An adaptive position adjustment method for a composite battery film

Abstract

This application provides a method for adaptive adjustment of the thin film position of a composite battery, comprising: obtaining the working state of the target composite battery by simulating the operation of the composite battery through several simulations, and monitoring the battery temperature, charge / discharge state and internal resistance of the target composite battery in real time; during the design process of the composite battery, driving the thin film support with a servo motor, and adjusting the angle between the thin film and the battery surface according to a first target tilt angle and the real-time battery temperature; establishing a mapping relationship between the position of the composite battery thin film and the battery working state by training with the monitoring data and adjustment data of each thin film tilt angle and rotation angle adjustment; during the design process of the composite battery, dynamically adjusting the adjustment amplitude and frequency of the thin film tilt angle and rotation angle, and targeting the energy consumption of the thin film position adjustment under the conditions of preset battery safety and efficiency, so that the position of the composite battery thin film is adaptively adjusted.

Description

Technical Field

[0001] This invention relates to the field of information technology, and in particular to a method for adaptive adjustment of the position of a thin film in a composite battery. Background Technology

[0002] In the design of composite batteries, the working environment and conditions are often complex and variable. Furthermore, during charging and discharging, internal parameters such as temperature, voltage, and current dynamically change. Simultaneously, the external environment, including ambient temperature and light intensity, is also constantly changing. These internal and external factors directly affect battery performance and lifespan, therefore, they require close attention during battery design. Firstly, the thin-film material in the composite battery plays a crucial role; its position and angle adjustment directly affect the battery's heat dissipation and photoelectric conversion efficiency. However, how to dynamically adjust the position and angle of the thin film in conjunction with changes in the external environment to improve heat dissipation and photoelectric conversion efficiency is a pressing technical challenge. Traditional thin-film position adjustment methods are usually fixed or based on preset conditions, failing to adapt to real-time changes in battery operating states and the environment. Therefore, how to achieve adaptive adjustment of the position of the composite battery film, so that it can dynamically adjust the tilt angle and rotation angle of the film according to the real-time state of the battery and changes in the external environment, thereby realizing dynamic control of battery heat dissipation and optimization of photoelectric conversion efficiency, is a technical problem that urgently needs to be solved, and it is also the key to achieving efficient and stable operation of composite batteries. Summary of the Invention

[0003] This invention provides a method for adaptive adjustment of the position of a thin film in a composite battery, mainly comprising:

[0004] The working state of the target composite battery is obtained by simulating the operation of the composite battery through several simulations, and the battery temperature, charge and discharge state and internal resistance of the target composite battery under the working state are monitored in real time.

[0005] The battery temperature, charge / discharge state and internal resistance monitoring data of the target composite battery under working conditions are compared with the preset safe ranges of battery temperature, charge / discharge state and internal resistance, respectively, to determine the first target tilt angle and the first target rotation angle of the composite battery film.

[0006] In the design process of the composite battery, a servo motor drives the thin film holder to adjust the angle between the thin film and the battery surface according to the first target tilt angle and the real-time temperature of the battery.

[0007] Based on the first target rotation angle, control the rotation of the film support to adjust the orientation of the film, detect whether the film is kept on the target light-receiving surface or reflective surface. If the rotation angle causes the film to be not on the target light-receiving surface or reflective surface, adjust the orientation of the film in time to keep the film on the target light-receiving surface or reflective surface.

[0008] During the adjustment of the film tilt angle and rotation angle, the battery temperature, charge and discharge status and internal resistance monitoring data are continuously acquired to determine the impact of the adjusted film position on the battery working state, forming a closed-loop feedback control, thereby adjusting the second target tilt angle and the second target rotation angle of the film.

[0009] By training with monitoring data and adjustment data of each thin film tilt angle and rotation angle adjustment, a mapping relationship between the position of the composite battery thin film and the battery operating state is established.

[0010] In the design process of composite batteries, the adjustment range and frequency of the thin film tilt angle and rotation angle are dynamically adjusted. Under the premise of preset battery safety and efficiency, the energy consumption of the target thin film position adjustment is optimized, so that the position of the composite battery thin film can be adaptively adjusted.

[0011] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0012] This invention discloses a method for adaptively adjusting the position of a thin film in a composite battery. The method acquires the working state of the composite battery through simulation, monitors the battery temperature, charge / discharge status, and internal resistance in real time, and determines the target tilt angle and rotation angle of the thin film after comparing these parameters with preset safety ranges. A servo motor drives the thin film support to adjust the angle and orientation between the thin film and the battery surface, forming a closed-loop feedback control. By continuously acquiring monitoring data, the influence of the thin film position on the battery's working state is determined, and a mapping model is established. Based on the model output, the adjustment amplitude and frequency of the thin film position are dynamically adjusted while ensuring battery safety and efficiency, achieving optimal energy consumption. This invention can adaptively adjust the thin film position according to the battery's working state, effectively improving the safety and efficiency of the composite battery and reducing energy consumption, thus possessing significant practical value. Attached Figure Description

[0013] Figure 1 This is a flowchart of a method for adaptively adjusting the position of a thin film in a composite battery according to the present invention.

[0014] Figure 2 This is a schematic diagram of a method for adaptively adjusting the position of a thin film in a composite battery according to the present invention.

[0015] Figure 3 This is another schematic diagram of a method for adaptive adjustment of the position of a thin film in a composite battery according to the present invention. Detailed Implementation

[0016] To further understand the content of this invention, a detailed description of the invention is provided in conjunction with the accompanying drawings and embodiments. The specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0017] like Figure 1 -3, The adaptive adjustment method for the position of the thin film of a composite battery in this embodiment may specifically include:

[0018] Step S101: The working state of the target composite battery is obtained by simulating the operation of the composite battery several times, and the battery temperature, charge and discharge state and internal resistance of the target composite battery under the working state are monitored in real time.

[0019] A temperature sensor array is used to acquire surface temperature data of the composite battery. Temperature distribution data is obtained through bicubic spline interpolation based on this temperature data. Heat flux density and thermal conductivity are calculated from the temperature distribution data, and temperature field data is obtained using the Laplace equation and the finite difference method. A convolutional neural network (CNN) training model is established based on the temperature field data. The CNN model uses the temperature field data as the input layer and current data as the output layer, and the charge / discharge state prediction result is obtained through forward propagation and backward gradient correction. Current and temperature feature vectors are extracted from the charge / discharge state prediction result. Feature matching is performed between the feature vectors and measured voltage data, and the voltage-to-current ratio is calculated using the least squares method to obtain the internal resistance change data of the composite battery.

