Temperature control method of warm isostatic press, electronic device, and storage medium

Abstract

The application relates to the technical field of temperature control, and discloses a temperature control method of a warm isostatic press, an electronic device and a storage medium. The method comprises the following steps: acquiring working condition data in a cavity of the warm isostatic press; inputting the working condition data into a preset pressure fluctuation prediction model, so as to predict the pressure fluctuation in the cavity of the warm isostatic press based on the working condition data, and obtain corresponding pressure fluctuation prediction data; determining temperature error prediction data corresponding to the pressure fluctuation prediction data based on a preset pressure fluctuation-temperature error mapping relationship; and performing feedforward correction on temperature control parameters of the warm isostatic press based on the temperature error prediction data, so as to offset temperature deviation represented by the temperature error prediction data. The embodiment of the application can improve the real-time performance and stability of temperature control in the pressure increasing and decreasing process of the warm isostatic press.

Description

Technical Field

[0001] This application relates to the field of temperature control technology, and in particular to a temperature control method, electronic device and storage medium for a thermostatic press. Background Technology

[0002] The warm isostatic press is a core piece of equipment for the densification of electrodes and electrolytes in solid-state batteries. During the solid-state battery fabrication process, the warm isostatic press needs to operate in a specific high-pressure, wide-temperature environment, with an operating temperature range of approximately 40-200°C and a common operating pressure as high as 600 MPa.

[0003] In related technologies, temperature control methods for warm isostatic presses mostly employ traditional PID control or simple linear model prediction, resulting in significant lag in the temperature control process. During the pressurization and depressurization process, the warm isostatic press cannot adapt to parameter fluctuations, easily leading to excessive temperature fluctuations. This causes thermal stress damage to the material, resulting in residual voids within the solid-state battery blank and poor solid-solid interface contact, severely impacting the quality of solid-state battery fabrication. Summary of the Invention

[0004] The purpose of this application is to provide a temperature control method, electronic device and storage medium for a thermostatic press, which aims to improve the real-time performance and stability of temperature control during the pressure increase and decrease process of the thermostatic press.

[0005] This application provides a temperature control method for a thermostatic press, including: Acquire operating condition data within the cavity of the thermostatic press; The operating condition data is input into a preset pressure fluctuation prediction model to predict the internal pressure fluctuation of the isostatic press based on the operating condition data, and obtain the corresponding pressure fluctuation prediction data. Based on the preset pressure fluctuation-temperature error mapping relationship, the temperature error prediction data corresponding to the pressure fluctuation prediction data is determined; the pressure fluctuation-temperature error mapping relationship is used to describe the thermodynamic mapping relationship between the pressure fluctuation amount and the temperature error amount. Based on the temperature error prediction data, the temperature control parameters of the isostatic press are feedforward corrected to offset the temperature deviation represented by the temperature error prediction data.

[0006] In some embodiments, the step of predicting the internal pressure fluctuation of the isostatic press based on the operating condition data includes: The operating condition data is time-aligned to construct a time-series input tensor containing pressure data, temperature data, and temperature control power data from multiple consecutive historical moments within the historical time domain. The temporal input tensor is subjected to time-step temporal dependency feature extraction processing to obtain a context encoding vector that encodes historical temporal dependencies. Using the pressure change of the isostatic press in the future time domain as the target, the context encoding vector is subjected to regression mapping to obtain the pressure fluctuation prediction data.

[0007] In some embodiments, the expression for the pressure fluctuation-temperature error mapping relationship is:

[0008] in, For temperature error prediction data, This provides the initial temperature data of the working medium for the current forecast period. The coefficient of volumetric expansion of the working medium. The density of the working medium, The specific heat capacity of the working medium. This is the pressure-temperature coupling coefficient. For pressure fluctuation prediction data, It is a natural constant. For pressurization duration, To predict the step size, is the thermal time constant.

[0009] In some embodiments, the step of feedforward correction of the temperature control parameters of the isostatic press based on the temperature error prediction data includes: Based on the temperature error prediction data, a feedforward compensation amount is generated; The feedforward compensation is added to the temperature setpoint of the isostatic press in a direction opposite to the temperature deviation trend represented by the temperature error prediction data to obtain the corrected temperature setpoint. Based on the corrected temperature setpoint, the temperature control power of the isostatic press is adjusted.

[0010] In some embodiments, the temperature control method for the isostatic press further includes: Obtain the actual temperature error data of the isostatic press; Using the actual temperature error data as a monitoring signal, the parameters of the pressure fluctuation prediction model and the thermodynamic parameters in the pressure fluctuation-temperature error mapping relationship are updated online iteratively.

[0011] In some embodiments, the temperature control method for the isostatic press further includes: When the temperature data inside the isostatic press chamber exceeds a preset temperature threshold, a first working medium is used for heating; otherwise, a second working medium is used for heating. The thermal stability of the second working medium is better than that of the first working medium, and the maximum working temperature of the second working medium is higher than that of the first working medium.

[0012] In some embodiments, the temperature control method for the isostatic press further includes: When the temperature data inside the isostatic press chamber exceeds the preset temperature safety range, an alarm is triggered and the heating or cooling actuator is cut off. When the pressure data inside the isostatic press chamber exceeds the preset pressure safety threshold, the pressurization system is controlled to stop pressurization.

[0013] In some embodiments, the temperature control method for the isostatic press further includes: The pressure fluctuation prediction data and the operating condition data are input into the thermal behavior simulation model of the solid-state battery module to predict the transient temperature gradient value inside the solid-state battery module. The pressure ramping and depressurization rates of the isostatic press are adjusted based on the deviation between the transient temperature gradient value and the preset gradient threshold.

[0014] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the temperature control method of the above-described isostatic press.

[0015] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the temperature control method for the isostatic press described above.

[0016] The beneficial effects of this application are as follows: By acquiring operating condition data and predicting pressure fluctuations, potential disturbances that may cause temperature changes can be detected in advance. Based on the pressure fluctuation-temperature error mapping relationship, the corresponding temperature error prediction data can be determined, quantifying the specific impact of pressure changes on temperature. This transforms physical phenomena into operable control criteria. Finally, feedforward correction is performed based on the temperature error prediction data, making the temperature control of the isostatic press no longer a passive response but an active intervention. Therefore, by predicting pressure fluctuations in real time and establishing a thermodynamic mapping relationship for feedforward temperature correction, the lag in temperature control under dynamic operating conditions is overcome. This improves the real-time performance and stability of temperature control during the pressure ramping and depressurization process of the isostatic press, avoids thermal stress damage to battery components, and improves the quality of solid-state battery fabrication. Attached Figure Description

[0017] Figure 1This diagram illustrates the application environment of the temperature control method for the isostatic press provided in the embodiments of this application.

