Method, device and equipment for controlling internal temperature field of rotary kiln and medium
By using the main branch air volume ratio prediction model in the rotary kiln, and adjusting the air volume ratio to control the temperature field, the problem of insufficient timeliness and accuracy of the temperature control of the rotary kiln is solved, and production efficiency and product quality are improved.
Patent Information
- Application Number
- CN202411181323.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-08
AI Technical Summary
There is insufficient timeliness and accuracy in the temperature control of rotary kilns, which makes it difficult to ensure production efficiency and product quality.
The pre-established prediction model for the main air volume ratio is used, and the analysis is based on the historical working conditions of the rotary kiln and the kiln axial temperature data, and the current main air volume ratio is adjusted to control the temperature field to improve the accuracy and timeliness of temperature control.
Through the application of the main branch air volume ratio prediction model, efficient and accurate control of the rotary kiln temperature field is achieved, temperature instability problems caused by human factors are reduced, and production efficiency and product quality are improved.
Smart Images

Figure CN118912901A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of rotary kilns, and in particular to a method, device, electronic equipment and computer-readable storage medium for controlling the internal temperature field of a rotary kiln. Background Art
[0002] The rotary kiln is a large-scale, continuously rotating high-temperature thermal equipment, which is widely used in the pillar industries of the national economy such as smelting, power generation, and building materials. The stability of the temperature field inside the kiln is a key factor affecting the quality of roasting products, production energy consumption, and pollutant emissions. However, due to the relatively complex thermal system of the rotary kiln, large system inertia, long lag time, and limited temperature detection methods, the temperature control of the rotary kiln has always been a difficult point in the industry.
[0003] Traditionally, the temperature control of rotary kilns is mainly based on manual experience to adjust the key factors that can affect the roasting temperature in the kiln, such as air volume, fuel ratio, feed amount and kiln speed. Among them, adjusting the air volume is the fastest way to control the temperature. However, manual experience operation has problems such as inaccurate judgment, untimely adjustment, and large adjustment range, which directly affects the control efficiency and product quality.
[0004] In view of this, how to control the temperature field of the rotary kiln more timely, efficiently and accurately becomes a problem that needs to be solved by those skilled in the art. Summary of the invention
[0005] The purpose of the embodiments of the present invention is to provide a method, device, electronic device and computer-readable storage medium for controlling the temperature field inside a rotary kiln, which can improve the accuracy and timeliness of the temperature field control of the rotary kiln during use, thereby improving the control efficiency and product quality.
[0006] To solve the above technical problems, the embodiments of the present invention provide the following technical solutions:
[0007] In one aspect, the present invention provides a method for controlling the temperature field inside a rotary kiln, comprising:
[0008] Collect the current working condition information of the rotary kiln and the expected temperature data of the kiln axial direction;
[0009] The current operating condition information and the kiln axial expected temperature data are analyzed using a pre-established main and branch air volume ratio prediction model to obtain the corresponding current main and branch air volume ratio; wherein the main and branch air volume ratio prediction model is pre-trained based on the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions; the historical operating conditions include the historical main and branch air volume ratio;
[0010] The temperature field inside the rotary kiln is controlled based on the current main branch air volume ratio.
[0011] In an exemplary embodiment, the main branch air volume proportion prediction model is pre-trained based on the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions, and includes:
[0012] Acquire various historical operating conditions of the rotary kiln and kiln axial temperature data corresponding to the historical operating conditions;
[0013] Based on the kiln axial temperature data, determining the axial temperature characteristics of each kiln corresponding to the historical operating conditions;
[0014] According to each of the historical operating conditions and each of the kiln axial temperature characteristics corresponding to each of the historical operating conditions, a main and branch air volume ratio prediction model is trained to obtain a main and branch air volume ratio prediction model; wherein, during the training process, the historical main and branch air volume ratios in the historical operating conditions are used as the output of the model, and each of the kiln axial temperature characteristics and other historical operating conditions are used as the input of the model.
[0015] In an exemplary embodiment, the obtaining of various historical operating conditions of the rotary kiln and kiln axial temperature data corresponding to the historical operating conditions includes:
[0016] Obtain various historical working conditions of the rotary kiln;
[0017] Obtaining kiln axial temperature data curves corresponding to each of the historical operating conditions;
[0018] A clustering algorithm is used to cluster and divide each of the kiln axial temperature data curves to obtain a historical kiln axial temperature curve corresponding to each historical working condition.
[0019] In an exemplary embodiment, it also includes:
[0020] Collecting actual temperature data of the rotary kiln in the kiln axial direction;
[0021] The current main branch air volume ratio is adjusted using the actual axial temperature data of the kiln;
[0022] Then, the temperature field inside the rotary kiln is controlled based on the current main branch air volume ratio, including:
[0023] The temperature field inside the rotary kiln is controlled by using the adjusted current main branch air volume ratio.
[0024] In an exemplary embodiment, the step of adjusting the current main branch air volume ratio by using the actual kiln axial temperature data includes:
[0025] Calculate the deviation between the actual temperature data in the kiln axial direction and the expected temperature data in the kiln axial direction;
[0026] The current main branch air volume ratio is adjusted according to the deviation.
[0027] In an exemplary embodiment, adjusting the current main branch air volume ratio according to the deviation includes:
[0028] When the deviation is greater than the preset threshold, judging whether the temperature of the high temperature zone of the kiln is greater than the preset temperature threshold according to the actual temperature data of the kiln axial direction, if so, reducing the proportion of the main branch air volume on the basis of the current proportion of the main branch air volume;
[0029] Or, when the deviation is greater than a preset threshold, determine whether the overall temperature in the kiln reaches the expected temperature based on the actual axial temperature data of the kiln; if not, increase the main branch air volume ratio based on the current main branch air volume ratio.
