing. The data collected by all environmental sensors are output to the lower module after pre-filtering, analog-to-digital conversion and calibration.

[0052] The environmental recognition and decision module is composed of an embedded controller, a matching storage unit, a communication interface and other circuits. The controller is installed in a sealed aluminum alloy shell inside the battery system cabinet. The shell is filled with thermal insulation material and equipped with cooling fins to adapt to an environment of -40°C to +70°C. The module is connected to the environmental perception module, the thermal management execution module and the battery management module through CAN / LIN bus, and can collect and process sensor data at high speed and issue control commands.

[0053] The environmental recognition and decision module analyzes the data from the environmental perception module and uses multi-sensor data fusion and artificial intelligence algorithms to identify the current environmental conditions. Specifically, the BP neural network is used to classify and predict the temperature, humidity, wind speed, dust concentration and radiation intensity features collected, to determine whether the current situation is "extremely hot during the day", "extremely cold at night" or "sandstorm approaching" and the like. At the same time, the uncertainty of the sensor data is processed by fuzzy logic to obtain a qualitative judgment of the current environment through fuzzy reasoning. In addition, the BP neural network and the fuzzy control method can learn online and continuously optimize, and are highly adaptable to extreme environments, and can accurately identify complex and variable desert environments. Specifically, when the external environment temperature exceeds 60°C and the radiation is strong, the system determines that it is in the "extremely hot during the day" state. When the surrounding dust concentration increases dramatically and the wind speed increases, it is determined that a "sandstorm is approaching".

[0054] The environment recognition module issues corresponding control strategy according to the recognition result, and adopts a PID adjustment scheme based on BP neural network and fuzzy control to realize adaptive control for different scenes; in the daytime high-temperature working condition, the decision module issues a forced heat dissipation command; in the night low-temperature working condition, a heating preheating command is issued; and in the sandstorm working condition, the fresh air inlet is closed and the circulating fan is started to clean the filter screen.

[0055] In specific control, a fuzzy adaptive PID controller is used for temperature adjustment: the PID controller is used for quickly and stably realizing temperature set value control, the BP neural network is used for online learning and adjusting the PID gain parameter, and the fuzzy control is used for eliminating the static error of the system in the mutation working condition through defining the fuzzy rule between temperature and adjustment, and the specific control process is as follows:

[0056] Firstly, the temperature deviation is defined as shown in the following formula: ;

[0057] wherein, is the temperature error at the current moment, is the battery temperature detected at the current moment, is the set target temperature;

[0058] Based on the error, the output control quantity of the PID controller is shown in the following formula:

[0059] ;

[0060] wherein, is the controller output signal, , , are proportional, integral and differential coefficients respectively;

[0061] Then, the BP neural network is introduced to dynamically adjust the PID parameters, and the update rule is shown in the following formula: ;

[0062] wherein, is the PID gain vector, is the learning rate, is the gradient of the error function with respect to the weight;

[0063] When the environment working condition changes dramatically, i.e. the day-night temperature difference mutates or the nonlinear response is significant, the fuzzy logic adjustment factor is introduced, the adjustment weight is generated according to the fuzzy membership relation of the current error and the error change rate, and the final control signal is shown in the following formula: ;

[0064] wherein, is the final control signal, fuzzy logic regulation factor, for the controller output signal;

[0065] This module acts as the "brain" of the system, receiving data inputs from the perception module and outputting control instructions to the execution module based on the identification results. After receiving information such as temperature, humidity, etc. from the environment recognition module, it sends control signals such as fan speed, heater power, etc. to the thermal management execution module. At the same time, it also transmits status information such as "high temperature", "low temperature", "sandstorm" etc. to the battery management module, guiding it to adjust the charging and discharging strategy.

[0066] In addition, the feedback from the execution module and the battery management module also returns to the decision module, realizing closed-loop control and embodying the system process of "perception → identification → decision → execution", ensuring that the decision is dynamically adjusted based on real-time environment and battery state.

[0067] The thermal management execution module is composed of heating and cooling devices. The cooling part includes battery pack cooling fins, heat pipes and fans; the heating part includes PTC resistance wire and Peltier thermoelectric pile; the cooling fins and heat pipes are directly attached to the surface of the battery module and are in close contact with the battery cells through heat-conducting materials such as silicone grease; the fan and cooling liquid pipeline are installed in the battery shell, and the fan blowing port and cooling liquid pipeline inlet are located in the shell ventilation port and equipped with dustproof filter screen; the heating element is arranged near the battery cell inside the battery to ensure rapid heating of the battery at low temperature. The module is sealed in a shell with multiple layers of thermal insulation structure, effectively isolating external heat radiation and sand dust invasion, and covering a reflective coating on the shell to reduce solar radiation absorption.