[0018] Figure 2 This is a flowchart of the temperature control method for a thermostatic press provided in the embodiments of this application.

[0019] Figure 3 This is a flowchart of a method for predicting internal pressure fluctuations in a thermostatic isostatic press provided in an embodiment of this application.

[0020] Figure 4 This is a flowchart of a method for feedforward correction of temperature control parameters of a thermostatic press provided in an embodiment of this application.

[0021] Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0023] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and drawings are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application. Furthermore, the information, data, and signals involved in the embodiments of this application are all authorized by relevant parties or have been fully authorized by all parties, and the collection, use, and processing of related data comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0025] In the temperature control process of a warm isostatic press, due to the high-pressure, wide-temperature-range working environment, a thermodynamic mapping relationship exists between pressure fluctuations and temperature errors when operating data changes. Traditional temperature control methods fail to establish a dynamic model of this mapping relationship, resulting in a lag in temperature control. Specifically, the change in the medium's heat capacity caused by pressure fluctuations is not compensated for in real time, leading to accumulated temperature deviations and affecting the densification quality of the solid-state battery blank. Furthermore, this lag prevents the temperature control system from adaptively adjusting parameters during pressure increases and decreases, causing temperature fluctuations to exceed the allowable range of the process. For example, in the solid-state battery electrolyte pressing process, when the pressure in the warm isostatic press chamber rapidly increases from 400 MPa to 600 MPa, the working medium experiences instantaneous temperature fluctuations due to its coefficient of thermal expansion. Moreover, the temperature control system, based on historical temperature data, cannot predict the thermodynamic effects caused by the pressure increase, causing the actual chamber temperature to deviate from the set value. Consequently, uneven thermal stress forms inside the blank, leading to microscopic voids in the electrolyte layer and deterioration of the solid-solid interface contact.

[0026] If these issues are not addressed, temperature fluctuations will exacerbate thermal stress damage to materials, leading to a continuous deterioration in the interfacial bonding strength within solid-state battery modules. Specifically, increased porosity will significantly reduce ionic conductivity, resulting in poor battery cycle performance. Furthermore, this problem will cause product consistency issues in mass production, hindering the industrial application of solid-state batteries.

[0027] Based on this, embodiments of this application provide a temperature control method, electronic device, and storage medium for a warm isostatic press. By predicting pressure fluctuations in real time and establishing a thermodynamic mapping relationship for feedforward temperature correction, the defect of temperature control lag under dynamic operating conditions is overcome. This can improve the real-time performance and stability of temperature control during the pressure increase and decrease process of the warm isostatic press, avoid thermal stress damage to battery components, and improve the quality of solid-state battery fabrication.

[0028] Figure 1 This diagram illustrates the application environment of the temperature control method for the isostatic press provided in this embodiment of the application. (See also...) Figure 1This method is applied to the temperature control system of a thermostatic press. The system includes a terminal 101 and a server 102. Terminal 101 and server 102 are connected via a network. Terminal 101 can be at least one of a mobile phone, tablet, laptop, or vehicle-mounted terminal. Server 102 can be a standalone server or a server cluster consisting of several servers. Terminal 101 sends operating condition data from within the thermostatic press cavity to server 102. Server 102 acquires the operating condition data from within the thermostatic press cavity, inputs the operating condition data into a preset pressure fluctuation prediction model, and predicts the internal pressure fluctuation of the thermostatic press based on the operating condition data, obtaining corresponding pressure fluctuation prediction data. Based on a preset pressure fluctuation-temperature error mapping relationship, it determines the temperature error prediction data corresponding to the pressure fluctuation prediction data. Based on the temperature error prediction data, it performs feedforward correction on the temperature control parameters of the thermostatic press to offset the temperature deviation represented by the temperature error prediction data. The pressure fluctuation-temperature error mapping relationship describes the thermodynamic mapping relationship between the pressure fluctuation and temperature error.

[0029] It should be understood that Figure 1 The application scenarios shown are merely examples. In practical applications, the temperature control method for the isostatic press provided in this application embodiment can also be applied to other scenarios. For example, the above-mentioned temperature control method for the isostatic press can be directly applied to terminal 101. Terminal 101 is used to acquire the operating condition data inside the isostatic press cavity, input the operating condition data into a preset pressure fluctuation prediction model, and predict the internal pressure fluctuation of the isostatic press based on the operating condition data to obtain the corresponding pressure fluctuation prediction data. Based on a preset pressure fluctuation-temperature error mapping relationship, the temperature error prediction data corresponding to the pressure fluctuation prediction data is determined. Based on the temperature error prediction data, the temperature control parameters of the isostatic press are fed forward to compensate for the temperature deviation represented by the temperature error prediction data.

[0030] See Figure 2 In one embodiment, a temperature control method for a thermostatic press is provided. The execution subject of the method is a terminal or a server, including but not limited to steps S201 to S204.

[0031] Step S201: Obtain the operating condition data inside the cavity of the isostatic press.

[0032] Operating data refers to the various real-time operating parameters generated within the chamber and related systems of a thermostatic press during operation. Operating data typically includes, but is not limited to, pressure data, temperature data, heating power data, and cooling flow rate data within the chamber. This data is used to monitor equipment status, evaluate the process, and make subsequent control decisions.

[0033] There are several ways to acquire operating data within the cavity of a thermostatic press. For example, manual inspection can be used, with operators periodically reading and recording the readings of the pressure gauges and thermometers installed on the press. Alternatively, independent sensors, such as thermocouples and pressure sensors, can be deployed to periodically collect temperature and pressure data within the cavity and store this data in a local data logger. Another approach is to utilize the equipment's built-in simple data interface to transmit the current pressure and temperature data to an external processing unit via a wired connection.

[0034] Step S202: Input the operating condition data into the preset pressure fluctuation prediction model to predict the internal pressure fluctuation of the isostatic press based on the operating condition data, and obtain the corresponding pressure fluctuation prediction data.

