A control method and device for combustion equipment of aluminum melting furnace

Abstract

The present invention relates to the technical field of aluminum melting furnace control, and in particular to a control method and device for aluminum melting furnace combustion equipment. A simulation system is constructed to perform combustion smelting simulation, and a recommended combustion control scheme and a predicted furnace characteristic parameter set are generated. The equipment is controlled to work according to the recommended scheme, and the actual furnace characteristic parameter set in the actual working process is obtained. The sub-prediction furnace characteristic parameter set within the preset working time period is extracted, and the drift of the furnace characteristic parameter is evaluated. If the parameter is in a normal state, no regulation is performed; if it is in a drift state, a real-time combustion working parameter set is obtained. A dynamic Bayesian network model is constructed using pre-fault characteristic parameters and fault characteristic parameters, and the real-time combustion working parameter set is imported into the model for prediction, and the equipment is regulated and processed according to the prediction results. This control method realizes the intelligent and automated control of the aluminum melting furnace combustion equipment, and improves production efficiency and safety.

Description

Technical Field

[0001] The invention relates to the technical field of aluminum melting furnace control, and in particular to a control method and device for aluminum melting furnace combustion equipment. Background Art

[0002] Traditional aluminum melting furnace combustion equipment mostly uses simple proportional-integral-differential (PID) control, which is difficult to adapt to the complex and changeable combustion environment of aluminum melting furnaces, resulting in low combustion efficiency, high energy consumption, and serious emission pollution. In order to improve the combustion efficiency of aluminum melting furnaces, reduce energy consumption, and reduce environmental pollution, researchers have been constantly exploring new combustion control methods in recent years.

[0003] Model predictive control (MPC) technology has achieved remarkable results in the field of industrial process control in recent years. MPC can predict the system state in the future based on the process model and optimize the control strategy to achieve precise control of complex processes. Applying MPC to the combustion control of aluminum melting furnaces can effectively solve the shortcomings of traditional PID control, improve combustion efficiency, reduce energy consumption and reduce emissions.

[0004] In addition, intelligent control methods, such as fuzzy control and neural network control, also show potential in aluminum melting furnace combustion control. Fuzzy control can simulate human experience and judgment, and process complex nonlinear relationships through fuzzy logic to achieve intelligent control of the combustion process. Neural network control can establish a nonlinear model of the combustion process by learning historical data and control according to the model.

[0005] In general, the combustion control method based on machine learning and deep learning can more accurately predict the combustion state and optimize the control according to the prediction results, thus realizing a more intelligent, efficient and environmentally friendly aluminum melting furnace combustion control. In view of this, the present invention proposes a more intelligent and automated aluminum melting furnace combustion control technology. Summary of the invention

[0006] The invention overcomes the shortcomings of the prior art and provides a control method and device for combustion equipment of an aluminum melting furnace.

[0007] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is:

[0008] The first aspect of the present invention discloses a control method for a combustion device of an aluminum melting furnace, comprising the following steps:

[0009] Construct an aluminum melting furnace combustion equipment simulation system, perform combustion smelting simulation on the aluminum material to be smelted based on the aluminum melting furnace combustion equipment simulation system, generate combustion smelting simulation results, and extract the recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set based on the combustion smelting simulation results;

[0010] Controlling the operation of the aluminum melting furnace combustion equipment according to the recommended combustion control scheme, and obtaining an actual furnace body characteristic parameter set of the aluminum melting furnace combustion equipment within a preset working time period during the actual working process; and extracting a sub-predicted furnace body characteristic parameter set of the aluminum melting furnace combustion equipment within the preset working time period from the predicted furnace body characteristic parameter set;

[0011] According to the actual furnace characteristic parameter set and the sub-prediction furnace characteristic parameter set, the drift of the furnace characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period is evaluated; if the furnace characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period are in a normal state, the aluminum melting furnace combustion equipment is not regulated;

[0012] If the furnace body characteristic parameters of the aluminum furnace combustion equipment within the preset working time period are in a drift state, then various real-time combustion working parameters of the aluminum furnace combustion equipment are obtained to obtain a real-time combustion working parameter set of the aluminum furnace combustion equipment;

[0013] The pre-fault characteristic parameters and fault characteristic parameters of the aluminum melting furnace combustion equipment are obtained, and a dynamic Bayesian network model is constructed according to the pre-fault characteristic parameters and the fault characteristic parameters; the real-time combustion working parameter set of the aluminum furnace combustion equipment is imported into the dynamic Bayesian network model for prediction, and the aluminum furnace combustion equipment is regulated and processed according to the prediction results.

[0014] Preferably, an aluminum melting furnace combustion equipment simulation system is constructed, and a combustion smelting simulation is performed on the aluminum material to be smelted based on the aluminum melting furnace combustion equipment simulation system to generate a combustion smelting simulation result, and a recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set are extracted according to the combustion smelting simulation result, specifically:

[0015] Obtaining the names and weight ratios of various aluminum materials to be melted, generating search tags according to the names and weight ratios of various aluminum materials to be melted, and retrieving the melting temperatures of the aluminum materials to be melted in the big data network based on the search tags;

[0016] Obtaining a work log of a combustion device of an aluminum melting furnace, and obtaining various historical combustion control schemes that enable the furnace body to burn to the melting temperature according to the work log;

[0017] Obtain design drawing information of the aluminum melting furnace combustion equipment, and construct a simulation system of the aluminum melting furnace combustion equipment according to the design drawing information and the name and weight ratio of the aluminum material to be smelted in combination with simulation software;

[0018] Based on various historical combustion control schemes, the aluminum melting furnace combustion equipment simulation system is controlled to simulate combustion, and the predicted furnace characteristic parameter set of the furnace body from the beginning of smelting to the melting temperature is obtained, and the predicted chemical composition of the aluminum liquid after the melting temperature is reached;

[0019] Acquire production requirement information of aluminum liquid, and determine the target chemical composition of the aluminum liquid according to the production requirement information; calculate the Pierce correlation coefficient between the predicted chemical composition and the target chemical composition based on the Pierce correlation coefficient algorithm;

[0020] If the Pierce correlation coefficient between a certain predicted chemical composition and the target chemical composition is greater than a preset coefficient threshold, the historical combustion control scheme corresponding to the predicted chemical composition is used as a recommended combustion control scheme, and a predicted furnace characteristic parameter set corresponding to the recommended combustion control scheme is obtained;

[0021] The recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set are transmitted to a preset terminal.