[0030] In an exemplary embodiment, it also includes:
[0031] The current working condition, the adjusted current main branch air volume ratio and the actual axial temperature data of the kiln are correspondingly stored in a historical sample library.
[0032] Another aspect of the present invention provides a device for controlling the temperature field inside a rotary kiln, comprising:
[0033] The acquisition module is used to collect the current working condition information of the rotary kiln and the expected temperature data of the kiln axial direction;
[0034] A prediction module is used to analyze the current operating condition information and the kiln axial expected temperature data using a pre-established main and branch air volume ratio prediction model to obtain the corresponding current main and branch air volume ratio; wherein the main and branch air volume ratio prediction model is pre-trained based on the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions by establishing a module; the historical operating conditions include the historical main and branch air volume ratio;
[0035] A control module is used to control the temperature field inside the rotary kiln based on the current main branch air volume ratio.
[0036] Another aspect of the present invention provides an electronic device, comprising:
[0037] Memory for storing computer programs;
[0038] A processor is used to implement the steps of the method for controlling the temperature field inside the rotary kiln as described above when executing the computer program.
[0039] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for controlling the temperature field inside the rotary kiln as described above are implemented.
[0040] It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:
[0041] A method for controlling the temperature field inside a rotary kiln is provided in an embodiment of the present invention, comprising: collecting current operating condition information of the rotary kiln and expected temperature data in the kiln axial direction; analyzing the current operating condition information and expected temperature data in the kiln axial direction using a pre-established main and branch air volume ratio prediction model to obtain the corresponding current main and branch air volume ratio; wherein the main and branch air volume ratio prediction model is pre-trained based on the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions; the historical operating conditions include the historical main and branch air volume ratios; and controlling the temperature field inside the rotary kiln based on the current main and branch air volume ratios.
[0042] It can be seen that in the embodiment of the present invention, the main and branch air volume ratio prediction model of the rotary kiln is trained in advance according to the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions. When the internal temperature field of the rotary kiln is controlled, the current operating conditions of the rotary kiln and the expected kiln axial temperature data of the rotary kiln can be obtained, and then the main and branch air volume ratio prediction model is used to analyze and predict the current operating conditions and the expected kiln axial temperature data of the rotary kiln, and the current main and branch air volume ratio corresponding to the current operating conditions is obtained, and the current main and branch air volume ratio is used to control the temperature field inside the rotary kiln, thereby improving the accuracy and timeliness of the temperature field control of the rotary kiln, which is beneficial to improving the control efficiency and product quality.
[0043] In addition, the present invention also provides corresponding implementation devices, electronic devices and computer-readable storage media for the control method of the internal temperature field of the rotary kiln, which further makes the method more practical, and the devices, electronic devices and computer-readable storage media have corresponding advantages.
[0044] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the prior art and the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0046] Figure 1A schematic flow chart of a method for controlling the temperature field inside a rotary kiln provided in an embodiment of the present invention;
[0047] Figure 2 A schematic diagram of the architecture of a main and branch air volume ratio prediction model provided in an embodiment of the present invention;
[0048] Figure 3 A schematic diagram of a closed-loop control principle of air supply to a rotary kiln provided in an embodiment of the present invention;
[0049] Figure 4 A schematic flow chart of a method for obtaining an axial temperature curve of a rotary kiln provided in an embodiment of the present invention;
[0050] Figure 5 A schematic diagram of the distribution of a rotary kiln temperature detection device provided by an embodiment of the present invention;
[0051] Figure 6 A schematic diagram of a material combustion process in a rotary kiln provided by an embodiment of the present invention;
[0052] Figure 7 A schematic diagram of a neural network architecture of a working condition and temperature curve characteristic parameter relationship model provided by an embodiment of the present invention;
[0053] Figure 8 A schematic diagram of the structure of a device for controlling the temperature field inside a rotary kiln provided in an embodiment of the present invention;
[0054] Fig. 9 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;
[0055] Fig.10 A schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0056] The embodiments of the present invention provide a method, device, electronic device and computer-readable storage medium for controlling the temperature field inside a rotary kiln, which can improve the accuracy and timeliness of controlling the temperature field of the rotary kiln during use, thereby improving control efficiency and product quality.
[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0058] It should be noted that there are currently two air supply methods for rotary kilns, one is air supply only at the feed end, and the other is air supply at the feed end and the kiln body at the same time. The controlled amount of air supply at the feed end alone is set as the air supply, and the controlled amount of air supply at the feed end and the kiln body at the same time is set as the main branch air volume ratio. In practical applications, the internal temperature of the rotary kiln can be controlled by controlling the air volume. Specifically, the air volume can be controlled by predicting the main branch air volume ratio.
[0059] Please refer to Figure 1 , Figure 1 A schematic flow chart of a method for controlling the temperature field inside a rotary kiln provided in an embodiment of the present invention. The method comprises:
[0060] S110: Collecting the current working condition information of the rotary kiln and the expected temperature data of the kiln axial direction;
[0061] It should be noted that, since the axial temperature change of the kiln can well reflect the temperature conditions inside the kiln, the expected axial temperature data of the kiln can be set in advance. In the embodiment of the present invention, when it is necessary to control the temperature inside the rotary kiln, the current operating condition information of the rotary kiln and the expected axial temperature data of the rotary kiln can be collected.