[0020] For example, a composite battery geometry is established using physics simulation software. A temperature sensor array is arranged on the composite battery surface with a 5mm grid spacing. Temperature, charge / discharge current, and voltage data are collected using a 1-second sampling period. The composite battery is then simulated. Temperature distribution data is obtained by processing the temperature data using bicubic spline interpolation. The heat flux density and thermal conductivity of the composite battery surface are calculated based on the temperature distribution data. The heat conduction process is solved using the Laplace equation. Newtonian cooling boundary conditions are added at the boundary points, and the overall temperature field data is obtained through iterative calculation using the finite difference method. The formula for the temperature distribution under Newtonian cooling conditions is as follows:

[0021]

[0022] Let T(x) represent the temperature at position x, T∞ represent the ambient temperature far from the boundary, Ts represent the surface temperature, and L represent the feature length. Data tables are established for temperature field data and current data. Temperature field data is used as the input layer, and current data as the output layer. A convolutional neural network is used for training, with training samples divided into training and validation sets at an 8:2 ratio. Charge / discharge state prediction results are obtained through forward propagation and backward gradient correction. Current and temperature feature vectors are extracted from the charge / discharge state prediction results and matched with measured voltage data. The voltage-to-current ratio is calculated using the least squares method. The internal resistance variation data of the composite battery is derived using Ohm's law and then standardized. Temperature field simulation of the composite battery relies on accurate geometric modeling. The battery structure typically includes multiple layers of composite materials such as positive and negative electrodes, a separator, and an electrolyte, each with different thermal conductivity characteristics. In practical applications, lithium nickel cobalt manganese oxide is commonly used as the positive electrode material, graphite is used as the negative electrode material, and polypropylene or polyethylene is used as the separator material. The thermal conductivity of these materials are 1.48, 25.0, and 0.22 watts per meter Kelvin, respectively. The temperature sensor array is arranged in a matrix with a 5 mm spacing. The number of sensors is determined based on the battery size, and the measurement error of a single sensor is within 0.1 degrees Celsius. When processing temperature data using bicubic spline interpolation, the continuity of the first derivative is maintained at the interpolation nodes, and the interpolation function forms a smooth transition between adjacent intervals. In the heat flux density calculation, the convective heat transfer coefficient between the composite battery surface and the air is taken as 15 watts per square meter Kelvin, and the ambient temperature is set at 25 degrees Celsius. In solving the Laplace equation, a five-point difference scheme is used to discretize the partial differential equation, with a mesh generation accuracy of 1 mm, and third-type boundary conditions are used. The finite difference iterative calculation sets a convergence threshold of 0.001 degrees Celsius and a maximum number of iterations of 1000. The charge / discharge state prediction employs a convolutional neural network structure. The input layer contains 32 temperature field feature maps, the hidden layers consist of 3 convolutional layers and 2 fully connected layers, and the output layer corresponds to the three states: charging, discharging, and resting. The training dataset contains 10,000 pairs of temperature field and current data, with 8,000 pairs used for training and 2,000 pairs for validation. The training process uses a stochastic gradient descent optimizer with a learning rate of 0.001. Internal resistance calculation uses the least squares method to process voltage and current data, with a sampling time window of 10 seconds, collecting 100 voltage and current data points within each time window. Internal resistance data standardization uses the Z-score method to transform the data into a distribution with a mean of 0 and a standard deviation of 1. The battery's internal resistance changes with the number of charge / discharge cycles. The internal resistance of a new battery is approximately 10 milliohms, rising to 15 milliohms after 500 charge / discharge cycles. A battery lifespan is considered terminated when the internal resistance increases by more than 50%. In actual measurements, internal resistance shows a negative correlation with temperature; for every 10 degrees Celsius increase in temperature, internal resistance decreases by approximately 5%.During fast charging, the composite battery exhibits a temperature distribution characterized by a high temperature at the center and a low temperature at the edges, with the central region being 3 to 5 degrees Celsius warmer than the peripheral regions. During discharging, the temperature distribution is more uniform, with a temperature gradient of less than 2 degrees Celsius per centimeter. The temperature field data shows a significant correlation with the charge / discharge state; the temperature rise rate during charging is 0.5 to 1 degree Celsius per minute, while the temperature rise rate during discharging is 0.3 to 0.8 degrees Celsius per minute.

[0023] Step S102: The battery temperature, charge / discharge status and internal resistance monitoring data of the target composite battery under working conditions are compared with the preset safe ranges of battery temperature, charge / discharge status and internal resistance, respectively, to determine the first target tilt angle and the first target rotation angle of the composite battery film.

[0024] The process involves acquiring battery temperature monitoring data, obtaining an initial film tilt angle based on the deviation between the temperature monitoring data and a preset safe temperature range, acquiring an excessive current density value based on the charging / discharging current monitoring data, obtaining a reference value for the film rotation angle based on the excessive current density value, collecting battery internal resistance values, converting the portion of the internal resistance value exceeding a preset internal resistance safety threshold into angular coordinate components, and obtaining a film tilt angle correction value by performing trigonometric function transformation on the temperature deviation and the angular coordinate components, and using a backpropagation neural network to perform weighted calculations on the initial film tilt angle value and the tilt angle correction value, and obtaining the first target tilt angle value and the first target rotation angle value of the film from the output layer of the neural network.

[0025] For example, battery temperature monitoring data is acquired through a real-time acquisition device. An upper limit of 45 degrees Celsius and a lower limit of 10 degrees Celsius are set for the safe temperature range. If the monitored temperature exceeds the upper limit or falls below the lower limit, the temperature deviation value is obtained by subtracting the boundary value from the excess value. This temperature deviation value is then converted into an initial thin-film tilt angle using a linear mapping formula, in degrees. For charge / discharge current monitoring data, an upper limit of 2 amperes per square centimeter for charging current density and 3 amperes per square centimeter for discharging current density are set. Excess values ​​for charge / discharge states are acquired. The thin-film adjustment weight is calculated based on the ratio of the excess value to the temperature deviation value. The reference value for the thin-film rotation angle is obtained by multiplying the weight value by a standardization coefficient. The battery internal resistance value is acquired using a real-time data detection device and compared with a preset internal resistance safety threshold of 20 milliohms. The portion exceeding the threshold is converted into a radius component in angular coordinates, and the temperature deviation value is converted into an angle component. The thin-film tilt angle correction is obtained through trigonometric function conversion, in degrees. A backpropagation neural network is used to weight the initial and corrected values ​​of the thin film tilt angle. The input layer contains three neurons representing temperature deviation, out-of-limit values, and internal resistance deviation. The hidden layer uses a hyperbolic tangent activation function, and the output layer corresponds to the target tilt angle and rotation angle values ​​of the thin film. The final adjustment parameters of the composite battery thin film are determined according to the magnitude of the tilt angle and rotation angle values. Temperature monitoring of the composite battery involves multi-level safety threshold settings. The upper limit of the safe temperature range, 45 degrees Celsius, represents the critical point of thermal runaway, at which point the internal electrochemical reaction accelerates dramatically. The lower limit, 10 degrees Celsius, corresponds to the critical temperature at which the battery material performance deteriorates. In practical applications, different types of composite batteries exhibit different temperature sensitivities. Lithium-ion batteries begin to show performance degradation at 35 degrees Celsius, while sodium-ion batteries remain stable at 40 degrees Celsius. The charge and discharge current density limits are set based on the battery material's tolerance. The upper limit of the charging current density is 2 amps per square centimeter to avoid lithium-ion deposition, as higher charging rates can lead to lithium dendrite growth. The upper limit of the discharging current density is set at 3 amps per square centimeter, at which the battery heat generation remains within a safe range. Actual test data shows that when the charging current exceeds the limit by 0.5 amps per square centimeter, the film tilt angle is adjusted by 15 degrees; when the discharging current exceeds the limit by 0.8 amps per square centimeter, the rotation angle is increased by 20 degrees. Battery internal resistance monitoring reflects the battery's health status. The baseline internal resistance for a new battery is 15 milliohms, and the safety threshold is set at 20 milliohms. The internal resistance growth rate varies with the number of cycles; the rate of increase is 0.01 milliohms per cycle for the first 100 cycles, increasing to 0.02 milliohms per cycle from 100 to 300 cycles. The internal resistance exceeding the limit is determined through polar coordinate transformation. The radius component represents the degree of exceeding the limit, and the angle component corresponds to the temperature effect. The resulting value is the corrected film tilt angle. The neural network weight adjustment uses an error backpropagation mechanism. The three neurons in the input layer receive the temperature deviation value, the current exceeding the limit value, and the internal resistance deviation value, respectively. The hidden layer uses a hyperbolic tangent function to handle nonlinear relationships, and the output layer provides the combined value of the film tilt angle and the rotation angle.Training data was collected from battery operating conditions under various circumstances, including abnormal scenarios such as rapid temperature rise, drastic current fluctuations, and sudden changes in internal resistance. During network training, the weighting coefficients for temperature deviation, current over-limit, and internal resistance deviation were 0.4, 0.35, and 0.25, respectively. In the dynamic response of the thin-film adjustment parameters, temperature, current, and internal resistance are interdependent. Increased temperature leads to a decrease in internal resistance, which in turn affects the charging and discharging current distribution. High-current charging and discharging exacerbates the temperature rise, creating a positive feedback effect. Thin-film tilt angle adjustment breaks this positive feedback by changing the heat dissipation area; when the temperature exceeds the limit by 5 degrees Celsius, increasing the tilt angle by 10 degrees increases the heat dissipation area by 15%. Rotation angle adjustment changes the direction of heat flow; when the current exceeds the limit, for every 30-degree increase in the rotation angle, the heat flow intensity decreases by 20%.

