Temperature control method and system for soda ash production process

Abstract

The present invention relates to the technical field of industrial production temperature control, and discloses a temperature control method and system for the soda ash production process. It includes training a temperature strategy model and a temperature prediction model based on historical data; obtaining real-time data in the soda ash production process, and controlling relevant equipment to adjust the temperature according to the temperature control strategy output by the temperature strategy model; comparing the real-time production equipment temperature with the temperature prediction curve output by the temperature prediction model to determine whether the real-time production equipment temperature meets the temperature range requirements; when an abnormal situation occurs, automatically adjusting the temperature control strategy and generating a new temperature prediction curve; if the abnormal situation is not resolved within the preset number of adjustment times, triggering an early warning mechanism. Thus, it effectively solves the problem that the traditional temperature control method lacks real-time data analysis and prediction capabilities, and improves the intelligent and automatic temperature control capabilities in the soda ash production process.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial production temperature control, and particularly relates to a temperature control method and system for the soda ash production process. Background Art

[0002] In the soda ash production process, temperature is a key factor affecting product quality and production efficiency. Traditional temperature control methods mainly rely on manual operation and empirical judgment, which are not suitable for complex and changeable production environments. Soda ash production involves multiple variables, and small changes in these variables may affect the production temperature, resulting in fluctuations in product quality and a decrease in production efficiency.

[0003] In addition, traditional temperature control methods lack real-time data analysis and prediction capabilities, and it is difficult to respond to temperature fluctuations in the production process in a timely manner. When the temperature of the production equipment deviates from the preset range, manual intervention is often required for adjustment, which not only increases labor costs but may also exacerbate production problems due to untimely or improper adjustment. Therefore, how to achieve intelligent and automated temperature control in the soda ash production process has become an urgent problem to be solved. Summary of the Invention

[0004] Aiming at the above-mentioned technical deficiencies, the purpose of the present invention is to provide a temperature control method and system for the soda ash production process to solve the problems existing in the prior art.

[0005] To solve the above technical problems, the present invention adopts the following technical solutions:

[0006] In the first aspect, the present invention provides a temperature control method for the soda ash production process, and the method includes:

[0007] Step S100: Obtain the first historical data in the soda ash production process, perform data preprocessing to obtain the second historical data, and use the second historical data to train a temperature strategy model and a temperature prediction model;

[0008] Step S200: Obtain the real-time data in the soda ash production process, and control the equipment in the soda ash production process to adjust the temperature according to the temperature control strategy output by the temperature strategy model;

[0009] Step S300: Input the real-time data and the real-time temperature control strategy into the temperature prediction model to obtain a temperature prediction curve, and compare the real-time production equipment temperature with the temperature prediction curve to determine whether the real-time production equipment temperature meets the temperature range requirements;

[0010] Step S400: When an abnormal situation occurs, automatically adjust the temperature control strategy and generate a new temperature prediction curve;

[0011] Step S500: If the abnormal situation is not resolved within the preset adjustment times, trigger the warning mechanism.

[0012] Preferably, in a possible implementation manner of the first aspect, the step S100 further includes:

[0013] Obtain the first historical data in the soda ash production process and transmit it to the control center;

[0014] Perform data preprocessing on the first historical data, including data cleaning and data conversion, to obtain the second historical data;

[0015] Based on the second historical data, use the deep learning method to train the temperature strategy model and the temperature prediction model respectively.

[0016] Preferably, in a possible implementation manner of the first aspect, the first historical data includes historical temperature and precipitation data, historical production equipment temperature data, historical production raw material data, historical natural gas supply speed data, historical combustion air flow data, and historical cooling water flow data; the second historical data is the first historical data after cleaning and data conversion, meeting the preset model training data format.

[0017] Preferably, in a possible implementation manner of the first aspect, the temperature strategy model outputs the temperature control strategy of the equipment during the preset control time in the soda ash production process, including controlling the natural gas supply speed, combustion air flow, and cooling water flow; the temperature prediction model outputs the temperature prediction curve during the preset control time according to the temperature control strategy during the preset control time.

[0018] Preferably, in a possible implementation manner of the first aspect, the step S200 further includes:

[0019] The control system obtains the real-time data in the soda ash production process, including real-time temperature and precipitation data, real-time production equipment temperature data, and real-time production raw material data, inputs the real-time data into the temperature strategy model, and performs operations according to the temperature control strategy output by the temperature strategy model to generate control instructions to control the equipment in the soda ash production process to adjust the temperature.

[0020] Preferably, in a possible implementation manner of the first aspect, in the step S300, determining whether the real-time production equipment temperature meets the preset temperature range requirement specifically includes: obtaining the temperature prediction curve, collecting the real-time production equipment temperature data at preset time intervals, comparing it with the temperature prediction curve, and determining whether the real-time production equipment temperature is within the preset upper and lower floating ranges at this time point of the temperature prediction curve.

[0021] Preferably, in a possible implementation manner of the first aspect, the step S400 further includes:

[0022] The abnormal conditions include that the temperature of the real-time production equipment is not within the preset upper and lower floating ranges of the temperature prediction curve, or the predicted temperature change curve does not meet the target temperature of the preset soda ash production equipment.

