Anode material graphitization process parameter improvement optimization method and system
Patent Information
- Application Number
- CN202510582027.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-07
- Publication Date
- 2026-08-21
- Estimated Expiration
- 2045-05-07
AI Technical Summary
[0003]当前市面上常见的负极材料石墨化参数优化方法主要依赖于传统的温度控制系统和基于经验公式的优化算法，这些方法通常通过设置固定的温度区间和电流密度来进行石墨化过程控制，虽然能达到一定的石墨化效果，但在实际应用中存在温度波动大、温控精度低的问题
通过基于串联式多腔体坩埚进行物料装载并构建包含温度梯度、电流以及石墨化程度量化值的历史生产数据集，能够精确分析石墨化过程中的各个关键参数，进而为石墨化过程的优化提供数据支持。通过建立石墨化预测模型，并结合分布式温度传感器获取的实时温度数据，可以动态调整坩埚内的温度，实现更加精确的温控。这种方法不仅能够在石墨化过程中实时预测未来的进程，还能根据实时的温度和石墨化状态与预测数据进行对比，及时发现偏差并调整控制策略，保证温控过程的准确性和稳定性。若误差值过大，系统能够根据当前实际石墨化程度调整温控指令，确保产品质量一致性。此外，通过将生产结果反馈至预测模型进行优化，形成闭环控制，不断提升模型的预测精度和工艺优化水平。本发明也优化了内串炉产量低、坩埚成本高的普遍缺点。
Smart Images
Figure CN120509175B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to parameter optimization technology, and in particular to a method and system for improving and optimizing the graphitization process parameters of negative electrode materials. Background Technology
[0002] With the increasing demand for lithium batteries, especially the widespread adoption of new energy vehicles and consumer electronics, the performance requirements for anode materials are constantly rising, making the optimization of the graphitization process particularly important. Optimizing the graphitization process can improve the overall performance of anode materials, enhancing battery energy density, cycle stability, and charge / discharge efficiency. Research shows that excessively high or low graphitization temperatures can affect the orderliness of the graphite layers, thereby impacting battery lifespan and performance. Therefore, finding the optimal graphitization conditions by scientifically and rationally adjusting various parameters of the graphitization process has become an important topic in current scientific research and industrial production.
[0003] Currently, common methods for optimizing graphitization parameters in anode materials mainly rely on traditional temperature control systems and optimization algorithms based on empirical formulas. These methods typically control the graphitization process by setting fixed temperature ranges and current densities. While they can achieve a certain graphitization effect, they suffer from large temperature fluctuations and low temperature control accuracy in practical applications. Furthermore, traditional methods often lack real-time data feedback mechanisms, making it impossible to dynamically adjust process parameters. They rely solely on pre-defined models and cannot flexibly adjust to changes in the actual production environment, resulting in low production efficiency and poor product quality stability. Summary of the Invention
[0004] To improve existing methods for optimizing graphitization parameters in anode materials, this paper presents a method and system for improving and optimizing graphitization process parameters. This method achieves dynamic temperature control and precise adjustment by acquiring real-time temperature data and combining it with a graphitization prediction model, thereby optimizing the graphitization process and improving production stability and efficiency. Through a closed-loop feedback mechanism, the prediction model is continuously optimized to ensure the consistency and stability of anode material quality.
[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for improving and optimizing the graphitization process parameters of anode materials, comprising: Material loading was performed using a series-connected multi-cavity crucible, and a historical production dataset containing quantitative values of temperature gradient, current, and graphitization degree of the negative electrode material was constructed. Based on historical production datasets, the graphitization degree of anode materials at different stages under different temperatures is obtained, and a graphitization prediction model is constructed. The pot body is divided into multiple heating zones. Real-time temperature data of each zone is obtained through distributed temperature sensors. The current density is dynamically controlled to obtain a uniform temperature value inside the crucible. Based on the acquired temperature data, it is substituted into the graphitization prediction model to obtain the degree of graphitization in the future time period and formulate temperature control instructions. The error value is obtained by comparing the real-time graphitization degree quantization value obtained by the sensor with the predicted graphitization degree quantization value, and the error value is used to determine whether to execute the specified instruction. If the error value is large, temperature control instructions will be formulated in real time based on the current graphitization degree quantification value, and the production results will be fed back to the prediction model for model optimization.
