Waste gas treatment intelligent control method and system for battery recycling

Abstract

The invention discloses a waste gas treatment intelligent control method and system for battery reutilization, and the method comprises the steps: obtaining a response signal transmitted by a sensor disposed on a battery waste gas treatment device, and generating a sensor network according to the response signal; performing data acquisition on the waste gas treatment device through a sensor network, performing feature extraction on the acquired sensing data, and constructing a dynamic adsorption biochemical catalysis model on the basis of the sensor network in combination with the extracted waste gas data features; performing simulation operation through the dynamic adsorption biochemical catalysis model, and performing real-time working condition prediction according to the collected simulation operation data to obtain a waste gas prediction result in preset future time; and based on the dynamic adsorption biochemical catalysis model, performing multi-objective optimization according to the waste gas prediction result to obtain a control decision corresponding to each waste gas treatment device, and controlling the waste gas treatment device according to the control decision.

Description

Technical Field

[0001] The present invention relates to the technical field of battery waste gas recovery, and particularly to an intelligent control method and system for waste gas treatment for battery reuse. Background Art

[0002] Currently, the waste gas treatment technology generated during the recycling and reuse of lithium batteries is still in the exploratory and development stage, lacking mature technologies that have been verified for a long time. For example, when the existing technology treats volatile organic compounds (VOCs) in waste gas, it may not be able to completely remove harmful substances, resulting in non-compliant emissions. At the same time, since battery recycling is carried out in a unified manner, there are a large number of devices for treating waste gas from battery recycling during the centralized treatment of battery recycling. Currently, it is impossible to perform integrated control on large-scale centralized treatment devices, resulting in the inability to uniformly control the VOCs treated by different devices, leading to low resource control utilization and waste gas recovery rate, and may cause secondary pollution.

[0003] The current integration and optimization degree of systematic waste gas treatment links are still relatively low, lacking the ability of real-time monitoring and intelligent adjustment control for the entire process of waste gas treatment, and it is difficult to achieve efficient and energy-saving waste gas treatment. Summary of the Invention

[0004] The present invention provides an intelligent control method for waste gas treatment for battery reuse to solve the technical problem in the prior art that the VOCs treated by different devices cannot be uniformly controlled, and it is difficult to achieve efficient and energy-saving battery waste gas treatment.

[0005] To solve the above technical problem, an embodiment of the present invention provides an intelligent control method for waste gas treatment for battery reuse, including: Obtain the response signals emitted by the sensors arranged on the battery waste gas treatment device, and generate a sensor network according to the response signals; wherein, at least one sensor is arranged on each battery waste gas treatment device, and each sensor emits a response signal corresponding to its identity information; Collect data from the waste gas treatment device through the sensor network, extract the characteristics of the collected sensing data, and based on the sensor network, combine the extracted waste gas data characteristics to construct a dynamic adsorption biochemical catalysis model; wherein, each dynamic adsorption biochemical catalysis model corresponds to a waste gas treatment device; Perform simulation operation through the dynamic adsorption biochemical catalysis model, and perform real-time working condition prediction according to the collected simulation operation data to obtain the waste gas prediction result within a preset future time; Based on the dynamic adsorption biochemical catalysis model, multi-objective optimization is carried out according to the waste gas prediction result to obtain the control decision corresponding to each waste gas treatment device, and the waste gas treatment device is controlled according to the control decision.

[0006] As a preferred solution, obtaining the response signal emitted by the sensor arranged on the battery waste gas treatment device, and generating a sensor network according to the response signal, specifically includes: Sending a docking signal to a preset range through a signal emission device, so that after each sensor arranged on the battery waste gas treatment device receives the docking signal, a response signal is generated and sent outwards; Obtaining the response signal, and parsing the identity information of each sensor according to the response signal; Based on the identity information of each sensor, identifying the battery waste gas treatment device set by each sensor, and generating node information corresponding to the battery waste gas treatment device according to the waste gas type treated by each battery waste gas treatment device; Based on the node information, combining the sensors to construct and generate a sensor network.

[0007] As a preferred solution, collecting data on the waste gas treatment device through the sensor network, extracting the characteristics of the collected sensing data, and constructing a dynamic adsorption biochemical catalysis model based on the sensor network and combining the extracted waste gas data characteristics, including: Monitoring each node of the battery waste gas treatment device through the sensor network to obtain the component data and equipment process parameters of each battery waste gas treatment device for treating battery waste gas; Removing abnormal data from the component data and equipment process parameters according to the Kalman filtering algorithm; Normalizing the component data and equipment process parameters after removing abnormal data, and extracting the characteristics of the normalized component data and equipment process parameters through a preset sliding window to obtain waste gas data characteristics; Based on the sensor network, adding time series characteristics to the waste gas data characteristics corresponding to each battery waste gas treatment device, thereby constructing a dynamic adsorption biochemical catalysis model.

[0008] As a preferred solution, adding time series characteristics to the waste gas data characteristics corresponding to each battery waste gas treatment device based on the sensor network, thereby constructing a dynamic adsorption biochemical catalysis model, specifically including: Based on the sensor network, and according to the node information of each battery waste gas treatment device, pulling the structure data corresponding to the node information of each battery waste gas treatment device node, and modeling according to the structure data to obtain an adsorption layer structure model corresponding to each battery waste gas treatment device; Based on the preset sliding window, add temporal features to the exhaust gas data features corresponding to each battery exhaust gas treatment device; Construct an adsorption and diffusion model according to the exhaust gas data features with added temporal features and the node information of each battery exhaust gas treatment device; Couple the adsorption layer structure model and the adsorption and diffusion model, and add a preset data drive to the coupled model to construct a dynamic adsorption biochemical catalysis model corresponding to each battery exhaust gas treatment device.