[0023] When an abnormal condition occurs, the automatic temperature control strategy adjusts the temperature control strategy by inputting the real-time temperature and precipitation data, the real-time temperature data of the production equipment, and the real-time raw material data of the production into the temperature strategy model.

[0024] To generate a new temperature prediction curve, input the real-time temperature and precipitation data, the real-time temperature data of the production equipment, the real-time raw material data of the production, and the adjusted temperature control strategy into the temperature prediction model to generate a new temperature prediction curve.

[0025] Preferably, in a possible implementation manner of the first aspect, the step S500 further includes:

[0026] When the abnormal condition is not resolved within the preset number of adjustment times, a warning mechanism is triggered. The warning mechanism includes that the control center generates a warning message, a pop-up prompt is made on the display screen of the control center, and the warning message is sent to the terminal device.

[0027] Preferably, in a possible implementation manner of the first aspect, if the abnormal condition is not resolved within the preset number of adjustment times, that is, after the abnormal condition is adjusted for the preset number of adjustment times and the abnormal condition appears again within the preset warning time, the warning mechanism is triggered; the preset number of adjustment times is at least once.

[0028] In a second aspect, the present invention provides a temperature control system for the soda ash production process. The system includes:

[0029] A model training module: acquiring first historical data in the soda ash production process, performing data preprocessing to obtain second historical data, and using the second historical data to train a temperature strategy model and a temperature prediction model;

[0030] A temperature control module: acquiring real-time data in the soda ash production process, and controlling the equipment in the soda ash production process to adjust the temperature according to the temperature control strategy output by the temperature strategy model;

[0031] A temperature judgment module: inputting the real-time data and the real-time temperature control strategy into the temperature prediction model to obtain a temperature prediction curve, and comparing the real-time temperature of the production equipment with the temperature prediction curve to judge whether the real-time temperature of the production equipment meets the temperature range requirement;

[0032] A temperature adjustment module: when an abnormal condition occurs, automatically adjusting the temperature control strategy and generating a new temperature prediction curve;

[0033] Early warning module: If the abnormal situation is not resolved within the preset number of adjustment times, the early warning mechanism is triggered.

[0034] The beneficial effects of the present invention are as follows: The present invention realizes intelligent and automatic control through deep learning technology, significantly improves the accuracy and real-time performance of temperature control, and reduces manual intervention. It realizes real-time monitoring and adjustment of the temperature of production equipment, ensures that the temperature is stable within the optimal range, stabilizes the product quality, and improves production efficiency. At the same time, it has the functions of automatic handling and early warning of abnormal situations, reduces production risks, reduces labor costs, and further reduces production costs. Description of the Drawings

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0036] Figure 1 This application provides a flowchart of a temperature control method for the soda ash production process.

[0037] Figure 2 This application provides a structural schematic diagram of a temperature control system for the soda ash production process.

[0038] Description of the reference numerals: 1 - Model training module, 2 - Temperature control module, 3 - Temperature judgment module, 4 - Temperature adjustment module, 5 - Early warning module. Detailed Embodiments

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0040] Embodiment 1: As Figure 1 shown, the present invention provides a temperature control method for the soda ash production process, including:

[0041] Step S100: Obtain the first historical data in the soda ash production process, perform data preprocessing to obtain the second historical data, and use the second historical data to train the temperature strategy model and the temperature prediction model;

[0042] Specifically, step S100 of this application further includes:

[0043] Step S110: Obtain the first historical data during the soda ash production process and transmit it to the control center.

[0044] The control center is a core facility integrating data collection, storage, processing, analysis, mining, and visualization, providing comprehensive, accurate, and timely data support and decision-making basis for the entire soda ash production process. The control center adopted in this embodiment is equipped with a high-performance computing unit, a PLC communication interface, a database, a deep learning training environment, and a display.

[0045] In this embodiment, the ammonia-soda process is used to produce soda ash, and natural gas is used as fuel. The temperature control in the production process is carried out in four steps, including the limestone calcination step, the brine ammonia absorption step, the carbonation reaction step, and the sodium bicarbonate calcination step. The first historical data includes the historical data of the four steps:

[0046] The limestone calcination step includes the lime kiln target temperature, historical air temperature and precipitation data, historical lime kiln temperature data, historical natural gas supply rate, historical combustion air flow rate, and historical limestone data;

[0047] The brine ammonia absorption step includes the ammonia absorption tower target temperature, historical air temperature and precipitation data, historical ammonia absorption tower temperature data, historical ammonia and brine flow rate data, and historical cooling water flow rate data;

[0048] The carbonation reaction step includes the carbonation tower target temperature, historical air temperature and precipitation data, historical carbonation tower temperature data, historical ammonia brine and carbon dioxide concentration data, historical intake air volume and water outlet rate, and historical cooling water flow rate data;

[0049] The sodium bicarbonate calcination step includes the rotary kiln target temperature, historical air temperature and precipitation data, historical rotary kiln temperature data, historical natural gas supply rate, historical combustion air flow rate, and historical sodium bicarbonate data.