[0026] The adjustment scale for the battery tilt angle is determined based on the value of the battery temperature exceeding the preset safety range and the value of the charge / discharge state exceeding the preset safety range, respectively; the adjustment scale for the rotation angle under the internal resistance condition is determined based on the value of the internal resistance exceeding the preset safety range, and the first target tilt angle and the first target rotation angle of the composite battery film are determined based on the adjustment scale for the battery tilt angle and the adjustment scale for the rotation angle under the internal resistance condition.

[0027] The tilt angle adjustment is calculated using three-point linear interpolation of temperature intervals based on the battery temperature exceeding the limit. This tilt angle adjustment, combined with the charge / discharge state exceeding the limit, and the rate segmentation points, yield the total tilt angle adjustment. For the internal resistance exceeding the limit, a standard resistance reference value is used to obtain the rate difference. This rate difference is mapped to an angle range using a hyperbolic tangent function to obtain a rotation angle reference value. The rotation angle reference value and the total tilt angle adjustment value construct an adjustment matrix. A long short-time memory network is used to train the correspondence between the battery temperature exceeding a preset safety range, the charge / discharge state exceeding a preset safety range, and the internal resistance exceeding a preset safety range, and the adjustment amount. This correspondence is limited to the adjustment range using an activation function to obtain a tilt angle / rotation angle mapping matrix. The dot product operation is performed between the values ​​of the mapping matrix and the adjustment matrix to obtain initial adjustment parameter values. These initial adjustment parameter values ​​are then iteratively calculated using the least squares method to obtain the first target tilt angle and the first target rotation angle of the composite battery film.

[0028] For example, uniformly distributed interpolation nodes are established for the collected battery temperature exceeding limits. Three-point linear interpolation with 5-degree temperature intervals is used to calculate the tilt angle adjustment corresponding to the temperature. The corresponding tilt angle correction is calculated based on the charge / discharge state exceeding limits using a piecewise linear function with 0.5 rate segment points. The total battery tilt angle adjustment value is obtained by multiplying the temperature weighting coefficient (0.6) and charge / discharge weighting coefficient (0.4) by the adjustment value and summing the results. A standard resistance reference value is used to compare the internal resistance exceeding limits. The obtained rate difference is mapped to an angle range of 0 to 90 degrees using a hyperbolic tangent function. A sine transform is then used to convert the rate difference into a rotation angle reference value. An adjustment matrix is ​​constructed from the total battery tilt angle adjustment value and the rotation angle reference value. A long short-term memory network is used to train the correspondence between the three exceeding limits and the adjustment values. The number of neurons in the hidden layer is set to twice the input dimension. The input data is processed using standard deviation normalization. An activation function is used to limit the output to an effective adjustment range, resulting in the tilt angle / rotation angle mapping matrix. The initial values ​​of the adjustment parameters are obtained by performing a dot product operation between the mapping matrix and the adjustment matrix. The sum of the squares of the products of the tilt angle adjustment and the angular velocity is set as the optimization objective function. The first target tilt angle and rotation angle of the composite battery film are obtained through least squares iterative calculation. When calculating the film tilt angle using linear interpolation, the adjustment interval is divided according to the degree of temperature exceeding the limit. When the temperature exceeds the preset range by 5 degrees Celsius, the tilt angle is adjusted by 10 degrees; when it exceeds 10 degrees Celsius, it is adjusted by 20 degrees; and when it exceeds 15 degrees Celsius, it is adjusted by 30 degrees. The adjustment angle corresponding to the intermediate temperature value is calculated through interpolation points. The charging and discharging state exceeding the limit is also calculated in segments. Based on the nominal rate of 1C, the tilt angle increases by 15 degrees when the charging current exceeds 0.5C, and by 25 degrees when it exceeds 1C. The discharging current uses similar segmentation points. The weighting coefficient reflects the proportion of the influence of temperature and charging and discharging state. The higher temperature weight reflects the priority of temperature control. The degree of anomaly in internal resistance exceeding the limit is quantified by ratio comparison. The standard internal resistance value is 15 milliohms. The ratio of the measured value to the standard value is mapped to the angle space using a hyperbolic tangent function. When the internal resistance is 1.2 times the standard value, the rotation angle is 30 degrees; 1.5 times, it is 60 degrees; and 2 times, it is close to 90 degrees. Sine transformation converts the linear proportional relationship into a nonlinear adjustment characteristic, avoiding excessively drastic angle adjustment. The adjustment matrix contains two dimensions: tilt angle and rotation angle, and the matrix elements represent the coupling relationship between different parameters. During the training of the Long Short-Term Memory network, the input layer receives three normalized out-of-limit values: temperature, charging / discharging state, and internal resistance. The hidden layer contains 6 neurons, and the temporal characteristics are processed through a triple structure of forget gate, input gate, and output gate. The network training samples come from measured data under different operating conditions, including extreme scenarios such as fast charging, fast discharging, and rapid temperature changes. The training data is normalized by standard deviation to eliminate the influence of dimensions. The dot product operation of the mapping matrix and the adjustment matrix takes into account the influence of various parameters. The initial adjustment value is optimized by the least squares method. The angular velocity term in the objective function limits the stability of the adjustment process.In practical applications, when the battery temperature suddenly rises by 8 degrees Celsius, the charging rate exceeds 0.8C, and the internal resistance increases by 40%, the calculated target tilt angle is 35 degrees and the rotation angle is 45 degrees. These two angles work together to change the heat dissipation conditions. Increasing the film tilt angle increases the heat dissipation area, while changing the rotation angle adjusts the direction of heat flow. Under their combined effect, the temperature exceeding the limit decreases by 80% within 300 seconds, and the charging rate drops to a safe range. Different types of batteries exhibit different adjustment characteristics. Lithium iron phosphate batteries have stronger temperature tolerance than ternary lithium batteries, and the tilt angle adjustment amount is reduced by 20% for the same exceeding limit. Sodium-ion batteries are more sensitive to changes in internal resistance, and the rotation angle adjustment amount increases by 30% when the internal resistance exceeds the limit. During the dynamic response of the adjustment parameters, the tilt angle change and rotational motion are mutually restrictive. The least squares method is used to find the equilibrium point, ensuring cooling effect while avoiding mechanical vibration.

