Unmanned iron mixing monitoring method and device for converter hot-metal bottle based on artificial intelligence

Abstract

The invention provides a converter hot-metal ladle unmanned iron blending monitoring method and device based on artificial intelligence, and the method comprises the steps: obtaining historical image data of a converter hot-metal ladle iron blending process, the historical image data comprising normal iron blending image data and abnormal iron blending image data; performing labeling and feature extraction on the historical image data; establishing a database based on the extracted features, and training an iron exchange monitoring model by using the database; and deploying the trained iron exchange monitoring model in an actual production environment, carrying out real-time monitoring on an unmanned iron exchange process, and providing an iron exchange process and an alarm prompt. Various states in the iron blending process are monitored in real time through the artificial model, normal / abnormal iron blending, the position relation between the molten iron tank and the converter, the rotating speed of the molten iron tank and the like are recognized, and an alarm is given out when abnormal conditions occur, so that safety accidents are avoided, the safety of unmanned operation is guaranteed, and application and popularization of the unmanned iron blending technology of the converter are promoted.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence and steelmaking technology, and in particular to an artificial intelligence-based method and device for monitoring the unmanned iron addition in a converter molten iron tank. Background Art

[0002] At present, there is a great enthusiasm for the development of unmanned iron adding systems for converters, but they are rarely used in actual production. The main reasons are: first, high-temperature molten metal is involved, and safety is of utmost importance; second, in actual production, iron is often added to the outside of the converter when the molten iron ladle is lifted by a crane, but the severity of the situation varies; in addition, the unmanned iron adding systems that have been developed are unable to detect and deal with these abnormal situations in time due to the lack of a safety monitoring system or an imperfect monitoring system. Therefore, the safety of unmanned operation of converter iron adding is not guaranteed. As a result, the unmanned iron adding technology for converters has not been promoted so far. Summary of the invention

[0003] In view of this, the present invention provides an artificial intelligence-based method and device for unmanned iron addition monitoring of a converter iron molten ladle to solve at least one of the above-mentioned problems.

[0004] In order to achieve the above object, the present invention adopts the following scheme:

[0005] According to a first aspect of the present invention, there is provided a method for monitoring unmanned iron addition in a molten iron tank of a converter based on artificial intelligence, the method comprising: acquiring historical image data of the iron addition process in the molten iron tank of the converter, the historical image data comprising normal iron addition image data and abnormal iron addition image data; annotating and extracting features from the historical image data, the features comprising the degree of molten iron splashing, the relative position of the molten iron tank and the converter, the angular velocity of the molten iron tank rotation, the time when the molten iron starts to flow out, and the time when the molten iron ends to flow out; establishing a database based on the extracted features, and using the database to train an iron addition monitoring model, so that the iron addition monitoring model learns to identify and judge normal iron addition, abnormal iron addition, the start and end of molten iron outflow from the molten iron tank, the normal and abnormal positional relationship between the molten iron tank and the converter, and the normal and abnormal rotation speeds of the molten iron tank; deploying the trained iron addition monitoring model into an actual production environment, performing real-time monitoring of the unmanned iron addition process, and providing the iron addition process and alarm prompts.

[0006] As an embodiment of the present invention, the prompts of the iron adding process in the above method include: iron adding preparation stage, iron adding start stage and iron adding end stage; the alarm prompts include: severe molten iron splashing, excessive position deviation of the molten iron tank and excessive rotation speed of the molten iron tank.

[0007] As an embodiment of the present invention, the above method also includes: based on the normal iron-adding image data in the historical image data, using a single-classification support vector machine algorithm to train an abnormality recognition model to identify abnormal iron-adding situations that do not appear in the abnormal iron-adding image data.

[0008] As an embodiment of the present invention, the single-class support vector machine algorithm in the above method adopts a radial basis kernel function, and optimizes the kernel parameter γ and the penalty parameter ν by a grid search or cross-validation method to determine the optimal anomaly recognition model.

[0009] As an embodiment of the present invention, the above method also includes: using sensors to obtain the weight, position, temperature and vibration data of the molten iron tank during the iron adding process of the converter molten iron tank, and based on the weight, position, temperature and vibration data of the molten iron tank and the monitoring results of the iron adding monitoring model, a comprehensive analysis of abnormal conditions in the iron adding process is performed.

[0010] As an embodiment of the present invention, the positional relationship between the molten iron ladle and the converter and the rotation speed of the molten iron ladle identified by the iron addition monitoring model in the above method are used for early warning, including: if the distance between the mouth of the molten iron ladle and the converter mouth exceeds a set threshold, a first early warning signal is issued; if the incremental speed of the rotation speed of the molten iron ladle exceeds a set threshold, a second early warning signal is issued.