[0050] In this embodiment, the historical air temperature and precipitation data are obtained from the meteorological department. The lime kiln target temperature is 1100 °C, the ammonia absorption tower target temperature is 50 °C, the carbonation tower target temperature is 25 °C, and the rotary kiln target temperature is 175 °C. The temperature sensors in the lime kiln, ammonia absorption tower, carbonation tower, and rotary kiln transmit the collected temperature data back to the control center every 5 minutes, that is, the historical temperature data is obtained from the control center; the historical natural gas supply rate, historical combustion air flow rate in the lime kiln and rotary kiln, and the historical cooling water flow rate data in the ammonia absorption tower and carbonation tower are obtained from the historical operation logs; the historical limestone data, historical ammonia and brine flow rate data, historical ammonia brine and carbon dioxide concentration data, intake air volume and alkali outlet rate, and historical sodium bicarbonate data are also obtained from the historical operation logs. All the obtained first historical data contains timestamps.

[0051] A thermocouple is selected as the temperature sensor to collect the equipment temperature. The thermocouple can maintain high-precision temperature measurement in high-temperature environments. The temperature sensor is equipped with a ZigBee module. A gateway device is used between the ZigBee module and the PLC. The gateway device has dual communication interfaces of ZigBee and Ethernet and can communicate with the ZigBee network and the PLC simultaneously. After the thermocouple is integrated with the ZigBee module, the temperature data is sent to the gateway device through the ZigBee wireless network. After receiving the ZigBee signal, the gateway device immediately converts it into an Ethernet data packet and sends it to the PLC through the Ethernet interface. Finally, the PLC conducts data transmission with the control center through the data interface.

[0052] Step S120: Perform data preprocessing on the first historical data, including data cleaning and data transformation, to obtain the second historical data.

[0053] In this embodiment, the Pandas library of Python is used to load the first historical data. First, data cleaning is performed. For each missing value, it is filled with the average of the previous valid value and the next valid value. Check whether there are exactly the same timestamp and historical data records in the data. For redundant records, only one of them is retained. The interquartile range (IQR) method is used to determine whether there are outliers or extreme values. The calculation formula is IQR = Q3 - Q1, where Q1 is the first quartile, which is the data point at the 25% position after the data is sorted, and Q3 is the third quartile, which is the data point at the 75% position after the data is sorted. An outlier is defined as a data point below Q1 - 1.5 * IQR or above Q3 + 1.5 * IQR.

[0054] After completing the data cleaning, data transformation is performed to convert the first historical data into the second historical data. The second historical data is the first historical data after cleaning and data transformation and meets the preset model training data format. In this embodiment, the unit of all temperature data is °C, reserved to one decimal place, the unit of all flow data is , reserved to two decimal places, the unit of all precipitation data is ml, reserved to two decimal places, the unit of all concentration data is %, reserved to one decimal place, the limestone data includes the limestone weight and the limestone moisture content. The unit of the limestone weight is kilograms, reserved to one decimal place, the unit of the limestone moisture content is %, reserved to one decimal place. The sodium bicarbonate data includes the sodium bicarbonate weight. The unit of the sodium bicarbonate weight is kilograms, reserved to one decimal place. The second historical data is divided into a training set, a validation set, and a test set according to the ratio of 8:1:1.

[0055] Step S130: Based on the second historical data, use deep learning methods to train the temperature strategy model and the temperature prediction model respectively.

[0056] Based on the second historical data, a deep learning method is used to train the model. In this embodiment, different models are trained according to different production steps, and the temperature control strategy of the equipment within the preset control time and the temperature prediction curve within the preset control time for different production steps are output. In this embodiment, the preset control time is 6 hours. This embodiment includes eight models, all of which adopt the PyTorch structure. Taking the limestone calcination temperature strategy model and the limestone calcination temperature prediction model as examples, the structure of the model is specifically described.

[0057] Limestone calcination temperature strategy model: The input layer defines a class named InputLayer, which inherits from nn.Module of PyTorch. In the initialization method __init__ of InputLayer, four parameters are received: num_temp_features, num_precip_features, num_lime_features, and num_stone_features, which represent temperature-related features, precipitation-related features, lime kiln temperature features, and limestone features respectively. For each type of feature, a fully connected layer (nn.Linear) is created to map the input features to a higher-dimensional space.

[0058] In the forward method, three parameters are received: temp_precip, lime_temp, and stone_data, which correspond to the batch data of temperature-precipitation features, lime kiln temperature features, and limestone features respectively. Each parameter represents the corresponding feature data of all samples in a batch at the same time step.

[0059] For each type of feature data, it is first processed through its respective fully connected layer, and the ReLU activation function is applied to increase non-linearity. Then, the processed feature data are concatenated along the feature dimension (i.e., the second dimension, dim = 1) to form a comprehensive feature vector combined_features that contains all types of feature information.

[0060] The feature extraction and fusion layer defines the LSTMFeatureExtractor module, which extracts and fuses the features of sequence data through the LSTM (Long Short-Term Memory Network) layer and is constructed by inheriting the nn.Module base class.