[0035] A pressure fluctuation prediction model is a mathematical or computational model used to analyze and predict future pressure trends within a thermostatic press. This model processes historical and real-time operating data to identify patterns in pressure changes and, based on these patterns, quantitatively predicts pressure fluctuations over a future period, thus providing forward-looking pressure fluctuation prediction data.

[0036] Pressure fluctuation prediction data is the output of the pressure fluctuation prediction model, which characterizes the amount or trend of pressure change in the cavity of the isostatic press at a specific point in time or over a period of time in the future. This data forms the basis for subsequently determining the temperature error prediction data.

[0037] Pressure fluctuation prediction models can be constructed using linear regression models. These models fit a straight line to pressure data from several past time points using the least squares method and extrapolate to predict pressure changes at the next time step. Alternatively, a prediction mechanism based on historical averages can be built, calculating the average pressure changes over a past period as the predicted value for future pressure fluctuations. In some cases, a lookup table method can also be used. A lookup table is pre-built based on typical pressure change patterns under different operating conditions. When current operating condition data is obtained, the corresponding pressure fluctuation prediction data is looked up in the table. Through these methods, a preliminary estimate of future pressure fluctuations can be obtained.

[0038] Step S203: Based on the preset pressure fluctuation-temperature error mapping relationship, determine the temperature error prediction data corresponding to the pressure fluctuation prediction data.

[0039] The pressure fluctuation-temperature error mapping relationship describes the thermodynamic mapping relationship between pressure fluctuations and temperature errors. It can be understood as a function or model describing the thermodynamic relationship between pressure fluctuations and the resulting temperature errors within a thermostatic press. This mapping relationship reveals how pressure changes affect the temperature within the chamber through thermodynamic effects, such as the thermal effects caused by gas compression or expansion.

[0040] The temperature error prediction data is determined based on the pressure fluctuation prediction data and the pressure fluctuation-temperature error mapping relationship. It characterizes the amount by which the internal temperature of the isostatic press may deviate from the target setpoint without any corrective measures. This data serves as the basis for feedforward correction.

[0041] The establishment of the pressure fluctuation-temperature error mapping relationship can be based on the ideal gas law or the simple first law of thermodynamics. An approximate proportionality coefficient can be derived through theoretical calculations, and the pressure fluctuation can be directly multiplied by this coefficient to obtain the temperature error. Alternatively, a series of controlled experiments can be conducted in a laboratory environment to record the temperature error generated under different pressure fluctuations. This data can then be plotted as an empirical curve, and interpolation methods can be used to determine the predicted temperature error data in practical applications. Another approach is to construct a piecewise linear function that divides the pressure fluctuation range into multiple intervals, each interval corresponding to a fixed pressure-temperature error conversion factor.

[0042] Step S204: Based on the temperature error prediction data, the temperature control parameters of the isostatic press are feedforward corrected to offset the temperature deviation represented by the temperature error prediction data.

[0043] Temperature control parameters refer to the various adjustable variables used to regulate the temperature of the isostatic press chamber. These parameters may include the temperature setpoint, heating power, cooling rate, and the proportional, integral, and derivative coefficients in the PID controller. By adjusting these parameters, precise control of the chamber temperature can be achieved.

[0044] Implementations of feedforward correction can include directly adjusting the temperature setpoint. For example, if a future temperature rise of 2°C is predicted, the current temperature setpoint can be lowered by 2°C to ensure that the actual temperature remains at the target value when pressure fluctuations occur. Alternatively, the heater's power output can be directly adjusted based on predicted temperature error data; for example, increasing the heating power in advance when a temperature drop is predicted. In some cases, parameters such as the proportional gain or integral time in the PID controller can be adjusted to make it respond more sensitively or less sensitively to predicted temperature errors. These feedforward correction measures aim to pre-compensate for temperature deviations before they actually occur.

[0045] The following example will provide a more detailed explanation of the above technical solution: Suppose that during the fabrication of a solid-state battery module, a warm isostatic press is densifying a batch of electrode materials at a target temperature of 150°C, and a pressure increase from 300 MPa to 400 MPa is required. Under traditional temperature control methods, when the pressure begins to rise, the chamber temperature increases due to the heat released by gas compression. However, PID controllers typically wait until the actual temperature deviates from the set value before adjusting, resulting in a hysteresis overshoot in temperature control.

[0046] The temperature control method of this embodiment significantly improves the process. First, multiple sensors within the isostatic press chamber continuously acquire operating data, including real-time pressure, temperature, and heating power. For example, this data is collected and transmitted to the actuator every second.

[0047] Subsequently, this operating data is input into a pre-defined pressure fluctuation prediction model. This model may be a simple autoregressive model trained on historical data, which analyzes the pressure change trend over the past 10 seconds to predict the potential increase in pressure over the next 5 seconds. For example, the model predicts that the pressure will rise by 20 MPa from its current value over the next 5 seconds. This yields the corresponding pressure fluctuation prediction data.

[0048] Next, based on a pre-defined pressure fluctuation-temperature error mapping relationship, the corresponding temperature error prediction data is determined. This mapping relationship may be an empirical formula, such as ΔT = k * ΔP, where k is a constant determined experimentally. Assuming that according to this mapping relationship, a predicted pressure increase of 20 MPa will lead to a 1.5°C increase in the cavity temperature, this 1.5°C is the temperature error prediction data.

[0049] Finally, based on the predicted temperature error data, the temperature control parameters of the isostatic press are feedforward corrected. Specifically, before the pressure actually rises and causes the temperature to increase, the control system lowers the current temperature setpoint from 150°C by 1.5°C, correcting it to 148.5°C. At this time, the heating system of the isostatic press will adjust according to the new setpoint, for example, by slightly reducing the heating power. When the pressure actually rises and the cavity temperature increases due to the compression effect, the upward trend of the actual temperature will be effectively offset because the setpoint has been lowered in advance, allowing the actual temperature inside the cavity to be maintained more closely around 150°C, thereby avoiding temperature overshoot.

[0050] Through the above process, this method achieves precise control of the internal temperature of a thermostatic press. The various technical features work closely together: the acquisition of operating data provides the basis for prediction; the pressure fluctuation prediction model provides forward-looking information; the pressure fluctuation-temperature error mapping relationship transforms pressure changes into temperature effects; and the feedforward correction uses this information to adjust control parameters in advance, forming a complete, closed-loop prediction-correction control chain that effectively solves the problem of temperature fluctuations caused by pressure changes.