[0029] In step S103, during the design process of the composite battery, the thin film support is driven by a servo motor to adjust the angle between the thin film and the battery surface according to the first target tilt angle and the real-time temperature of the battery.

[0030] The film angle adjustment value is calculated based on the first target tilt angle and the battery temperature signal. The adjustment value changes according to a preset increment when the temperature exceeds the safe range. An incremental encoder is used to acquire the servo motor rotor position signal. The angle control quantity is obtained by comparing the position signal with a preset resolution parameter. The angle control quantity is used to generate a pulse width modulation signal. The deviation between the actual torque and the desired torque is calculated based on the servo motor rotor position signal. The motor compensation signal is obtained by comparing the torque deviation with a reference speed parameter. Kalman filtering is performed on the position data collected by the film angle sensor. The real-time calibration value is obtained by comparing the filtered position data with the target angle. The calibration value is output to the servo driver.

[0031] For example, the film angle adjustment value is calculated based on the first target tilt angle and the real-time battery temperature. An upper limit of 45 degrees Celsius and a lower limit of 10 degrees Celsius are set for the safe temperature range. The temperature change rate is calculated using a 0.1-second sampling period. If the temperature exceeds the safe range, the angle increases by 5 degrees per second; if the temperature drops below the safe range, the angle decreases by 3 degrees per second. The servo motor speed control is obtained through kinematic transformation. A 2000-line incremental encoder acquires the servo motor rotor position signal. A quadruple frequency decoding is used to obtain an angle resolution of 0.045 degrees per pulse. The speed compensation is calculated using a proportional gain coefficient of 1.5, generating a 20 kHz pulse width signal with an adjustable duty cycle to drive the servo motor. For the servo motor rotor position signal, the deviation between the actual torque and the desired torque is calculated using a gradient descent algorithm. A closed-loop feedback controller is constructed for the torque deviation, generating a motor control compensation signal based on a reference speed of 1000 rpm. The controller sampling period is 1 millisecond. Based on the position data collected by the thin-film angle sensor, a Kalman filter is used to eliminate mechanical vibration noise below 50 Hz. The position feedback data is compared with the target angle, and the real-time calibration value of the thin-film angle is output to the servo driver. During the thin-film angle adjustment process, the temperature change rate reflects the rate of battery heat accumulation. When the temperature rises rapidly from 25 degrees Celsius to 40 degrees Celsius, the temperature change rate reaches 1.5 degrees Celsius per second, and the angle adjustment speed correspondingly increases to 7.5 degrees Celsius per second, with the heat dissipation area increasing rapidly. Conversely, when the temperature drops from 40 degrees Celsius to 30 degrees Celsius, the change rate is -1 degree Celsius per second, and the angle adjustment speed decreases to 3 degrees Celsius per second, maintaining moderate heat dissipation. In kinematic conversion, the relationship between motor speed and angle change rate is 120 revolutions per minute corresponding to 6 degrees of angle change per second. The incremental encoder achieves position detection through quadrature signals. The A and B phase signals generate a 90-degree phase difference, and the resolution is improved to 8000 pulses per revolution through frequency quadrature technology. In practical applications, when the motor speed is 600 rpm, the encoder output frequency is 80 kHz, achieving a position resolution of 0.045 degrees. The proportional gain coefficient is dynamically adjusted according to the speed, with a gain of 2.0 at low speeds and decreasing to 1.2 at high speeds to avoid system oscillation. The pulse width signal, at a carrier frequency of 20 kHz, has a duty cycle ranging from 10% to 90%, corresponding to motor speeds from 0 to 3000 rpm. Torque control employs a gradient descent algorithm to achieve rapid convergence, completing one iteration calculation within a 1-m sampling period. Actual measurement data shows that the peak torque reaches 2 Nm during motor startup, decreasing to 0.5 Nm during steady-state operation, with torque fluctuation controlled within 0.1 Nm. The reference speed is set at 1000 rpm, corresponding to a diaphragm angle change rate of 50 degrees per minute, meeting the requirements for dynamic temperature response. Mechanical vibration mainly originates from motor operation and support movement, with spectral analysis showing it is primarily concentrated in the 20-50 Hz range.The state equation of the Kalman filter includes two components: position and velocity. The standard deviation of the observation noise is set to 0.1 degrees, and the standard deviation of the process noise is 0.05 degrees per second. After filtering, the smoothness of the position data is improved, and the residual vibration amplitude is reduced to 0.02 degrees. In a typical heat dissipation scenario, as the battery temperature rises from 25 degrees Celsius to 42 degrees Celsius, the film angle gradually increases from an initial 15 degrees to 45 degrees. Rapid heat dissipation causes the temperature rise rate to decrease from 1.2 degrees Celsius per second to 0.3 degrees Celsius per second. During the temperature recovery phase, the angle decreases slowly, returning to 20 degrees within 300 seconds. Throughout the process, the servo motor speed remains stable, and the position control accuracy is better than 0.1 degrees. Different types of batteries exhibit different temperature characteristics. Ternary lithium batteries have a more sensitive temperature response, with a 20% faster angle adjustment speed under the same operating conditions, while lithium iron phosphate batteries have better temperature stability, with a 30% slower angle adjustment speed.

[0032] Step S104: Control the film support to rotate according to the first target rotation angle, thereby adjusting the orientation of the film and detecting whether the film is kept on the target light-receiving surface or reflective surface. If the rotation angle causes the film to be not on the target light-receiving surface or reflective surface, adjust the orientation of the film in time to keep the film on the target light-receiving surface or reflective surface.

[0033] The deviation value is calculated based on the target rotation angle and the feedback signal from the rotary encoder. A current sampler is used to detect the three-phase current value of the drive motor. The rotation compensation amount is calculated based on the amplitude and phase of the three-phase current value. The photoelectric sensor array is controlled to operate according to the rotation compensation amount. The photoelectric sensor array receives surface reflected light data and obtains a light-receiving feature map through convolutional neural network processing. The backlight area value of the thin film is extracted from the light-receiving feature map. The orientation deviation angle is obtained by processing the backlight area value through a proportional-integral arithmetic unit. The orientation deviation angle is processed by a sliding mean filter. The filtered value is compared with a preset threshold. If the light intensity is lower than the preset standard value, the correction amount is increased. The rotation compensation angle of the bracket is output through the correction amount.