[0022] Preferably, the drift of the furnace characteristic parameters of the aluminum melting furnace combustion equipment within a preset working time period is evaluated according to the actual furnace characteristic parameter set and the sub-prediction furnace characteristic parameter set, specifically:

[0023] Constructing timestamps of the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set, and calculating the similarity between the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set by using dynamic time warping;

[0024] If the similarity between the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set is greater than the preset similarity, it means that the furnace body characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period are in a normal state;

[0025] If the similarity between the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set is not greater than the preset similarity, it means that the furnace body characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period are in a drift state.

[0026] Preferably, the pre-fault characteristic parameters and the fault characteristic parameters of the aluminum melting furnace combustion equipment are obtained, and a dynamic Bayesian network model is constructed according to the pre-fault characteristic parameters and the fault characteristic parameters, specifically:

[0027] Obtaining a work log of the aluminum melting furnace combustion equipment, and obtaining various historical fault events of the aluminum melting furnace combustion equipment according to the work log;

[0028] Obtain the historical combustion working parameters of the aluminum melting furnace combustion equipment when various historical fault events occur, which are defined as fault characteristic parameters; and obtain the historical combustion working parameters of the aluminum melting furnace combustion equipment before various historical fault events occur, which are defined as pre-fault characteristic parameters;

[0029] Iteratively calculate the fault characteristic parameters based on the FCM algorithm to obtain the membership of the fault characteristic parameters, and construct a fault characteristic membership matrix according to the membership of the fault characteristic parameters;

[0030] and performing iterative calculations on the pre-fault characteristic parameters based on the FCM algorithm to obtain the membership of the pre-fault characteristic parameters, and constructing a pre-fault characteristic membership matrix according to the membership of the pre-fault characteristic parameters;

[0031] Construct a dynamic Bayesian network and define variables in the network, including pre-fault features and fault features; introduce the Baum-Welch algorithm and set the number of iterations, and estimate the state transition probability and maximum likelihood between each pre-fault feature parameter and fault feature parameter based on the fault feature membership matrix and the pre-fault feature membership matrix combined with the Baum-Welch algorithm;

[0032] When the maximum likelihood is greater than a preset likelihood threshold, the iteration is stopped, the state transition probability between each pre-fault characteristic parameter and the fault characteristic parameter is output, and a state transition probability matrix is ​​generated according to the state transition probability between each pre-fault characteristic parameter and the fault characteristic parameter;

[0033] The state transition probability matrix is ​​introduced into the dynamic Bayesian network for back-propagation learning until the loss function gradually decreases and is less than a preset convergence value, the final learning parameters are saved, and the dynamic Bayesian network model is output.

[0034] Preferably, the real-time combustion working parameter set of the aluminum furnace combustion equipment is imported into the dynamic Bayesian network model for prediction, and the aluminum furnace combustion equipment is regulated and processed according to the prediction results, specifically:

[0035] The real-time combustion working parameter set of the aluminum furnace combustion equipment is imported into the dynamic Bayesian network model for prediction, and the transition probability of the aluminum furnace combustion equipment transitioning to the fault characteristic state is obtained;

[0036] If the probability of the aluminum furnace combustion equipment transitioning to the fault characteristic state is greater than a preset probability value, the aluminum furnace combustion equipment is controlled to shut down and a fault alarm is generated;

[0037] If the probability of the aluminum furnace combustion equipment transitioning to the fault state is not greater than the preset probability value, then various real-time furnace body characteristic parameters of the aluminum melting furnace combustion equipment at the current time node are obtained, and various predicted furnace body characteristic parameters of the aluminum melting furnace combustion equipment at the current time node are obtained;

[0038] Calculate the parameter differences between various real-time furnace characteristic parameters and predicted furnace characteristic parameters, and only extract the real-time furnace characteristic parameters whose parameter differences are greater than a preset difference threshold, which are defined as drift furnace characteristic parameters of the aluminum melting furnace combustion equipment;

[0039] Obtaining a parameter difference between the drift furnace body characteristic parameter and the predicted furnace body characteristic parameter to obtain a drift value of the drift furnace body characteristic parameter;

[0040] The corresponding real-time combustion working parameters of the aluminum melting furnace combustion equipment are regulated and processed according to the drift value of the drift furnace body characteristic parameter.

[0041] Preferably, the corresponding real-time combustion working parameters of the aluminum melting furnace combustion equipment are regulated and processed according to the drift value of the drift furnace body characteristic parameter, specifically:

[0042] Formulate in advance the preset control scheme of the aluminum melting furnace combustion equipment under various drift value conditions after the various furnace characteristic parameters in the aluminum melting furnace combustion equipment drift;

[0043] Construct a knowledge graph, and import the preset control schemes of the aluminum melting furnace combustion equipment under various drift value conditions into the knowledge graph to generate a feature knowledge graph;

[0044] Obtaining the drift value of the drift furnace body characteristic parameter in the aluminum melting furnace combustion equipment, importing the drift value of the drift furnace body characteristic parameter into the characteristic knowledge graph for matching, and matching to obtain a corresponding preset control scheme;

[0045] The matched preset control scheme is transmitted to the control terminal of the aluminum melting furnace combustion equipment to control the aluminum melting furnace combustion equipment.

[0046] The second aspect of the present invention discloses a control device for aluminum melting furnace combustion equipment, the control device includes a memory and a processor, the memory stores a control method program for the aluminum melting furnace combustion equipment, when the control method program for the aluminum melting furnace combustion equipment is executed by the processor, any one of the control method steps for the aluminum melting furnace combustion equipment is implemented.