[0011] According to a second aspect of the present invention, there is provided an unmanned iron addition monitoring device for a molten iron tank in a converter based on artificial intelligence, the device comprising: a historical data acquisition unit, for acquiring historical image data of the iron addition process of the molten iron tank in the converter, the historical image data comprising normal iron addition image data and abnormal iron addition image data; a feature extraction unit, for annotating and extracting features from the historical image data, the features comprising the degree of molten iron splashing, the relative position of the molten iron tank and the converter, the angular velocity of the molten iron tank, the time when the molten iron starts to flow out, and the time when the molten iron ends to flow out; a model training unit, for establishing a database based on the extracted features, and using the database to train an iron addition monitoring model, so that the iron addition monitoring model learns to identify and judge normal iron addition, abnormal iron addition, the start and end of molten iron outflow from the molten iron tank, the normal and abnormal positional relationship between the molten iron tank and the converter, and the normal and abnormal rotation speeds of the molten iron tank; a model deployment unit, for deploying the trained iron addition monitoring model into an actual production environment, for real-time monitoring of the unmanned iron addition process, and providing the iron addition process and alarm prompts.

[0012] As an embodiment of the present invention, the prompts of the above-mentioned iron adding process include: iron adding preparation stage, iron adding start stage and iron adding end stage; the alarm prompts include: severe molten iron splashing, excessive position deviation of the molten iron tank and excessive rotation speed of the molten iron tank.

[0013] As an embodiment of the present invention, the above-mentioned device also includes: an abnormality recognition unit, which is used to train an abnormality recognition model based on the normal iron-adding image data in the historical image data using a single-classification support vector machine algorithm to identify abnormal iron-adding situations that do not appear in the abnormal iron-adding image data.

[0014] As an embodiment of the present invention, the above-mentioned single-classification support vector machine algorithm adopts a radial basis kernel function, and optimizes the kernel parameter γ and the penalty parameter ν by a grid search or cross-validation method to determine the optimal anomaly recognition model.

[0015] According to one embodiment of the present invention, the above-mentioned device also includes: a sensor unit, which is used to obtain the weight, position, temperature and vibration data of the molten iron tank during the iron adding process of the converter molten iron tank by using a sensor; and a comprehensive analysis unit, which is used to conduct a comprehensive analysis of abnormal conditions in the iron adding process based on the weight, position, temperature and vibration data of the molten iron tank and the monitoring results of the iron adding monitoring model.

[0016] According to one embodiment of the present invention, the above-mentioned device also includes an early warning unit for issuing an early warning based on the positional relationship between the molten iron ladle and the converter and the rotation speed of the molten iron ladle identified by the iron addition monitoring model, including: if the distance between the mouth of the molten iron ladle and the converter mouth exceeds a set threshold, issuing a first early warning signal; if the incremental speed of the rotation speed of the molten iron ladle exceeds the set threshold, issuing a second early warning signal.

[0017] According to a third aspect of the present invention, there is provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0018] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0019] According to a fifth aspect of the present invention, there is provided a computer program product, comprising a computer program / instructions, which implement the steps of the above method when executed by a processor.

[0020] It can be seen from the above technical scheme that the artificial intelligence-based converter molten iron tank unmanned iron addition monitoring method and device provided by the present invention monitors various states of the iron addition process in real time through an artificial model, identifies normal / abnormal iron addition, the positional relationship between the molten iron tank and the converter, the rotation speed of the molten iron tank, etc., and issues an alarm when an abnormal situation occurs, thereby avoiding safety accidents and ensuring the safety of unmanned operation. It fills the gap of the existing unmanned iron addition system lacking a complete monitoring system and promotes the promotion and application of unmanned iron addition technology for converters. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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. In the drawings:

[0022] Figure 1 It is a flow chart of an unmanned iron addition monitoring method for a converter iron molten ladle based on artificial intelligence provided by an embodiment of the present application;

[0023] Figure 2 It is a flow chart of an unmanned iron addition monitoring method for a converter molten iron tank based on artificial intelligence provided by another embodiment of the present application;

[0024] Figure 3 It is a flow chart of an unmanned iron addition monitoring method for a converter molten iron tank based on artificial intelligence provided by another embodiment of the present application;

[0025] Figure 4 It is a structural schematic diagram of an unmanned iron addition monitoring device for a converter molten iron tank based on artificial intelligence provided in an embodiment of the present application;

[0026] Figure 5 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0028] like Figure 1 The figure shows a flow chart of an unmanned iron addition monitoring method for a converter molten iron tank based on artificial intelligence provided by an embodiment of the present application, the method comprising the following steps:

[0029] Step S101: acquiring historical image data of the iron adding process of the converter molten iron tank, wherein the historical image data includes normal iron adding image data and abnormal iron adding image data.