[0034] For example, the deviation value is calculated based on the first target rotation angle and the feedback signal from the rotary encoder. A current sampler with a sampling frequency of 10 kHz is used to detect the three-phase current value of the drive motor. The rotation compensation amount is calculated from the current amplitude and phase. Combined with the calibrated speed of 1000 revolutions per minute, a motor control quantity is generated, and the motor rotation angle is controlled through closed-loop feedback. An 8×8 photoelectric sensor array is arranged around the thin film surface with a spacing of 10 mm to receive surface reflected light data. A light-receiving feature map is constructed through a convolutional neural network containing 3 convolutional layers and 2 fully connected layers. The output is the matching degree between the light intensity distribution data of the thin film surface and the preset standard data of the light-receiving surface. The backlight area value of the thin film is extracted from the light intensity distribution data. The orientation deviation angle is obtained by a proportional-integral arithmetic unit. The proportional coefficient is set to 1.5 and the integration time constant is set to 0.5 seconds. The thin film orientation correction amount is calculated based on the orientation deviation angle and the upper limit of the support rotation speed of 90 degrees per second. For the orientation correction, a 16-point sliding average filter is used to remove high-frequency jitter. An adaptive threshold judgment rule is set: when the light intensity is lower than 80% of the preset standard value, the correction amount is increased by 20%; when the light intensity is higher than the standard value, the correction amount remains unchanged. The bracket rotation compensation angle is output from the correction amount, realizing closed-loop control of the film orientation. The film rotation accuracy control involves the coordinated operation of multiple links, the first being the motor drive control. A 10 kHz sampling frequency is used to detect the three-phase current, which can accurately capture subtle changes in the current waveform. The measured data shows that the current phase deviation is controlled within 2 degrees. When the target angle is 45 degrees, the motor runs at the calibrated speed of 1000 rpm, and the positioning error is limited to within 0.1 degrees through closed-loop control. The photoelectric sensor array adopts a matrix layout, with an 8×8 array covering an 80×80 mm area, and each sensor has a field of view of 30 degrees. In practical applications, when the film is on the light-receiving surface, the light intensity in the central region reaches 1000 lux, while the edge region reaches 800 lux. When it turns to the reflective surface, the light intensity in the central region drops to 200 lux, and the edge region reaches 150 lux. A convolutional neural network extracts light intensity features through a 3-layer, 16-channel convolutional structure. The fully connected layer outputs a matching degree value; when the matching degree exceeds 90%, the film is determined to be in the correct orientation. Backlight region feature extraction focuses on changes in light intensity gradient. Under normal orientation, the light intensity in the backlight region does not exceed 100 lux and is uniformly distributed. The proportional-integral controller parameters are optimized: a proportional coefficient of 1.5 ensures fast response, and an integral time constant of 0.5 seconds suppresses overshoot. Actual measurement data shows that during the switch from the light-receiving surface to the reflective surface, a 90-degree rotation is completed within 1 second, with an overshoot of less than 2 degrees. The moving average filter uses a 16-point data window, corresponding to a 1.6-millisecond time span, effectively filtering out mechanical vibrations above 50 Hz. The adaptive threshold is dynamically adjusted under different operating conditions. When the ambient light intensity decreases, the photoelectric signal attenuates by 20% as a whole, and the threshold is reduced accordingly to maintain detection sensitivity.Under cloudy conditions, the light intensity benchmark automatically drops to 600 lux, and the judgment rules are adjusted accordingly. In dynamic scene testing, the film orientation switches every 10 seconds, accumulating 1000 cycles without failure. During a single switching process, the peak starting current of the motor is 2 amps, and the steady-state current is 0.5 amps, with smooth rotation without vibration. Photoelectric detection provides real-time feedback of angle information, with a positioning accuracy better than 0.5 degrees. Under different temperature conditions, within the range of -10 to 50 degrees Celsius, the sensitivity change of the photoelectric device does not exceed 5%, and detection stability is maintained through adaptive threshold compensation. Repeat positioning accuracy testing shows that after 100 switching cycles between the light-receiving and reflective surfaces, the endpoint angle error is less than 1 degree, meeting the positioning requirements.

[0035] In step S105, during the adjustment of the film tilt angle and rotation angle, the battery temperature, charge / discharge status and internal resistance monitoring data are continuously acquired to determine the impact of the adjusted film position on the battery's operating state, forming a closed-loop feedback control, thereby adjusting the second target tilt angle and the second target rotation angle of the film.

[0036] A high-speed sampling device is used to acquire battery temperature monitoring data, charge / discharge status data, and internal resistance detection data. Based on these data, central difference calculations are used to obtain the temperature change rate, charge / discharge status change rate, and internal resistance change rate values. A three-dimensional response space is established based on these values. Radial basis function (RBF) support vector regression is used to calculate the influence of thin film adjustment on the correction of the three response values. The position adjustment correction amount is obtained from the combined change of the three-axis response values. A variable step-size gain controller is used to generate an adjustment signal for the position adjustment correction amount. The second target tilt angle value of the thin film is obtained by multiplying the response weights with the correction amount. If there is an angular deviation between the second target tilt angle value and the current tilt angle value, the angular deviation and the three response values ​​are used to form an input vector, which is then mapped through the output layer of a feedforward neural network to obtain the second target rotation angle value.

[0037] For example, battery temperature monitoring data, charge / discharge state data, and internal resistance detection data are collected every 0.1 seconds using a high-speed sampling device. Five-point central difference calculations are used to obtain the temperature change rate, charge / discharge state change rate, and internal resistance change rate values. The change rate values ​​obtained before and after thin-film adjustment are paired according to their time sequence to calculate the parameter adjustment response value. A three-dimensional response space is established based on the parameter adjustment response value, with the temperature change rate on the X-axis, the charge / discharge state change rate on the Y-axis, and the internal resistance change rate on the Z-axis. Support vector regression using a radial basis function kernel is used to calculate the correction influence of thin-film adjustment on the three response values. The position adjustment correction amount is output from the combined change of the three-axis response values. A variable step-size gain controller is used to generate the adjustment signal for the position adjustment correction amount. The weight of the temperature response is set to 0.5, the weight of the charge / discharge response is set to 0.3, and the weight of the internal resistance response is set to 0.2. The second target tilt angle value of the thin film is obtained by multiplying the response weights and the correction amount, combined with real-time response data. The angle deviation is obtained by subtracting the current tilt angle from the second target tilt angle value. This angle deviation, along with three response values, forms an input vector, which is then fed into a feedforward neural network with four hidden neurons. The hidden layers employ a hyperbolic tangent activation function, and the output layer is mapped to the range of 0 to 360 degrees to obtain the second target rotation angle value. Real-time monitoring of the battery parameter change rate reflects the immediate effect of thin-film adjustment; a sampling period of 0.1 seconds can capture rapid changes. In practical applications, when the thin-film tilt angle is adjusted from 30 degrees to 45 degrees, the temperature change rate decreases from 0.8 degrees Celsius per second to 0.3 degrees Celsius per second, the charging current change rate decreases from 0.5 amperes per second to 0.2 amperes per second, and the internal resistance change rate decreases from 0.05 milliohms per second to 0.02 milliohms per second. The center difference calculation uses data from two points before and after the adjustment to eliminate the influence of single-point fluctuations. During the construction of the three-dimensional response space, the temperature change rate was set to -2 to 2 degrees Celsius per second, the charge / discharge change rate to -1 to 1 ampere per second, and the internal resistance change rate to -0.1 to 0.1 milliohms per second. Support vector regression used a radial basis function kernel with a kernel parameter of 0.5 and a penalty factor of 1.0. When the temperature drops rapidly, the charging current stabilizes, and the internal resistance rises slowly, the correction influence shows that the temperature response dominates, and the correction amount is mainly determined by the temperature change. In variable step-size gain control, different response weights reflect the priority relationship of the parameters. The temperature response weight of 0.5 reflects the importance of heat dissipation control, the charge / discharge response weight of 0.3 focuses on current stability, and the internal resistance response weight of 0.2 monitors the battery health status. Experimental data shows that when the temperature change rate decreases by 50%, the tilt angle adjustment is 15 degrees, and when the charging current change rate decreases by 30%, the tilt angle adjustment is 8 degrees. The input vector of the neural network contains four components, processed through four hidden layers, each containing 16 neurons. The hyperbolic tangent activation function limits the output to the range of -1 to 1, and then converts it into the actual angle value through a linear mapping.During dynamic adjustment, when the tilt angle deviation is 20 degrees and the temperature change rate is 0.6 degrees Celsius per second, the network outputs a rotation angle of 90 degrees, achieving rapid adjustment. In actual operation, differences in response characteristics were observed between different types of batteries. Ternary lithium batteries are more sensitive to temperature changes, with a 60% reduction in temperature change rate under the same tilt angle adjustment, while lithium iron phosphate batteries have a slower temperature response, with a 40% reduction in the change rate. Charge and discharge characteristics also show significant differences; high-rate batteries experience rapid temperature rise during high-current charging, requiring larger tilt angle adjustments. Internal resistance changes are related to the battery's lifespan stage; new batteries have stable internal resistance, while aged batteries experience larger fluctuations. The controller adapts to different operating conditions through weighted adaptive adjustments.