[0051] Based on the above examples, the overall technical concept of this embodiment demonstrates a significant technical contribution. In traditional temperature control methods for warm isostatic presses, such as pure PID control, it is essentially a feedback control mechanism. When the pressure inside the warm isostatic press chamber changes, causing the temperature to deviate from the set value, the PID controller only detects this deviation and then calculates a correction to adjust the heating or cooling power. This "post-hoc" adjustment method inevitably has a response lag, especially during rapid pressure increases or decreases, which can easily lead to significant temperature overshoot or undershoot, causing the material to remain in a non-ideal temperature state for an extended period.

[0052] In contrast, this embodiment achieves "pre-emptive" compensation for temperature deviations by introducing pressure fluctuation prediction and a feedforward correction mechanism based on thermodynamic mapping. In the example above, when it is predicted that an increase in pressure will lead to an increase in temperature, the temperature setpoint can be lowered or the heating power adjusted in advance, thus offsetting the temperature increase before it actually occurs. This proactive control strategy effectively overcomes the lag problem of traditional feedback control. Specifically, the technical contributions of this embodiment are as follows: First, by acquiring operating data and predicting pressure fluctuations, potential disturbances that may cause temperature changes can be detected in advance, which contrasts sharply with traditional methods that rely solely on temperature sensors to detect temperature deviations that have already occurred. Second, the introduction of the pressure fluctuation-temperature error mapping relationship quantifies the specific impact of pressure changes on temperature, transforming physical phenomena into operable control criteria, rather than relying solely on experience or trial and error. Finally, feedforward correction based on predicted temperature errors makes the temperature control of the isostatic press no longer a passive response, but an active intervention. Therefore, temperature fluctuations within the chamber are significantly suppressed, and the material can be maintained in a more stable temperature environment throughout the process, thereby reducing the risk of thermal stress damage and ultimately contributing to improved fabrication quality and performance consistency of solid-state battery modules. The technical solution of this embodiment provides a more precise, efficient, and robust temperature control strategy for a warm isostatic press.

[0053] See Figure 3 In one embodiment, the method for predicting the internal pressure fluctuation of a thermostatic press includes, but is not limited to, steps S301 to S303.

[0054] Step S301: Perform time-series alignment processing on the operating data to construct a time-series input tensor containing pressure data, temperature data, and temperature control power data from multiple consecutive historical moments within the historical time domain.

[0055] Step S302: Perform time-step temporal dependency feature extraction processing on the temporal input tensor to obtain the context encoding vector that encodes the historical temporal dependency relationship.

[0056] Step S303: Taking the pressure change of the isostatic press in the future time domain as the target, perform regression mapping on the context encoding vector to obtain pressure fluctuation prediction data.

[0057] Time-series alignment of operating data can be performed by resampling the data to a uniform time interval using interpolation algorithms (such as linear interpolation and spline interpolation); or by padding (such as zero padding and forward padding) to handle missing data or align time series of different lengths.

[0058] Temporal dependency feature extraction on temporal input tensors can be performed step-by-step using recurrent neural networks (RNNs) and their variants, such as long short-term memory networks (LSTMs) or gated recurrent units (GRUs), which excel at processing temporal input tensors and memorizing long-term dependencies. Alternatively, an attention-based Transformer model can be used to capture global dependencies in temporal input tensors in a parallel manner.

[0059] Regression mapping of the context encoding vector can be performed by using a fully connected neural network layer, taking the context encoding vector as input, and outputting continuous pressure fluctuation prediction data; or by using statistical regression models such as support vector regression (SVR) to generate pressure fluctuation prediction data.

[0060] This application's solution achieves accurate prediction of pressure fluctuations within the isostatic press cavity through refined temporal processing and feature extraction of operating condition data. Specifically, firstly, the original operating condition data undergoes temporal alignment to ensure consistency across different types of operating condition data in the time dimension. Next, the aligned data is constructed into a temporal input tensor. This tensor not only contains operating condition information at a single moment but, more importantly, integrates pressure, temperature, and temperature control power data from multiple consecutive moments in the historical time domain, forming an input sequence with rich temporal context. Subsequently, through time-step temporal dependency feature extraction processing, such as using recurrent neural networks, it is possible to deeply learn and capture the complex dynamic patterns and interactions inherent in these historical data sequences, thereby generating a context encoding vector that encodes these historical temporal dependencies. This context encoding vector is a highly abstract and generalized representation of past operating conditions and their evolution trends. Finally, targeting the pressure change of the isostatic press in the future time domain, regression mapping is performed on this context encoding vector to transform the abstract features into specific pressure fluctuation prediction data. This method fully utilizes the temporal information of historical operating data, overcoming the limitation of traditional static models in capturing dynamic changes, thus making pressure fluctuation prediction more accurate. In this way, the proposed scheme provides a more reliable input for subsequent temperature error prediction based on the pressure fluctuation-temperature error mapping relationship, thereby making the feedforward correction of the temperature control parameters of the isostatic press more effective and significantly improving the accuracy and stability of the isostatic press temperature control.

[0061] The following is a concrete example to illustrate this. After obtaining the operating condition data inside the isostatic press cavity, this data can first be time-aligned. For example, if the pressure sensor samples at 10Hz, the temperature sensor at 1Hz, and the temperature control power data is updated at 5Hz, linear interpolation or spline interpolation can be used to uniformly resample all data to a frequency of 1Hz, ensuring accurate timestamp alignment. Subsequently, the aligned pressure, temperature, and temperature control power data from the past N time steps (e.g., N=60, representing the past minute) are stacked to construct a time-series input tensor. This tensor can be a three-dimensional array with dimensions (batch size, N, 3), where 3 represents the three features: pressure, temperature, and temperature control power. Next, a Long Short-Term Memory (LSTM) network can be used as a time-step-by-time temporal dependency feature extraction model. This LSTM network receives the aforementioned time-series input tensor and processes the data in the sequence time-step, learning and memorizing long-term temporal dependencies through its internal gating mechanism. The hidden state output of the last time step of the LSTM network can be used as a context encoding vector to encode historical temporal dependencies. Finally, this context encoding vector is input into a regression network consisting of multiple fully connected layers. After training, this regression network can map the context encoding vector to the pressure change of the isostatic press at a future time point (e.g., 5 seconds in the future), thereby obtaining pressure fluctuation prediction data.