[0009] As a preferred solution, the dynamic adsorption biochemical catalysis model is used for simulation operation, and real-time working condition prediction is carried out according to the collected simulation operation data to obtain the exhaust gas prediction result within a preset future time, specifically including: Through the dynamic adsorption biochemical catalysis model, simulate the corresponding battery exhaust gas treatment device, and collect data of the running dynamic adsorption biochemical catalysis model in real time during the simulation to obtain the simulation operation data of each dynamic adsorption biochemical catalysis model; Input the collected simulation operation data into a preset LSTM neural network, and carry out real-time working condition prediction of the dynamic adsorption biochemical catalysis model within a preset future time, so as to obtain the exhaust gas prediction result within a preset future time.

[0010] As a preferred solution, the construction method of the preset LSTM neural network specifically includes: Obtain the historical simulation data of the dynamic adsorption biochemical catalysis model, and preprocess the historical simulation data; Select features from the preprocessed historical simulation data to obtain key historical data features; Based on the dimension of the key historical data features, construct an initial LSTM neural network, and set a loss function and an optimization algorithm; Train the initial LSTM neural network based on the loss function and the optimization algorithm, and evaluate the trained LSTM neural network through a preset test set, so as to obtain an LSTM neural network with qualified evaluation results as the preset LSTM neural network.

[0011] As a preferred solution, based on the dynamic adsorption biochemical catalysis model, multi-objective optimization is carried out according to the exhaust gas prediction result to obtain the control decision corresponding to each exhaust gas treatment device, and the exhaust gas treatment device is controlled according to the control decision, specifically including: Based on the dynamic adsorption biochemical catalysis model, determine the energy consumption target, removal rate target and solvent recovery rate target; Constrain the energy consumption target, removal rate target and solvent recovery rate target to obtain multi-objective optimization conditions; Take the predicted exhaust gas results as a particle swarm, and based on the multi-objective optimization conditions, calculate the fitness of each particle in the particle swarm, and update the individual particle optimal solution and the global particle swarm optimal solution; wherein, each particle corresponds to the predicted exhaust gas result of each dynamic adsorption biochemical catalytic model, and the position and velocity of each particle are respectively represented as a point and a moving direction in its solution space. Update the velocity and position of each particle according to the individual particle optimal solution and the global particle swarm optimal solution, and output the optimal position of the global particle swarm as the optimization result until the preset iteration condition is reached. Determine the optimization object and optimization goal of the dynamic adsorption biochemical catalytic model according to the optimization result, so as to generate control decisions corresponding to each exhaust gas treatment device. Send each of the control decisions to each exhaust gas treatment device, and control the exhaust gas treatment device based on the corresponding control decision.

[0012] Correspondingly, the present invention also provides an intelligent control system for exhaust gas treatment for battery reuse, including: a control host computer and a plurality of battery exhaust gas treatment devices connected to the control host computer. The battery exhaust gas treatment device is used for collecting and adsorbing the exhaust gas produced by the battery reuse equipment, and collecting exhaust gas data through a sensor arranged therein. The control host computer includes: a response module, a model module, a simulation module and an optimization module. The response module is used for obtaining the response signal emitted by the sensor arranged on the battery exhaust gas treatment device, and generating a sensor network according to the response signal; wherein, at least one sensor is arranged on each battery exhaust gas treatment device, and each sensor emits a response signal corresponding to its identity information. The model module is used for collecting data of the exhaust gas treatment device through the sensor network, extracting features of the collected sensing data, and constructing a dynamic adsorption biochemical catalytic model based on the sensor network and in combination with the extracted exhaust gas data features; wherein, each dynamic adsorption biochemical catalytic model corresponds to an exhaust gas treatment device. The simulation module is used for performing simulation operation through the dynamic adsorption biochemical catalytic model, and predicting the real-time working condition according to the collected simulation operation data to obtain the predicted exhaust gas results within a preset future time. The optimization module is used for performing multi-objective optimization based on the dynamic adsorption biochemical catalytic model according to the predicted exhaust gas results to obtain control decisions corresponding to each exhaust gas treatment device, and controlling the exhaust gas treatment device according to the control decisions.

[0013] Accordingly, the present invention further provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the intelligent control method for waste gas treatment for battery reuse described in any one of the above is implemented.

[0014] Accordingly, the present invention further provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the intelligent control method for waste gas treatment for battery reuse described in any one of the above.

[0015] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The technical solution of the present invention obtains the response signals emitted by the sensors arranged on the battery waste gas treatment device, thereby generating a corresponding sensor network, and collecting corresponding data based on the sensor network, and then generating corresponding waste gas data characteristics to construct a corresponding dynamic adsorption biochemical catalytic model, so that the dynamic adsorption biochemical catalytic model can be simulated and run, and real-time working conditions can be predicted, so as to obtain the waste gas prediction results within a preset future time, and finally multi-objective optimization is carried out to implement the control decisions corresponding to each waste gas treatment device, so as to realize the cluster control of each waste gas treatment device, thereby ensuring the integration degree and optimization degree of the systematic waste gas treatment link, and improving the real-time monitoring ability and intelligent adjustment and control ability. Description of the Drawings

[0016] Figure 1 : A flowchart of an intelligent control method for waste gas treatment for battery reuse provided by an embodiment of the present invention; Figure 2 : A structural diagram of an intelligent control system for waste gas treatment provided by an embodiment of the present invention; Figure 3 : A structural diagram of a control host computer provided by an embodiment of the present invention. Detailed Embodiments

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. Embodiment 1

[0018] Please refer to Figure 1, which is an intelligent control method for waste gas treatment for battery reuse provided by an embodiment of the present invention and is executed by a control host computer, including the following steps S101-S104: Step S101: Obtain the response signals emitted by the sensors arranged on the battery waste gas treatment device, and generate a sensor network according to the response signals; wherein, at least one sensor is arranged on each battery waste gas treatment device, and each sensor emits a response signal corresponding to its identity information.