[0038] Step S106: By training with monitoring data and adjustment data of film tilt angle and rotation angle for each adjustment, a mapping relationship between the position of the composite battery film and the battery operating state is established.

[0039] Acquire battery temperature data, charge / discharge status data, and internal resistance detection data. Record the thin-film tilt angle and rotation angle values ​​at corresponding times based on the battery temperature data, charge / discharge status data, and internal resistance detection data. Perform maximum-minimum value normalization to obtain normalized data. Establish a recurrent neural network model based on the normalized data. Input the tilt angle and rotation angle values ​​into the recurrent neural network model to obtain temperature values, charge / discharge status values, and internal resistance detection values. Establish a matrix database for the temperature values, charge / discharge status values, and internal resistance detection values. Use the tilt angle and rotation angle values ​​as row and column indices in the matrix database to filter and obtain filtered matrix data. Perform bidirectional linear interpolation calculations on the filtered matrix data to obtain battery state parameters under any combination of tilt angle and rotation angle values. Perform Gaussian smoothing on the battery state parameters and establish a state prediction model based on the matrix database.

[0040] For example, for battery temperature data, charge / discharge status data, and internal resistance detection data collected every 0.1 seconds, the corresponding thin-film tilt angle and rotation angle values ​​are recorded. Max-min normalization is used to map all data to the 0-1 range. Training data for a single adjustment process is formed by linking these data with timestamps. The training data is considered valid when the data fluctuation amplitude is less than 0.1. A recurrent neural network is constructed based on the single adjustment training data. The input layer contains two neurons for tilt angle and rotation angle values, the hidden layer contains four layers with 32 neurons each, and the output layer contains three neurons for temperature, charge / discharge status, and internal resistance. The learning rate is set to 0.01, and the training iterations are 1000 times. Gradient updates are performed using the mean squared error function. A matrix database is built based on the trained data records, using tilt angle and rotation angle values ​​as row and column indices. Matrix elements store battery state parameters. Outlier filtering is performed using quartiles, and missing data is supplemented using a cubic spline function to construct a continuous mapping data structure. Battery state parameters under arbitrary tilt and rotation angle combinations are calculated using bidirectional linear interpolation. Gaussian smoothing is applied to the interpolation results to eliminate peaks. A state prediction function is established by combining historical adjustment sequence data to achieve the mapping transformation from thin-film position to battery operating state. During training data acquisition, a precise correspondence is established between battery state parameters and thin-film position adjustment. Taking a typical adjustment process as an example, when the thin-film tilt angle increases from 15 degrees to 45 degrees, the temperature decreases from 42 degrees Celsius to 35 degrees Celsius, the charging current decreases from 2.5 amps to 1.8 amps, and the internal resistance decreases from 18 milliohms to 15 milliohms. Normalization maps the temperature to the range of 0.4–0.8, the charging current to the range of 0.3–0.9, and the internal resistance to the range of 0.2–0.7, eliminating the influence of dimensions. The recurrent neural network architecture is optimized for temporal characteristics. The input layer receives normalized position data, and deep features are extracted through four hidden layers. Each layer of 32 neurons provides sufficient feature extraction capability, avoiding underfitting due to an insufficiently small network. During training, a learning rate of 0.01 strikes a balance between convergence speed and stability, and 1000 iterations ensure sufficient learning. Real-world data shows that the prediction error is controlled within 5% after training. The database uses a matrix structure to store mapping relationships, with an inclination angle range of 0-90 degrees and a rotation angle range of 0-360 degrees, divided into 90×360 matrices at 1-degree intervals. Interquartile filtering removes outliers; data deviating from the median by 1.5 times the interquartile range is considered anomaly. Cubic spline interpolation maintains curve smoothness, ensuring a smooth transition between adjacent data points. In practical applications, when the inclination angle is 30 degrees and the rotation angle is 180 degrees, the corresponding temperature is 38 degrees Celsius, the charging current is 2.0 amps, and the internal resistance is 16 milliohms. Bidirectional linear interpolation enables the calculation of state parameters at arbitrary locations, performing interpolation operations within a 1-degree matrix grid. Gaussian smoothing uses a kernel function with a standard deviation of 0.5 to effectively suppress data fluctuations introduced by interpolation.Historical data shows that the state parameters fluctuate by 10% under different operating conditions with the same position adjustment, which can be dynamically adjusted through a predictive function. The mapping relationship between different battery types shows significant differences; ternary lithium batteries are more sensitive to temperature response, with the same tilt angle change resulting in a 15% temperature change, while lithium iron phosphate batteries only experience an 8% temperature change. Charge-discharge characteristics also show significant differences, with high-rate batteries requiring greater position adjustment during high-current charging. The internal resistance mapping relationship changes with battery life; the internal resistance of new batteries changes gradually, while after 500 cycles, the sensitivity of internal resistance to position adjustment increases by 30%.

[0041] Step S107: During the design process of the composite battery, the adjustment range and frequency of the thin film tilt angle and rotation angle are dynamically adjusted. Under the preset battery safety and efficiency conditions, the energy consumption of the target thin film position adjustment is optimized so that the position of the composite battery thin film can be adaptively adjusted.

[0042] Based on the battery operating state parameters, temperature safety threshold, charge / discharge safety threshold, and internal resistance safety threshold are obtained. A position adjustment amount is calculated using a proportional-integral-derivative (PID) controller. Upon receiving the position adjustment amount, a position adjustment optimizer is constructed using a deep neural network. This deep neural network outputs tilt adjustment step size and adjustment interval values ​​based on battery state parameters and motor energy consumption data. For the tilt adjustment step size and adjustment interval values, a speed sequence is constructed using an Euler-based numerical integrator. The total energy consumption of the adjustment process is obtained by accumulating the voltage-current product. A displacement curve is generated by combining the temperature safety threshold, charge / discharge safety threshold, and internal resistance safety threshold. A state transition matrix is ​​constructed based on the displacement curve. Real-time position deviation is obtained using a position sensor. The compensation amount is calculated by multiplying the position deviation by the gain matrix. Finally, a thin-film position adjustment command is output by combining the compensation amount with the battery state update value.