[0062] S120: Analyze the current working condition information and the kiln axial expected temperature data using a pre-established main and branch air volume ratio prediction model to obtain the corresponding current main and branch air volume ratio; wherein the main and branch air volume ratio prediction model is pre-trained based on the historical working conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical working conditions; the historical working conditions include the historical main and branch air volume ratio;
[0063] It should be noted that, in the embodiment of the present invention, multiple groups of historical operating conditions and the kiln axial temperature data corresponding to each group of historical operating conditions can be obtained in advance, wherein the historical operating conditions may include the proportion of main and branch air volume, and may also include multiple parameters such as rotary kiln speed, feed amount, total air volume, etc. Specifically, in the actual training process, the historical main and branch air volume proportion in the historical operating conditions can be used as the output of the model, and the axial temperature characteristics of each kiln and other historical operating conditions can be used as the input of the model, so that the main and branch air volume proportion prediction model can be trained.
[0064] Specifically, when it is necessary to control the internal temperature of the rotary kiln, in an embodiment of the present invention, when the current operating condition information of the rotary kiln and the expected temperature data in the kiln axial direction are obtained, the current operating condition information of the rotary kiln and the expected temperature data in the kiln axial direction can be input into a pre-established main and branch air volume ratio prediction model. By analyzing the input data through the main and branch air volume ratio prediction model, the current main and branch air volume ratio corresponding to the current operating condition and the expected temperature data in the kiln axial direction can be predicted.
[0065] S130: Controlling the temperature field inside the rotary kiln based on the current main and branch air volume ratio.
[0066] Specifically, after obtaining the current main branch air volume ratio, the temperature field inside the rotary kiln can be further controlled according to the current main branch air volume ratio, so that the temperature field inside the rotary kiln can be more consistent with the axial temperature data of the rotary kiln, thereby achieving accurate and efficient control of the temperature field inside the rotary kiln.
[0067] In an exemplary embodiment, the main branch air volume proportion prediction model in the above S120 is a process pre-trained based on the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions, which may include:
[0068] Obtain various historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions;
[0069] Based on the kiln axial temperature data, the axial temperature characteristics of each kiln corresponding to the historical operating conditions are determined;
[0070] According to each historical operating condition and each kiln axial temperature characteristic corresponding to each historical operating condition, the main and branch air volume ratio prediction model is trained to obtain the main and branch air volume ratio prediction model; wherein, during the training process, the historical main and branch air volume ratio in the historical operating conditions is used as the output of the model, and the axial temperature characteristics of each kiln and other historical operating conditions are used as the input of the model.
[0071] It should be noted that, in the embodiment of the present invention, each historical operating condition of the rotary kiln and the kiln axial temperature data corresponding to each historical operating condition can be obtained in advance, wherein specifically, each historical operating condition can be simulated by a CFD simulation model to obtain a steady-state temperature field in the kiln corresponding to the historical operating condition, and based on the steady-state temperature field in the kiln, the corresponding kiln axial temperature data can be obtained. Then, based on the kiln axial temperature data, each kiln axial temperature characteristic corresponding to the historical operating condition is further determined, and the historical operating condition includes the historical main and branch air volume ratio and other operating condition information. The historical main and branch air volume ratio in the historical operating condition can be used as the output of the model, and the axial temperature characteristics of each kiln and other historical operating conditions can be used as the input of the model to train the neural network model, and obtain the main and branch air volume ratio prediction model. Furthermore, the above-mentioned process of obtaining each historical operating condition of the rotary kiln and the kiln axial temperature data corresponding to the historical operating condition can include:
[0072] Obtain various historical working conditions of the rotary kiln;
[0073] Obtain the kiln axial temperature data curve corresponding to each historical operating condition;
[0074] The clustering algorithm is used to cluster the axial temperature data curves of each kiln, and the historical kiln axial temperature curves corresponding to each historical working condition are obtained.
[0075] It should be noted that in practical applications, multiple groups of historical working conditions can be obtained for the rotary kiln, and then the corresponding kiln axial temperature data curve can be determined for each group of historical working conditions. Different kiln axial temperature curves may be of the same type, so a clustering algorithm (fuzzy clustering, K-means clustering algorithm) can be used to cluster and divide each kiln axial temperature data curve, and it can be further determined that the kiln axial temperature data curves of those historical working conditions are of the same type and can be classified into one category. The classification results can also be visualized, and the historical kiln axial temperature curves corresponding to each historical working condition can be used as the kiln axial temperature data corresponding to each historical working condition, that is, the kiln axial temperature data can be the kiln axial temperature curve. Then, a nonlinear fitting model between the working conditions, axial temperature curve characteristics and main branch air volume ratio can be constructed based on a neural network, so as to predict the approximate main branch air volume ratio based on the expected temperature change curve.