[0006] Preferably, the step of acquiring the graphitization degree state of the negative electrode material at different stages under different temperatures based on historical production datasets and constructing a graphitization prediction model specifically includes: Based on historical production datasets, temperature curve change data and graphitization degree of negative electrode material are obtained at each stage; Based on the temperature curve change data and the graphitization degree of the negative electrode material, a graphitization degree time series is constructed, with the graphitization degree within each time stamp corresponding to a certain temperature; Based on the time series of graphitization degree, the change characteristics are extracted to obtain the graphitization trend of the negative electrode material with temperature. A graphitization prediction model is constructed based on the characteristics of change and the graphitization trend.
[0007] Preferably, the step of dividing the pot body into multiple heating zones, acquiring real-time temperature data of each zone through distributed temperature sensors, and obtaining a uniform temperature value inside the crucible by dynamically controlling the current density specifically includes: Temperature distribution data of each heating zone inside the crucible is obtained by using distributed temperature sensors inside the crucible. Outliers in the temperature data are obtained based on interquartile range, and the average temperature inside the crucible after removing outliers is calculated and set as the target temperature. Based on outlier temperature data, locate its region within the crucible; Based on the location of the outlier temperature region, the temperature is adjusted to the target temperature by controlling the current density within that region; Based on the adjusted temperature data, repeat the above steps until there are no temperature outliers and obtain a uniform temperature value inside the crucible.
[0008] Preferably, the step of substituting the acquired temperature data into the graphitization prediction model to obtain the degree of graphitization in the future time period and formulating temperature control instructions specifically includes: The acquired temperature data is substituted into the graphitization prediction model to obtain the degree and trend of graphitization in the future time period. Add timestamps based on inflection points in the graphitization trend; Based on the added timestamp, a gradient temperature control strategy is used to formulate temperature control commands; The gradient temperature variation strategy is specifically as follows: Based on the number of inflection points, the heating process is divided into multiple heating stages. Within each heating stage, the temperature inside the crucible is raised to a specified temperature at different heating rates, and the final temperature is controlled at 3000°C. .
[0009] Preferably, the step of comparing the real-time graphitization degree quantization value obtained from the sensor with the predicted graphitization degree quantization value to obtain an error value, and determining whether to execute the specified instruction based on the magnitude of the error value, specifically includes: The graphitization degree of the negative electrode material is obtained in real time by using a spectral sensor inside the crucible; The real-time graphitization level is timestamped and aligned with the graphitization prediction process obtained through the graphitization prediction model. Based on the real-time process and the prediction process after timestamp alignment, obtain the error value between the two. Based on the magnitude of the error, if it is within the threshold range, the temperature control command based on the gradient temperature variation strategy is executed.
[0010] Preferably, if the error value is large, a temperature control command is formulated in real time based on the current graphitization degree quantification value, and the production results are fed back to the prediction model for model optimization. This specifically includes: If the error value exceeds the threshold range, the heating stage is divided based on the inflection point of change in the current degree of graphitization. Heating operations based on a gradient temperature variation strategy are performed based on the divided heating stages. Based on the temperature change data and the quantitative value of graphitization degree of the negative electrode material from the above steps, the graphitization prediction model is retrained, the prediction results are optimized, and the prediction type and accuracy are improved.
[0011] Furthermore, a system for improving and optimizing the graphitization process parameters of the negative electrode material is proposed, including: Distributed sensors: Real-time distributed sensors are mainly used to acquire temperature data inside the crucible and the degree of graphitization of the negative electrode material; Model building module: The model building module is mainly used to build graphitization prediction models; Temperature unification module: The temperature unification module is mainly used to unify the temperature of each area in the crucible for subsequent model input operations. Comparison module: The comparison module is mainly used to compare the real-time graphitization degree quantization value obtained based on the sensor with the predicted graphitization degree quantization value to obtain the error value; Temperature control command module: The temperature control command module is mainly used to formulate temperature control commands based on gradient temperature change strategy to heat the negative electrode material in the crucible; Optimization module: The optimization module is mainly used to use the real-time temperature control strategy under the condition of large error value as training sample to optimize the graphitization prediction model; Database module: The database module is mainly used to store real-time data and historical data in the crucible, as well as training data and optimization data of the graphitization prediction model; Processor: The processor is mainly used for the calculation process of each formula and the construction calculation process of each model.