[0062] In some embodiments, the expression for the pressure fluctuation-temperature error mapping relationship is:

[0063] in, For temperature error prediction data, This provides the initial temperature data of the working medium for the current forecast period. The coefficient of volumetric expansion of the working medium. The density of the working medium, The specific heat capacity of the working medium. This is the pressure-temperature coupling coefficient. For pressure fluctuation prediction data, It is a natural constant. For pressurization duration, To predict the step size, is the thermal time constant.

[0064] The proposed solution explicitly defines the pressure fluctuation-temperature error mapping relationship as a physical expression encompassing multiple thermodynamic and system parameters. This transforms the relationship between pressure fluctuations and temperature errors within the isostatic press cavity from a simple empirical correlation into a precise description based on the actual thermophysical properties of the working medium and the system's dynamic response. When the pressure fluctuation prediction model outputs pressure fluctuation prediction data, this expression can combine key parameters such as the initial temperature data T0 of the working medium within the current prediction period, the working medium's volumetric expansion coefficient, density, specific heat capacity, pressure-temperature coupling coefficient, pressurization duration, prediction step size, and thermal time constant τ to calculate the corresponding temperature error prediction data in real time and accurately. This physical model-based mapping relationship more realistically reflects the complex thermodynamic processes within the isostatic press, thus providing a more accurate and reliable basis for subsequent feedforward correction of temperature control parameters. In this way, the impact of pressure fluctuations on temperature can be predicted and quantified, enabling proactive control strategies to effectively improve the accuracy and stability of temperature control.

[0065] See Figure 4 In one embodiment, the method for feedforward correction of the temperature control parameters of the isostatic press includes, but is not limited to, steps S401 to S403.

[0066] Step S401: Generate feedforward compensation amount based on temperature error prediction data.

[0067] Step S402: The feedforward compensation is superimposed on the temperature setpoint of the isostatic press in the opposite direction to the temperature deviation trend represented by the temperature error prediction data to obtain the corrected temperature setpoint.

[0068] Step S403: Based on the corrected temperature setpoint, adjust the temperature control power of the isostatic press.

[0069] To generate the feedforward compensation amount, a correspondence table between temperature error prediction data and feedforward compensation amount can be established in advance, and the corresponding compensation amount can be directly looked up based on the current temperature error prediction data; or, it can be achieved through function mapping, by designing a linear or nonlinear function that takes the temperature error prediction data as input and outputs the corresponding feedforward compensation amount. This function can be a simple proportional coefficient or a more complex model trained based on historical data.

[0070] By adding the feedforward compensation to the temperature setpoint of the isostatic press in the opposite direction to the temperature deviation trend represented by the temperature error prediction data, the target temperature can be pre-adjusted. This ensures that when the actual temperature reaches the setpoint, the predicted deviation has already been offset, avoiding temperature overshoot or under-adjustment. For example, if a temperature increase is predicted (positive deviation), the feedforward compensation is negative and added to the temperature setpoint, resulting in a lower corrected setpoint; if a temperature decrease is predicted (negative deviation), the feedforward compensation is positive and added to the temperature setpoint, resulting in a higher corrected setpoint. The control system can include an adder module that receives the original temperature setpoint and the signed feedforward compensation, performs algebraic addition directly, and outputs the corrected temperature setpoint.

[0071] Based on the corrected temperature setpoint, the temperature control power of the isostatic press can be adjusted. A proportional-integral-derivative (PID) controller can be used, taking the corrected temperature setpoint as the target value and the actual temperature as the feedback value, calculating the control deviation, and outputting the corresponding temperature control power command according to the PID algorithm. Alternatively, the temperature control system can use a fuzzy controller or a neural network controller, taking the corrected temperature setpoint and the actual temperature as inputs, and directly outputting the temperature control power through preset control rules or a trained model.

[0072] The proposed solution converts the predicted temperature error into a specific feedforward compensation value, which is then superimposed on the temperature setpoint of the isostatic press in the opposite direction to the temperature deviation trend, thereby obtaining a corrected temperature setpoint. The temperature control power is then adjusted based on this corrected setpoint. This feedforward correction mechanism allows the isostatic press's temperature control system to proactively respond to temperature deviations caused by pressure fluctuations, rather than passively waiting for the deviation to occur before making feedback adjustments. Once the operating data within the isostatic press cavity is acquired and the predicted temperature error data is obtained through a pressure fluctuation prediction model and a pressure fluctuation-temperature error mapping relationship, this predicted data is immediately used to generate the feedforward compensation value. This compensation value is then cleverly integrated into the isostatic press's temperature setpoint, forming a corrected temperature setpoint. This corrected setpoint serves as the new control target, directly driving the temperature control system to adjust the temperature control power. This proactive, predictive adjustment allows the system to take measures to offset the actual temperature deviation from the setpoint before pressure fluctuations cause it, thus significantly improving the real-time performance and accuracy of temperature control.

[0073] The following is a concrete example. Suppose a warm isostatic press is performing heat treatment on a certain material, and the chamber temperature needs to be precisely maintained at a certain set value. First, the operating condition data inside the warm isostatic press chamber is acquired and input into a preset pressure fluctuation prediction model. This model predicts a positive pressure fluctuation in the chamber over a certain period of time. Then, through the pressure fluctuation-temperature error mapping relationship, it predicts that this will lead to a positive temperature error in the chamber. To offset this predicted temperature error, a feedforward compensation is generated based on the predicted temperature error. For example, if the predicted temperature increase is 2°C, a -2°C feedforward compensation is generated. Subsequently, this -2°C feedforward compensation is added to the current temperature setpoint in the opposite direction to the predicted temperature deviation trend. Assuming the current temperature setpoint is 150°C, the corrected temperature setpoint will become 148°C. Finally, using 148°C as the new target value, the temperature control power of the heater is adjusted. By reducing the heating power, the temperature control target is lowered in advance before the actual temperature rises due to pressure fluctuations. This allows the actual temperature to be maintained more precisely at around 150°C when pressure fluctuations occur, thus avoiding temperature overshoot caused by pressure fluctuations.