[0076] Specifically, in the embodiment of the present invention, when performing model training, reference can be made to Figure 2 , compare the historical operating conditions (rotary kiln speed x1, feed amount x2, fuel ratio x3, total air volume x4) with the historical axial temperature curve (expected temperature curve characteristics (such as Figure 2 The expected axial temperature curve features 1 x5, ... the expected axial temperature curve features n xn)) are used as the input of the neural network, and the main branch air volume ratio is used as the output of the neural network. The neural network includes an input layer, a hidden layer and an output layer. The number of hidden layers and the number of nodes of the neural network are determined by trial and error. The parameters of each layer are updated during the training process. When the loss value is less than the preset loss value or the training rounds reach the preset rounds, the trained main branch air volume ratio prediction model is obtained. Figure 2 In represents the connection weight between the i-th neuron in the input layer and the j-th neuron in the hidden layer, represents the threshold of the input layer and the hidden layer, f1 represents the activation function of the hidden layer neurons, f2 represents the output transfer function, Indicates the connection weight between the hidden layer and the output layer, and r1 indicates the threshold value between the hidden layer and the output layer. Then, in the process of temperature field control, the main branch air volume ratio prediction model can be used to analyze the current working condition information and the expected temperature data of the kiln axial direction, obtain the corresponding current main branch air volume ratio, and control the temperature field inside the rotary kiln according to the current main branch air volume ratio.
[0077] For further information, please refer to Figure 3 In the process of controlling the temperature field inside the rotary kiln according to the current main branch air volume ratio, the method may further include:
[0078] Collect the actual temperature data of the rotary kiln axis;
[0079] The actual temperature data of the kiln axis is used to adjust the current main branch air volume ratio; then, the temperature field inside the rotary kiln is controlled based on the current main branch air volume ratio, including:
[0080] The temperature field inside the rotary kiln is controlled by using the adjusted current main and branch air volume ratio.
[0081] It can be understood that the current main branch air volume ratio (i.e., the predicted main branch air volume ratio y in 3) can be obtained through the main branch air volume ratio prediction model, and the actual axial temperature data of the rotary kiln can be collected in real time (specifically, the data can be collected as follows Figure 3 The actual axial temperature curve in the rotary kiln) can be specifically predicted according to the current working condition of the rotary kiln to obtain the actual axial temperature curve corresponding to the current working condition (the specific prediction process will be described in detail below, and can be specifically referred to Figure 4 Corresponding embodiment), then adjust the current main branch air volume ratio according to the actual temperature data in the kiln axial direction combined with the expected temperature data in the kiln axial direction, and then use the adjusted current main branch air volume ratio to control the temperature field inside the rotary kiln.
[0082] Furthermore, the process of adjusting the current main and branch air volume ratio using the actual kiln axial temperature data may specifically include:
[0083] Calculate the deviation between the actual temperature data in the kiln axial direction and the expected temperature data in the kiln axial direction;
[0084] Adjust the current main branch air volume ratio according to the deviation.
[0085] Specifically, after obtaining the current main branch air volume ratio (i.e., the predicted main branch air volume ratio y in 3), the actual kiln axial temperature data obtained according to the current working conditions (i.e., Figure 3 The deviation between the actual axial temperature curve in the kiln and the expected axial temperature data of the kiln is then obtained through the air volume ratio controller according to the deviation, and then the predicted main branch air volume ratio y is adjusted according to the air volume ratio adjustment amount to obtain the actual main branch air volume ratio y, and the actual main branch air volume ratio y is used to control the temperature field inside the rotary kiln.
[0086] Among them, in the embodiment of the present invention, the process of adjusting the current main branch air volume ratio according to the deviation may include:
[0087] The obtained deviation is compared with the preset threshold. When the deviation is greater than the preset threshold, it is determined whether the temperature of the high temperature zone of the kiln is greater than the preset temperature threshold according to the actual temperature data of the kiln axis. If so, the proportion of the main branch air volume is reduced based on the current proportion of the main branch air volume.
[0088] Or, when the deviation is greater than a preset threshold, determine whether the overall temperature in the kiln reaches the expected temperature based on the actual temperature data in the kiln axis. If not, increase the main branch air volume ratio based on the current main branch air volume ratio.
[0089] That is, when the deviation is less than or equal to the preset threshold, it means that the air supply to the rotary kiln is appropriate, and the adjustment of the predicted main and branch air volume ratio can be stopped.
[0090] Specifically, the method may further include:
[0091] The current working conditions, the adjusted current main and branch air volume ratio, and the actual kiln axial temperature data are stored in the historical sample library, thereby improving the historical sample library and improving the control accuracy.
[0092] It can be seen that in the embodiment of the present invention, the main and branch air volume ratio prediction model of the rotary kiln is trained in advance according to the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions. When the internal temperature field of the rotary kiln is controlled, the current operating conditions of the rotary kiln and the expected kiln axial temperature data of the rotary kiln can be obtained, and then the main and branch air volume ratio prediction model is used to analyze and predict the current operating conditions and the expected kiln axial temperature data of the rotary kiln, and the current main and branch air volume ratio corresponding to the current operating conditions is obtained, and the current main and branch air volume ratio is used to control the temperature field inside the rotary kiln, thereby improving the accuracy and timeliness of the temperature field control of the rotary kiln, which is beneficial to improving the control efficiency and product quality.
[0093] That is, the method provided by the embodiment of the present invention can realize intelligent multi-level control of the air supply of the rotary kiln, reduce the lag effect, and improve the control efficiency; it can effectively reduce the problems such as the axial temperature instability of the rotary kiln caused by human factors, thereby affecting the production efficiency; it is helpful to realize unmanned rotary kiln intelligent production and reduce labor costs.