[0030] The historical image data here mainly consists of a large number of videos of the process of adding iron to the converter molten iron ladle recorded by high-definition cameras, and then image data is extracted from the videos. The historical image data collected here should include two categories: normal iron adding image data and abnormal iron adding image data. The normal iron adding image data includes the picture of molten iron flowing smoothly into the converter with only a small amount of iron flowers splashing; the abnormal iron adding image data includes the picture of abnormal conditions such as splashing and spilling of flowing molten iron, abnormal position of the molten iron ladle, and excessive rotation speed.

[0031] In order to ensure the training effect of the subsequent iron monitoring model, this step requires the collection of enough data samples, covering all possible normal and abnormal situations. At the same time, the collected image data is stored according to normal and abnormal classification for subsequent annotation and feature extraction.

[0032] Step S102: annotating and extracting features from the historical image data, wherein the features include the degree of molten iron splashing, the relative position of the molten iron ladle and the converter, the angular velocity of the molten iron ladle, the time when the molten iron starts to flow out, and the time when the molten iron stops flowing out.

[0033] Here, the annotation of historical image data can be done manually or by a semi-automatic annotation method that uses a pre-trained model for preliminary annotation and then manual assistance correction. Because there are currently no mature artificial intelligence applications in the field of unmanned iron addition in the converter molten iron tank, and for things like "normal iron addition" and "abnormal iron addition", certain professional knowledge and judgment are required. Therefore, using manual annotation or manual assisted annotation to annotate the training data is a reliable method to ensure the quality of annotation. In addition to the labels of "normal iron addition" and "abnormal iron addition", you can also annotate "molten iron in the molten iron tank begins to flow out", "molten iron in the molten iron tank is poured out", "normal position relationship between the molten iron tank and the converter", "abnormal position relationship between the molten iron tank and the converter", "normal rotation speed of the molten iron tank" and "abnormal rotation speed of the molten iron tank". Among them:

[0034] “Iron starts to flow out of the ladle”: marks the moment when molten iron starts to flow out of the ladle.

[0035] "The molten iron in the molten iron tank is finished": marks the moment when the molten iron stops flowing out and the iron addition is completed.

[0036] “Normal position relationship between the molten iron ladle and the converter”: Mark the state of the molten iron ladle mouth protruding into the converter mouth.

[0037] “Abnormal position relationship between the molten iron ladle and the converter”: marks the state where the mouth of the molten iron ladle does not extend into the converter mouth.

[0038] “Normal iron ladle rotation speed”: indicates that the iron ladle rotation speed is appropriate and there is no or little molten iron spilling.

[0039] “Abnormal iron ladle rotation speed”: indicates that the iron ladle rotates too fast and a large amount of iron is spilled outside the converter.

[0040] The feature extraction in this step refers to extracting the following features from the annotated historical image data:

[0041] “Extent of molten iron splashing”: quantify the extent of molten iron splashing, such as splashing area, splashing height, etc. through image analysis technology.

[0042] "Relative position of the molten iron ladle and converter": measure the distance and angle between the molten iron ladle mouth and the converter mouth to determine whether the position relationship is normal.

[0043] “Angular velocity of the molten iron ladle rotation (ω)”: By identifying the angular change (Δθ) and the corresponding time (Δt) of the molten iron ladle rotation in continuous images, the angular velocity ω = Δθ / Δt is calculated.

[0044] “Moment when molten iron starts to flow out”: marks the time point when molten iron starts to flow out of the molten iron tank.

[0045] “Moment when molten iron stops flowing out”: marks the time point when molten iron stops flowing out.

[0046] Step S103: Establish a database based on the extracted features, and use the database to train an iron addition monitoring model, so that the iron addition monitoring model learns to identify and judge normal iron addition, abnormal iron addition, the beginning and end of the molten iron flow out of the molten iron tank, the normal and abnormal positional relationship between the molten iron tank and the converter, and the normal and abnormal rotation speed of the molten iron tank.

[0047] The extracted feature data and corresponding image labels are stored in the database to form a training data set, and then a suitable AI model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), or a Transformer, is selected for the training of the iron ore monitoring model. During the model training process, the performance of the model is continuously optimized by adjusting model parameters, increasing training data, etc., to improve the accuracy of identifying abnormal situations.

[0048] Through the above training, the iron addition monitoring model of the present application learns the relationship between different features and different iron addition situations. In addition to giving the judgment of "normal iron addition / abnormal iron addition", it can also give various situations corresponding to normal iron addition or abnormal iron addition. For example, when the angular velocity of the molten iron tank rotates too fast and the degree of molten iron splashing is very high, it can correspond to "abnormal iron addition-too fast rotation speed", or when the mouth of the molten iron tank does not extend into the converter furnace mouth, it corresponds to "abnormal iron addition-abnormal position" and so on.