[0019] As a preferred solution of this embodiment, the obtaining the response signals emitted by the sensors arranged on the battery waste gas treatment device and generating a sensor network according to the response signals specifically includes: Transmit a docking signal to a preset range through a signal transmitting device, so that after each sensor arranged on the battery waste gas treatment device receives the docking signal, generate a response signal and send it outwards; obtain the response signals, and parse the identity information of each sensor according to the response signals; based on the identity information of each sensor, identify the battery waste gas treatment device where each sensor is arranged, and generate node information corresponding to the battery waste gas treatment device according to the type of waste gas treated by each battery waste gas treatment device; based on the node information, combine with the sensors to construct and generate a sensor network.

[0020] In this embodiment, the signal transmitting device is arranged in the control host computer, and the control host computer controls and executes the signal transmitting device. By transmitting a docking signal to a preset range through the signal transmitting device, it can enable each sensor on the battery waste gas treatment device to generate a response signal and send out the response signal after receiving the docking signal, thereby ensuring that the sensors in the preset range can all receive and process.

[0021] In this embodiment, after the control host computer receives the response signals corresponding to each sensor, it parses the identity information of each sensor, including but not limited to the type of sensor, the type of data collected for waste gas, the type and model of the battery waste gas treatment device where it is arranged, and so on. Among them, each battery waste gas treatment device at least includes one or more devices such as a dynamic adsorption layer, a biological catalytic filter bed, an electrochemical reactor, and a solvent recovery device, the sensors include but not limited to VOCs concentration sensors, temperature and humidity sensors, pressure sensors, gas composition mass spectrometers, etc., and each battery waste gas treatment device at least includes one sensor.

[0022] In this embodiment, through the identity information of each sensor, the battery exhaust gas treatment devices set by each sensor can be identified, and then the node information corresponding to the battery exhaust gas treatment devices can be generated, that is, including the type, model, operating status data, etc. of the battery exhaust gas treatment devices in the node, and also including the model of the sensor corresponding to the battery exhaust gas treatment device, the type of data collected, and the data value, etc. Furthermore, through each piece of node information, a corresponding sensor network can be constructed.

[0023] Step S102: Collect data on the exhaust gas treatment device through the sensor network, extract features from the collected sensing data, and based on the sensor network, combine the extracted exhaust gas data features to construct a dynamic adsorption biochemical catalysis model; wherein, each dynamic adsorption biochemical catalysis model corresponds to an exhaust gas treatment device.

[0024] As a preferred solution of this embodiment, the collecting data on the exhaust gas treatment device through the sensor network, extracting features from the collected sensing data, and based on the sensor network, combining the extracted exhaust gas data features to construct a dynamic adsorption biochemical catalysis model includes: Monitoring the battery exhaust gas treatment devices at each node through the sensor network to obtain the component data and equipment process parameters of each battery exhaust gas treatment device for treating battery exhaust gas; according to the Kalman filter algorithm, eliminating abnormal data from the component data and equipment process parameters; normalizing the component data and equipment process parameters after eliminating abnormal data, and extracting features from the normalized component data and equipment process parameters through a preset sliding window to obtain exhaust gas data features; based on the sensor network, adding time series features to the exhaust gas data features corresponding to each battery exhaust gas treatment device, thereby constructing a dynamic adsorption biochemical catalysis model.

[0025] In this embodiment, through the sensor network deployed at each node (i.e., the battery exhaust gas treatment device), the operating status of the battery exhaust gas treatment device is monitored in real time, and the sensor network can obtain key component data (such as VOCs concentration, particulate matter concentration, etc.) and equipment process parameters (such as temperature, pressure, flow rate, etc.) during the exhaust gas treatment process.

[0026] In this embodiment, the Kalman filter algorithm is used to process the collected component data and equipment process parameters. Among them, the Kalman filter is a filtering method based on statistical estimation, which can effectively identify and eliminate outliers or noise in the data, estimate the state of the battery exhaust gas treatment device and the overall system dynamically, and at the same time combine the measured value and / or predicted value, thereby reducing the influence of noise on the data. It can be understood that the measured value can be evaluated through the collected data, and the predicted value can be obtained by calculating the corresponding weight value after fitting the measured value.

[0027] In this embodiment, the component data and equipment process parameters after abnormal data removal are normalized so that their ranges are unified to between [0, 1] or [-1, 1]. It can be understood that normalization can eliminate the dimensional differences between different parameters and facilitate subsequent processing. Furthermore, the normalized data is processed through a preset sliding window. The sliding window technique can extract local features in the data and reduce the data dimension. Exemplarily, a window with a fixed size is set, and statistical features (such as mean, variance, etc.) of the data within the window are extracted each time it slides, thereby obtaining the features of the exhaust gas data.

[0028] In this embodiment, based on the sensor network, temporal features are added to the exhaust gas data features corresponding to each battery exhaust gas treatment device. Temporal features can reflect the changing trend of the data over time, which helps the model capture dynamic changes. Then, combining the normalized feature data and temporal features, a dynamic adsorption biochemical catalysis model is constructed. Among them, the model can simulate the dynamic changes in processes such as adsorption, biochemical reaction, and catalysis during the exhaust gas treatment process, thereby achieving accurate prediction and control of the exhaust gas treatment process. It can be understood that through sensor network monitoring, Kalman filtering algorithm, data normalization and feature extraction, and the construction of a dynamic adsorption biochemical catalysis model, the intelligent monitoring and optimization of the battery exhaust gas treatment process are realized, which has significant economic and environmental benefits.

[0029] As a preferred solution of this embodiment, based on the sensor network, temporal features are added to the exhaust gas data features corresponding to each battery exhaust gas treatment device, thereby constructing a dynamic adsorption biochemical catalysis model, which specifically includes: Based on the sensor network and according to the node information of each battery exhaust gas treatment device, the structure data corresponding to the node information of each battery exhaust gas treatment device is pulled, and a modeling is performed according to the structure data to obtain an adsorption layer structure model corresponding to each battery exhaust gas treatment device; Based on the preset sliding window, temporal features are added to the exhaust gas data features corresponding to each battery exhaust gas treatment device; According to the exhaust gas data features with added temporal features and the node information of each battery exhaust gas treatment device, an adsorption diffusion model is constructed; The adsorption layer structure model and the adsorption diffusion model are coupled, and preset data driving is added to the coupled model to construct a dynamic adsorption biochemical catalysis model corresponding to each battery exhaust gas treatment device.