[0047] The present invention solves the technical defects existing in the background technology, and the present invention has the following beneficial effects: First, by constructing a simulation system to perform combustion smelting simulation, a recommended combustion control scheme and a predicted furnace characteristic parameter set are generated. Then, the equipment is controlled to work according to the recommended scheme, and the actual furnace characteristic parameter set in the actual working process is obtained. Next, the sub-prediction furnace characteristic parameter set within the preset working time period is extracted to evaluate the drift of the furnace characteristic parameters. If the parameter is in a normal state, no regulation is performed; if it is in a drift state, a real-time combustion working parameter set is obtained. Finally, a dynamic Bayesian network model is constructed using the pre-fault characteristic parameters and the fault characteristic parameters, the real-time combustion working parameter set is imported into the model for prediction, and the equipment is regulated and processed according to the prediction results. This control method realizes the intelligent and automated control of the combustion equipment of the aluminum melting furnace, improves production efficiency, and reduces energy consumption and environmental pollution. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0049] Figure 1 It is a flow chart of the overall method of a control method of a combustion device of an aluminum melting furnace;

[0050] Figure 2 A partial method flow chart of a control method for a combustion device of an aluminum melting furnace;

[0051] Figure 3 The present invention is a schematic diagram of a control device for a combustion equipment of an aluminum melting furnace. DETAILED DESCRIPTION

[0052] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0054] like Figure 1 As shown, the first aspect of the present invention discloses a control method for a combustion device of an aluminum melting furnace, comprising the following steps:

[0055] S102: constructing an aluminum melting furnace combustion equipment simulation system, performing combustion smelting simulation on the aluminum material to be smelted based on the aluminum melting furnace combustion equipment simulation system, generating combustion smelting simulation results, and extracting a recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set according to the combustion smelting simulation results;

[0056] S104: controlling the operation of the aluminum melting furnace combustion equipment according to the recommended combustion control scheme, and obtaining an actual furnace body characteristic parameter set of the aluminum melting furnace combustion equipment in a preset working time period during the actual working process; and extracting a sub-prediction furnace body characteristic parameter set of the aluminum melting furnace combustion equipment in the preset working time period from the predicted furnace body characteristic parameter set;

[0057] S106: evaluating the drift of the furnace characteristic parameters of the aluminum melting furnace combustion equipment within a preset working time period according to the actual furnace characteristic parameter set and the sub-prediction furnace characteristic parameter set; if the furnace characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period are normal, then the aluminum melting furnace combustion equipment is not regulated;

[0058] S108: If the furnace body characteristic parameters of the aluminum furnace combustion equipment within the preset working time period are in a drift state, various real-time combustion working parameters of the aluminum furnace combustion equipment are obtained to obtain a real-time combustion working parameter set of the aluminum furnace combustion equipment;

[0059] S110: Obtain pre-fault characteristic parameters and fault characteristic parameters of the aluminum melting furnace combustion equipment, and construct a dynamic Bayesian network model based on the pre-fault characteristic parameters and fault characteristic parameters; import the real-time combustion working parameter set of the aluminum furnace combustion equipment into the dynamic Bayesian network model for prediction, and regulate the aluminum furnace combustion equipment according to the prediction results.

[0060] It should be noted that, firstly, by constructing a simulation system for combustion and smelting simulation, a recommended combustion control scheme and a predicted furnace characteristic parameter set are generated. Then, the equipment is controlled to work according to the recommended scheme, and the actual furnace characteristic parameter set in the actual working process is obtained. Next, the sub-predicted furnace characteristic parameter set within the preset working time period is extracted to evaluate the drift of the furnace characteristic parameter. If the parameter is in a normal state, no regulation is performed; if it is in a drift state, the real-time combustion working parameter set is obtained. Finally, a dynamic Bayesian network model is constructed using the pre-fault characteristic parameters and the fault characteristic parameters, the real-time combustion working parameter set is imported into the model for prediction, and the equipment is regulated and processed according to the prediction results. The recommended combustion control scheme and the predicted furnace characteristic parameter set are generated by the simulation system, which improves the combustion efficiency and smelting quality. The drift of the furnace characteristic parameters is monitored and evaluated in real time, and problems are discovered and regulated in time, ensuring the stability and reliability of the equipment. The dynamic Bayesian network model is used for prediction and regulation, which improves the accuracy and timeliness of fault diagnosis and processing, and reduces equipment failures and downtime. On the whole, this control method realizes intelligent and automated control of the combustion equipment of the aluminum melting furnace, improves production efficiency, and reduces energy consumption and environmental pollution.

[0061] Preferably, an aluminum melting furnace combustion equipment simulation system is constructed, and a combustion smelting simulation is performed on the aluminum material to be smelted based on the aluminum melting furnace combustion equipment simulation system to generate a combustion smelting simulation result, and a recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set are extracted according to the combustion smelting simulation result, specifically:

[0062] Obtaining the names and weight ratios of various aluminum materials to be melted, generating search tags according to the names and weight ratios of various aluminum materials to be melted, and retrieving the melting temperatures of the aluminum materials to be melted in the big data network based on the search tags;

[0063] Obtaining a work log of a combustion device of an aluminum melting furnace, and obtaining various historical combustion control schemes that enable the furnace body to burn to the melting temperature according to the work log;

[0064] Obtain design drawing information of the aluminum melting furnace combustion equipment, and construct a simulation system of the aluminum melting furnace combustion equipment according to the design drawing information and the name and weight ratio of the aluminum material to be smelted in combination with simulation software;

[0065] Based on various historical combustion control schemes, the aluminum melting furnace combustion equipment simulation system is controlled to simulate combustion, and the predicted furnace characteristic parameter set of the furnace body from the beginning of smelting to the melting temperature is obtained, and the predicted chemical composition of the aluminum liquid after the melting temperature is reached;

[0066] Acquire production requirement information of aluminum liquid, and determine the target chemical composition of the aluminum liquid according to the production requirement information; calculate the Pierce correlation coefficient between the predicted chemical composition and the target chemical composition based on the Pierce correlation coefficient algorithm;

[0067] If the Pierce correlation coefficient between a certain predicted chemical composition and the target chemical composition is greater than a preset coefficient threshold, the historical combustion control scheme corresponding to the predicted chemical composition is used as a recommended combustion control scheme, and a predicted furnace characteristic parameter set corresponding to the recommended combustion control scheme is obtained;

[0068] The recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set are transmitted to a preset terminal.