[0012] Compared with the prior art, the advantages of the present invention are: By loading materials using a series-connected multi-cavity crucible and constructing a historical production dataset containing quantified values of temperature gradient, current, and graphitization degree, key parameters in the graphitization process can be accurately analyzed, providing data support for process optimization. By establishing a graphitization prediction model and combining it with real-time temperature data acquired by distributed temperature sensors, the temperature within the crucible can be dynamically adjusted for more precise temperature control. This method not only predicts future progress in real time during graphitization but also compares real-time temperature and graphitization status with predicted data to promptly identify deviations and adjust control strategies, ensuring the accuracy and stability of the temperature control process. If the error value is too large, the system can adjust the temperature control command according to the current actual graphitization degree, ensuring consistent product quality. Furthermore, by feeding production results back to the prediction model for optimization, a closed-loop control is formed, continuously improving the model's prediction accuracy and process optimization level. This invention also addresses the common drawbacks of low output and high crucible cost associated with internal series furnaces. Attached Figure Description
[0013] Figure 1 This is a schematic diagram of the method proposed in this invention; Figure 2 This is a schematic diagram illustrating the construction of the prediction model proposed in this invention; Figure 3 This is a schematic diagram of the temperature unification proposed in this invention; Figure 4 This is a schematic diagram of the process acquisition and temperature control proposed in this invention; Figure 5 This is a schematic diagram of the error judgment proposed in this invention; Figure 6 This is a schematic diagram of the model optimization proposed in this invention; Figure 7 This is an architecture diagram of the electronic devices in this solution; Figure 8 This is a schematic diagram of the computer-readable storage medium structure in this scheme. Detailed Implementation
[0014] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.
[0015] A system for improving and optimizing graphitization process parameters of negative electrode materials includes: Distributed sensors: Real-time distributed sensors are mainly used to acquire temperature data inside the crucible and the degree of graphitization of the negative electrode material; Model building module: The model building module is mainly used to build graphitization prediction models; Temperature unification module: The temperature unification module is mainly used to unify the temperature of each area in the crucible for subsequent model input operations. Comparison module: The comparison module is mainly used to compare the real-time graphitization degree quantization value obtained based on the sensor with the predicted graphitization degree quantization value to obtain the error value; Temperature control command module: The temperature control command module is mainly used to formulate temperature control commands based on gradient temperature change strategy to heat the negative electrode material in the crucible; Optimization module: The optimization module is mainly used to use the real-time temperature control strategy under the condition of large error value as training sample to optimize the graphitization prediction model; Database module: The database module is mainly used to store real-time data and historical data in the crucible, as well as training data and optimization data of the graphitization prediction model; Processor: The processor is mainly used for the calculation process of each formula and the construction calculation process of each model.
[0016] See Figure 1 As shown, a method for improving and optimizing the graphitization process parameters of anode materials includes: Step 1: Load materials using a series-connected multi-cavity crucible and construct a historical production dataset containing quantitative values of temperature gradient, current, and graphitization degree of the negative electrode material; Step 2: Based on historical production datasets, obtain the graphitization degree of anode materials at different stages under different temperatures, and construct a graphitization prediction model; Step 3: Divide the pot into multiple heating zones, acquire real-time temperature data of each zone through distributed temperature sensors, and obtain a uniform temperature value inside the crucible by dynamically controlling the current density. Step 4: Based on the acquired temperature data, input it into the graphitization prediction model to obtain the degree of graphitization in the future time period and formulate temperature control instructions; Step 5: Compare the real-time graphitization degree quantization value obtained by the sensor with the predicted graphitization degree quantization value to obtain the error value, and determine whether to execute the specified instruction based on the magnitude of the error value; Step 6: If the error value is large, formulate temperature control instructions in real time based on the current graphitization degree quantification value, and feed the production results back to the prediction model for model optimization.
[0017] In a series-connected multi-cavity crucible, the material is distributed into multiple cavities, each of which may contain different temperatures, resulting in different temperature gradients. Temperature is a crucial factor affecting the graphitization degree of the anode material; therefore, temperature sensors need to be installed at different locations within the crucible to acquire temperature data within each cavity and calculate the temperature gradient.
[0018] Current data is closely related to the graphitization process because current reflects changes in heating power. By measuring the current in the crucible heating system, the heating efficiency and the material's response can be indirectly reflected.
[0019] The degree of graphitization is an important indicator, representing the extent of graphitization in the anode material. The degree of graphitization can be measured at each time point t. , [0,1].
[0020] See Figure 2 As shown, based on historical production datasets, the graphitization degree of anode materials at different stages under different temperatures is obtained, and a graphitization prediction model is constructed, specifically including: Based on historical production datasets, temperature curve change data and graphitization degree of negative electrode material are obtained at each stage; Based on the temperature curve change data The degree of graphitization of the negative electrode material Constructing a time series of graphitization degree The degree of graphitization within each timestamp corresponds to a specific temperature. Based on the time series of graphitization degree, the change characteristics are extracted to obtain the graphitization trend of the negative electrode material with temperature. A graphitization prediction model is constructed based on the characteristics of change and the graphitization trend.