[0043] For example, based on the battery operating state parameters obtained from the mapping operation, a temperature safety threshold of 45 degrees Celsius, a charge / discharge safety threshold of 3 times, and an internal resistance safety threshold of 20 milliohms are set. A proportional-integral-derivative (PID) controller is used to calculate the position adjustment amount. The servo motor voltage and current values ​​are monitored in real time through a power detection circuit. The energy consumption for a single adjustment is obtained from the voltage-current product. The minimum adjustment step size is calculated by combining the safety threshold and the energy consumption value. A position adjustment optimizer is constructed using a deep neural network. The input layer contains battery state parameters and motor energy consumption data. The hidden layer contains a 4-layer structure with 64 neurons per layer. The output layer corresponds to the tilt angle adjustment step size and adjustment interval value. The reward function is set as a weighted sum of the safety margin and the reciprocal of the energy consumption. The network parameters are updated using the gradient ascent method to obtain the adjustment rules of the tilt angle and rotation angle. For the tilt angle adjustment value and the rotation angle value, a numerical integrator based on the Euler method is used to construct a speed sequence. The integration step size adaptively changes within the range of 0.1 to 1 second. The total energy consumption of the adjustment process is calculated by accumulating the voltage-current product. A speed curve is generated by combining the battery safety boundary constraints. The displacement curve is obtained by integrating the speed curve. An 8×8 state transition matrix is ​​constructed based on the displacement curve. A controller with a proportional gain of 1.5 and a derivative time of 0.5 seconds is used to perform trajectory tracking. A position sensor provides real-time position deviation feedback. The compensation amount is calculated by multiplying the deviation by the gain matrix. The compensation amount is then combined with the battery state update value to output the thin-film position adjustment command. The battery operating state and thin-film position adjustment form a closed-loop optimization system. The safety threshold is set based on the battery's physical characteristics. The temperature threshold of 45 degrees Celsius corresponds to the material stability boundary; above this temperature, electrolyte decomposition accelerates. The charge / discharge rate of 3C is the balance point between capacity and lifespan; higher rates lead to lithium dendrite growth. The internal resistance threshold of 20 milliohms reflects the battery's health status; exceeding this value indicates significant performance degradation. The energy consumption optimization process is achieved through real-time monitoring of motor parameters. Under typical operating conditions, the servo motor operates at a voltage of 24 volts, with a no-load current of 0.5 amps and a load current of 2.5 amps. A single adjustment process lasts 2 seconds, with a total energy consumption of approximately 120 joules. The minimum adjustment step size is dynamically adjusted according to energy consumption. When energy consumption exceeds 150 joules, the step size decreases to 5 degrees; when energy consumption is below 50 joules, the step size increases to 15 degrees. The deep neural network is trained using multi-condition data, including standard operating conditions, fast charging conditions, and high-temperature conditions. The input data is normalized, with temperature range mapped to 0-1, current to 0-1.5, and internal resistance to 0-2. During network training, the reward function weights are set to a safety margin of 0.7 and an energy consumption term of 0.3, reflecting a safety-first principle. Training results show that the adjustment interval is 10 seconds under standard operating conditions and shortened to 5 seconds under fast charging conditions. Numerical integration uses an adaptive step size strategy: the step size is 0.1 seconds when temperature changes drastically and increases to 1 second when the temperature is stable. Experimental data shows that during a 45-degree tilt adjustment, a 0.1-second step size results in high trajectory smoothness and less than 1 degree of position overshoot, but increases computational load by 5 times.The state transition matrix reflects the transformation relationship between eight typical position points, each containing two components: tilt angle and rotation angle. Different battery types exhibit unique regulation characteristics. Ternary lithium batteries have a fast temperature response and a short adjustment interval, typically 3 seconds; lithium iron phosphate batteries have good temperature stability, allowing the adjustment interval to be extended to 15 seconds. Large-capacity batteries, due to their large heat capacity, typically have an adjustment step size of 10 degrees or more; small-capacity batteries, with their smaller heat capacity, have an adjustment step size reduced to around 5 degrees. New batteries have stable internal resistance, and their regulation is mainly determined by temperature; cyclically aged batteries have large internal resistance fluctuations, and their regulation is more constrained by internal resistance. Controller parameters also change with operating conditions. During fast charging, the proportional gain is increased to 2.0 to accelerate response speed; under low-temperature conditions, the derivative time is extended to 0.8 seconds to reduce overshoot. Position deviation compensation uses a nonlinear gain, with a gain of 1.0 for small deviations and increasing to 1.8 for large deviations, achieving rapid convergence.

[0044] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for adaptively adjusting the position of a thin film in a composite battery, characterized in that, The method includes: simulating the operation of the composite battery through several simulations to obtain the operating state of the target composite battery; monitoring the battery temperature, charge / discharge state, and internal resistance of the target composite battery in real time during its operating state; comparing the battery temperature, charge / discharge state, and internal resistance monitoring data of the target composite battery with preset safe ranges for battery temperature, charge / discharge state, and internal resistance, respectively, to determine the first target tilt angle and the first target rotation angle of the composite battery film, including: acquiring battery temperature monitoring data; obtaining the initial tilt angle of the film based on the deviation between the temperature monitoring data and the preset safe temperature range; obtaining the current density over-limit value based on the charge / discharge current monitoring data; and determining the initial tilt angle based on the current... The process includes: obtaining a reference value for the film rotation angle based on the density exceeding the limit; collecting the battery internal resistance value, converting the portion of the internal resistance value exceeding a preset internal resistance safety threshold into angular coordinate components, and obtaining the film tilt angle correction amount by performing trigonometric function transformation on the deviation value and the angular coordinate components; using a backpropagation neural network to perform weighted calculation on the initial film tilt angle and the tilt angle correction amount, and obtaining the first target tilt angle value and the first target rotation angle value of the film from the neural network output layer; further including: determining the adjustment scale of the battery tilt angle based on the value of the battery temperature exceeding the preset safety range and the value of the charge / discharge state exceeding the preset safety range respectively; and determining the internal resistance condition based on the value of the internal resistance exceeding the preset safety range. The adjustment scale for the rotation angle is determined based on the adjustment scale for the battery tilt angle and the adjustment scale for the rotation angle under the condition of internal resistance. This includes: calculating the tilt angle adjustment amount corresponding to the temperature using three-point linear interpolation of the temperature interval based on the battery temperature exceeding the limit value; calculating the total tilt angle adjustment value by combining the tilt angle adjustment amount with the charge / discharge state exceeding the limit value and the rate segmentation point; obtaining the rate difference value using a standard resistance reference value for the internal resistance exceeding the limit value; mapping the rate difference value to the angle interval using a hyperbolic tangent function to obtain the rotation angle reference value; constructing an adjustment amount matrix with the rotation angle reference value and the total tilt angle adjustment value; and using long and short time intervals... The memory network trains the correspondence between the excessive values ​​of battery temperature exceeding the preset safety range, charging / discharging state exceeding the preset safety range, and internal resistance exceeding the preset safety range and the adjustment amount. The correspondence is limited to the adjustment range by an activation function to obtain a tilt angle / rotation angle mapping matrix. The initial values ​​of the adjustment parameters are obtained by performing a dot product operation on the values ​​of the mapping matrix and the adjustment amount matrix. The initial values ​​of the adjustment parameters are used to calculate the first target tilt angle and the first target rotation angle of the composite battery film through least squares iterative calculation. In the design process of the composite battery, the film support is driven by a servo motor, and the angle between the film and the battery surface is adjusted according to the first target tilt angle and the real-time battery temperature.Based on the first target rotation angle, the thin-film support is controlled to rotate, thereby adjusting the orientation of the thin film. It is detected whether the thin film remains on the target light-receiving or reflective surface. If the rotation angle causes the thin film to deviate from the target light-receiving or reflective surface, the film orientation is adjusted promptly to ensure it remains on the target surface. During the adjustment of the thin film tilt and rotation angles, battery temperature, charge / discharge status, and internal resistance monitoring data are continuously acquired to determine the impact of the adjusted thin film position on the battery's operating state, forming a closed-loop feedback control to adjust the second target tilt and rotation angles of the thin film. By training with the monitoring data and adjustment data of each thin film tilt and rotation angle adjustment, a mapping relationship between the composite battery thin film position and the battery's operating state is established. During the design of the composite battery, the adjustment amplitude and frequency of the thin film tilt and rotation angles are dynamically adjusted. Under preset battery safety and efficiency conditions, the energy consumption of the targeted thin film position adjustment is controlled, enabling the composite battery thin film position to adaptively adjust.