[0069] It should be noted that the name and weight ratio information of various aluminum materials to be smelted are obtained, and search tags are generated based on this, which are used to retrieve the melting temperature of the aluminum materials to be smelted in the big data network. At the same time, the work log of the aluminum melting furnace combustion equipment is obtained, the historical combustion control scheme is extracted, and the design drawing information is consulted, and the simulation system of the aluminum melting furnace combustion equipment is constructed in combination with the simulation software. The historical combustion control scheme is used to simulate the combustion work in the simulation system, predict the process characteristic parameter set of the furnace body from the start of smelting to the melting temperature, and predict the chemical composition of the aluminum liquid. This process helps to understand the impact of different control strategies on the smelting process. According to the production requirements of the aluminum liquid, the target chemical composition is determined. The correlation between the predicted chemical composition and the target chemical composition is quantified by the Pierce correlation coefficient algorithm. For the predicted components with high correlation with the target chemical composition, the corresponding control scheme is regarded as the recommended scheme. The recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set are transmitted to the preset terminal. This step aims to transform the theoretical optimization results into practical operation guidance and improve the efficiency and product quality of the aluminum melting process. Through big data analysis, precise control of the aluminum melting process is achieved, and the smelting efficiency and aluminum liquid quality are improved. Utilize historical combustion control schemes to avoid repeated experiments and save resources. Use simulation systems for rehearsal to effectively reduce uncertainty and risks in actual operations. Through Pierce correlation coefficient evaluation, ensure that the recommended scheme is highly consistent with the production target and improve the chemical composition consistency of the aluminum liquid. The output recommended scheme and its characteristic parameter set provide an intuitive and efficient decision-making basis for the actual control process, which helps to improve overall production efficiency and product quality. In summary, this method realizes intelligent control of the aluminum melting process by integrating multiple data sources, using simulation technology for rehearsal, and data-driven decision optimization, which can significantly improve the efficiency and quality of aluminum smelting.

[0070] Preferably, the drift of the furnace characteristic parameters of the aluminum melting furnace combustion equipment within a preset working time period is evaluated according to the actual furnace characteristic parameter set and the sub-prediction furnace characteristic parameter set, specifically:

[0071] Constructing timestamps of the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set, and calculating the similarity between the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set by using dynamic time warping;

[0072] If the similarity between the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set is greater than the preset similarity, it means that the furnace body characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period are in a normal state;

[0073] If the similarity between the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set is not greater than the preset similarity, it means that the furnace body characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period are in a drift state.

[0074] It should be noted that by constructing the timestamps of the actual furnace characteristic parameter set and the sub-prediction furnace characteristic parameter set, the similarity between the two is calculated using the Dynamic Time Warping (DTW) algorithm. If the similarity exceeds the preset threshold, the furnace characteristic parameters are considered to be in a normal state; conversely, if the similarity does not meet the standard, it indicates that the furnace characteristic parameters have drifted, that is, the equipment operation status is abnormal. Through the dynamic time warping algorithm, real-time monitoring and evaluation of the operating status of the aluminum melting furnace combustion equipment can be achieved to ensure the stability and safety of the production process. When the furnace characteristic parameters drift, that is, the parameter set similarity is lower than the preset value, potential faults or abnormalities can be discovered in time, providing a basis for early intervention. By accurately judging the equipment status, unnecessary downtime and adjustments can be avoided, thereby improving production efficiency and reducing maintenance costs.

[0075] Preferably, if Figure 2 As shown, the pre-fault characteristic parameters and fault characteristic parameters of the aluminum melting furnace combustion equipment are obtained, and a dynamic Bayesian network model is constructed according to the pre-fault characteristic parameters and fault characteristic parameters, specifically:

[0076] S202: Obtaining a work log of the aluminum melting furnace combustion equipment, and obtaining various historical fault events of the aluminum melting furnace combustion equipment according to the work log;

[0077] S204: obtaining historical combustion working parameters of the aluminum melting furnace combustion equipment when various historical fault events occur, which are defined as fault characteristic parameters; and obtaining historical combustion working parameters of the aluminum melting furnace combustion equipment before various historical fault events occur, which are defined as pre-fault characteristic parameters;

[0078] S206: performing iterative calculations on the fault characteristic parameters based on the FCM algorithm to obtain the membership of the fault characteristic parameters, and constructing a fault characteristic membership matrix according to the membership of the fault characteristic parameters;

[0079] S208: performing iterative calculations on the pre-fault characteristic parameters based on the FCM algorithm to obtain the membership of the pre-fault characteristic parameters, and constructing a pre-fault characteristic membership matrix according to the membership of the pre-fault characteristic parameters;

[0080] S210: construct a dynamic Bayesian network and define variables in the network, including pre-fault features and fault features; introduce the Baum-Welch algorithm and set the number of iterations, estimate the state transition probability and maximum likelihood between each pre-fault feature parameter and the fault feature parameter according to the fault feature membership matrix and the pre-fault feature membership matrix in combination with the Baum-Welch algorithm;

[0081] S212: when the maximum likelihood is greater than a preset likelihood threshold, the iteration is stopped, the state transition probability between each pre-fault characteristic parameter and the fault characteristic parameter is output, and a state transition probability matrix is ​​generated according to the state transition probability between each pre-fault characteristic parameter and the fault characteristic parameter;

[0082] S214: Importing the state transition probability matrix into the dynamic Bayesian network for back propagation learning until the loss function gradually decreases and is less than a preset convergence value, saving the final learning parameters, and outputting the dynamic Bayesian network model.

