Rotary kiln working condition prediction method coupled with simulation and deep learning neural network

Abstract

The application discloses a rotary kiln working condition prediction method coupled with simulation and a deep learning neural network, relates to the technical field of rotary kiln working condition prediction, obtains sample data through rotary kiln simulation, combines a POD method and a neural network, develops an efficient prediction model, thereby realizing rapid prediction of a rotary kiln flow field temperature field, significantly reducing the huge cost of calculation resources and time of traditional CFD simulation, solving the limitations of previous simulation technology in real-time performance, and adjusting the prediction data through a correction algorithm, improving the practicability and reliability of the model, realizing the deployment of the rotary kiln reduction and the digital twin model to an industrial site, providing guidance for a production process in real time, and ensuring the improvement of production efficiency and quality.

Description

Technical Field

[0001] The present invention belongs to the technical field of rotary kiln operating condition prediction, and specifically relates to a rotary kiln operating condition prediction method using coupled simulation and deep learning neural network. Background Art

[0002] A rotary kiln is a continuously operating rotating cylinder thermal equipment. Its working principle is to use the inclination and slow rotation of the kiln body to make the material roll forward in the kiln, and at the same time exchange heat with the hot gas in the kiln, so that the material inside can complete a series of thermal treatment processes such as heating, decomposition, and calcination under high temperature conditions. In this process, the rotation of the rotary kiln not only promotes full contact between the material and the hot gas, but also helps the physical and chemical reactions inside the material, such as water evaporation, organic matter decomposition, and mineral reorganization, thereby achieving efficient and uniform heat treatment effects. It is an indispensable key equipment in cement production, metallurgy, chemical industry and other industries.

[0003] However, in actual production, unstable control levels of rotary kilns, as key equipment, can cause clinker to be "under-burned" or "over-burned" during the calcination process, leading to problems such as kiln ring formation and local temperature anomalies. These problems affect the normal flow of materials and heat exchange efficiency, affecting the quality of the clinker and posing challenges to quality management and process adjustments. Furthermore, the temperature inside the rotary kiln is extremely high, reaching over 1800°C, and the gas contains a large amount of dust. Direct measurement of material flow and temperature distribution at high temperatures increases the difficulty of precise control, relying on the operator's manual experience and lacking quantitative indicators to reflect internal laws. This leads to subjectivity and response lag.

[0004] Computational fluid dynamics (CFD) simulation technology plays a vital role in modern engineering design and scientific research. By using CFD technology to build rotary kiln simulation models and conduct simulation analysis, the overall operating conditions of the equipment can be predicted, enabling optimization of operating parameters and improving the kiln's production efficiency. However, when simulating large-scale, high-precision tasks like rotary kilns involving flow and heat transfer, the high computational cost of CFD simulation limits its application in practical engineering problems. Furthermore, due to the complex operating conditions, real-time simulation is difficult to achieve, making it impossible to quickly provide optimization recommendations or decision support. Currently, CFD simulation is primarily used in research and development or during problem diagnosis, but real-time calculations are difficult to implement to guide production practices.

[0005] CFD simulation models can collect large amounts of data to analyze and monitor the operating status of rotary kilns. However, due to the high computational complexity of CFD models, to improve the computational speed of numerical simulations and achieve real-time prediction of full flow field data, the rotary kiln simulation model must be reduced in order. This requires the development of a digital twin model based on the rotary kiln simulation model that balances accuracy and computational efficiency. A key technical challenge in achieving rotary kiln model reduction and digital twinning is how to leverage features derived from POD intrinsic orthogonal decomposition to accurately predict and represent the temperature field under specified operating conditions. This allows for real-time predictions to determine optimal setpoints, ensuring the rotary kiln is always in optimal condition.

[0006] So how to combine CFD simulation with deep learning to quickly obtain the operating parameters of the rotary kiln, provide optimization suggestions or decision support, and make intelligent dynamic adjustments to the rotary kiln to ensure its stable operation, improve pulverized coal combustion efficiency and production efficiency, and save energy and reduce consumption? This is a problem. Based on this, a solution is provided. Summary of the Invention

[0007] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a rotary kiln operating condition prediction method based on coupled simulation and deep learning neural network.