[0094] In addition, it should be noted that the process of obtaining the kiln axial temperature data curve corresponding to the historical working conditions or obtaining the actual axial temperature data curve corresponding to the current working conditions involved in the embodiment of the present invention can be specifically implemented in the following manner, please refer to Figure 4 :
[0095] S210: Obtaining the working condition of the rotary kiln;
[0096] S220: Determine, based on the current working condition, a kiln axial temperature curve feature corresponding to the working condition from the first historical working condition and the corresponding kiln axial temperature curve feature stored in the database;
[0097] S230: Analyze the working condition using a pre-established working condition and temperature curve characteristic parameter relationship model to obtain corresponding temperature curve characteristic parameters; wherein the working condition and temperature curve characteristic parameter relationship model is established based on the first historical working condition and the temperature curve characteristic parameter corresponding to the first historical working condition;
[0098] S240: constructing a kiln axial temperature curve corresponding to the working condition based on the kiln axial temperature curve characteristics and each temperature curve characteristic parameter.
[0099] Specifically, when it is necessary to measure the axial temperature curve of the rotary kiln, the working conditions of the rotary kiln can be obtained first, wherein the working conditions may include one or more combinations of air volume, secondary air ratio, rotary kiln speed, feed amount and total coal ratio, and of course may also include other working condition information, and the specific embodiments of the present invention do not limit the characteristics.
[0100] Based on the working condition, the kiln axial temperature curve characteristics corresponding to the working condition are determined from the first historical working condition (which may be the same as the above historical working condition or different) and the corresponding kiln axial temperature curve characteristics stored in the database. It should be noted that multiple groups of first historical working conditions and the historical kiln axial temperature curves corresponding to each group of first historical working conditions can be obtained in advance, and the curve characteristics of the historical kiln axial temperature curves can be obtained, that is, the kiln axial temperature curve characteristics corresponding to each first historical working condition are obtained, and the first historical working condition and the corresponding kiln axial temperature curve characteristics are stored in the database in correspondence, wherein the kiln axial temperature curve characteristics can be used to indicate the shape of the curve or the type of the curve, such as whether the curve is a straight line or a certain curve, etc. Then, according to the working condition, the kiln axial temperature curve characteristics corresponding to the working condition can be determined from the historical working conditions and the corresponding kiln axial temperature curve characteristics stored in the database.
[0101] The acquired working condition is analyzed by using a pre-established working condition and temperature curve characteristic parameter relationship model to obtain corresponding temperature curve characteristic parameters; wherein the working condition and temperature curve characteristic parameter relationship model is established based on the first historical working condition and the temperature curve characteristic parameter corresponding to the first historical working condition;
[0102] It should be noted that, in the embodiment of the present invention, multiple groups of kiln axial temperature curves corresponding to different first historical working conditions can be obtained in advance, and each temperature curve characteristic parameter of each kiln axial temperature curve can be extracted, that is, one kiln axial temperature curve can correspond to multiple temperature curve characteristic parameters, thereby obtaining a group of temperature curve characteristic parameters corresponding to each first historical working condition, that is, a group of first historical working conditions corresponds to a group of temperature curve characteristic parameters. Then, the first historical working conditions and the corresponding temperature curve characteristics are used as sample data to train the neural network and obtain a relationship model between the working conditions and the temperature curve characteristic parameters.
[0103] Specifically, when measuring the axial temperature curve of a rotary kiln, the obtained working condition can be input into a relationship model between the working condition and characteristic parameters of the temperature curve, and the relationship model between the working condition and characteristic parameters of the temperature curve outputs a set of characteristic parameters of the temperature curve corresponding to the working condition.
[0104] The kiln axial temperature curve corresponding to the working condition is constructed based on the kiln axial temperature curve characteristics and each temperature curve characteristic parameter. It should be noted that after determining the kiln axial temperature curve characteristics and each temperature curve characteristic parameter corresponding to the working condition, the kiln axial temperature curve corresponding to the working condition can be fitted by a curve fitting method according to the kiln axial temperature curve characteristics and each temperature curve characteristic parameter.
[0105] The implementation process of the above S220 may include:
[0106] Obtain each first historical working condition from the database;
[0107] A clustering algorithm is used to perform cluster analysis on the working condition and each first historical condition to obtain a target first historical condition corresponding to the working condition;
[0108] The kiln axial temperature curve characteristics corresponding to the target first historical working condition in the database are used as the kiln axial temperature curve characteristics of the working condition.
[0109] It should be noted that after obtaining the working conditions, a clustering algorithm can be used to perform cluster analysis on the working conditions and the various first historical conditions stored in the database to determine the target first historical conditions that belong to the same category as the working conditions, and then the kiln axial temperature curve characteristics corresponding to the target first historical conditions are used as the kiln axial temperature curve characteristics of the working conditions.
[0110] Specifically, in actual applications, multiple first historical operating conditions and kiln axial temperature curve characteristics corresponding to each first historical operating condition are stored in the database, wherein the kiln axial temperature curve characteristics of different operating conditions may be the same. Therefore, each first historical operating condition and each corresponding kiln axial temperature curve characteristic can be clustered and analyzed in advance, and each first historical operating condition and the corresponding kiln axial temperature curve characteristic can be classified to determine the first historical operating conditions belonging to the same category.
[0111] The implementation process of the above S230 may specifically include:
[0112] Acquire each first historical operating condition and each temperature curve characteristic parameter corresponding to each first historical operating condition;
[0113] Each first historical operating condition and a plurality of temperature curve characteristic coefficients corresponding to each first historical operating condition are used to train a neural network to obtain a relationship model between the operating condition and the temperature curve characteristic parameters.