[0083] It should be noted that, firstly, by analyzing the work log, historical fault events and their corresponding combustion working parameters are extracted, which are defined as fault characteristic parameters and pre-fault characteristic parameters respectively. Then, the fuzzy C-means (FCM) algorithm is used to iteratively calculate these parameters to determine their membership, and to construct the fault characteristic membership matrix and the pre-fault characteristic membership matrix. Then, a dynamic Bayesian network is constructed, and the Baum-Welch algorithm is used to estimate the state transition probability and maximum likelihood between the pre-fault characteristic parameters and the fault characteristic parameters. When the likelihood exceeds the preset threshold, the iteration is stopped and the state transition probability matrix is ​​output. Finally, the dynamic Bayesian network model is optimized by back propagation learning until convergence is reached. Using the FCM algorithm to calculate the membership degree helps to identify different fault modes and provides an important basis for fault diagnosis. In addition, by accurately estimating the state transition probability between the pre-fault characteristic parameters and the fault characteristic parameters, a quantitative indicator is provided for predicting faults. The constructed dynamic Bayesian network model can capture the dynamic process of fault occurrence and improve the accuracy and reliability of fault prediction. Based on the state transition probability matrix, a preventive maintenance strategy can be formulated and measures can be taken in advance to prevent the occurrence of potential failures. In summary, this method provides strong technical support for the fault prediction and maintenance of aluminum melting furnace combustion equipment by comprehensively using data mining, fuzzy logic and probability models, which is of great significance for improving production efficiency, reducing maintenance costs and ensuring safe production.

[0084] Preferably, the real-time combustion working parameter set of the aluminum furnace combustion equipment is imported into the dynamic Bayesian network model for prediction, and the aluminum furnace combustion equipment is regulated and processed according to the prediction results, specifically:

[0085] The real-time combustion working parameter set of the aluminum furnace combustion equipment is imported into the dynamic Bayesian network model for prediction, and the transition probability of the aluminum furnace combustion equipment transitioning to the fault characteristic state is obtained;

[0086] If the probability of the aluminum furnace combustion equipment transitioning to the fault characteristic state is greater than a preset probability value, the aluminum furnace combustion equipment is controlled to shut down and a fault alarm is generated;

[0087] If the probability of the aluminum furnace combustion equipment transitioning to the fault state is not greater than the preset probability value, then various real-time furnace body characteristic parameters of the aluminum melting furnace combustion equipment at the current time node are obtained, and various predicted furnace body characteristic parameters of the aluminum melting furnace combustion equipment at the current time node are obtained;

[0088] Calculate the parameter differences between various real-time furnace characteristic parameters and predicted furnace characteristic parameters, and only extract the real-time furnace characteristic parameters whose parameter differences are greater than a preset difference threshold, which are defined as drift furnace characteristic parameters of the aluminum melting furnace combustion equipment;

[0089] Obtaining a parameter difference between the drift furnace body characteristic parameter and the predicted furnace body characteristic parameter to obtain a drift value of the drift furnace body characteristic parameter;

[0090] The corresponding real-time combustion working parameters of the aluminum melting furnace combustion equipment are regulated and processed according to the drift value of the drift furnace body characteristic parameter.

[0091] It should be noted that the real-time combustion working parameters are first input into the trained dynamic Bayesian network model to predict the probability of the equipment transitioning to a fault state. If the probability exceeds the preset threshold, the equipment operation is stopped immediately and a fault alarm is issued. If the predicted probability is lower than the threshold, the difference between the real-time furnace body characteristic parameters at the current moment and the predicted furnace body characteristic parameters is further analyzed, and the characteristic parameters whose parameter differences exceed the preset threshold are extracted, which are defined as drift furnace body characteristic parameters. Finally, according to the difference value of the drift characteristic parameters, the corresponding combustion working parameters are adjusted in real time to correct the equipment operation state and avoid the occurrence of potential faults. The dynamic Bayesian network model can be used to predict according to real-time data, warn of potential faults in advance, avoid unexpected equipment shutdowns, and improve production efficiency and safety. By analyzing the drift characteristic parameters, the combustion working parameters are adjusted in a targeted manner to ensure stable equipment operation, improve smelting efficiency and product quality. This method combines fault prediction with real-time regulation and control, realizes intelligent control of aluminum melting furnace combustion equipment, reduces manual intervention, and improves the level of production automation. In summary, this method realizes the intelligent management of equipment operation by applying the dynamic Bayesian network model to the fault prediction and real-time control of the combustion equipment of the aluminum melting furnace, effectively improving production efficiency, reducing the failure rate, and improving safety and reliability.

[0092] Preferably, the corresponding real-time combustion working parameters of the aluminum melting furnace combustion equipment are regulated and processed according to the drift value of the drift furnace body characteristic parameter, specifically:

[0093] Formulate in advance the preset control scheme of the aluminum melting furnace combustion equipment under various drift value conditions after the various furnace characteristic parameters in the aluminum melting furnace combustion equipment drift;

[0094] Construct a knowledge graph, and import the preset control schemes of the aluminum melting furnace combustion equipment under various drift value conditions into the knowledge graph to generate a feature knowledge graph;

[0095] Obtaining the drift value of the drift furnace body characteristic parameter in the aluminum melting furnace combustion equipment, importing the drift value of the drift furnace body characteristic parameter into the characteristic knowledge graph for matching, and matching to obtain a corresponding preset control scheme;

[0096] The matched preset control scheme is transmitted to the control terminal of the aluminum melting furnace combustion equipment to control the aluminum melting furnace combustion equipment.