[0008] A rotary kiln operating condition prediction method based on coupled simulation and deep learning neural network includes the following steps:

[0009] Step 1: The numerical simulation module establishes a transient simulation model of the rotary kiln based on the basic Euler two-phase flow model and couples the heat transfer model with the chemical reaction model. The simulation model is then verified and adjusted. The rotary kiln boundary and operating parameters are determined, and dozens of different operating conditions are simulated using CFD software to obtain sample data.

[0010] Step 2: Use intrinsic orthogonal decomposition to process the simulation sample data to extract the fundamental modes and key eigenvalues ​​of the rotary kiln under various operating conditions. Use backpropagation neural network to establish a multi-layer neural network model from operating parameters to fundamental mode coefficients, and train a multi-input and output mapping model between the operating parameter space and the fundamental mode eigenvalue coefficients of the flow field to achieve a better fitting effect.

[0011] Step 3: After configuring a small number of open-source Python libraries, the model is deployed on the factory's industrial control equipment. The BPNN model is used to quickly predict the rotary kiln's flow and temperature fields. Sensor detection is performed at local points in the rotary kiln to obtain local observation data. The data from these local observation points is combined with the global prediction data. A filtering correction algorithm is used to update the prediction data for the entire field. This effectively improves the accuracy of the flow field prediction value while retaining the true characteristics of the flow field, making the predicted data closer to the data of the real physical field.

[0012] Compared with the prior art, the present application has the beneficial effects that:

[0013] The present application develops an efficient prediction model by combining POD method and neural network through rotary kiln simulation to obtain sample data, thereby realizing rapid prediction of the rotary kiln flow field temperature field, significantly reducing the huge cost of calculation resources and time of traditional CFD simulation, solving the limitations of previous simulation technology in real-time, and adjusting the prediction data through the correction algorithm to improve the practicability and reliability of the model, realizing the deployment of the rotary kiln reduction and digital twin model to the industrial site, providing guidance for the production process in real time, and ensuring the improvement of production efficiency and quality. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 is the prediction method flowchart of the present application;

[0015] Figure 2 is the neural network structure of the BPNN neural network of the present application;

[0016] Figure 3 is the specific steps of model training of the present application. DETAILED DESCRIPTION

[0017] The technical solutions of the present application will be described clearly and completely in combination with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0018] Please refer to Figure 1-Figure 3The core of this application is to build an approximate model from working condition variables to flow field data based on a neural network as an agent model, and realize the establishment of a data-driven rotary kiln reduced-order model and digital twin method. This process only requires the use of CFD software to simulate dozens of different working conditions, and then use the intrinsic orthogonal decomposition to process the simulation sample data, so as to extract the basic mode and its key eigenvalues ​​of the rotary kiln under various working conditions, and use the back propagation neural network (BPNN) to establish a multi-layer neural network model from working condition parameters to basic mode coefficients, so as to achieve rapid prediction of the rotary kiln flow field, solve the problem of high cost and long time of CFD simulation calculation, solve the problem of high cost and long time of traditional CFD simulation calculation, and also calibrate the difference between simulation prediction data and actual sensor data by combining the correction algorithm, ensure the accuracy of the model, realize the actual deployment of reduced-order model and digital twin model in industrial site, and provide real-time guidance and support for optimizing production processes.

[0019] This application provides a rotary kiln operating condition prediction method using coupled simulation and deep learning neural network, which specifically includes the following steps:

[0020] S1: CFD simulation of rotary kiln;

[0021] The numerical simulation module is based on the basic Euler two-phase flow model and couples the heat transfer model with the chemical reaction model to establish a transient simulation model of the rotary kiln. The simulation results are then verified and the model is adjusted.

[0022] The Euler two-fluid model has three phases. The first phase is the gas phase, which is the main phase. It contains various gas components: O2, CO2, N2, NO, CO, H2O(g), HCN, CH4, C2H4, C2H6, H2, a total of 11 gas components; the second phase is coal powder solid particles, which contain four components: fixed carbon, volatile matter, ash, and H2O(l); the third phase is the burning material particles, which contain six components: CaCO3, CAO, C2S, C3S, C3A, and C4AF.