[0074] In some embodiments, the temperature control method for the isostatic press further includes: acquiring actual temperature error data of the isostatic press; and using the actual temperature error data as a monitoring signal to perform online iterative updates on the parameters of the pressure fluctuation prediction model and the thermodynamic parameters in the pressure fluctuation-temperature error mapping relationship.

[0075] This application's solution addresses the potential static limitations of preset models and mapping relationships by introducing a feedback mechanism based on actual temperature error data. Specifically, during operation, the isostatic press first predicts the temperature error based on operating data using a pressure fluctuation prediction model and the pressure fluctuation-temperature error mapping relationship, and then performs feedforward correction. Based on this, actual temperature error data within the chamber is further acquired. This actual temperature error data serves as a crucial monitoring signal, directly reflecting the difference between the current prediction and correction effects and the actual situation. If the actual temperature error deviates from the predicted temperature error, this monitoring signal drives an online iterative update mechanism to dynamically adjust the internal parameters of the pressure fluctuation prediction model and the thermodynamic parameters in the pressure fluctuation-temperature error mapping relationship. For example, if the actual temperature consistently exceeds the predicted temperature, the update mechanism adjusts the relevant parameters, enabling the pressure fluctuation prediction model to more accurately reflect this trend in future predictions. This continuous adaptive learning process allows the pressure fluctuation prediction model and the pressure fluctuation-temperature error mapping relationship to adapt in real time to the dynamic characteristics of the isostatic press under different operating conditions and aging levels, thereby ensuring the accuracy and effectiveness of the feedforward correction. In this way, the solution proposed in this application upgrades static predictive control to dynamic adaptive predictive control, which significantly enhances the robustness and long-term accuracy of the temperature control system.

[0076] The following is a concrete example. During the heat treatment of solid-state battery modules in a isostatic press, the system first predicts pressure fluctuations over a future period based on current heating power, chamber pressure, and other operating data. This prediction is then combined with thermodynamic formulas to derive the corresponding predicted temperature error, which is used to adjust the heater power for feedforward compensation. Simultaneously, multiple high-precision platinum resistance temperature sensors installed inside the chamber collect real-time temperature data and compare it with the set target temperature to calculate the actual temperature error. For example, if the actual temperature error consistently shows a positive value (i.e., the actual temperature is higher than the target temperature), this indicates that the previous prediction may have underestimated the temperature rise, or that some thermodynamic parameters in the mapping relationship (such as specific heat capacity) deviate from the actual situation. In this case, the actual temperature error data is used as a supervisory signal and input into an adaptive algorithm module, such as an online learning algorithm based on gradient descent. This algorithm fine-tunes the weights and biases in the neural network model, as well as the thermodynamic parameters in the pressure fluctuation-temperature error mapping relationship, based on the difference between the actual and predicted temperature errors. For example, the temperature coupling coefficient related to pressure fluctuations in the mapping relationship can be appropriately increased, resulting in a larger temperature prediction error under the same pressure fluctuations. This prompts the feedforward correction to take more aggressive cooling measures. This iterative update process can be executed every few seconds or minutes to ensure that the model and mapping relationship remain highly consistent with the current operating state of the isostatic press.

[0077] In some embodiments, the temperature control method of the isostatic press further includes: when the temperature data inside the isostatic press cavity exceeds a preset temperature threshold data, heating is performed using a first working medium; otherwise, heating is performed using a second working medium.

[0078] The thermal stability of the second working medium is better than that of the first working medium, and the maximum working temperature of the second working medium is higher than that of the first working medium.

[0079] This application's solution optimizes the heating efficiency and temperature control accuracy of a thermostatic press (WSP) across different temperature ranges by introducing two working media with different properties and intelligently switching between them based on real-time temperature data within the WSP chamber. Specifically, when the chamber temperature is low, a first working medium is used for heating. This medium may have better heat transfer efficiency and cost advantages, making it suitable for conventional heating needs. Once the chamber temperature exceeds a preset temperature threshold, indicating the entry into a high-temperature operating state, the system automatically switches to the second working medium. Because the second working medium exhibits superior thermal stability compared to the first, and its maximum operating temperature is higher, it provides more stable and reliable heating capabilities at high temperatures, effectively avoiding potential performance degradation, decomposition, or safety risks associated with the first working medium at high temperatures. This dynamic switching mechanism ensures that the WSP continuously provides efficient and precise temperature control across a wide operating temperature range, enabling more reliable execution of temperature feedforward correction based on pressure fluctuation prediction, thereby significantly improving the overall temperature control performance and process adaptability of the WSP.

[0080] The following is a specific example to illustrate this. The temperature data within the isostatic press chamber can be acquired in real time using a built-in temperature sensor (such as a thermocouple or infrared thermometer). The preset temperature threshold can be set according to specific process requirements and the characteristics of the materials being processed; for example, it can be set to 90°C. When the chamber temperature is below 90°C, deionized water can be used as the primary working medium for heating, as it exhibits good heat transfer performance at lower temperatures. When the chamber temperature exceeds 90°C, the process can switch to a special heat transfer oil as the secondary working medium. This special heat transfer oil possesses excellent thermal stability and a high specific heat capacity at high temperatures, providing efficient and uniform heating, and its maximum operating temperature is significantly higher than the effective heating limit of deionized water in some applications. This switching can be achieved by controlling different medium supply valves and heating circuits, ensuring that the most suitable working medium is always used within different temperature ranges.

[0081] In some embodiments, the temperature control method of the isostatic press further includes: triggering an alarm and cutting off the heating or cooling actuator when the temperature data in the isostatic press cavity exceeds a preset temperature safety range; and controlling the pressurization system to stop pressurization when the pressure data in the isostatic press cavity exceeds a preset pressure safety threshold.

[0082] This application's solution, based on the aforementioned temperature control method, further introduces a comprehensive safety monitoring and emergency response mechanism. Specifically, the actuator continuously monitors the temperature and pressure data within the temperature isostatic press chamber. When the temperature data exceeds the preset safety range (e.g., too high or too low), an alarm is immediately triggered, and the actuator responsible for heating or cooling is shut off to prevent the temperature from deviating further from the safe range, thus avoiding damage to the workpiece or equipment. Simultaneously, when the pressure data within the chamber exceeds the preset safety pressure threshold, the pressurization system is controlled to stop pressurizing to prevent continuous pressure increases that could lead to equipment overload or structural damage. This safety mechanism, combined with the aforementioned temperature feedforward correction method based on pressure fluctuation prediction, forms a more comprehensive control system. Feedforward correction aims to improve the accuracy and stability of daily operation, while safety monitoring serves as a final line of defense, ensuring the effective protection of equipment and process safety under extreme or abnormal operating conditions, thereby significantly improving the reliability and safety of the temperature isostatic press operation.