[0021] Specifically, temperature change data is correlated with the degree of graphitization to construct a time series of graphitization levels. A timestamp is set. For each data point, the degree of graphitization S(t) corresponds to the temperature T(t) within that time stamp. The time series is in the form of: The degree of graphitization usually has a functional relationship with temperature, which can be described by a linear regression model, as shown in the formula: After obtaining the relationship between temperature and graphitization degree, the graphitization degree is calculated for each time stamp by substituting its corresponding temperature value. Based on the graphitization degree value calculated for each time stamp, a complete graphitization degree time series is formed.
[0022] See Figure 3 As shown, the pot body is divided into multiple heating zones. Real-time temperature data of each zone is acquired through distributed temperature sensors. By dynamically controlling the current density, a uniform temperature value inside the crucible is obtained. Specifically, this includes: Temperature distribution data of each heating zone inside the crucible is obtained by using distributed temperature sensors inside the crucible. Outliers in the temperature data are obtained based on interquartile range, and the average temperature inside the crucible after removing outliers is calculated and set as the target temperature. Based on outlier temperature data, locate its region within the crucible; Based on the location of the outlier temperature region, the temperature is adjusted to the target temperature by controlling the current density within that region; Based on the adjusted temperature data, repeat the above steps until there are no temperature outliers and obtain a uniform temperature value inside the crucible.
[0023] Specifically, the temperature change in each heating zone is related to the heat power. Assuming uniform heat conduction within the zone, the temperature change can be described by the heat conduction equation, which is: in, Let i be the specific heat capacity of the i-th region. For the quality of the i-th region, The heat loss coefficient is... Let i be the actual temperature of the i-th region. For ambient temperature, Let be the thermal power of the i-th region.
[0024] The power output of each zone is adjusted by controlling the current density in each heating zone. A feedback control strategy is used to adjust the current density to reduce the deviation between the target temperature and the actual temperature. The feedback control formula is as follows: in, For current density, For proportional gain, For integral gain, For differential gain, This represents the deviation between the target temperature and the actual temperature.
[0025] Upon reaching steady state, the temperature of all heated regions will approach the target temperature. At this point, the current density will tend to a stable value, meaning the current in each region will no longer change drastically. In the process of acquiring outliers in temperature data based on interquartile range (IQR) and calculating the average crucible temperature after removing outliers, special attention must be paid to the accurate identification and handling of outliers. The IQR method identifies outliers by calculating the first and third quartiles of the data. When a temperature data point exceeds the upper or lower limit, it is considered an outlier. In practical operation, when controlling the current density of the control area, the spatial distribution differences of temperature in each area need to be considered. During the adjustment of the current density, the temperature changes reported by each sensor must be monitored step by step to ensure that the temperature control adjustment can quickly eliminate temperature outliers while avoiding local temperature fluctuations due to over-adjustment, ensuring that the temperature inside the crucible eventually reaches the target value.
[0026] See Figure 4 As shown, based on the acquired temperature data, it is substituted into the graphitization prediction model to obtain the degree of graphitization in the future time period, and specific temperature control instructions are formulated, including: The acquired temperature data is substituted into the graphitization prediction model to obtain the degree and trend of graphitization in the future time period. Add timestamps based on inflection points in the graphitization trend; Based on the added timestamp, a gradient temperature control strategy is used to formulate temperature control commands; The gradient temperature variation strategy is specifically as follows: Based on the number of inflection points, the heating process is divided into multiple heating stages. Within each heating stage, the temperature inside the crucible is raised to a specified temperature at different heating rates, and the final temperature is controlled at 3000°C. .
[0027] Specifically, local extremum detection algorithms (such as the discrete second-order difference method) are used. ,like If the sign changes, then This could be an inflection point.
[0028] Based on the number k identified inflection points, the entire heating process is divided into k+1 stages, each corresponding to a heating rate. The heating rates for different stages are... The time interval between each stage and temperature increment Decide, In the initial stage, temperature changes have little impact on the graphitization reaction, so a slower heating rate is adopted. In the intermediate stage (the main graphitization reaction stage), temperature changes have a greater impact on the degree of graphitization, so the heating rate needs to be appropriately accelerated. In the final stage, the degree of graphitization tends to stabilize, and in order to avoid damage to the carbon structure, the heating rate is gradually reduced.