[0023] For rotary kiln simulation, the first thing is the simulation of pulverized coal combustion, which determines the overall temperature field of the rotary kiln; further, the multiphase flow transmission and heat transfer simulation studies the movement law and heat exchange law of the calcination material particles inside the rotary kiln; the calcination material calcination simulation model studies the evolution law of the mineral composition inside the calcination material under the material transmission / heat transfer / mass transfer behavior. Finally, during the calcination process of the calcination material, the particles will gradually grow, which in turn affects the movement law and heat exchange law of the calcination material particles. The above parts are interrelated and influence each other. The simulation model fully considers the structural characteristics, material characteristics and other factors of the rotary kiln, and better predicts the combustion, flow and heat exchange conditions in the rotary kiln, reflecting its internal laws such as velocity field, temperature field, and three-phase gas-solid component field data. At the same time, the simulation results are verified based on the actual production data of the plant. By comparing the simulation results with the actual production data, the simulation model is adjusted to verify the accuracy of the simulation parameters and model construction to improve the accuracy and reliability of the model;

[0024] Euler-Euler two-phase flow continuity equation

[0025]

[0026] Where: α q is the volume fraction of the q phase, is the q-phase velocity, is the mass flow rate transferred from phase p to phase q, is the mass flow rate transferred from phase q to phase p, S q is the source term.

[0027] The momentum governing equation is:

[0028]

[0029] Where:

[0030]

[0031] where μ q and λ q The q phase is the shear viscosity and the bulk viscosity, respectively, F q is the external force, F lift,q It's lift. is the turbulent dissipation force, Virtual mass force, is the interaction force between the phases, is the phase speed.

[0032] The energy governing equation is:

[0033]

[0034] where k eff,qis the thermal conductivity, S q is the source term, Q pq is the heat exchange between phases p and q, h q is the enthalpy of phase q, p op is the reference atmospheric pressure and p is the gauge pressure.

[0035] S2: Set multiple parameter inputs to obtain sample space;

[0036] According to the actual adjustable process parameters, such as coal feed rate, primary air volume and temperature, secondary air volume and temperature, etc., the established rotary kiln simulation model is used to perform multi-parameter simulation calculations; in order to avoid the exponential growth of the sample number with the increase of parameters, orthogonal experimental design is adopted to balance the sample space accuracy and calculation time to obtain different sample spaces and data.

[0037] S3: eigenorthogonal decomposition of sample data;

[0038] The simulation sample data is processed using the intrinsic orthogonal decomposition method based on the sample variance maximization theory to extract the fundamental modes and key eigenvalues ​​of the rotary kiln under various working conditions.

[0039] Intrinsic orthogonal decomposition is a method of vector data statistical analysis that can reduce the order of high-dimensional flow field data and map it to a low-dimensional orthogonal base modal space, thereby analyzing the main characteristics of the flow field and its corresponding base modal coefficients. First, the sample (flow field data) calculated by simulation needs to be standardized. Let the original data be x i , where i = 1, 2, 3, ..., r, sample data x i is an n-dimensional vector (n is related to the number of grids divided during CFD calculations), and r is the number of samples.

[0040]

[0041] Data standardization helps eliminate differences between sample data features and avoid the influence of individual discrete values ​​on analysis results. From this, the covariance matrix of standardized data can be obtained:

[0042]

[0043] By solving the eigenvalue of the nXn order covariance matrix, the first m order eigenvalues ​​can be recorded as λ 1 ,λ 2 ,…,λ m , the corresponding basic mode eigenvector can be recorded as ξ 1 ,ξ 2 、…、ξ mThe value of m is determined by the ratio of the variance of different basic modes to the total variance, ensuring that the characteristic components contained in the basic mode account for more than 95% of the entire sample space. Then the original sample data can be approximately expressed as X = U λ ξ, so that the fundamental mode coefficient matrix and a small amount of POD fundamental modes can be used to represent most of the information of the original sample.