2. The method according to claim 1, characterized in that, The process of simulating the operation of the composite battery through several simulations to obtain the working state of the target composite battery and to monitor the battery temperature, charge / discharge state, and internal resistance in real time includes: acquiring surface temperature data of the composite battery using a temperature sensor array; obtaining temperature distribution data based on the temperature data through bicubic spline interpolation; calculating heat flux density and thermal conductivity based on the temperature distribution data; obtaining temperature field data through the Laplace equation and the finite difference method; establishing a convolutional neural network model for the temperature field data, wherein the convolutional neural network model uses the temperature field data as the input layer and current data as the output layer, and obtaining charge / discharge state prediction results through forward propagation and backward gradient correction; extracting current and temperature feature vectors from the charge / discharge state prediction results; performing feature matching based on the feature vectors and measured voltage data; and obtaining composite battery internal resistance change data by calculating the voltage-to-current ratio using the least squares method.

3. The method according to claim 1, characterized in that, In the design process of the composite battery, a servo motor drives a thin-film support to adjust the angle between the thin film and the battery surface based on a first target tilt angle and the real-time battery temperature. This includes: calculating a thin-film angle adjustment value based on the first target tilt angle and the battery temperature signal, wherein the adjustment value changes according to a preset increment when the temperature exceeds the safe range; acquiring the servo motor rotor position signal using an incremental encoder, obtaining an angle control quantity by comparing the position signal with a preset resolution parameter, and using the angle control quantity to generate a pulse width modulation signal; calculating the deviation between the actual torque and the desired torque based on the servo motor rotor position signal, obtaining a motor compensation signal by comparing the torque deviation with a reference speed parameter; performing Kalman filtering on the position data collected by the thin-film angle sensor, obtaining a real-time calibration value by comparing the filtered position data with the target angle, and outputting the calibration value to the servo driver.

4. The method according to claim 1, characterized in that, The process of controlling the film support to rotate according to the first target rotation angle, thereby adjusting the orientation of the film, and detecting whether the film is on the target light-receiving or reflective surface, and if the rotation angle causes the film to be off the target light-receiving or reflective surface, then adjusting the film orientation in time to keep the film on the target light-receiving or reflective surface, includes: calculating the deviation value based on the target rotation angle and the feedback signal of the rotary encoder; using a current sampler to detect the three-phase current value of the drive motor; calculating the rotation compensation amount based on the amplitude and phase of the three-phase current value; controlling the operation of the photoelectric sensor array according to the rotation compensation amount; the photoelectric sensor array receiving surface reflected light data and processing it through a convolutional neural network to obtain a light-receiving feature map; extracting the backlight area value of the film from the light-receiving feature map; processing the backlight area value through a proportional-integral arithmetic unit to obtain the orientation deviation angle; processing the orientation deviation angle using a sliding mean filter; judging based on the filtered value and a preset threshold, if the light intensity is lower than a preset standard value, increasing the correction amount; and outputting the support rotation compensation angle through the correction amount.

5. The method according to claim 1, characterized in that, During the adjustment of the film tilt angle and rotation angle, battery temperature, charge / discharge status, and internal resistance monitoring data are continuously acquired to determine the impact of the adjusted film position on the battery's operating state, forming a closed-loop feedback control to adjust the second target tilt angle and the second target rotation angle of the film. This includes: acquiring battery temperature monitoring data, charge / discharge status data, and internal resistance detection data using a high-speed sampling device; obtaining the temperature change rate, charge / discharge status change rate, and internal resistance change rate values ​​through central difference calculation based on the battery temperature monitoring data, charge / discharge status data, and internal resistance detection data; and then, based on the temperature change rate and... A three-dimensional response space is established using the numerical values ​​of the charge / discharge state change rate and the internal resistance change rate. The influence of thin film adjustment on the correction of the three response values ​​is calculated using radial basis function kernel function support vector regression. The position adjustment correction amount is obtained from the combined change of the three-axis response values. An adjustment signal is generated using a variable step size gain controller for the position adjustment correction amount. The second target tilt angle value of the thin film is obtained by multiplying the response weight with the correction amount. If there is an angular deviation between the second target tilt angle value and the current tilt angle value, the angular deviation and the three response values ​​are used to form an input vector. The value of the second target rotation angle is obtained by mapping the output layer of the feedforward neural network.

6. The method according to claim 1, characterized in that, The process involves training the system using monitoring data and adjustment data for each thin-film tilt and rotation angle adjustment to establish a mapping relationship between the composite battery thin-film position and the battery's operating state. This includes: acquiring battery temperature data, charge / discharge state data, and internal resistance detection data; recording the corresponding thin-film tilt and rotation angle values ​​based on these data; performing maximum-minimum normalization to obtain normalized data; establishing a recurrent neural network model based on the normalized data; inputting the tilt and rotation angle values ​​into the recurrent neural network model to obtain temperature, charge / discharge state, and internal resistance detection values; establishing a matrix database for these values, using the tilt and rotation angle values ​​as row and column indices, and filtering the data to obtain filtered matrix data; performing bidirectional linear interpolation on the filtered matrix data to obtain battery state parameters for any combination of tilt and rotation angle values; performing Gaussian smoothing on the battery state parameters; and establishing a state prediction model based on the matrix database.

7. The method according to claim 1, characterized in that, In the design process of the composite battery, the adjustment amplitude and frequency of the thin film tilt angle and rotation angle are dynamically adjusted. Under the premise of preset battery safety and efficiency, the energy consumption of the target thin film position adjustment is targeted to enable the composite battery thin film position to be adaptively adjusted. This includes: obtaining temperature safety threshold, charge / discharge safety threshold, and internal resistance safety threshold based on battery operating state parameters; calculating the position adjustment amount through a proportional-integral-derivative controller; receiving the position adjustment amount and constructing a position adjustment optimizer using a deep neural network. The deep neural network outputs tilt angle adjustment step size and adjustment interval values ​​based on battery state parameters and motor energy consumption data; constructing a speed sequence using a numerical integrator based on the Euler method for the tilt angle adjustment step size and adjustment interval values; obtaining the total energy consumption of the adjustment process by accumulating the voltage-current product; generating a displacement curve by combining the temperature safety threshold, charge / discharge safety threshold, and internal resistance safety threshold; constructing a state transition matrix based on the displacement curve; obtaining real-time position deviation using a position sensor; calculating the compensation amount by multiplying the position deviation by the gain matrix; and outputting a thin film position adjustment command by combining the compensation amount with the battery state update value.

Images