[0030] In this embodiment, the sensor network is monitored and the structural data is modeled. Based on the sensor network, the node information of each battery waste gas treatment device is monitored. Among them, the sensor network collects the operation data of the waste gas treatment device in real time through sensor nodes deployed at different positions. Then, according to the structural data of each node, an adsorption layer structure model is constructed for each battery waste gas treatment device. The structural data includes physical parameters of the adsorption layer (such as the type of adsorbent, porosity, specific surface area, etc.) and process parameters (such as waste gas flow rate, temperature, etc.), which are used to simulate the physical and chemical properties of the adsorption layer. Then, time series feature extraction is carried out. Using the preset sliding window technology, time series features are added to the waste gas data features (such as VOCs concentration, particulate matter concentration, etc.) corresponding to each battery waste gas treatment device. In addition, the sliding window technology slides a fixed-size window on the time series data to extract statistical features (such as mean, variance, etc.) within the window, so as to capture the dynamic changes of the data over time.

[0031] In this embodiment, an adsorption diffusion model is constructed. By combining the waste gas data features with added time series features and the node information of each battery waste gas treatment device, an adsorption diffusion model is constructed. This model is used to describe the diffusion process of waste gas in the adsorption layer, taking into account the adsorption capacity of the adsorbent and the diffusion characteristics of the waste gas. The adsorption diffusion model can predict the distribution and concentration changes of waste gas in the adsorption layer, providing a theoretical basis for dynamic control. Then, the coupling model and data-driven approach are optimized. The adsorption layer structure model and the adsorption diffusion model are coupled to form a comprehensive dynamic adsorption biochemical catalytic model. The coupling model can more accurately simulate the dynamic behavior of waste gas treatment by integrating the physical structure and diffusion process of the adsorption layer. In addition, preset data-driven methods (such as historical operation data, fault diagnosis data, etc.) are added to the coupling model to further optimize the prediction ability and adaptability of the model.

[0032] In this embodiment, the adsorption layer structure model can be constructed based on CAD (accuracy ±0.1 mm); the adsorption diffusion model can be constructed by using Darcy's law and the Langmuir equation (adsorption isotherm equation), and combining the waste gas data features, and simulating the pore diffusion process of the adsorbent by using the finite element method.

[0033] Step S103: Perform simulation operation through the dynamic adsorption biochemical catalytic model, and perform real-time working condition prediction according to the collected simulation operation data to obtain the waste gas prediction result within a preset future time.

[0034] As a preferred solution of this embodiment, the performing simulation operation through the dynamic adsorption biochemical catalytic model, and performing real-time working condition prediction according to the collected simulation operation data to obtain the waste gas prediction result within a preset future time specifically includes: Through the dynamic adsorption biochemical catalysis model, the corresponding battery waste gas treatment device is simulated, and during the simulation process, the data of the running dynamic adsorption biochemical catalysis model is collected in real time to obtain the simulation operation data of each dynamic adsorption biochemical catalysis model; The collected simulation operation data is input into a preset LSTM neural network, and the real-time working conditions of the dynamic adsorption biochemical catalysis model are predicted within a preset future time, thereby obtaining the waste gas prediction results within the preset future time.

[0035] In this embodiment, through the constructed dynamic adsorption biochemical catalysis model, the corresponding battery waste gas treatment device is simulated. During the simulation process, the data of the model operation is collected in real time, including key indicators such as the adsorption layer structure parameters, waste gas composition changes, temperature, and pressure of the waste gas treatment device, so as to obtain the simulation operation data of each dynamic adsorption biochemical catalysis model.

[0036] In this embodiment, the simulation operation data is input into a preset LSTM neural network. Among them, the LSTM network is a long short-term memory network that can effectively process time series data and capture the dynamic changes and long-term dependence relationships in the data. Within a preset future time, the LSTM network predicts the real-time working conditions of the dynamic adsorption biochemical catalysis model and outputs the waste gas prediction results within the future time, including key parameters such as the waste gas composition concentration and treatment efficiency.

[0037] As a preferred solution, the construction method of the preset LSTM neural network specifically includes: Obtain the historical simulation data of the dynamic adsorption biochemical catalysis model and preprocess the historical simulation data; Perform feature selection on the preprocessed historical simulation data to obtain key historical data features; Based on the dimension of the key historical data features, construct an initial LSTM neural network and set the loss function and optimization algorithm; Train the initial LSTM neural network based on the loss function and optimization algorithm, and evaluate the trained LSTM neural network through a preset test set, so as to obtain an LSTM neural network with qualified evaluation results as the preset LSTM neural network.

[0038] In this embodiment, during data preprocessing and model training, before inputting the simulation operation data into the LSTM network, it is necessary to preprocess the data, including operations such as normalization and feature extraction. Among them, normalization can scale the data to a unified range and reduce the dimensional difference between different features; feature extraction analyzes the time series characteristics of the data and extracts features that are significant for prediction, thereby helping to improve the training efficiency and prediction accuracy of the model. Specifically, collect the waste gas data emitted during the production process, including the real-time concentrations of various VOCs, as well as related production parameters such as equipment operating status and raw material usage. At the same time, environmental parameters such as temperature, humidity, and air pressure that may affect the emission and diffusion of VOCs can be further collected. Furthermore, clean the collected data, dealing with missing values, outliers, etc. Then standardize or normalize the data to eliminate the dimensional difference between different variables and improve the training effect of the model. Thus, analyze and select the features that have a significant impact on the VOCs concentration fluctuation, among which, methods such as correlation analysis and importance analysis can be used to determine, for example, environmental factors such as temperature, humidity, and air pressure.