[0061] In the initialization method of the LSTMFeatureExtractor, several key parameters are defined: input_size, hidden_size, num_layers, bidirectional, and dropout. These parameters are used to configure the input feature dimension of the LSTM layer, the size of the hidden layer, the number of LSTM layers, whether to use bidirectional LSTM, and whether to apply dropout between layers to prevent overfitting.

[0062] In the forward method, the input data x (whose shape is (batch, seq_len, input_size)) is passed to the LSTM layer. After being processed by the LSTM layer, two main outputs are returned: outputs and (hn, cn). Outputs contains the hidden state and cell state of the LSTM at each time step, while (hn, cn) contains the hidden state and cell state of the last time step. Finally, the forward method returns the processed hidden state hn as the feature representation of the entire sequence.

[0063] The output layer defines a PyTorch module named OutputLayer, which inherits from nn.Module. Its main role is to predict the control strategies of the natural gas supply rate and the combustion air flow rate based on the output of the LSTM. In the initialization method __init__ of OutputLayer, three parameters are received: hidden_size, num_time_steps, and num_outputs. Hidden_size is the size of the hidden layer of the LSTM, which determines the number of features input to the fully connected layer (nn.Linear). Num_outputs is the number of neurons in the output layer, that is, the number of predicted values of the natural gas supply rate and the combustion air flow rate.

[0064] self.fc_gas and self.fc_air are two fully connected layers, which are used to predict the natural gas supply rate and the combustion air flow rate respectively from the hidden state h_n of the LSTM or other recurrent neural network layers. The number of input features of both of these fully connected layers is hidden_size, and the number of output features is num_outputs.

[0065] In the forward method, the last hidden state h_n of the LSTM or other recurrent neural network layers is received as the input. Then, this hidden state is passed to self.fc_gas and self.fc_air respectively to calculate the predicted values of the natural gas supply rate and the combustion air flow rate. Finally, these two predicted values are returned together.

[0066] The mean squared error (MSE) loss function is adopted as the loss function of the model. A PyTorch module named ModelLoss is defined, which inherits from nn.Module. In the initialization method __init__ of ModelLoss, the basic initialization is completed by calling the __init__ method of the parent class, and an object self.mse_loss of the mean squared error (MSE) loss function built into PyTorch is instantiated for subsequent loss calculation.

[0067] In the forward method, two parameters are received: predictions and targets. Predictions is a tuple containing two elements, namely the predicted value gas_speed_pred of the natural gas supply rate and the predicted value air_flow_pred of the combustion air flow rate. Targets is also a tuple containing two elements, namely the true value gas_speed_target of the natural gas supply rate and the true value air_flow_target of the combustion air flow rate. The instantiated MSE loss function self.mse_loss is used to calculate the losses between the predicted values and the true values of the natural gas supply rate and the combustion air flow rate respectively, that is, gas_loss and air_loss. Finally, these two loss values are added together to obtain the total loss value total_loss, which is then returned.

[0068] Limestone calcination temperature prediction model: A class named LimeKilnTemperaturePredictor is defined, which inherits from nn.Module of PyTorch. In the initialization method __init__ of the LimeKilnTemperaturePredictor class, several key model parameters are defined: input_dim, the feature dimension of each time step, that is, the number of features contained in each time step in the data input to the LSTM layer; hidden_dim, the hidden layer dimension of the LSTM layer, which determines the dimension of the internal state of the LSTM cell; num_layers, the number of layers of the LSTM layer, and multiple layers of LSTM can capture more complex sequence relationships; output_dim, the output dimension, which here refers to the dimension of the final output of the model.

[0069] An LSTM layer is defined through nn.LSTM, with an input dimension of input_dim, a hidden layer dimension of hidden_dim, and a number of layers of num_layers, and batch_first=True is set. The first dimension of the input data is the batch size. The LSTM layer is responsible for extracting useful features from the input time series data.

[0070] Through a fully connected layer nn.Linear, the features of the last time step output by the LSTM are converted into the final prediction result, and it is mapped to the output dimension through the fully connected layer, that is, the temperature prediction values for the next few time points are obtained.

[0071] In the forward method, the forward propagation process of the data through the model is defined. First, the input data x (with shape (batch_size, seq_len, input_dim)) is fed into the LSTM layer, where seq_len is the length of the time series. After the LSTM layer processes the entire sequence, the output of the last time step is taken as the summary of the entire sequence. This summary is fed into the fully connected layer to obtain the final prediction result predictions, whose shape is (batch_size, output_dim), that is, the future temperature prediction values for each sample. The MSE loss function is also used as the loss function of the model.

[0072] The model is trained using the training set, and the test set is used to evaluate its generalization ability after the model training is completed, that is, its performance on unseen data. The validation set tests the model at different stages of model training to adjust the hyperparameters of the model to avoid overfitting and ensure that the model has good performance on unseen data.