[0097] It should be noted that, first of all, for the drift values ​​of different furnace characteristic parameters, relevant technical personnel pre-formulate corresponding control plans, and build a knowledge graph to store these preset plans. When the furnace characteristic parameters drift during the operation of the equipment, the system will automatically obtain the drift value, import it into the knowledge graph for matching, and find the corresponding preset control plan. Finally, the matched plan is transmitted to the control terminal to realize the intelligent adjustment of the aluminum melting furnace combustion equipment. By constructing a knowledge graph, the preset control plan is matched with the drift characteristic parameters to realize the intelligent adjustment of the equipment, reduce manual intervention, and improve the control efficiency. The knowledge graph can quickly retrieve and match the corresponding control plan, shorten the response time, and adjust the equipment operation status in time to avoid greater deviations or failures.

[0098] The predicted furnace body characteristic parameters, the actual furnace body characteristic parameters and the real-time furnace body characteristic parameters all include the gas flow rate, gas pressure, gas composition and aluminum liquid level inside the furnace body.

[0099] The above-mentioned real-time combustion operating parameters and historical combustion operating parameters include fuel flow, air flow, fuel-air ratio, combustion temperature, furnace pressure, emission content, operating current and operating voltage.

[0100] In specific applications, the method may further include the following steps:

[0101] After the aluminum material to be smelted is burned and smelted by the aluminum melting furnace combustion equipment, the porosity data of the aluminum liquid at several preset detection position nodes in the furnace body are obtained based on the X-ray detector; and the relative coordinate information of each preset detection position node in the furnace body is obtained;

[0102] The Bezier curve method is introduced, and the order of the Bezier curve is determined. The Bezier curve equation is calculated based on the porosity data of the aluminum liquid at several preset detection position nodes in the furnace body and the relative coordinate information of each preset detection position node in the furnace body and combined with the order of the Bezier curve;

[0103] According to the Bezier curve equation, a porosity Bezier curve of the aluminum liquid at a plurality of preset detection position nodes in the furnace body is drawn to obtain a porosity Bezier curve of the aluminum liquid after combustion smelting;

[0104] Acquire production requirement information of aluminum liquid, determine upper and lower limit threshold ranges of porosity of standard aluminum liquid according to the production requirement information, and use Bezier curve method to fit the upper and lower limit threshold ranges to obtain Bezier curve of porosity threshold range of standard aluminum liquid;

[0105] Analyze the position relationship between the porosity Bezier curve of aluminum liquid after combustion smelting and the porosity threshold range Bezier curve of standard aluminum liquid in the entire definition domain;

[0106] If the porosity Bezier curve of the aluminum liquid after combustion and smelting is completely within the definition domain of the Bezier curve of the porosity threshold range of the standard aluminum liquid, it means that the aluminum liquid after combustion and smelting meets the standard requirements, then the combustion equipment of the aluminum melting furnace is controlled to carry out the next cycle of combustion and smelting;

[0107] If the porosity Bezier curve of the aluminum liquid after combustion smelting partially or completely exceeds the porosity threshold range of the standard aluminum liquid within the definition domain of the Bezier curve, it means that the aluminum liquid after combustion smelting does not meet the standard requirements, and an early warning message is generated.

[0108] It should be noted that, first, the porosity data of the aluminum liquid at several preset detection position nodes in the furnace body are obtained by an X-ray detector, and the relative coordinate information of these nodes in the furnace body is recorded. : The Bezier curve method is introduced. According to the collected porosity data and node coordinates, the order of the Bezier curve is determined, and the Bezier curve equation is calculated. The Bezier curve equation can describe the trend of porosity changing with position. According to the Bezier curve equation, the porosity Bezier curves of the aluminum liquid at several preset detection position nodes in the furnace body are drawn to obtain the porosity Bezier curve of the aluminum liquid after combustion smelting. This curve can intuitively show the distribution of porosity in the furnace body. Obtain the production requirement information of the aluminum liquid and determine the upper and lower limit threshold ranges of the porosity of the standard aluminum liquid. Use the Bezier curve method to fit the upper and lower limit threshold ranges to obtain the porosity threshold range Bezier curve of the standard aluminum liquid. This curve defines the standard range of porosity. Analyze the positional relationship between the porosity Bezier curve of the aluminum liquid after combustion smelting and the porosity threshold range Bezier curve of the standard aluminum liquid in the entire definition domain. If the porosity Bezier curve of the aluminum liquid after combustion smelting is completely within the definition domain of the Bezier curve of the porosity threshold range of the standard aluminum liquid, it means that the aluminum liquid after combustion smelting meets the standard requirements. According to the curve comparison result, if the aluminum liquid after combustion smelting meets the standard requirements, the aluminum melting furnace combustion equipment is controlled to perform the next cycle of combustion smelting. If the porosity Bezier curve of the aluminum liquid after combustion smelting partially or completely exceeds the definition domain of the Bezier curve of the porosity threshold range of the standard aluminum liquid, it means that the aluminum liquid after combustion smelting does not meet the standard requirements, and an early warning message is generated to prompt adjustments or other measures. This method monitors the porosity of the aluminum liquid in the furnace body in real time, and analyzes and judges it through the Bezier curve method, so as to timely discover problems and take corresponding measures, thereby ensuring the quality of the aluminum liquid and the stability of production. At the same time, this method has high accuracy and reliability, and can effectively improve production efficiency and product quality.

[0109] In specific applications, the method may further include the following steps:

[0110] If the porosity Bezier curve of the aluminum liquid after combustion smelting partially or completely exceeds the porosity threshold range of the standard aluminum liquid within the definition domain of the Bezier curve, then several inducing factors that cause porosity in the aluminum liquid after combustion smelting are retrieved based on the big data network;

[0111] The multivariate linear regression analysis algorithm was introduced, and the regression equation was established. The porosity Bezier curve of aluminum liquid after combustion smelting was used as the reference sequence, and several inducing factors that caused the porosity of aluminum liquid after combustion smelting were used as the comparison sequence.