[0039] In this embodiment, define the structure of the LSTM model, including the input layer, hidden layer, and output layer. The dimension of the input layer should be consistent with the number of selected features, and the output layer predicts the VOCs concentration fluctuation within a preset future time. Preferably, the preset future time can be set to 30 minutes. In the hidden layer, select an appropriate activation function (such as the ReLU function) to avoid the gradient vanishing problem and improve the non-linear fitting ability of the model. Additionally, a Dropout layer can be added to prevent the model from overfitting.

[0040] In this embodiment, divide the preprocessed data set into a training set and a test set, and use the training set to train the LSTM model. During the training process, set an appropriate loss function (such as mean square error) and an optimization algorithm (such as the Adam optimizer) to minimize the loss function. At the same time, it is necessary to select appropriate hyperparameters, such as learning rate, number of training epochs, batch size, etc., to improve the training efficiency and prediction accuracy of the model. The best combination of hyperparameters can be determined through experiments or by using hyperparameter optimization algorithms. Further, in order to enhance the adaptability and prediction ability of the model, some improved LSTM model structures can be considered. For example, introduce the attention mechanism into the LSTM model to better handle complex environmental adaptability and data information learning.

[0041] In this embodiment, during the training process of the LSTM network, an optimization algorithm (including but not limited to the Adam optimizer, etc.) is used to adjust the weights and biases of the network to minimize the prediction error. At the same time, verify the model through methods such as cross-validation to ensure that the model has good generalization ability on unseen data.

[0042] In this embodiment, a trained LSTM model is evaluated using a test set, and the evaluation metrics may include mean squared error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), etc. The verified and optimized LSTM model is applied to an actual battery production waste gas treatment system to receive current time series data in real time and output the predicted results of VOCs concentration fluctuations in the next 30 minutes. The waste gas prediction results can provide a basis for the operation adjustment of waste gas treatment equipment and take corresponding measures in advance to reduce the emissions of VOCs.

[0043] Step S104: Based on the dynamic adsorption biochemical catalysis model, perform multi-objective optimization according to the waste gas prediction results to obtain control decisions corresponding to each waste gas treatment device, and control the waste gas treatment device according to the control decisions.

[0044] As a preferred solution of this embodiment, the multi-objective optimization based on the dynamic adsorption biochemical catalysis model according to the waste gas prediction results to obtain control decisions corresponding to each waste gas treatment device, and control the waste gas treatment device according to the control decisions specifically includes: Based on the dynamic adsorption biochemical catalysis model, determine the energy consumption target, removal rate target, and solvent recovery rate target; Constrain the energy consumption target, removal rate target, and solvent recovery rate target to obtain multi-objective optimization conditions; Use the waste gas prediction results as the particle swarm, and based on the multi-objective optimization conditions, calculate the fitness of each particle in the particle swarm, and update the individual particle optimal solution and the global particle swarm optimal solution; wherein, each particle corresponds to the waste gas prediction result of each dynamic adsorption biochemical catalysis model, and the position and velocity of each particle are respectively represented as a point and a movement direction in its solution space; According to the individual particle optimal solution and the global particle swarm optimal solution, update the velocity and position of each particle until the preset iteration condition is reached, and then output the optimal position of the global particle swarm as the optimization result; According to the optimization result, determine the optimization object and optimization target of the dynamic adsorption biochemical catalysis model, so as to generate control decisions corresponding to each waste gas treatment device; Send each control decision to each waste gas treatment device, and control the waste gas treatment device based on the corresponding control decision.

[0045] In this embodiment, multi-objective optimization conditions are determined. By using a dynamic adsorption biochemical catalysis model, an energy consumption target, a removal rate target, and a solvent recovery rate target are determined. Among them, the above targets reflect the key performance indicators in the waste gas treatment process. For example, the energy consumption target can be used to evaluate the reduction of energy consumption in the waste gas treatment process; the removal rate target can be used to evaluate the removal efficiency of pollutants (such as VOCs) in the waste gas; the solvent recovery rate target can be used to evaluate the recovery and utilization rate of the solvent. Then, the above targets are constrained to form multi-objective optimization conditions, which are used to guide the subsequent optimization process to ensure that the optimization results meet multiple performance indicators simultaneously.

[0046] In this embodiment, the waste gas prediction result is used as the initial input of the particle swarm. Each particle corresponds to a waste gas prediction result of the dynamic adsorption biochemical catalysis model, and its position and velocity are respectively represented as a point and a moving direction in the solution space. Among them, the parameters of the particle swarm are initialized, including: the number of particles, the inertia weight, the individual learning factor, the swarm learning factor, and the upper and lower bounds of the search space; the number of particles is determined according to the problem scale and complexity, the inertia weight, the individual learning factor, and the swarm learning factor can all control the movement behavior of the particles, and the upper and lower bounds of the search space are used to limit the position range of the particles.

[0047] In this embodiment, based on the multi-objective optimization conditions, the fitness of each particle in the particle swarm is calculated. Among them, the fitness function is usually a multi-objective function that comprehensively considers energy consumption, removal rate, and solvent recovery rate. In each iteration: update the individual particle best solution (pbest): if the fitness of the current particle is better than its historical best value, then update its individual best position; and update the global particle swarm best solution (gbest): if the fitness of the current particle is better than the global best value, then update the global best position. Then, the velocity and position of each particle can be updated according to the individual best solution and the global best solution. Repeat the above fitness calculation and particle update process until the preset iteration conditions (such as the maximum number of iterations or fitness convergence) are reached, and finally output the optimal position of the global particle swarm as the optimization result.

[0048] In this embodiment, according to the optimization result, the optimization object and optimization target of the dynamic adsorption biochemical catalysis model are determined, the control decision corresponding to each waste gas treatment device is generated, and then the control decision is sent to each waste gas treatment device, and the device is controlled in real time based on the corresponding control decision to optimize the waste gas treatment process.