[0073] The other six models are respectively the brine ammonia absorption temperature strategy model, the brine ammonia absorption temperature prediction model, the carbonation reaction temperature strategy model, the carbonation reaction temperature prediction model, the sodium bicarbonate calcination temperature strategy model, and the sodium bicarbonate calcination temperature prediction model. The model structures are respectively similar to those of the limestone calcination temperature strategy model and the limestone calcination temperature prediction model, so they will not be elaborated one by one.

[0074] Step S200: Obtain the real-time data in the soda ash production process, and control the equipment in the soda ash production process to adjust the temperature according to the temperature control strategy output by the temperature strategy model.

[0075] Specifically, the control system receives the data from the sensors in real time according to the temperature control strategy output by the deep learning model. The PLC, as the core control unit, calculates and processes the data according to the preset temperature control strategy and generates control instructions. These instructions are executed through devices such as electric control valves to adjust relevant parameters (including the cooling water flow rate, the natural gas supply speed, and the combustion air flow rate). The sensors continue to monitor the adjusted parameters and feedback the real-time data to the PLC to form a closed-loop control to ensure the stability and accuracy of the production process.

[0076] The temperature regulation of the equipment in the soda ash production process is divided into four steps, namely the limestone calcination step, the brine ammonia absorption step, the carbonation reaction step, and the sodium bicarbonate calcination step. In this embodiment, the limestone calcination step and the brine ammonia absorption step are taken as examples. The temperature regulation of the carbonation reaction step and the brine ammonia absorption step is similar, both of which adopt adjusting the cooling water flow rate to control the temperature. The temperature regulation of the sodium bicarbonate calcination step and the limestone calcination step is similar, and the temperature is controlled by adjusting the natural gas supply rate and the combustion air flow rate.

[0077] Limestone calcination step: Load the pre-trained limestone calcination temperature strategy model in the control center, obtain the real-time temperature and precipitation data from the meteorological department, obtain the real-time lime kiln temperature data through the temperature sensor, and obtain the limestone data used from the control center. The limestone data includes limestone weight and moisture content.

[0078] Input the real-time data into the limestone calcination temperature strategy model, and the model outputs the temperature control strategy, which specifically involves the regulation scheme of the natural gas supply rate and the combustion air flow rate during the calcination process.

[0079] The natural gas supply speed is related to the combustion efficiency. When the natural gas supply speed is appropriate, the fuel and air can be fully mixed to achieve complete combustion, thereby improving the combustion efficiency. The natural gas supply speed also affects the flame temperature. When the fuel supply amount is certain, increasing the natural gas supply speed can increase the flame temperature because more fuel burns in a short time and releases more heat. The combustion air flow rate affects the mixing degree of natural gas and air. Appropriate air flow rate helps the fuel and air to be fully mixed to form a uniform mixed gas, thereby improving the combustion efficiency.

[0080] The control system adjusts the natural gas supply speed and the combustion air flow rate in the limestone calcination process in real time according to the temperature control strategy output by the model. A natural gas flow rate sensor and a combustion air flow rate sensor are adopted on the gas supply pipeline to measure and transmit the flow rate data in real time. An electric control valve is installed on the natural gas pipeline, and the valve opening is adjusted by receiving the control signal to control the natural gas supply speed; an electric control valve is also installed on the combustion air pipeline to adjust the combustion air flow rate.

[0081] The control center uses a programmable logic controller as the core control unit, receives the data from the sensors, and performs calculations and processing according to the preset control logic and algorithms; a human-machine interface is configured to set process parameters, monitor the production process, receive alarm information, and perform data interaction with the PLC.

[0082] The PLC sends control commands to the electric control valves based on the natural gas supply speed and combustion air flow rate output. The sensors collect the natural gas flow rate and combustion air flow rate in real time and transmit the data to the PLC. The PLC analyzes and compares the received data to determine the deviation between the current state and the target state. Based on the magnitude and direction of the deviation, the PLC adjusts the control commands and gradually reduces the deviation by adjusting the opening degrees of the natural gas control valve and the combustion air control valve, making the actual parameters approach or reach the set values. The sensors continue to monitor the adjusted parameters and transmit the new data to the PLC. The PLC further adjusts according to the new data, forming a closed loop to ensure the stability and accuracy of the limestone calcination process.

[0083] Brine ammonia absorption step: Load the pre-trained brine ammonia absorption temperature strategy model in the control center, obtain the real-time temperature and precipitation data from the meteorological department, obtain the real-time ammonia absorption tower temperature data through the temperature sensor, and obtain the flow rate data of ammonia and brine from the control center.

[0084] Input the real-time temperature and precipitation data, the real-time ammonia absorption tower temperature data, and the flow rate data of ammonia and brine into the brine ammonia absorption temperature strategy model to output the temperature control strategy during the brine ammonia absorption process, that is, the cooling water flow rate control strategy during the entire limestone calcination process.

[0085] By controlling the flow rate of the cooling water, the temperature of the brine in the ammonia absorption tower can be effectively adjusted and maintained, which is beneficial to the dissolution and absorption of ammonia in the brine. Keeping the brine at a lower temperature can accelerate the diffusion rate of ammonia molecules into the brine, thereby improving the ammonia absorption efficiency. If the brine temperature is too high, it will not only affect the ammonia absorption effect but may also cause some components in the brine to undergo unwanted chemical reactions or crystallize out, blocking the equipment and pipelines.