[0068] The thermal management execution module realizes the functions of cooling and heating under extreme temperature conditions. When the daytime temperature is as high as 70℃, the fan is turned on and the cooling fins work together to quickly conduct the battery heat and discharge it through forced air convection or liquid cooling circulation; at the same time, the phase change material can be used to store heat to flatten the transient temperature rise, specifically: the phase change material absorbs the excess heat generated during charging and releases it at night to resist cold.

[0069] When the temperature is as low as -40℃ at night, the heating element is powered on to heat the battery pack and raise the temperature of the battery cells to the safe working range. Since the optimal working temperature of lithium batteries is 15~35℃, the system dynamically adjusts the cooling / heating intensity based on the actual battery temperature to ensure that the battery temperature remains within this range.

[0070] For sandstorm environment, strong wind and floating particles can reduce the cooling efficiency. This module automatically closes the shell intake fan when it identifies the sandstorm state, only internal circulation to prevent sand from entering; at the same time, periodic start-up of filter screen cleaning function to filter out accumulated dust.

[0071] The thermal management execution module responds to the control unit instructions and implements fine adjustment, adopts a PID closed-loop control algorithm, takes the difference between the actual temperature of the battery and the target temperature as input, controls the fan speed and the heater power through the incremental PID algorithm, so as to quickly make the temperature converge to the set value; the BP neural network can be used for online optimization of the PID parameters, the PID gain is optimized in real time through learning the historical environment and temperature response characteristics, and the control precision is improved; the fuzzy control is used for processing the nonlinear change in the extreme case, and the fuzzy logic can intelligently adjust the PID output according to the temperature gradient size when the ambient temperature changes greatly or cold starts, so as to avoid temperature overshoot or oscillation.

[0072] In operation, the thermal management execution module receives control instructions from the decision unit, such as “start forced heat dissipation” or “start heating”, and feeds back the execution state. Specifically, when the decision unit detects high temperature during the day, it sends a “full-speed heat dissipation” command to the module, drives the fan to run at full speed and activates the liquid pump circulation, and at the same time the heater is turned off; when low temperature or battery preheating is required, the decision unit issues a “heating” command, and the heating element controls the power supply according to the PID output on-off control, and the fan speed and heater power are monitored in real time during the execution process by the temperature sensor and fed back to the control unit, realizing closed-loop control; the module receives the environment recognition instructions and performs the corresponding adjustment operation, completing the key link from “recognition” to “execution”.

[0073] The battery management module is mainly composed of a battery management system (BMS) and a battery state sensor, and mainly functions to comprehensively detect the aging degree and internal resistance change of the battery, dynamically optimize the charging and discharging strategy according to the recognized temperature, humidity and radiation intensity, and realize bidirectional information interaction between the running state and the environment state through data communication between the BMS and the environment recognition and decision module through the CAN bus. The detailed functions of the module are introduced from three aspects as follows:

[0074] In terms of control strategy, in a high-temperature environment, if the external temperature is high or the internal temperature of the cell rises too fast, the BMS actively limits the charging current and charging power to reduce the heat generation rate and prevent thermal runaway; in a low-temperature environment (such as at night or in cold regions), the system will preferentially activate the cell heating unit to make it reach the appropriate charging temperature zone through temperature compensation, and then start constant-current charging; at this time, the charging cutoff voltage can also be appropriately reduced to slow down the risk of lithium precipitation; in a dry or strong radiation environment, if the battery internal resistance rises due to environmental factors, the system will control the heat generation degree by adjusting the discharge rate to avoid local overheating and prolong the battery life.

[0075] In the intelligent control aspect, the fuzzy controller and the BP neural network algorithm are integrated, the fuzzy controller takes SOC and temperature as core input variables, and adjusts the charging strategy in real time according to preset rules; the BP neural network learns and trains the aging characteristics and temperature behavior of the battery during the operation process, and is used for predicting the capacity attenuation trend under different working conditions.

[0076] In the system aspect, the BMS synchronously uploads the real-time states of all single batteries to the environment identification and decision module, the real-time states including voltage, current, temperature and SOC; after the module issues an instruction, the BMS performs a task according to the set control logic, and if the BMS detects an abnormal state, the BMS will immediately issue an alarm information or execute an emergency stop instruction through the bus.

[0077] It should be noted that the BMS includes a microprocessor, a voltage detection unit, a sampling resistor and a current detection device, and is connected to the positive and negative poles of each single battery of the battery pack through a cable, and real-time operation data such as voltage, current, temperature and state of charge (SOC) are collected, in order to realize efficient integration and thermal management, these key components are arranged on the control board at the top or side of the battery pack, and are connected with the distributed temperature sensor array, forming a multi-parameter cooperative monitoring network of the battery operation state. In addition, in order to adapt to the non-uniform working environment among the modules, the system introduces a temperature compensation mechanism and an equalization control strategy, so that the temperature rise consistency and SOC balance are realized in each module, and the cooperativity and output stability of the system are effectively improved.