[0049] Implementing the above embodiments has the following effects: The technical solution of the present invention generates a corresponding sensor network by obtaining the response signals emitted by the sensors provided on the battery waste gas treatment device, and performs corresponding data collection based on the sensor network, and then generates corresponding waste gas data characteristics to construct a corresponding dynamic adsorption biochemical catalysis model, so as to enable the simulation operation of the dynamic adsorption biochemical catalysis model and perform real-time working condition prediction, thereby obtaining the waste gas prediction results within a preset future time, and finally performing multi-objective optimization to achieve the control decisions corresponding to each waste gas treatment device, so as to achieve the cluster control of each waste gas treatment device, thereby ensuring the integration degree and optimization degree of the systematic waste gas treatment link, and improving the real-time monitoring ability and intelligent regulation and control ability. Embodiment 2

[0050] Please refer to Figure 2 , which further provides an intelligent control system for waste gas treatment for battery reuse, including: a control host computer 01 and a plurality of battery waste gas treatment devices 02 connected to the control host computer 01; The battery waste gas treatment device 02 is used for collecting and adsorbing the waste gas produced by the battery reuse equipment, and collecting waste gas data through the sensors arranged therein; Please refer to Figure 3 , the control host computer 01 includes: a response module 201, a model module 202, a simulation module 203 and an optimization module 204; The response module 201 is used for obtaining the response signals emitted by the sensors provided on the battery waste gas treatment device 02, and generating a sensor network according to the response signals; wherein, at least one sensor is arranged on each battery waste gas treatment device 02, and each sensor emits a response signal corresponding to its identity information; The model module 202 is used for collecting data of the waste gas treatment device 02 through the sensor network, extracting features of the collected sensing data, and constructing a dynamic adsorption biochemical catalysis model based on the sensor network and in combination with the extracted waste gas data characteristics; wherein, each dynamic adsorption biochemical catalysis model corresponds to a waste gas treatment device 02; The simulation module 203 is used for performing simulation operation through the dynamic adsorption biochemical catalysis model, and performing real-time working condition prediction according to the collected simulation operation data, so as to obtain the waste gas prediction results within a preset future time; The optimization module 204 is used for performing multi-objective optimization based on the dynamic adsorption biochemical catalysis model according to the waste gas prediction results, obtaining the control decisions corresponding to each waste gas treatment device 02, and controlling the waste gas treatment device 02 according to the control decisions.

[0051] As a preferred solution, obtaining the response signals emitted by the sensors disposed on the battery waste gas treatment device 02 and generating a sensor network according to the response signals specifically includes: Transmitting docking signals to a preset range through a signal transmitting device, so that after each sensor disposed on the battery waste gas treatment device 02 receives the docking signals, response signals are generated and sent outwards; Obtaining the response signals and parsing the identity information of each sensor according to the response signals; Based on the identity information of each sensor, identifying the battery waste gas treatment device 02 where each sensor is disposed, and generating node information corresponding to the battery waste gas treatment device 02 according to the waste gas types treated by each battery waste gas treatment device 02; Based on the node information and in combination with the sensors, constructing and generating a sensor network.

[0052] As a preferred solution, collecting data on the waste gas treatment device 02 through the sensor network, extracting features of the collected sensing data, and constructing a dynamic adsorption biochemical catalysis model based on the sensor network and in combination with the extracted waste gas data features, including: Monitoring each battery waste gas treatment device 02 at each node through the sensor network to obtain the component data and equipment process parameters of each battery waste gas treatment device 02 for treating battery waste gas; Eliminating abnormal data from the component data and equipment process parameters according to the Kalman filtering algorithm; Normalizing the component data and equipment process parameters after eliminating abnormal data, and extracting features of the normalized component data and equipment process parameters through a preset sliding window to obtain waste gas data features; Based on the sensor network, adding time series features to the waste gas data features corresponding to each battery waste gas treatment device 02, thereby constructing a dynamic adsorption biochemical catalysis model.

[0053] As a preferred solution, adding time series features to the waste gas data features corresponding to each battery waste gas treatment device 02 based on the sensor network, thereby constructing a dynamic adsorption biochemical catalysis model, specifically including: Based on the sensor network and according to the node information of each battery waste gas treatment device 02, pulling the structure data corresponding to the node information of each battery waste gas treatment device 02 node, and performing modeling according to the structure data to obtain an adsorption layer structure model corresponding to each battery waste gas treatment device 02; Based on the preset sliding window, adding time series features to the waste gas data features corresponding to each battery waste gas treatment device 02; Construct an adsorption diffusion model based on the exhaust gas data characteristics of the time-added characteristics and the node information of each battery exhaust gas treatment device 02; Couple the adsorption layer structure model and the adsorption diffusion model, and add preset data driving to the coupled model to construct a dynamic adsorption biochemical catalytic model corresponding to each battery exhaust gas treatment device 02.

[0054] As a preferred solution, the dynamic adsorption biochemical catalytic model is used for simulation operation, and real-time working condition prediction is performed according to the collected simulation operation data to obtain the exhaust gas prediction result within a preset future time, specifically including: Through the dynamic adsorption biochemical catalytic model, simulate the corresponding battery exhaust gas treatment device 02, and collect data of the running dynamic adsorption biochemical catalytic model in real time during the simulation to obtain the simulation operation data of each dynamic adsorption biochemical catalytic model; Input the collected simulation operation data into a preset LSTM neural network, and perform real-time working condition prediction of the dynamic adsorption biochemical catalytic model within a preset future time, thereby obtaining the exhaust gas prediction result within a preset future time.

[0055] As a preferred solution, the construction method of the preset LSTM neural network specifically includes: Obtain the historical simulation data of the dynamic adsorption biochemical catalytic model, and preprocess the historical simulation data; Perform feature selection on the preprocessed historical simulation data to obtain key historical data features; Based on the dimension of the key historical data features, construct an initial LSTM neural network, and set a loss function and an optimization algorithm; Train the initial LSTM neural network based on the loss function and the optimization algorithm, and evaluate the trained LSTM neural network through a preset test set to obtain an LSTM neural network with qualified evaluation results as the preset LSTM neural network.