[0044] S4: training BPNN neural network;

[0045] Build a neural network and train a multi-input-output mapping model between the working condition parameter space and the fundamental modal eigenvalue coefficients of the flow field. The specific training method is as follows:

[0046] 1) Divide the samples into training set and validation set for training and result verification;

[0047] 2) Use orthogonal initialization of the weight matrix. Weight initialization affects the training effect and convergence speed of the neural network. By initializing the weight matrix to an orthogonal matrix, the information transmission is maintained and the gradient disappearance problem in training is reduced. The weight matrix W is orthogonal, that is, W T W = I;

[0048] 3) Calculate the input and output of the first hidden layer and use the "Sigmoid" activation function to increase the nonlinear expression ability of the model, smooth the gradient, and avoid jumping output values;

[0049] 4) Calculate the input and output of the second hidden layer and use the "Leaky Relu" activation function to accelerate training convergence. This solves the problem of gradient vanishing when a negative number is input during backpropagation, and also avoids the problem of neuron saturation.

[0050] 5) Calculate the reverse error of each layer and update the weight matrix;

[0051] 6) Calculate the prediction error of the validation set by comparing the predicted value with the validation value and using the average relative error: Among them A i Indicates the verification value, B i Represent the predicted value, ensure that the average relative error of the prediction set to the validation set in the sample space does not exceed 3%, evaluate the reasonable training rounds, and ensure that the model has sufficient computational accuracy;

[0052] S5: Model deployment and flow field prediction;

[0053] The reduced-order model generated by this method is relatively small in size, fast in calculation, low in memory usage, and does not rely on foreign CFD software environments. It can be deployed on factory industrial control equipment after configuring a small amount of open source Python libraries. For a new set of factory actual parameter combinations Zj , the fundamental mode eigenvalue coefficient can be quickly predicted through the BPNN model Then perform reverse reconstruction based on POD to obtain the predicted flow field value Achieve millisecond-level input and output;

[0054] S6: sensor deployment and prediction data correction;

[0055] In the actual production process of the factory, due to the interweaving of various complex factors, there is inevitably a deviation between the predicted data and the actual situation on site. By performing sensor detection at local points in the rotary kiln, local observation data is obtained, and the data of the local observation point is combined with the global prediction data. The prediction data is updated globally using a distance-based correction and a Gaussian function-based filtering correction algorithm. Assuming that n sensors are arranged, the actual measurement value of each sensor is T i (i=1,2,3...n), the flow field prediction value at the same position is Then for any data point x in the predicted flow field k , and its corrected value is:

[0056]

[0057] Among them, d i is the data point x k The distance from each sensor location; σ is the correction coefficient, which is related to the rotary kiln radius and is obtained by fitting the sensor data of different rotary kilns using the nonlinear least squares method. This algorithm systematically considers the correction of the predicted data by all sensor measurement points. It can effectively improve the accuracy of the flow field prediction value while retaining the true characteristics of the flow field, making the predicted data closer to the data of the real physical field. After correction with the measured data, the predicted flow field and temperature field data of the rotary kiln are obtained, and the internal flow field of the rotary kiln is understood. This data is used as an important basis for optimizing decision support and adjusting operating conditions to ensure that the rotary kiln operates under optimal conditions.

[0058] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A rotary kiln operating condition prediction method based on coupled simulation and deep learning neural network, characterized in that: The method specifically comprises the following steps: Step 1: The numerical simulation module is based on the Euler two-phase flow basic model and couples the heat transfer model with the chemical reaction model to establish a transient simulation model of the rotary kiln. The simulation model is then verified and adjusted. Determine the rotary kiln boundary and operating parameters, simulate dozens of different operating conditions using CFD software, and obtain sample data; Step 2: Use intrinsic orthogonal decomposition to process batches of simulation sample data to extract the fundamental modes and key eigenvalues ​​of the rotary kiln under various operating conditions; Build and train the BPNN back-propagation neural network, establish a multi-layer neural network model from operating parameters to fundamental mode eigenvalue coefficients, and train a multi-input-output mapping model between the operating parameter space and the fundamental mode eigenvalue coefficients of the flow field; Step 3: After configuring a small number of open-source Python libraries, the model is deployed on the factory's industrial control equipment. The BPNN model is used to quickly predict the rotary kiln's flow and temperature fields. Sensor detection is performed at local points in the rotary kiln to obtain local observation data. The data from these local observation points is combined with the global prediction data, and a filtering correction algorithm is used to update the prediction data globally.