[0114] It should be noted that, in the embodiment of the present invention, the temperature curve characteristic parameters corresponding to each first historical working condition can be obtained in advance, which can be specifically achieved in the following manner:
[0115] The CFD simulation model is used to simulate the steady-state temperature field in the kiln under multiple groups of different first historical conditions;
[0116] For each group of the steady-state temperature field in the kiln under the first historical working condition, the temperature curve of the steady-state temperature field in the kiln in the axial direction is extracted;
[0117] According to the temperature curve, determine the kiln axial temperature curve characteristics of the temperature curve;
[0118] Extract the temperature curve in sections to obtain the characteristic parameters of the temperature curve corresponding to each section;
[0119] The first historical operating condition, the corresponding kiln axial temperature curve characteristics and the temperature curve characteristic parameters corresponding to each section are correspondingly stored in the database.
[0120] It should be noted that, according to the orthogonal experimental method, a set of 6 variable factors (operating parameters) can be designed, namely, gas volume, total air volume, secondary air volume ratio, rotary kiln speed, feed amount, total coal ratio, and a CFD (Computational Fluid Dynamics) simulation test with 3 or 5 levels. The level number corresponds to the specific value of the variable, which is determined according to the specific experiment. The number of experimental groups is 18 or 25. Experimental Table 1 is as follows. Each group of experiments obtains a set of steady-state temperature fields in the kiln according to the specific values of the variable factors, so that the steady-state temperature fields in the kiln corresponding to multiple groups of operating conditions can be simulated. Of course, in practical applications, it is not limited to the first historical operating conditions of the above number, and multiple groups of stable temperature fields in the kiln with different first historical operating conditions can be simulated according to actual needs.
[0121] Table 1 Experimental data table
[0122]
[0123] Before using the CFD simulation model to simulate the steady-state temperature field in the kiln, the initial CFD simulation model can be calibrated first. Specifically:
[0124] In practical applications, a kiln head thermal imager can be set at the kiln head, and multiple thermocouples can be set at the kiln body. The specific distribution diagram is as follows: Figure 5As shown, according to different working conditions, the actual temperature data of multiple temperature measuring points between the kiln head and the first thermocouple of the kiln body can be collected by a kiln head thermal imager arranged at the kiln head (for example, 10 temperature measuring points can be taken at the kiln head along the axial direction of the rotary kiln), and the actual temperature data of each temperature measuring point of the kiln body can be collected by multiple thermocouples arranged at the kiln body, thereby forming sparse temperature discrete points in the axial direction of the rotary kiln.
[0125] It can be understood that, according to the set level, corresponding tests can be carried out in the test kiln, and the actual temperature data of each temperature measuring point under different working conditions collected by the thermal imager at the kiln head and the thermocouples of the kiln body can be obtained at the same time, and the actual temperature data under each group of working conditions can be used to calibrate the initial CFD simulation model, and then the calibrated CFD simulation model can be used to simulate the steady-state temperature field in the kiln under multiple groups of different first historical working conditions.
[0126] Specifically, after obtaining the steady-state temperature field in the kiln corresponding to each first historical working condition, the temperature curve of the steady-state temperature field in the kiln in the axial direction can be further extracted to obtain the temperature curve corresponding to each first historical working condition, and then for each temperature curve, the kiln axial temperature curve characteristics of the temperature curve are further determined, so that the kiln axial temperature curve characteristics corresponding to each first historical working condition can be obtained. Then, for each temperature curve, the temperature curve characteristic parameters of the temperature curve are extracted in sections using a curve fitting method to obtain the temperature curve characteristic parameters corresponding to each section, wherein one section may correspond to multiple temperature curve characteristic parameters.
[0127] In practical applications, the rotary kiln can be divided into three sections according to the combustion process inside the rotary kiln. Figure 6 , from the kiln head to the kiln tail, they are: cooling zone, main reduction zone and main drying preheating zone. Specifically, the characteristic parameters of the temperature curve can be extracted for each temperature curve according to these three sections. Specifically, after the extraction is completed, each group of the first historical working conditions, the kiln axial temperature curve characteristics corresponding to the first historical working conditions, and the temperature curve characteristic parameters corresponding to each section under the first historical working conditions can be stored in the database.
[0128] Specifically, when each operating condition and a plurality of temperature curve characteristic coefficients corresponding to each operating condition are used to train the neural network, each operating condition and a plurality of temperature curve characteristic coefficients corresponding to each operating condition can be divided into a training set and a test set. Specifically, the neural network can be trained using a plurality of temperature curve characteristic coefficients corresponding to each operating condition in the training set. The neural network architecture is as follows: Figure 7 As shown, in each round of training, the first historical condition is used as the input of the neural network, which can be specifically input into the input layer. The data output by the input layer is related to the connection weights. or threshold parameter After being combined, it is transmitted to the hidden layer. After being summed in the hidden layer, the connection weights of the hidden layer and the output layer are combined. It is transmitted to the output layer, and after being processed by the output layer, the predicted characteristic coefficient (that is, the predicted temperature curve characteristic parameter) y1 is obtained, where r1 represents the threshold value of the hidden layer and the output layer, and then the actual characteristic coefficient (that is, the multiple temperature curve characteristic coefficients of each segment corresponding to the current first historical working condition in the sample) is combined with the predicted characteristic coefficient for error feedback to update the parameters of each layer in the neural network until the loss value is less than the preset loss or the training rounds reach the preset number of times, and the working condition and temperature curve characteristic parameter relationship model is obtained. Of course, after testing the working condition and temperature curve characteristic parameter relationship model through the test set, if the working condition and temperature curve characteristic parameter relationship model can meet the preset requirements, the working condition and temperature curve characteristic parameter relationship model can be used as the trained working condition and temperature curve characteristic parameter relationship model. If it does not meet the preset requirements, the training can be continued until the trained working condition and temperature curve characteristic parameter relationship model is obtained after the test passes.