[0086] The control system adjusts the cooling water flow rate during the brine ammonia absorption process according to the output temperature control strategy during the brine ammonia absorption process. A flow sensor is used on the cooling water pipeline to monitor the flow rate of the cooling water in real time and provide real-time data for the control system. The PLC receives the signal from the flow sensor and is responsible for issuing and executing the commands. An electric control valve is installed on the cooling water pipeline to automatically adjust the opening degree of the valve according to the controller's command, thereby controlling the flow rate of the cooling water.

[0087] The flow sensor monitors the flow rate of the cooling water in real time and transmits the data to the PLC. The PLC compares the received flow rate data with the result output by the brine ammonia absorption temperature strategy model to determine whether it is necessary to adjust the cooling water flow rate. If adjustment is required, the PLC will calculate the adjustment amount and generate a control command.

[0088] The PLC sends control instructions to the electric control valve, and the electric control valve automatically adjusts the opening of the valve according to the instructions, thereby changing the flow rate of the cooling water. During the adjustment process, the flow sensor continues to monitor the flow rate of the cooling water and feeds back the real-time data to the controller. The PLC evaluates the adjustment effect based on the feedback data and makes further adjustments as needed.

[0089] Step S300: Input the real-time data and the real-time temperature control strategy into the temperature prediction model to obtain a temperature prediction curve. Compare the real-time temperature of the production equipment with the temperature prediction curve to determine whether the real-time temperature of the production equipment meets the temperature range requirements.

[0090] Specifically, determining whether the real-time temperature of the production equipment meets the preset temperature range requirements includes obtaining the temperature prediction curve, collecting the real-time temperature data of the production equipment at preset time intervals, comparing it with the temperature prediction curve, and determining whether the real-time temperature of the production equipment is within the preset upper and lower floating ranges at this time point of the temperature prediction curve. This embodiment includes four stages, namely the limestone calcination stage, the brine ammonia absorption stage, the carbonation reaction stage, and the sodium bicarbonate calcination stage.

[0091] S310 Limestone Calcination Stage: Before production starts, obtain the real-time temperature and precipitation data from the meteorological department, use a temperature sensor to obtain the real-time temperature of the lime kiln, and at the same time obtain the weight and moisture content of the limestone from the control center, as well as the natural gas supply speed and combustion air flow rate output by the limestone calcination temperature strategy model. These data are input into the limestone calcination temperature prediction model to generate a temperature prediction curve for the lime kiln in the next six hours. During production, the temperature of the lime kiln is collected every five minutes, and then the recorded temperature value is compared with the prediction curve to determine whether it fluctuates within the range of 25°C above and below the prediction curve. Under normal circumstances, both the temperature management strategy and the temperature prediction curve for limestone calcination are updated every hour, that is, the data is re-analyzed through relevant models every hour and the strategy and prediction curve are adjusted.

[0092] S320 Brine Ammonia Absorption Stage: Before production starts, also obtain the real-time meteorological data from the meteorological department, obtain the real-time temperature of the ammonia absorption tower through a temperature sensor, and obtain the flow rate information of ammonia and brine and the cooling water flow rate output by the brine ammonia absorption temperature strategy model from the control center. These input data are sent into the brine ammonia absorption temperature prediction model to generate a temperature prediction curve for the ammonia absorption tower in the next six hours. During production, the temperature of the ammonia absorption tower is recorded every five minutes and compared with the prediction curve to confirm whether it is within the predicted range of 5°C above and below. Under normal circumstances, the temperature control strategy and the temperature prediction curve for brine ammonia absorption are also updated every hour to ensure precise control.

[0093] S330 Carbonation reaction stage: Before production starts, obtain meteorological data, the real-time temperature of the carbonation tower, the concentrations of ammoniated brine and carbon dioxide, the inlet and outlet water flow rates, and the cooling water flow rate output by the carbonation reaction temperature strategy model. These data are input into the carbonation reaction temperature prediction model to generate a temperature prediction curve for the next six hours. During production, the temperature of the carbonation tower is monitored every five minutes and compared with the prediction curve to verify whether it is within the predicted range of plus or minus 5°C. Under normal circumstances, the temperature control strategy for the carbonation reaction and the prediction curve are updated every hour.

[0094] S340 Sodium bicarbonate calcination stage: Before production starts, obtain meteorological data, the immediate temperature of the rotary kiln, the weight of sodium bicarbonate, and the natural gas and air flow rates output by the sodium bicarbonate calcination strategy model. These data are fed into the sodium bicarbonate calcination temperature prediction model to generate a rotary kiln temperature prediction curve for the next six hours. During production, the temperature of the rotary kiln is recorded every five minutes and compared with the prediction curve to confirm whether it is within the predicted range of plus or minus 10°C. Under normal circumstances, the temperature control strategy for sodium bicarbonate calcination and the temperature prediction curve are also updated every hour.