[0112] Calculating the correlation coefficient at each time point according to the reference sequence and the comparison sequence combined with the regression equation, and obtaining the grey correlation degree between various inducing factors and the porosity Bezier curve of the aluminum liquid after combustion smelting according to the corresponding correlation coefficient;

[0113] Extract the inducing factors corresponding to the gray correlation degree greater than the preset correlation degree threshold, and define them as suspicious inducing factors; obtain the real-time multi-dimensional control parameters of the control module corresponding to the suspicious inducing factors, import the real-time multi-dimensional control parameters of the control module corresponding to the suspicious inducing factors into the Markov chain model to perform state transition probability prediction, and obtain the fault state transition probability of the control module corresponding to the suspicious inducing factors;

[0114] If the fault state transition probability is greater than the preset probability, the combustion equipment of the aluminum melting furnace is controlled to stop production and generate an early warning message;

[0115] The inducing factors include combustion smelting temperature factor, combustion smelting time factor, combustion smelting stirring speed factor, smelting furnace body sealing factor and workshop environment factor.

[0116] It should be noted that by comparing the porosity Bezier curve of the aluminum liquid after combustion and smelting with the porosity threshold range Bezier curve of the standard aluminum liquid, it is determined whether there is a situation beyond the definition domain. If so, the big data network is used to retrieve possible inducing factors. Then, the multivariate linear regression analysis algorithm is introduced to establish a regression equation, the porosity Bezier curve is used as the reference sequence, the inducing factor is used as the comparison sequence, and the correlation coefficient at each time point is calculated to obtain the gray correlation between various inducing factors and the porosity Bezier curve. Next, the inducing factors with a gray correlation greater than the preset threshold are extracted and defined as suspicious inducing factors. Then, the real-time multidimensional control parameters of the control module that controls these suspicious inducing factors are obtained, and they are imported into the Markov chain model for state transition probability prediction to obtain the fault state transition probability of the control module corresponding to the suspicious inducing factor. Finally, if the fault state transition probability is greater than the preset probability, the aluminum melting furnace combustion equipment is controlled to stop production and generate early warning information. Among them, the inducing factors include combustion smelting temperature, time, stirring speed, furnace body sealing and workshop environment. This method can quickly and accurately detect and predict the suspected inducing factors that may cause the porosity of aluminum liquid to exceed the standard, so as to take timely measures to avoid producing more unqualified products. At the same time, by analyzing the real-time multi-dimensional control parameters of the control module, the operating status of the equipment can be better understood, providing a reference for equipment maintenance and optimization.

[0117] The second aspect of the present invention discloses a control device for a combustion device of an aluminum melting furnace, such as Figure 3As shown, the control device includes a memory 20 and a processor 70. The memory 20 stores a control method program for an aluminum melting furnace combustion equipment. When the control method program for the aluminum melting furnace combustion equipment is executed by the processor 70, any one of the control method steps for the aluminum melting furnace combustion equipment is implemented.

[0118] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A control method for a combustion device of an aluminum melting furnace, characterized in that: The following steps are involved: Construct an aluminum melting furnace combustion equipment simulation system, perform combustion smelting simulation on the aluminum material to be smelted based on the aluminum melting furnace combustion equipment simulation system, generate combustion smelting simulation results, and extract the recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set based on the combustion smelting simulation results; Controlling the operation of the aluminum melting furnace combustion equipment according to the recommended combustion control scheme, and obtaining an actual furnace body characteristic parameter set of the aluminum melting furnace combustion equipment within a preset working time period during the actual working process; and extracting a sub-predicted furnace body characteristic parameter set of the aluminum melting furnace combustion equipment within the preset working time period from the predicted furnace body characteristic parameter set; According to the actual furnace characteristic parameter set and the sub-prediction furnace characteristic parameter set, the drift of the furnace characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period is evaluated; if the furnace characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period are in a normal state, the aluminum melting furnace combustion equipment is not regulated; If the furnace body characteristic parameters of the aluminum furnace combustion equipment within the preset working time period are in a drift state, then various real-time combustion working parameters of the aluminum furnace combustion equipment are obtained to obtain a real-time combustion working parameter set of the aluminum furnace combustion equipment; The pre-fault characteristic parameters and fault characteristic parameters of the aluminum melting furnace combustion equipment are obtained, and a dynamic Bayesian network model is constructed according to the pre-fault characteristic parameters and the fault characteristic parameters; the real-time combustion working parameter set of the aluminum furnace combustion equipment is imported into the dynamic Bayesian network model for prediction, and the aluminum furnace combustion equipment is regulated and processed according to the prediction results.

2. The control method of a combustion equipment of an aluminum melting furnace according to claim 1, characterized in that: Construct an aluminum melting furnace combustion equipment simulation system, perform combustion smelting simulation on the aluminum material to be smelted based on the aluminum melting furnace combustion equipment simulation system, generate combustion smelting simulation results, and extract the recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set based on the combustion smelting simulation results, specifically: Obtaining the names and weight ratios of various aluminum materials to be melted, generating search tags according to the names and weight ratios of various aluminum materials to be melted, and retrieving the melting temperatures of the aluminum materials to be melted in the big data network based on the search tags; Obtaining a work log of a combustion device of an aluminum melting furnace, and obtaining various historical combustion control schemes that enable the furnace body to burn to the melting temperature according to the work log; Obtain design drawing information of the aluminum melting furnace combustion equipment, and construct a simulation system of the aluminum melting furnace combustion equipment according to the design drawing information and the name and weight ratio of the aluminum material to be smelted in combination with simulation software; Based on various historical combustion control schemes, the aluminum melting furnace combustion equipment simulation system is controlled to simulate combustion, and the predicted furnace characteristic parameter set of the furnace body from the beginning of smelting to the melting temperature is obtained, and the predicted chemical composition of the aluminum liquid after the melting temperature is reached; Acquire production requirement information of aluminum liquid, and determine the target chemical composition of the aluminum liquid according to the production requirement information; calculate the Pierce correlation coefficient between the predicted chemical composition and the target chemical composition based on the Pierce correlation coefficient algorithm; If the Pierce correlation coefficient between a certain predicted chemical composition and the target chemical composition is greater than a preset coefficient threshold, the historical combustion control scheme corresponding to the predicted chemical composition is used as a recommended combustion control scheme, and a predicted furnace characteristic parameter set corresponding to the recommended combustion control scheme is obtained; The recommended combustion control scheme and its corresponding predicted furnace characteristic parameter set are transmitted to a preset terminal.