[0056] As a preferred solution, based on the dynamic adsorption biochemical catalytic model, perform multi-objective optimization according to the exhaust gas prediction result to obtain the control decision corresponding to each exhaust gas treatment device 02, and control the exhaust gas treatment device 02 according to the control decision, specifically including: Based on the dynamic adsorption biochemical catalytic model, determine the energy consumption target, removal rate target, and solvent recovery rate target; Constrain the energy consumption target, removal rate target, and solvent recovery rate target to obtain multi-objective optimization conditions; Use the predicted exhaust gas results as a particle swarm, and based on the multi-objective optimization conditions, calculate the fitness of each particle in the particle swarm, and update the individual particle optimal solution and the global particle swarm optimal solution; where each particle corresponds to the predicted exhaust gas result of each dynamic adsorption biochemical catalysis model, and the position and velocity of each particle are respectively represented as a point and a movement direction in its solution space. Update the velocity and position of each particle according to the individual particle optimal solution and the global particle swarm optimal solution, and output the optimal position of the global particle swarm as the optimization result until the preset iteration condition is reached. Determine the optimization object and optimization goal of the dynamic adsorption biochemical catalysis model according to the optimization result, so as to generate the control decision corresponding to each exhaust gas treatment device 02. Send each of the control decisions to each exhaust gas treatment device 02, and control the exhaust gas treatment device 02 based on the corresponding control decision.

[0057] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process of the device described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0058] Implementing the above embodiments has the following effects: The technical solution of the present invention generates a corresponding sensor network by obtaining the response signals emitted by the sensors arranged on the battery exhaust gas treatment device, and performs corresponding data collection based on this sensor network, and then generates corresponding exhaust gas data characteristics to construct a corresponding dynamic adsorption biochemical catalysis model, so as to enable the simulation operation of the dynamic adsorption biochemical catalysis model and perform real-time working condition prediction, so as to obtain the predicted exhaust gas results within a preset future time, and finally perform multi-objective optimization to realize the control decisions corresponding to each exhaust gas treatment device, so as to realize the cluster control of each exhaust gas treatment device, thereby ensuring the integration degree and optimization degree of the systematic exhaust gas treatment link, and improving the real-time monitoring ability and intelligent adjustment control ability. Embodiment III

[0059] Correspondingly, the present invention also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the intelligent control method for exhaust gas treatment for battery reuse described in any one of the above embodiments.

[0060] The terminal device of this embodiment includes: a processor, a memory, and computer programs and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, it implements each step in the above Embodiment 1, for example Figure 1The steps S101 to S104 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above device embodiment, such as the simulation module 203.

[0061] Exemplarily, the computer program can be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and this instruction segment is used to describe the execution process of the computer program in the terminal device. For example, the simulation module 203 is used to perform simulation operations through the dynamic adsorption biochemical catalysis model, and perform real-time working condition prediction based on the collected simulation operation data to obtain the waste gas prediction result within a preset future time.

[0062] The terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the schematic diagram is only an example of the terminal device, and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the terminal device may further include input / output devices, network access devices, a bus, etc.

[0063] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal device, and connects various parts of the entire terminal device through various interfaces and lines.

[0064] The memory can be used to store the computer program and / or modules. By running or executing the computer program and / or modules stored in the memory, and invoking the data stored in the memory, the processor realizes various functions of the terminal device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0065] Among them, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals. Embodiment 4

[0066] Correspondingly, the present invention also provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. Among them, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the intelligent control method for waste gas treatment for battery reuse described in any one of the above embodiments.

[0067] The specific embodiments described above further elaborate on the object, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only for the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. In particular, it is pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent control method for waste gas treatment in battery reuse, characterized in that, include: Acquire a response signal emitted by a sensor disposed on the battery exhaust gas treatment device, and generate a sensor network according to the response signal; wherein each battery exhaust gas treatment device is provided with at least one sensor, and each sensor emits a response signal corresponding to its identity information; The exhaust gas treatment device is subjected to data collection through a sensor network, and features are extracted from the collected sensor data. Based on the sensor network and in combination with the extracted exhaust gas data features, a dynamic adsorption biochemical catalytic model is constructed; wherein each dynamic adsorption biochemical catalytic model corresponds to an exhaust gas treatment device; The dynamic adsorption biochemical catalytic model is used to perform simulation operation, and real-time operating condition prediction is performed based on the collected simulation operation data to obtain exhaust gas prediction results within a preset future time; Based on the dynamic adsorption biochemical catalytic model, multi-objective optimization is performed according to the exhaust gas prediction results to obtain control decisions corresponding to each exhaust gas treatment device, and the exhaust gas treatment device is controlled according to the control decisions.

2. The intelligent control method for waste gas treatment in battery reuse according to claim 1, characterized in that The step of acquiring a response signal emitted by a sensor disposed on the battery exhaust gas treatment device and generating a sensor network according to the response signal specifically includes: The signal transmitting device transmits a docking signal to a preset range, so that each sensor provided on the battery exhaust gas treatment device generates a response signal and sends it out after receiving the docking signal; Acquire the response signal, and parse the identity information of each sensor according to the response signal; Based on the identity information of each sensor, identify the battery exhaust gas treatment device set by each sensor, and generate the node information of the corresponding battery exhaust gas treatment device according to the exhaust gas type treated by each battery exhaust gas treatment device; Based on the node information and in combination with the sensors, a sensor network is constructed.