[0095] Step S400: When an abnormal situation occurs, automatically adjust the temperature control strategy and generate a new temperature prediction curve.

[0096] Abnormal situations include that the real-time temperature of the production equipment is not within the preset upper and lower floating ranges of the temperature prediction curve or the predicted temperature change curve does not meet the target temperature of the preset soda ash production equipment.

[0097] Specifically, in the limestone calcination step, when the real-time temperature of the lime kiln at a certain moment does not meet the range of plus or minus 25°C of the temperature change curve, the control center performs inference on the limestone calcination temperature strategy model based on the current real-time data, adjusts the equipment through the control center with the inferred temperature control strategy, and generates a new temperature change prediction curve through the limestone calcination temperature prediction model according to the new temperature control strategy.

[0098] When the temperature change prediction curve does not meet the target temperature at a certain moment, that is, during the limestone calcination process, the temperature change prediction curve shows a temperature outside the range of 1075°C to 1125°C and the moment when this temperature appears is when the limestone calcination has started and not yet completed, indicating that continuing with the current temperature control strategy will result in the lime kiln not meeting the target temperature. The control center performs inference on the limestone calcination temperature strategy model based on the current real-time data, adjusts the equipment through the control center with the inferred temperature control strategy, and generates a new temperature change prediction curve through the limestone calcination temperature prediction model according to the new temperature control strategy.

[0099] Similarly, in steps such as ammonia absorption in brine, carbonation reaction, and calcination of sodium bicarbonate, when it is detected that the real-time temperature deviates from the allowable range of the predicted temperature change curve for each step (±5°C, ±5°C, and ±10°C respectively) or the predicted curve indicates that the future temperature will deviate from the target range (45°C to 55°C, 20°C to 30°C, and 165°C to 185°C respectively), the control center will perform reasoning and adjustment based on the corresponding temperature strategy model and update the temperature prediction curve in real time to ensure the stability and efficiency of the production process.

[0100] Step S500: If the abnormal situation is not resolved within the preset number of adjustment times, trigger the warning mechanism.

[0101] Specifically, when the abnormal situation is not resolved within the preset number of adjustment times, the warning mechanism is triggered. The warning mechanism includes the control center generating a warning message, popping up a prompt on the control center display screen, and sending the warning message to the terminal device. The abnormal situation not being resolved within the preset number of adjustment times means that after the abnormal situation has been adjusted for the preset number of adjustment times and the abnormal situation reappears within the preset warning time, the warning mechanism is triggered; in this embodiment, the preset number of adjustment times is once, and the preset warning time is one hour.

[0102] In this embodiment, when the real-time temperature of the equipment deviates from the temperature change curve or the temperature change curve does not meet the target temperature, the temperature control strategy is automatically adjusted, and the temperature change prediction curve is updated. If the situation where the real-time temperature deviates from the temperature change curve or the temperature change curve does not meet the target temperature occurs again within one hour, the warning mechanism is triggered.

[0103] A warning prompt is displayed on the control center display screen. Clicking on the warning prompt will show detailed data on the temperature change during the operation process. If the warning prompt displayed on the display screen is not processed for more than 5 minutes, a warning will be sent to the terminal device. Sending a warning to the terminal device is done by sending a text message to the mobile phones of the management personnel. The text message sending platform uses Alibaba Cloud SMS Service. By calling the API interface, the warning message is formatted into the text message content, and the list of mobile phone numbers of the management personnel who will receive the text message is specified. Alibaba Cloud SMS Service will return the sending result, including the list of mobile phone numbers with successful sends and the list of mobile phone numbers with failed sends. The system will perform corresponding processing based on the returned result, including resending the failed text messages and recording the sending logs.

[0104] Embodiment 2: As Figure 2 shown, the present invention provides a temperature control system for the soda ash production process, including 1 - model training module, 2 - temperature control module, 3 - temperature judgment module, 4 - temperature adjustment module, 5 - warning module, where:

[0105] Model training module: Obtain the first historical data in the soda ash production process, perform data preprocessing to obtain the second historical data, and use the second historical data to train the temperature strategy model and the temperature prediction model;

[0106] Temperature control module: Obtain the real-time data in the soda ash production process, and control the equipment in the soda ash production process to adjust the temperature according to the temperature control strategy output by the temperature strategy model;

[0107] Temperature judgment module: Input the real-time data and the real-time temperature control strategy into the temperature prediction model to obtain the temperature prediction curve, and compare the real-time production equipment temperature with the temperature prediction curve to judge whether the real-time production equipment temperature meets the temperature range requirements;

[0108] Temperature adjustment module: When an abnormal situation occurs, automatically adjust the temperature control strategy and generate a new temperature prediction curve;

[0109] Early warning module: If the abnormal situation is not resolved within the preset number of adjustments, trigger the early warning mechanism.