[0129] It should also be noted that in order to further improve the accuracy of the relationship model between the operating conditions and the characteristic parameters of the temperature curve, the actual temperature data of each temperature measuring point under different operating conditions can be collected before the thermocouple in the kiln body fails, and then the kiln axial temperature curve under these different operating conditions can be obtained by the above method. For each operating condition, the actual temperature data of each discrete point under the corresponding working condition is fitted by the CFD simulation module to obtain the corresponding real-time kiln axial temperature curve, and the real-time kiln axial temperature curve is used to correct the relationship model between the operating conditions and the characteristic parameters of the temperature curve. Then, the corrected relationship model between the operating conditions and the characteristic parameters of the temperature curve is used as the final relationship model between the operating conditions and the characteristic parameters of the temperature curve to predict the subsequent rotary kiln axial temperature curve, so that the predicted kiln axial temperature curve is more accurate.
[0130] It can be understood that in the embodiment of the present invention, the kiln axial temperature curve corresponding to the working condition can be obtained by the above method, so as to obtain the historical kiln axial temperature curve corresponding to each historical working condition, and the neural network is trained according to each historical working condition and each historical kiln axial temperature curve to obtain the main branch air volume ratio prediction model, and then in the process of controlling the temperature field of the rotary kiln, the main branch air volume ratio prediction model is used to analyze and predict the current working condition and the kiln axial expected temperature data of the rotary kiln, and the current main branch air volume ratio corresponding to the current working condition is obtained, and the current main branch air volume ratio is used to control the temperature field inside the rotary kiln. In the process of controlling the temperature field of the rotary kiln by using the current main branch air volume ratio, the actual kiln axial temperature curve corresponding to the current working condition can also be obtained according to the above method, and the predicted current main branch air volume ratio is adjusted by using the actual kiln axial temperature curve, and the adjusted actual main branch air volume ratio is used to control the temperature field inside the rotary kiln, thereby realizing accurate and efficient control of the temperature field inside the rotary kiln.
[0131] The present invention also provides a corresponding device for the control method of the internal temperature field of the rotary kiln, which further makes the method more practical. Among them, the device can be described from the perspective of functional modules and hardware. The control device of the internal temperature field of the rotary kiln provided by the present invention is introduced below. The device is used to implement the control method of the internal temperature field of the rotary kiln provided by the present invention. In this embodiment, the control device of the internal temperature field of the rotary kiln can include or be divided into one or more program modules, and the one or more program modules are stored in a storage medium and executed by one or more processors to complete the control method of the internal temperature field of the rotary kiln disclosed in the above embodiment. The program module referred to in the present invention refers to a series of computer program instruction segments that can complete specific functions, which is more suitable for describing the execution process of the control device of the internal temperature field of the rotary kiln in the storage medium than the program itself. The following description will specifically introduce the functions of each program module of this embodiment. The control device of the internal temperature field of the rotary kiln described below and the control method based on the internal temperature field of the rotary kiln described above can be referred to each other.
[0132] From the perspective of functional modules, see Figure 8 , Figure 8 A structural diagram of a device for controlling the temperature field inside a rotary kiln provided by the present invention in a specific embodiment, the device may include:
[0133] The acquisition module 11 is used to collect the current working condition information of the rotary kiln and the expected temperature data of the kiln axial direction;
[0134] The prediction module 12 is used to analyze the current working condition information and the kiln axial expected temperature data using a pre-established main and branch air volume ratio prediction model to obtain the corresponding current main and branch air volume ratio; wherein the main and branch air volume ratio prediction model is pre-trained based on the historical working conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical working conditions by establishing a module; the historical working conditions include the historical main and branch air volume ratio;
[0135] The control module 13 is used to control the temperature field inside the rotary kiln based on the current main branch air volume ratio.
[0136] It should be noted that the control device for the internal temperature field of the rotary kiln in the embodiment of the present invention has the same beneficial effects as the control method for the internal temperature field of the rotary kiln provided in the above embodiment, and for the specific introduction of the control method for the internal temperature field of the rotary kiln involved in the embodiment of the present invention, please refer to the above embodiment, and this application will not repeat it here.
[0137] The control device for the internal temperature field of the rotary kiln mentioned above is described from the perspective of functional modules. Furthermore, the present invention also provides an electronic device, which is described from the perspective of hardware. Fig. 9 A structural diagram of an electronic device provided in an embodiment of the present application, such as Fig. 9 As shown, the electronic device includes: a memory 20 for storing a computer program;
[0138] The processor 21 is used to implement the steps of the method for controlling the temperature field inside the rotary kiln in the above embodiment when executing the computer program.
[0139] The electronic device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer or a desktop computer.
[0140] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.
[0141] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the memory 20 may be an internal storage unit of an electronic device, such as a hard disk of a server. In other embodiments, the memory 20 may also be an external storage device of an electronic device, such as a plug-in hard disk equipped on a server, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. Further, the memory 20 may also include both an internal storage unit of an electronic device and an external storage device. The memory 20 may not only be used to store application software and various types of data installed in the electronic device, such as: the code of the program in the process of executing the control method of the internal temperature field of the rotary kiln, etc., but also be used to temporarily store data that has been output or is to be output. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, the relevant steps of the control method of the internal temperature field of the rotary kiln disclosed in any of the aforementioned embodiments can be implemented. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include but is not limited to (data corresponding to the control result of the temperature field inside the rotary kiln) and the like.