3. The intelligent control method for waste gas treatment in battery reuse according to claim 2, characterized in that, The exhaust gas treatment device is collected data through a sensor network, the collected sensor data is subjected to feature extraction, and a dynamic adsorption biochemical catalytic model is constructed based on the sensor network and in combination with the extracted exhaust gas data features, including: Through the sensor network, the battery exhaust gas treatment device of each node is monitored to obtain the component data and equipment process parameters of the battery exhaust gas treated by each battery exhaust gas treatment device; According to the Kalman filter algorithm, abnormal data of the component data and equipment process parameters are eliminated; The data is normalized by removing the abnormal data from the component data and equipment process parameters, and the features of the normalized component data and equipment process parameters are extracted through a preset sliding window to obtain the exhaust gas data features; Based on the sensor network, the exhaust gas data features corresponding to each battery exhaust gas treatment device are added with time series features, so as to construct a dynamic adsorption biochemical catalysis model.

4. The intelligent control method for waste gas treatment in battery reuse according to claim 3, characterized in that, Based on the sensor network, the exhaust gas data features corresponding to each battery exhaust gas treatment device are added with time series features, so as to construct a dynamic adsorption biochemical catalysis model, which specifically includes: Based on the sensor network, and according to the node information of each battery waste gas treatment device, pull the structural data corresponding to the node information of each battery waste gas treatment device, and perform modeling based on the structural data to obtain an adsorption layer structure model corresponding to each battery waste gas treatment device; Based on the preset sliding window, add time series features to the waste gas data features corresponding to each battery waste gas treatment device; Construct an adsorption and diffusion model according to the waste gas data features with added time series features and the node information of each battery waste gas treatment device; Couple the adsorption layer structure model and the adsorption and diffusion model, and add a preset data drive to the coupled model to construct a dynamic adsorption biochemical catalytic model corresponding to each battery waste gas treatment device.

5. The intelligent control method for waste gas treatment in battery reuse according to claim 4, characterized in that, The simulation operation is carried out through the dynamic adsorption biochemical catalytic model, and the real-time working condition prediction is carried out according to the collected simulation operation data to obtain the waste gas prediction result within a preset future time, which specifically includes: Through the dynamic adsorption biochemical catalytic model, simulate the corresponding battery waste gas treatment device, and collect data of the running dynamic adsorption biochemical catalytic model in real time during the simulation process to obtain the simulation operation data of each dynamic adsorption biochemical catalytic model; Input the collected simulation operation data into a preset LSTM neural network, and perform real-time working condition prediction of the dynamic adsorption biochemical catalytic model within a preset future time, and then obtain the waste gas prediction result within a preset future time.

6. The intelligent control method for waste gas treatment in battery reuse according to claim 5, characterized in that, The construction method of the preset LSTM neural network specifically includes: Obtain the historical simulation data of the dynamic adsorption biochemical catalytic model, and preprocess the historical simulation data; Perform feature selection on the preprocessed historical simulation data to obtain key historical data features; Based on the dimension of the key historical data features, construct an initial LSTM neural network, and set a loss function and an optimization algorithm; Train the initial LSTM neural network based on the loss function and the optimization algorithm, and evaluate the trained LSTM neural network through a preset test set to obtain an LSTM neural network with qualified evaluation results as the preset LSTM neural network.

7. An intelligent control method for waste gas treatment in battery reuse according to any one of claims 1-5, characterized in that, Based on the dynamic adsorption biochemical catalytic model, perform multi-objective optimization according to the waste gas prediction result to obtain the control decision corresponding to each waste gas treatment device, and control the waste gas treatment device according to the control decision, which specifically includes: Based on the dynamic adsorption biochemical catalytic model, determine the energy consumption target, removal rate target and solvent recovery rate target; Constrain the energy consumption target, removal rate target and solvent recovery rate target to obtain multi-objective optimization conditions; Use the waste gas prediction result as a particle swarm, and based on the multi-objective optimization conditions, calculate the fitness of each particle in the particle swarm, and update the individual particle optimal solution and the global particle swarm optimal solution; wherein, each particle corresponds to the waste gas prediction result of each dynamic adsorption biochemical catalytic model, and the position and velocity of each particle are respectively represented as a point and a movement direction in its solution space. Update the velocity and position of each particle according to the individual particle optimal solution and the global particle swarm optimal solution until the preset iteration condition is reached, and then output the optimal position of the global particle swarm as the optimization result; Determine the optimization object and optimization target of the dynamic adsorption biochemical catalysis model according to the optimization result, so as to generate the control decision corresponding to each waste gas treatment device; Send each control decision to each waste gas treatment device, and control the waste gas treatment device based on the corresponding control decision.

8. An intelligent control system for waste gas treatment in battery reuse, characterized in that, Comprising: A control host computer and a plurality of battery waste gas treatment devices connected to the control host computer; The battery waste gas treatment device is used for collecting and adsorbing the waste gas produced by the battery reuse equipment, and collecting waste gas data through a sensor arranged therein; The control host computer includes a response module, a model module, a simulation module and an optimization module; The response module is used for acquiring the response signal emitted by the sensor arranged on the battery waste gas treatment device, and generating a sensor network according to the response signal; wherein, at least one sensor is arranged on each battery waste gas treatment device, and each sensor emits a response signal corresponding to its identity information; The model module is used for collecting data of the waste gas treatment device through the sensor network, extracting features of the collected sensing data, and constructing a dynamic adsorption biochemical catalysis model based on the sensor network and in combination with the extracted waste gas data features; wherein, each dynamic adsorption biochemical catalysis model corresponds to a waste gas treatment device; The simulation module is used for performing simulation operation through the dynamic adsorption biochemical catalysis model, and predicting the real-time working condition according to the collected simulation operation data to obtain the waste gas prediction result within a preset future time; The optimization module is used for performing multi-objective optimization based on the dynamic adsorption biochemical catalysis model according to the waste gas prediction result to obtain the control decision corresponding to each waste gas treatment device, and controlling the waste gas treatment device according to the control decision.

9. A terminal device, characterized in that, Comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the waste gas treatment intelligent control method for battery reuse according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the waste gas treatment intelligent control method for battery reuse according to any one of claims 1 to 7.

Images