[0083] The following is a concrete example. Multiple K-type thermocouples are installed inside the isostatic press chamber to collect temperature data in real time and transmit this data to a programmable logic controller (PLC) for processing. The preset temperature safety range can be set according to specific process requirements. For example, if the target process temperature is 120°C, the safety range can be set to 115°C to 125°C. When any thermocouple detects a temperature exceeding this range, the PLC will immediately trigger an audible and visual alarm and display an abnormality message on the operator interface. Simultaneously, the PLC will control a solid-state relay to cut off the power supply to the heating rods, or control a solenoid valve to shut off the cooling water circulation, to quickly bring the temperature back to the safe range. For pressure monitoring, a high-precision piezoresistive pressure sensor can be installed inside the chamber to monitor the pressure in real time. The preset pressure safety threshold can be set to 1.1 times the maximum operating pressure of the equipment. For example, if the maximum operating pressure is 200 MPa, the safety threshold is 220 MPa. When the pressure sensor detects that the pressure exceeds this threshold, it immediately sends a stop command to the booster system. For example, it can stop the operation of the high-pressure pump by controlling the frequency converter or close the high-pressure gas inlet valve to effectively prevent the pressure from continuing to rise and ensure equipment safety.

[0084] In some embodiments, the temperature control method of the isostatic press further includes: inputting pressure fluctuation prediction data and operating condition data into the thermal behavior simulation model of the solid-state battery module to predict the transient temperature gradient value inside the solid-state battery module; and adjusting the pressure ramping and depressurization rate of the isostatic press based on the deviation between the transient temperature gradient value and a preset gradient threshold.

[0085] The thermal behavior simulation model for solid-state battery modules aims to simulate the thermodynamic response of solid-state battery modules during isostatic pressing (WPS). Its function is to calculate and predict the internal temperature distribution and transient temperature gradient of the solid-state battery module based on input operating condition data and pressure fluctuation prediction data. This model can be constructed using the finite element analysis (FEA) method, by discretizing the solid-state battery module into a finite number of elements and solving the physical equations for heat conduction, convection, and radiation for each element; alternatively, the model can employ computational fluid dynamics (CFD) methods, combining the simulation of heat exchange between fluid and solid; or, a reduced-order model (ROM) or a machine learning-based model can be used, trained on a large amount of experimental data or high-precision simulation data to quickly predict thermal behavior.

[0086] The proposed solution uses predicted pressure fluctuation data and operating condition data within the warm isostatic press chamber as input to a thermal behavior simulation model of a solid-state battery module. Based on these inputs, the model can accurately predict the transient temperature gradient value inside the solid-state battery module during the warm isostatic pressing process. This predictive capability goes beyond simply controlling the chamber temperature, delving into the refined management of the thermal state of the processed solid-state battery module itself. If the predicted transient temperature gradient value inside the solid-state battery module may exceed a preset gradient threshold, the pressure ramping and depressurization rate of the warm isostatic press is actively adjusted based on the deviation between the two. For example, if the predicted gradient is too large, the pressure ramping and depressurization rate is reduced to slow down the temperature change of the working medium, thereby providing more time for heat conduction inside the solid-state battery module and effectively reducing the internal temperature gradient. Conversely, if the gradient is within a safe range, the pressure ramping and depressurization rate may be appropriately increased to optimize processing efficiency. This prediction-based dynamic adjustment of the pressure ramping and depressurization rate, combined with the aforementioned method of predicting pressure fluctuations and correcting temperature control parameters, forms a more comprehensive and refined warm isostatic pressing process control strategy. It not only ensures the stability of the cavity temperature, but also further guarantees the controllability of the internal thermal stress of the solid-state battery module, thereby avoiding module defects caused by excessive internal temperature gradient and significantly improving the processing quality and reliability of the solid-state battery module.

[0087] The following is a concrete example to illustrate this. In the process of warm isostatic pressing (WIP) solid-state battery module processing, the operating conditions within the WIP chamber are first acquired, including real-time temperature, pressure, and heating power. This operating data, along with pressure fluctuation prediction data obtained through a pressure fluctuation prediction model, is input into a simulation model of the solid-state battery module's thermal behavior built based on finite element analysis (FEA). This simulation model pre-establishes a three-dimensional geometric model of the solid-state battery module and defines the thermophysical parameters of each material (such as thermal conductivity, specific heat capacity, and density). During the simulation, the model calculates the convective heat transfer between the surface of the solid-state battery module and the working medium based on the input pressure fluctuations and chamber temperature changes, and simulates the heat conduction process within the module, outputting the temperature values ​​of each node within the module in real time. By post-processing these temperature values, the transient temperature gradient value of any region within the module can be calculated. For example, if the simulation results show that the transient temperature gradient value in a critical region (such as the electrode-electrolyte interface) reaches 15°C / mm, while the preset gradient threshold is 10°C / mm, then the risk of an excessively large gradient is identified. At this point, based on the deviation between 15°C / mm and 10°C / mm, for example, through a preset control algorithm (such as a fuzzy controller), the buck-boost rate of the isostatic press is reduced from the current 5 MPa / min to 3 MPa / min. By reducing the buck-boost rate, the temperature change of the working medium can be mitigated, thereby reducing the thermal shock on the surface of the solid-state battery module and providing a longer relaxation time for internal heat conduction, ultimately effectively controlling the transient temperature gradient within the 10°C / mm threshold.

[0088] This application also provides an electronic device. Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. For example... Figure 5 As shown, the electronic device in this embodiment mainly includes a processor 501 and a memory 502. The memory 502 can be configured to store a program for executing the temperature control method of the isostatic press in the above-described method embodiments. The processor 501 can be configured to execute the program in the memory 502, which includes, but is not limited to, a program for executing the temperature control method of the isostatic press in the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application.