[0029] See Figure 5 As shown, the process involves comparing the real-time graphitization degree quantization value obtained from the sensor with the predicted graphitization degree quantization value to obtain an error value. The determination of whether to execute the specified instruction based on the magnitude of the error value specifically includes: The graphitization degree of the negative electrode material is obtained in real time by using a spectral sensor inside the crucible; The real-time graphitization level is timestamped and aligned with the graphitization prediction process obtained through the graphitization prediction model. Based on the real-time process and the prediction process after timestamp alignment, obtain the error value between the two. Based on the magnitude of the error, if it is within the threshold range, the temperature control command based on the gradient temperature variation strategy is executed.
[0030] Specifically, since the timestamps of real-time data and predicted data are different, interpolation methods can be used to ensure that they are compared at the same point in time. A linear interpolation method can be used as follows: in, , These are the prediction processes. Adjacent time points, This refers to the time point at which data is acquired in real time.
[0031] Understandably, gradient temperature control strategies assume gradual temperature adjustments. However, in practice, due to the thermal inertia of the material and the response lag of the heating system, temperature control may not immediately achieve the desired effect. The gradient rate can be dynamically adjusted based on the response time of the temperature control system and the thermal characteristics of the negative electrode material to avoid system instability caused by excessively rapid temperature adjustments. By monitoring the temperature and graphitization level in real time and periodically calibrating the prediction model, the accuracy of temperature control commands can be ensured, and system lag issues can be reduced.
[0032] See Figure 6 As shown, if the error value is large, a temperature control command is formulated in real time based on the current graphitization degree quantification value, and the production results are fed back to the prediction model for model optimization. Specifically, this includes: If the error value exceeds the threshold range, the heating stage is divided based on the inflection point of change in the current degree of graphitization. Heating operations based on a gradient temperature variation strategy are performed based on the divided heating stages. Based on the temperature change data and the quantitative value of graphitization degree of the negative electrode material from the above steps, the graphitization prediction model is retrained, the prediction results are optimized, and the prediction type and accuracy are improved.
[0033] Furthermore, the method according to the embodiments of this application can also be achieved by means of... Figure 7 The architecture of the electronic device shown is used to implement this. For example... Figure 7 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a method and system for improving and optimizing graphitization process parameters of a negative electrode material provided in this application. The electronic device 500 may also include a terminal interface 508. Of course, Figure 7 The architecture shown is merely exemplary and can be omitted as needed when implementing different devices. Figure 7 One or more components in the illustrated electronic device.
[0034] Figure 8 This is a schematic diagram of a computer-readable storage medium structure provided in one embodiment of this application. Figure 8 The diagram illustrates a computer-readable storage medium 600 according to one embodiment of this application. The computer-readable storage medium 600 stores computer-readable instructions. When executed by a processor, the computer-readable instructions can perform a method and system for improving and optimizing graphitization process parameters of a negative electrode material according to an embodiment of this application, as described with reference to the above figures. The storage medium 600 includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.
[0035] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.
[0036] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.
[0037] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A method for improving and optimizing the graphitization process parameters of anode materials, characterized in that, include: Material loading was performed using a series-connected multi-cavity crucible, and a historical production dataset containing quantitative values of temperature gradient, current, and graphitization degree of the negative electrode material was constructed. Based on historical production datasets, temperature curve change data and quantitative values of graphitization degree of negative electrode material are obtained at each stage. Based on the temperature curve change data and the quantitative value of the graphitization degree of the negative electrode material, a graphitization degree time series is constructed, with the graphitization degree within each time stamp corresponding to a certain temperature; Based on the time series of graphitization degree, the evolution characteristics of graphitization degree with temperature are extracted to obtain the graphitization evolution trend of the anode material with temperature. A graphitization prediction model is constructed based on evolutionary characteristics and graphitization evolution trends; The pot body is divided into multiple heating zones. Real-time temperature data of each zone is obtained through distributed temperature sensors. The current density is dynamically controlled to obtain a uniform temperature value inside the crucible. Based on the acquired temperature data, it is substituted into the graphitization prediction model to obtain the degree of graphitization in the future time period and formulate temperature control instructions. The error value is obtained by comparing the real-time graphitization degree quantization value obtained by the sensor with the predicted graphitization degree quantization value, and the error value is used to determine whether to execute the specified instruction. If the error value is large, temperature control instructions will be formulated in real time based on the current graphitization degree quantification value, and the production results will be fed back to the prediction model for model optimization.