[0110] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A temperature control method for the soda ash production process, characterized in that, Including: Step S100: Obtain the first historical data in the soda ash production process, perform data preprocessing to obtain the second historical data, and use the second historical data to train the temperature strategy model and the temperature prediction model; Step S200: Obtain the real-time data in the soda ash production process, and control the equipment in the soda ash production process to adjust the temperature according to the temperature control strategy output by the temperature strategy model; Step S300: Input the real-time data and the real-time temperature control strategy into the temperature prediction model to obtain the temperature prediction curve, and compare the real-time production equipment temperature with the temperature prediction curve to determine whether the real-time production equipment temperature meets the temperature range requirements; Step S400: When an abnormal situation occurs, automatically adjust the temperature control strategy and generate a new temperature prediction curve; The abnormal situation includes that the real-time production equipment temperature is not within the preset upper and lower floating ranges of the temperature prediction curve or the predicted temperature change curve does not meet the target temperature of the preset soda ash production equipment; For the automatic adjustment of the temperature control strategy, when an abnormal situation occurs, input the real-time temperature and precipitation data, the real-time production equipment temperature data, and the real-time production raw material data into the temperature strategy model to adjust the temperature control strategy; For generating a new temperature prediction curve, input the real-time temperature and precipitation data, the real-time production equipment temperature data, the real-time production raw material data, and the adjusted temperature control strategy into the temperature prediction model to generate a new temperature prediction curve; Step S500: If the abnormal situation is not resolved within the preset number of adjustment times, trigger the warning mechanism.

2. The method according to claim 1, wherein The step S100 further includes: Obtain the first historical data in the soda ash production process and transmit it to the control center; Perform data preprocessing on the first historical data, including data cleaning and data conversion, to obtain the second historical data; Based on the second historical data, use the deep learning method to train the temperature strategy model and the temperature prediction model respectively.

3. The method according to claim 2, wherein The first historical data includes historical temperature and precipitation data, historical production equipment temperature data, historical production raw material data, historical natural gas supply speed data, historical combustion air flow data, and historical cooling water flow data; the second historical data is the first historical data after cleaning and data conversion, meeting the preset model training data format.

4. The method according to claim 2, wherein The temperature strategy model outputs the temperature control strategy of the equipment within the preset control time in the soda ash production process, including controlling the natural gas supply speed, the combustion air flow, and the cooling water flow; the temperature prediction model outputs the temperature prediction curve within the preset control time according to the temperature control strategy within the preset control time.

5. The method according to claim 1, characterized in that, The step S200 further includes: The control system obtains the real-time data in the soda ash production process, including real-time temperature and precipitation data, real-time production equipment temperature data, and real-time production raw material data, inputs the real-time data into the temperature strategy model, and performs operations according to the temperature control strategy output by the temperature strategy model to generate a control instruction to control the equipment in the soda ash production process to adjust the temperature.

6. The method according to claim 1, wherein In step S300, it is determined whether the temperature of the real-time production equipment meets the requirements of the preset temperature range, specifically: obtain the temperature prediction curve, collect the real-time production equipment temperature data according to the preset time interval, compare it with the temperature prediction curve, and determine whether the temperature of the real-time production equipment is within the preset upper and lower floating ranges of the temperature prediction curve at this time point.

7. The method according to claim 1, wherein Step S500 further includes: When the abnormal situation is not resolved within the preset number of adjustment times, trigger the early warning mechanism. The early warning mechanism includes that the control center generates early warning information, pops up a prompt on the control center display screen, and sends the early warning information to the terminal device.

8. The method according to claim 7, wherein If the abnormal situation is not resolved within the preset number of adjustment times, that is, after the abnormal situation is adjusted for the preset number of adjustment times and the abnormal situation appears again within the preset early warning time, the early warning mechanism is triggered; The preset number of adjustment times is at least once.

9. A temperature control system for the soda ash production process, characterized in that, It includes: Model training module: Obtain the first historical data in the soda ash production process, perform data preprocessing to obtain the second historical data, and use the second historical data to train the temperature strategy model and the temperature prediction model; Temperature control module: Obtain the real-time data in the soda ash production process, and control the equipment in the soda ash production process to adjust the temperature according to the temperature control strategy output by the temperature strategy model; Temperature judgment module: Input the real-time data and the real-time temperature control strategy into the temperature prediction model to obtain the temperature prediction curve, compare the temperature of the real-time production equipment with the temperature prediction curve, and determine whether the temperature of the real-time production equipment meets the temperature range requirements; Temperature adjustment module: When an abnormal situation occurs, automatically adjust the temperature control strategy and generate a new temperature prediction curve; The abnormal situation includes that the temperature of the real-time production equipment is not within the preset upper and lower floating ranges of the temperature prediction curve or the predicted temperature change curve does not meet the target temperature of the preset soda ash production equipment; For the automatic adjustment of the temperature control strategy, when an abnormal situation occurs, input the real-time temperature and precipitation data, the real-time production equipment temperature data, and the real-time production raw material data into the temperature strategy model to adjust the temperature control strategy; For generating a new temperature prediction curve, input the real-time temperature and precipitation data, the real-time production equipment temperature data, the real-time production raw material data, and the adjusted temperature control strategy into the temperature prediction model to generate a new temperature prediction curve; Early warning module: If the abnormal situation is not resolved within the preset number of adjustment times, trigger the early warning mechanism.

Images