2. The rotary kiln operating condition prediction method of coupled simulation and deep learning neural network according to claim 1 is characterized in that: The numerical simulation module is based on the Euler two-phase flow basic model and couples the heat transfer model with the chemical reaction model to establish a transient simulation model of the rotary kiln. The Euler two-fluid model has three phases, the first phase is the main phase; the first phase is the gas phase, which contains various gas components: O2, CO2, N2, NO, CO, H2O(g), HCN, CH4, C2H4, C2H6, H2, a total of 11 gas components; the second phase is coal powder solid particles, which contain four components: fixed carbon, volatile matter, ash, and H2O(l); the third phase is the burning material particles, which contain six components: CaCO3, CAO, C2S, C3S, C3A, and C4AF.

3. The rotary kiln operating condition prediction method of coupled simulation and deep learning neural network according to claim 1 is characterized in that: The rotary kiln simulation also includes the following sub-models: The pulverized coal combustion simulation model is used to simulate the entire process of pulverized coal combustion and determine the overall temperature field of the rotary kiln; Multiphase flow transmission and heat transfer simulation model, used to simulate the movement law and heat exchange law of burning material particles inside the rotary kiln; Clinker calcination simulation model, used to simulate the evolution of mineral composition inside the burning material under material transmission, heat transfer and mass transfer behavior; The particle growth model is used to simulate the influence of particle growth on the movement and heat exchange of the particles during the calcination process.

4. The rotary kiln operating condition prediction method of coupled simulation and deep learning neural network according to claim 1 is characterized in that: The specific method of training the multi-input-output mapping model is: 1) Divide the samples into training set and validation set for training and result verification; 2) Use orthogonal initialization of the weight matrix. Weight initialization affects the training effect and convergence speed of the neural network. By initializing the weight matrix as an orthogonal matrix, information transmission is maintained and the gradient vanishing problem during training is reduced. The weight matrix W is orthogonal, that is, W T W = I; 3) Calculate the input and output of the first hidden layer and use the "Sigmoid" activation function to increase the nonlinear expression ability of the model, smooth the gradient, and avoid jumps in output values; 4) Calculate the input and output of the second hidden layer and use the "Leaky Relu" activation function to accelerate training convergence; 5) Calculate the reverse error of each layer and update the weight matrix; 6) Calculate the prediction error of the validation set by comparing the predicted value with the validation value and using the average relative error: Among them A i Indicates the verification value, B i Represent the predicted value, ensure that the average relative error of the prediction set to the validation set in the sample space does not exceed 3%, and evaluate the reasonable training rounds until the model has sufficient computational accuracy.

5. The rotary kiln operating condition prediction method of coupled simulation and deep learning neural network according to claim 1 is characterized in that: For a new set of factory actual parameter combinations Z j , the fundamental mode eigenvalue coefficient can be quickly predicted through the BPNN model Then, based on the POD, reverse reconstruction is performed to obtain the predicted flow field value.

6. The rotary kiln operating condition prediction method of coupled simulation and deep learning neural network according to claim 1 is characterized in that: The predicted data is corrected based on the data from the observation points where the factory sensors are deployed. The specific method is as follows: By performing sensor detection at local points in the rotary kiln, local observation data is obtained, the data of the local observation points are combined with the global prediction data, and the prediction data is updated globally using distance-based correction and Gaussian function-based filtering correction algorithms; Assume that n sensors are arranged and the measured value of each sensor is T i (i=1,2,3...n), the flow field prediction value at the same position is Then for any data point x in the predicted flow field k , and its corrected value is: Among them, d i is the data point x k The distance from each sensor position; σ is the correction coefficient, which is related to the radius of the rotary kiln and is obtained by fitting the sensor data of different rotary kilns through the nonlinear least squares method.

Images