2. The method for improving and optimizing the graphitization process parameters of a negative electrode material according to claim 1, characterized in that, The process of dividing the pot body into multiple heating zones, acquiring real-time temperature data for each zone through distributed temperature sensors, and obtaining a uniform temperature value within the crucible by dynamically controlling the current density specifically includes: Temperature distribution data of each heating zone inside the crucible is obtained by using distributed temperature sensors inside the crucible. Outliers in the temperature data are obtained based on interquartile range, and the average temperature inside the crucible after removing outliers is calculated and set as the target temperature. Based on outlier temperature data, locate its region within the crucible; Based on the location of the outlier temperature region, the temperature is adjusted to the target temperature by controlling the current density within that region; Based on the adjusted temperature data, repeat the above steps until there are no temperature outliers and obtain a uniform temperature value inside the crucible.
3. The method for improving and optimizing the graphitization process parameters of a negative electrode material according to claim 1, characterized in that, The process of inputting the acquired temperature data into the graphitization prediction model to obtain the degree of graphitization in the future time period and formulating temperature control commands specifically includes: The acquired temperature data is substituted into the graphitization prediction model to obtain the degree and trend of graphitization in the future time period. Add timestamps based on inflection points in the graphitization trend; Based on the added timestamp, a gradient temperature control strategy is used to formulate temperature control commands; The gradient temperature variation strategy is specifically as follows: Based on the number of inflection points, the heating process is divided into multiple heating stages. Within each heating stage, the temperature inside the crucible is raised to a specified temperature at different heating rates, and the final temperature is controlled at 3000°C. .
4. The method for improving and optimizing the graphitization process parameters of a negative electrode material according to claim 1, characterized in that, The process of comparing the real-time graphitization degree quantization value obtained from the sensor with the predicted graphitization degree quantization value to obtain an error value, and determining whether to execute the specified instruction based on the magnitude of the error value, specifically includes: The graphitization degree of the negative electrode material is obtained in real time by using a spectral sensor inside the crucible; The real-time graphitization level is timestamped and aligned with the graphitization prediction process obtained through the graphitization prediction model. Based on the real-time process and the prediction process after timestamp alignment, obtain the error value between the two. Based on the magnitude of the error, if it is within the threshold range, the temperature control command based on the gradient temperature variation strategy is executed.
5. The method for improving and optimizing the graphitization process parameters of a negative electrode material according to claim 1, characterized in that, If the error value is large, a temperature control command will be formulated in real time based on the current graphitization degree quantification value, and the production results will be fed back to the prediction model for model optimization. Specifically, this includes: If the error value exceeds the threshold range, the heating stage is divided based on the inflection point of change in the current degree of graphitization. Heating operations based on a gradient temperature variation strategy are performed based on the divided heating stages. Based on the temperature change data and the quantitative value of graphitization degree of the negative electrode material from the above steps, the graphitization prediction model is retrained, the prediction results are optimized, and the prediction type and accuracy are improved.
6. A system for improving and optimizing graphitization process parameters of anode materials, used to implement the method for improving and optimizing graphitization process parameters of anode materials as described in any one of claims 1-5, characterized in that, include: Distributed sensors: Real-time distributed sensors are mainly used to acquire temperature data inside the crucible and the degree of graphitization of the negative electrode material; Model building module: The model building module is mainly used to build graphitization prediction models; Temperature unification module: The temperature unification module is mainly used to unify the temperature of each area in the crucible for subsequent model input operations. Comparison module: The comparison module is mainly used to compare the real-time graphitization degree quantization value obtained based on the sensor with the predicted graphitization degree quantization value to obtain the error value; Temperature control command module: The temperature control command module is mainly used to formulate temperature control commands based on gradient temperature change strategy to heat the negative electrode material in the crucible; Optimization Module: The optimization module is mainly used to optimize the graphitization prediction model by using the real-time temperature control strategy under the condition of large error value as training sample; Database module: The database module is mainly used to store real-time data and historical data in the crucible, as well as training data and optimization data of the graphitization prediction model; Processor: The processor is mainly used for the calculation process of each formula and the construction calculation process of each model.
7. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform a method for improving and optimizing graphitization process parameters of a negative electrode material as described in any one of claims 1-5.
8. A computer-readable storage medium storing computer-readable instructions, characterized in that, When the computer-readable instructions are executed by the processor, they implement the method for improving and optimizing the graphitization process parameters of the negative electrode material according to any one of claims 1-5.