3. The control method of a combustion equipment of an aluminum melting furnace according to claim 1, characterized in that: According to the actual furnace characteristic parameter set and the sub-prediction furnace characteristic parameter set, the furnace characteristic parameter drift of the aluminum melting furnace combustion equipment within the preset working time period is evaluated, specifically: Constructing timestamps of the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set, and calculating the similarity between the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set by using dynamic time warping; If the similarity between the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set is greater than the preset similarity, it means that the furnace body characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period are in a normal state; If the similarity between the actual furnace body characteristic parameter set and the sub-prediction furnace body characteristic parameter set is not greater than the preset similarity, it means that the furnace body characteristic parameters of the aluminum melting furnace combustion equipment within the preset working time period are in a drift state.

4. The control method of a combustion equipment of an aluminum melting furnace according to claim 1, characterized in that: Obtain the pre-fault characteristic parameters and the fault characteristic parameters of the aluminum melting furnace combustion equipment, and construct a dynamic Bayesian network model according to the pre-fault characteristic parameters and the fault characteristic parameters, specifically: Obtaining a work log of the aluminum melting furnace combustion equipment, and obtaining various historical fault events of the aluminum melting furnace combustion equipment according to the work log; Obtain the historical combustion working parameters of the aluminum melting furnace combustion equipment when various historical fault events occur, which are defined as fault characteristic parameters; and obtain the historical combustion working parameters of the aluminum melting furnace combustion equipment before various historical fault events occur, which are defined as pre-fault characteristic parameters; Iteratively calculate the fault characteristic parameters based on the FCM algorithm to obtain the membership of the fault characteristic parameters, and construct a fault characteristic membership matrix according to the membership of the fault characteristic parameters; and performing iterative calculations on the pre-fault characteristic parameters based on the FCM algorithm to obtain the membership of the pre-fault characteristic parameters, and constructing a pre-fault characteristic membership matrix according to the membership of the pre-fault characteristic parameters; Construct a dynamic Bayesian network and define the variables in the network, including pre-fault characteristics and fault characteristics; Introduction Baum-Welch algorithm, and set the number of iterations, estimate the state transition probability and maximum likelihood between each pre-fault characteristic parameter and the fault characteristic parameter according to the fault characteristic membership matrix and the pre-fault characteristic membership matrix combined with Baum-Welch algorithm; When the maximum likelihood is greater than a preset likelihood threshold, the iteration is stopped, the state transition probability between each pre-fault characteristic parameter and the fault characteristic parameter is output, and a state transition probability matrix is ​​generated according to the state transition probability between each pre-fault characteristic parameter and the fault characteristic parameter; The state transition probability matrix is ​​introduced into the dynamic Bayesian network for back-propagation learning until the loss function gradually decreases and is less than a preset convergence value, the final learning parameters are saved, and the dynamic Bayesian network model is output.

5. The control method of a combustion equipment of an aluminum melting furnace according to claim 1, characterized in that: The real-time combustion working parameter set of the aluminum furnace combustion equipment is imported into the dynamic Bayesian network model for prediction, and the aluminum furnace combustion equipment is regulated and processed according to the prediction results, specifically: The real-time combustion working parameter set of the aluminum furnace combustion equipment is imported into the dynamic Bayesian network model for prediction, and the transition probability of the aluminum furnace combustion equipment transitioning to the fault characteristic state is obtained; If the probability of the aluminum furnace combustion equipment transitioning to the fault characteristic state is greater than a preset probability value, the aluminum furnace combustion equipment is controlled to shut down and a fault alarm is generated; If the probability of the aluminum furnace combustion equipment transitioning to the fault state is not greater than the preset probability value, then various real-time furnace body characteristic parameters of the aluminum melting furnace combustion equipment at the current time node are obtained, and various predicted furnace body characteristic parameters of the aluminum melting furnace combustion equipment at the current time node are obtained; Calculate the parameter differences between various real-time furnace characteristic parameters and predicted furnace characteristic parameters, and only extract the real-time furnace characteristic parameters whose parameter differences are greater than a preset difference threshold, which are defined as drift furnace characteristic parameters of the aluminum melting furnace combustion equipment; Obtaining a parameter difference between the drift furnace body characteristic parameter and the predicted furnace body characteristic parameter to obtain a drift value of the drift furnace body characteristic parameter; The corresponding real-time combustion working parameters of the aluminum melting furnace combustion equipment are regulated and processed according to the drift value of the drift furnace body characteristic parameter.

6. The control method of a combustion equipment of an aluminum melting furnace according to claim 5, characterized in that: According to the drift value of the drift furnace characteristic parameter, the corresponding real-time combustion working parameters of the aluminum melting furnace combustion equipment are regulated and processed, specifically: Formulate in advance the preset control scheme of the aluminum melting furnace combustion equipment under various drift value conditions after the various furnace characteristic parameters in the aluminum melting furnace combustion equipment drift; Construct a knowledge graph, and import the preset control schemes of the aluminum melting furnace combustion equipment under various drift value conditions into the knowledge graph to generate a feature knowledge graph; Obtaining the drift value of the drift furnace body characteristic parameter in the aluminum melting furnace combustion equipment, importing the drift value of the drift furnace body characteristic parameter into the characteristic knowledge graph for matching, and matching to obtain a corresponding preset control scheme; The matched preset control scheme is transmitted to the control terminal of the aluminum melting furnace combustion equipment to control the aluminum melting furnace combustion equipment.

7. A control device for a combustion device of an aluminum melting furnace, characterized in that: The control device includes a memory and a processor, wherein the memory stores a control method program for an aluminum melting furnace combustion equipment. When the control method program for the aluminum melting furnace combustion equipment is executed by the processor, the control method steps for the aluminum melting furnace combustion equipment as described in any one of claims 1 to 6 are implemented.

Images