[0142] In some embodiments, the electronic device may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26. Among them, the display screen 22 and the input / output interface 23, such as a keyboard, belong to the user interface, and the optional user interface may also include a standard wired interface, a wireless interface, and the like. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device, and the like. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface. The communication interface 24 may optionally include a wired interface and / or a wireless interface, such as a WI-FI interface, a Bluetooth interface, and the like, which are generally used to establish a communication connection between the electronic device and other electronic devices. The communication bus 26 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, and the like. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0143] Those skilled in the art will understand that Fig. 9 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure.
[0144] It is understandable that if the control method of the temperature field inside the rotary kiln in the above embodiment 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 this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, magnetic disk or optical disk and other media that can store program codes.
[0145] Based on this, Fig.10As shown, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program 31 is stored. When the computer program 31 is executed by a processor, the steps of the method for controlling the temperature field inside the rotary kiln as described above are implemented.
[0146] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0147] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.
[0148] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for controlling the internal temperature field of a rotary kiln, characterized in that: include: Collect the current working condition information of the rotary kiln and the expected temperature data of the kiln axial direction; The current operating condition information and the kiln axial expected temperature data are analyzed using a pre-established main and branch air volume ratio prediction model to obtain the corresponding current main and branch air volume ratio; wherein the main and branch air volume ratio prediction model is pre-trained based on the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions; the historical operating conditions include the historical main and branch air volume ratio; The temperature field inside the rotary kiln is controlled based on the current main branch air volume ratio.
2. The method for controlling the internal temperature field of a rotary kiln according to claim 1, characterized in that: The main branch air volume ratio prediction model is pre-trained based on the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions, and includes: Acquire various historical operating conditions of the rotary kiln and kiln axial temperature data corresponding to the historical operating conditions; Based on the kiln axial temperature data, determining the axial temperature characteristics of each kiln corresponding to the historical operating conditions; According to each of the historical operating conditions and each of the kiln axial temperature characteristics corresponding to each of the historical operating conditions, a main and branch air volume ratio prediction model is trained to obtain a main and branch air volume ratio prediction model; wherein, during the training process, the historical main and branch air volume ratios in the historical operating conditions are used as the output of the model, and each of the kiln axial temperature characteristics and other historical operating conditions are used as the input of the model.
3. The method for controlling the internal temperature field of a rotary kiln according to claim 1, characterized in that: The obtaining of various historical operating conditions of the rotary kiln and kiln axial temperature data corresponding to the historical operating conditions includes: Obtain various historical working conditions of the rotary kiln; Obtaining kiln axial temperature data curves corresponding to each of the historical operating conditions; A clustering algorithm is used to cluster and divide each of the kiln axial temperature data curves to obtain a historical kiln axial temperature curve corresponding to each historical working condition.
4. The method for controlling the internal temperature field of a rotary kiln according to any one of claims 1 to 3, characterized in that: Also includes: Collecting actual temperature data of the rotary kiln in the kiln axial direction; The current main branch air volume ratio is adjusted using the actual axial temperature data of the kiln; Then, the temperature field inside the rotary kiln is controlled based on the current main branch air volume ratio, including: The temperature field inside the rotary kiln is controlled by using the adjusted current main branch air volume ratio.
5. The method for controlling the internal temperature field of a rotary kiln according to claim 4, characterized in that: The use of the actual axial temperature data of the kiln to adjust the current main branch air volume ratio includes: Calculate the deviation between the actual temperature data in the kiln axial direction and the expected temperature data in the kiln axial direction; The current main branch air volume ratio is adjusted according to the deviation.
6. The method for controlling the internal temperature field of a rotary kiln according to claim 5, characterized in that: The adjusting the current main branch air volume ratio according to the deviation includes: When the deviation is greater than the preset threshold, judging whether the temperature of the high temperature zone of the kiln is greater than the preset temperature threshold according to the actual temperature data of the kiln axial direction, if so, reducing the proportion of the main branch air volume on the basis of the current proportion of the main branch air volume; Or, when the deviation is greater than a preset threshold, determine whether the overall temperature in the kiln reaches the expected temperature based on the actual axial temperature data of the kiln; if not, increase the main branch air volume ratio based on the current main branch air volume ratio.
7. The method for controlling the internal temperature field of a rotary kiln according to claim 4, characterized in that: Also includes: The current working condition, the adjusted current main branch air volume ratio and the actual axial temperature data of the kiln are correspondingly stored in a historical sample library.
8. A device for controlling the temperature field inside a rotary kiln, characterized in that: include: The acquisition module is used to collect the current working condition information of the rotary kiln and the expected temperature data of the kiln axial direction; A prediction module is used to analyze the current operating condition information and the kiln axial expected temperature data using a pre-established main and branch air volume ratio prediction model to obtain the corresponding current main and branch air volume ratio; wherein the main and branch air volume ratio prediction model is pre-trained based on the historical operating conditions of the rotary kiln and the kiln axial temperature data corresponding to the historical operating conditions by establishing a module; the historical operating conditions include the historical main and branch air volume ratio; A control module is used to control the temperature field inside the rotary kiln based on the current main branch air volume ratio.
9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the method for controlling the internal temperature field of a rotary kiln as claimed in any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for controlling the internal temperature field of a rotary kiln as claimed in any one of claims 1 to 7 are implemented.