[0078] The above only describes the preferred embodiments of the present application and is not used to limit the present application, for those skilled in the art, the present application has various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A military battery operation regulating system based on extreme environment recognition detection, characterized in that, The application comprises the following modules: An environment perception module for collecting environment parameter information, including temperature, humidity, wind speed, dust concentration and solar radiation intensity, and outputting the collected original signals to the next module after filtering and limiting amplitude processing; An environment recognition and decision module for receiving the information output by the environment perception module, identifying and classifying the environment state based on BP neural network and fuzzy logic algorithm, and outputting targeted adjustment strategies and control commands in combination with fuzzy adaptive PID control algorithm; A thermal management execution module for executing battery cooling, heating or heat storage operation according to the control commands output by the environment recognition and decision module, the thermal management execution module comprising a fan, a heat pipe, a PTC resistance wire, a Peltier thermoelectric module and a phase change heat storage material; A battery management module for dynamically adjusting the charging and discharging current, voltage parameters and safety protection strategies according to the state synchronization information of the environment recognition and decision module and the state feedback of the thermal management execution module, and feeding back the battery state information; The environment recognition and decision module is composed of an embedded controller and its matching storage unit and communication interface, the controller is installed in a sealed aluminum alloy shell and located inside the battery system cabinet, the shell is filled with thermal insulation material and equipped with cooling fins to adapt to-40℃~+70℃ environment; the environment recognition and decision module is connected with the environment perception module, the thermal management execution module and the battery management module through CAN / LIN bus, can collect and process high-speed sensor data, and issue control commands; The environment recognition and decision module comprehensively analyzes the data from the environment perception module, identifies the current environment working condition by using multi-sensor data fusion and artificial intelligence algorithm; classifies and predicts the collected temperature, humidity, wind speed, dust concentration and radiation intensity characteristics by using BP neural network, and determines whether the current situation is "daytime extreme heat", "nighttime extreme cold" or "sandstorm coming"; at the same time, the uncertainty of sensor data is processed by fuzzy logic, and the qualitative judgment of the current environment is obtained by fuzzy reasoning; The environment recognition module issues corresponding control strategies according to the recognition result, adopts PID adjustment scheme based on BP neural network and fuzzy control for adaptive control in different scenes; in daytime high temperature working condition, the decision module issues forced cooling command; In nighttime low temperature working condition, the heating preheating command is issued; in sandstorm working condition, the fresh air inlet is closed and the circulating fan is started to clean the filter screen; In specific control, the fuzzy adaptive PID controller is used for temperature adjustment: the PID controller is used for fast and stable temperature set value control, the BP neural network is used for online learning and adjustment of PID gain parameters; and the fuzzy control eliminates the static error of the system in the mutation working condition by defining the fuzzy rules between temperature and adjustment amount, the specific control process is as follows: Firstly, the temperature deviation is defined, which is specifically shown in the formula: ； wherein, is a temperature error for the current time instant, is a currently detected battery temperature, is a set target temperature; Based on this error, the output control amount of the PID controller is shown in the formula: ； wherein is a controller output signal, , , are proportional, integral, and derivative coefficients, respectively; Then, the BP neural network is introduced to dynamically adjust the PID parameters, and the adaptive ability of the system is enhanced, the updating rule is specifically shown in the formula: ； wherein, is a PID gain vector, is a learning rate, is a gradient of the error function with respect to the weights; When the environmental conditions change dramatically, i.e. the temperature difference between day and night is suddenly changed or the nonlinear response is significant, a fuzzy logic adjustment factor is introduced, and according to the fuzzy membership of the current error and the error rate, the adjustment weight is generated, and the final control signal is specifically shown as follows: ； wherein, is the final control signal, is the fuzzy logic adjustment factor, is the controller output signal.

2. The military battery operation adjusting system based on extreme environment identification detection according to claim 1, characterized in that: The environment perception module is composed of multiple environmental sensors, including temperature sensors, humidity sensors, air pressure sensors, wind speed / wind direction sensors, dust concentration sensors and solar radiation intensity sensors; the temperature sensors are installed inside and outside the battery pack respectively, for real-time detection of the temperature of the battery cell and the surrounding environment; the humidity and dust sensors are installed at the air inlet of the equipment, for monitoring the dryness and suspended particle concentration in the air; the radiation sensor is placed on the top of the battery shell to collect solar radiation intensity data; Each sensor collects environmental parameters in real time and outputs an electrical signal; the temperature sensor measures the temperature of the environment and the battery cell; the humidity sensor monitors the air dryness; The wind speed sensor measures the wind speed; the dust sensor detects the concentration of dust in the air based on the laser scattering principle to cope with sudden high wind speed and corrosive dust in the desert; the radiation sensor collects the intensity of direct sunlight; The environment perception module mainly performs signal preprocessing, including denoising filtering and amplitude limiting protection; Kalman filtering is used to filter the sensor signals to eliminate transient impact and noise disturbance; for high-frequency interference signals such as wind and sand, simple threshold and fuzzy filtering are used to judge sudden events; the environment perception module does not directly output control commands, but inputs the processed environmental information as perception results into the environment identification module; the module transmits the monitored temperature, humidity, wind speed, dust and radiation information to the environment identification and decision module through the data bus, forming the "perception→identification" path of the system.