[0089] In some embodiments, the electronic device may include multiple processors 501 and multiple memories 502. The program executing the temperature control method of the isostatic press according to the above method embodiments can be divided into multiple subroutines. Each subroutine can be loaded and run by a processor 501 to execute different steps of the temperature control method of the isostatic press according to the above method embodiments. Specifically, each subroutine can be stored in a different memory 502, and each processor 501 can be configured to execute programs in one or more memories 502 to jointly implement the temperature control method of the isostatic press according to the above method embodiments. That is, each processor 501 executes different steps of the temperature control method of the isostatic press according to the above method embodiments to jointly implement the temperature control method of the isostatic press according to the above method embodiments.

[0090] The aforementioned multiple processors 501 can be processors deployed on the same device. For example, the aforementioned electronic device can be a high-performance device composed of multiple processors, and the aforementioned multiple processors 501 can be processors configured on that high-performance device. Alternatively, the aforementioned multiple processors 501 can also be processors deployed on different devices. For example, the aforementioned electronic device can be a server cluster, and the aforementioned multiple processors 501 can be processors on different servers within the server cluster.

[0091] This application also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to this application, the computer-readable storage medium can be configured to store a program for performing the temperature control method of the warm isostatic press according to the above-described method embodiments. This program can be loaded and run by a processor to implement the temperature control method of the warm isostatic press. For ease of explanation, only the parts related to the embodiments of this application are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of this application. The computer-readable storage medium can be a memory formed by various electronic devices. Optionally, in the embodiments of this application, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0092] The temperature control method, electronic equipment, and storage medium for a thermostatic press provided in this application, by acquiring operating data and predicting pressure fluctuations, can detect potential disturbances that may cause temperature changes in advance. Based on the pressure fluctuation-temperature error mapping relationship, it determines the temperature error prediction data corresponding to the pressure fluctuation prediction data, quantifying the specific impact of pressure changes on temperature. This transforms physical phenomena into operable control criteria. Finally, feedforward correction is performed based on the temperature error prediction data, making the temperature control of the thermostatic press no longer a passive response but an active intervention. Therefore, by predicting pressure fluctuations in real time and establishing a thermodynamic mapping relationship for feedforward temperature correction, the lag in temperature control under dynamic operating conditions is overcome. This improves the real-time performance and stability of temperature control during the pressure ramping and depressurization process of the thermostatic press, avoids thermal stress damage to battery components, and improves the quality of solid-state battery fabrication.

[0093] Exemplary embodiments of this disclosure have been specifically shown and described above. It should be understood that this disclosure is not limited to the detailed structures, arrangements, or implementations described herein; rather, this disclosure is intended to cover various modifications and equivalent arrangements contained within the spirit and scope of the appended claims.

Claims

1. A temperature control method for a thermostatic press, characterized in that, include: Acquire operating condition data within the cavity of the thermostatic press; The operating condition data is input into a preset pressure fluctuation prediction model to predict the internal pressure fluctuation of the isostatic press based on the operating condition data, and obtain the corresponding pressure fluctuation prediction data. Based on the preset pressure fluctuation-temperature error mapping relationship, the temperature error prediction data corresponding to the pressure fluctuation prediction data is determined. The pressure fluctuation-temperature error mapping relationship is used to describe the thermodynamic mapping relationship between the pressure fluctuation amount and the temperature error amount. Based on the temperature error prediction data, the temperature control parameters of the isostatic press are feedforward corrected to offset the temperature deviation represented by the temperature error prediction data.

2. The temperature control method for a isostatic press according to claim 1, characterized in that, The step of predicting internal pressure fluctuations in the isostatic press based on the operating data includes: The operating condition data is time-aligned to construct a time-series input tensor containing pressure data, temperature data, and temperature control power data from multiple consecutive historical moments within the historical time domain. The temporal input tensor is subjected to time-step temporal dependency feature extraction processing to obtain a context encoding vector that encodes historical temporal dependencies. Using the pressure change of the isostatic press in the future time domain as the target, the context encoding vector is subjected to regression mapping to obtain the pressure fluctuation prediction data.

3. The temperature control method for a isostatic press according to claim 1, characterized in that, The expression for the pressure fluctuation-temperature error mapping relationship is: in, For temperature error prediction data, This provides the initial temperature data of the working medium for the current forecast period. The coefficient of volumetric expansion of the working medium. The density of the working medium, The specific heat capacity of the working medium. This is the pressure-temperature coupling coefficient. For pressure fluctuation prediction data, It is a natural constant. For pressurization duration, To predict the step size, is the thermal time constant.

4. The temperature control method for a isostatic press according to claim 1, characterized in that, The step of feedforward correction of the temperature control parameters of the isostatic press based on the temperature error prediction data includes: Based on the temperature error prediction data, a feedforward compensation amount is generated; The feedforward compensation is added to the temperature setpoint of the isostatic press in a direction opposite to the temperature deviation trend represented by the temperature error prediction data to obtain the corrected temperature setpoint. Based on the corrected temperature setpoint, the temperature control power of the isostatic press is adjusted.

5. The temperature control method for a isostatic press according to claim 1, characterized in that, Also includes: Obtain the actual temperature error data of the isostatic press; Using the actual temperature error data as a monitoring signal, the parameters of the pressure fluctuation prediction model and the thermodynamic parameters in the pressure fluctuation-temperature error mapping relationship are updated online iteratively.

6. The temperature control method for a isostatic press according to claim 1, characterized in that, Also includes: When the temperature data inside the isostatic press chamber exceeds a preset temperature threshold, a first working medium is used for heating; otherwise, a second working medium is used for heating. The thermal stability of the second working medium is better than that of the first working medium, and the maximum working temperature of the second working medium is higher than that of the first working medium.

7. The temperature control method for a isostatic press according to claim 1, characterized in that, Also includes: When the temperature data inside the isostatic press chamber exceeds the preset temperature safety range, an alarm is triggered and the heating or cooling actuator is cut off. When the pressure data inside the isostatic press chamber exceeds the preset pressure safety threshold, the pressurization system is controlled to stop pressurization.

8. The temperature control method for a isostatic press according to claim 1, characterized in that, Also includes: The pressure fluctuation prediction data and the operating condition data are input into the thermal behavior simulation model of the solid-state battery module to predict the transient temperature gradient value inside the solid-state battery module. The pressure ramping and depressurization rates of the isostatic press are adjusted based on the deviation between the transient temperature gradient value and the preset gradient threshold.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the temperature control method of the isostatic press according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the temperature control method of the isostatic press according to any one of claims 1 to 8.

Images