3. The military battery operation adjusting system based on extreme environment identification detection according to claim 1, characterized in that: The thermal management execution module is composed of heating and cooling devices; the cooling part includes battery pack cooling fins, heat pipes and fans; the heating part includes PTC resistance wire and Peltier thermoelectric pile; the cooling fins and heat pipes are directly attached to the surface of the battery module and are in close contact with the battery cells through heat-conducting materials; the fan and the cooling liquid path are installed in the battery shell, and the fan blowing port and the cooling liquid path inlet are located in the shell ventilation port and are equipped with dustproof filter screens; the heating elements are arranged inside the battery near the battery cells to ensure rapid heating of the battery during low-temperature start; the module is sealed in a shell with multiple thermal insulation structures, and a reflective coating is covered on the shell; The thermal management execution module realizes the functions of cooling and heating under extreme temperature conditions; when the temperature is as high as 70℃ during the day, the fan is turned on and the cooling fins work together to quickly conduct the heat of the battery and discharge it through forced air convection and liquid cooling circulation; at the same time, the phase change material is used to store heat to flatten the transient temperature rise. In the night, the heating element is powered on to heat the battery pack and raise the temperature of the battery cells to a safe operating range. Since the optimal operating temperature for lithium batteries is between 15-35°C, the cooling / heating intensity is dynamically adjusted based on the actual battery temperature. For sandstorm environments, strong winds and floating particles can reduce cooling efficiency. In this module, the intake fan is automatically turned off when the sandstorm state is identified, and only internal circulation is used to prevent sand from entering. At the same time, the filter screen cleaning function is periodically activated to remove accumulated dust. The thermal management execution module responds to the control unit's instructions and implements adjustments. It uses a PID closed-loop control algorithm, taking the difference between the actual battery temperature and the target temperature as input. The fan speed and heater power are controlled using an incremental PID algorithm to quickly converge the temperature to the set value. BP neural networks are used for online tuning of PID parameters, and they learn from historical environmental and temperature response characteristics to optimize PID gains in real time. Fuzzy control is used to handle nonlinear changes in extreme situations. In cases of sudden environmental temperature changes and cold starts, fuzzy logic intelligently adjusts PID output based on temperature gradients to avoid temperature overshoot and oscillation. During operation, the thermal management execution module receives control instructions from the decision unit and feeds back the execution status. When the decision unit detects high daytime temperatures, it sends a "full-speed cooling" command to the module, which drives the fan to run at full speed and activates the liquid pump circulation, while the heater is turned off. When low temperatures or battery preheating is required, the decision unit issues a "heating" command, and the heating element controls the power supply based on PID output. The fan speed and heater power are monitored in real time by temperature sensors and fed back to the control unit during execution, achieving closed-loop control.

4. The military battery operation adjustment system based on extreme environment recognition detection according to claim 1, characterized in that: The battery management module is mainly composed of a battery management system (BMS) and battery state sensors. It dynamically optimizes charging and discharging strategies based on the detected temperature, humidity, and radiation intensity, as well as the aging degree and internal resistance changes of the battery. The BMS communicates with the environment recognition and decision module through a CAN bus, enabling bidirectional information exchange between the operating state and the environmental state. The detailed functions of the battery management module are introduced from three aspects: In high-temperature environments, if the external temperature is high, the BMS actively limits the charging current and power to reduce heat generation. In low-temperature environments, the battery cell heating unit is activated first to achieve the appropriate charging temperature range through temperature compensation, and then constant-current charging is started. Intelligent control integrates fuzzy controllers and BP neural network algorithms. The fuzzy controller takes SOC and temperature as core input variables and adjusts the charging strategy in real time based on pre-set rules. The BP neural network learns and trains the aging characteristics and temperature behavior based on long-term data during battery operation and is used to predict capacity degradation trends under different working conditions. The BMS synchronously uploads the real-time state of all single batteries, including voltage, current, temperature, and SOC, to the environment recognition and decision module. When the module issues an instruction, the BMS will perform the task according to the set control logic. If the BMS detects an abnormal state, it will immediately issue an alarm message or execute an emergency stop instruction through the bus.

Images