[0049] Step S104: deploy the trained iron exchange monitoring model to the actual production environment, monitor the unmanned iron exchange process in real time and provide the iron exchange process and alarm prompts.

[0050] The trained iron mixing monitoring model is deployed to the hardware equipment in the actual production environment, such as industrial computers or embedded devices. At the same time, the image data of the iron mixing process is collected in real time using high-definition cameras and input into the deployed AI model for analysis. Finally, the key parameters of the iron mixing process, such as the rotation angle of the molten iron tank and the degree of iron splashing, can be displayed in real time on the system interface to facilitate operator monitoring.

[0051] Preferably, the prompts of the above-mentioned iron adding process include: the iron adding preparation stage, the iron adding start stage and the iron adding end stage; and the warning prompts include: severe molten iron splashing, excessive deviation of the position of the molten iron tank and excessive rotation speed of the molten iron tank. When the iron adding monitoring model detects an abnormal situation, it immediately sends out an audible and visual alarm signal, and displays information such as the abnormal type, danger level, and handling suggestions to remind the operator to take timely measures. For example, if it is detected that the molten iron tank is rotating too fast, an alarm of "the molten iron tank is rotating too fast" is issued, and it is recommended to "slow down the speed".

[0052] It can be seen from the above technical scheme that the artificial intelligence-based converter molten iron tank unmanned iron addition monitoring method and device provided by the present invention monitors various states of the iron addition process in real time through an artificial model, identifies normal / abnormal iron addition, the positional relationship between the molten iron tank and the converter, the rotation speed of the molten iron tank, etc., and issues an alarm when an abnormal situation occurs, thereby avoiding safety accidents and ensuring the safety of unmanned operation. It fills the gap of the existing unmanned iron addition system lacking a complete monitoring system and promotes the promotion and application of unmanned iron addition technology for converters.

[0053] The above-mentioned converter iron ladle unmanned iron addition monitoring method can detect abnormal situations in the iron addition process in the historical image data when the amount of training data is sufficient. However, when it is difficult to collect enough abnormal image data samples, the above-mentioned iron addition monitoring model may miss the situation. In addition, since the converter iron ladle unmanned iron addition process itself has a wide variety of abnormal situations, in order to increase the reliability of the final monitoring results, such as Figure 2 As shown, the artificial intelligence-based unmanned iron addition monitoring method for a converter molten iron tank of the present application may include the following steps:

[0054] Step S201: Acquire historical image data of the iron adding process of the converter molten iron tank, wherein the historical image data includes normal iron adding image data and abnormal iron adding image data.

[0055] Step S202: annotating and extracting features from the historical image data, wherein the features include the degree of molten iron splashing, the relative position of the molten iron ladle and the converter, the angular velocity of the molten iron ladle, the time when the molten iron starts to flow out, and the time when the molten iron stops flowing out.

[0056] Step S203: Establish a database based on the extracted features, and use the database to train an iron addition monitoring model, so that the iron addition monitoring model learns to identify and judge normal iron addition, abnormal iron addition, the beginning and end of the molten iron flow out of the molten iron tank, the normal and abnormal positional relationship between the molten iron tank and the converter, and the normal and abnormal rotation speed of the molten iron tank.

[0057] The above steps S201-S203 are the same as steps S101-S103 in the aforementioned embodiment, and will not be further described here.

[0058] Step S204: Based on the normal iron-adding image data in the historical image data, a single-class support vector machine algorithm (One-Class SVM) is used to train an abnormality recognition model to identify abnormal iron-adding situations that do not appear in the abnormal iron-adding image data.

[0059] This step is performed simultaneously with S202 and S203. The difference from step S202 and step S203 is that this step only uses the normal iron-mixing image data in the historical image data. The purpose of this step is to identify abnormal iron-mixing situations that have not appeared in the abnormal iron-mixing image data.

[0060] The single-class support vector machine is an anomaly detection algorithm. It does not identify anomalies by learning abnormal samples, but by learning the characteristics of normal iron-to-iron data to build a model that describes the normal iron-to-iron state. This model can be regarded as a boundary surrounding normal data points. During the training process, the single-class support vector machine algorithm will try to find a hyperplane that includes as many normal iron-to-iron data points as possible, while minimizing the area outside the hyperplane. This hyperplane defines the boundary of "normal" iron-to-iron. When new iron-to-iron data arrives, if the data point falls within the hyperplane (that is, within the boundary), it is considered to be normal iron-to-iron; if the data point falls outside the hyperplane, it is considered to be abnormal iron-to-iron, even if this abnormal situation has never appeared in the training data. Therefore, the single-class support vector machine can be trained to identify abnormal situations based only on normal iron-to-iron data.

[0061] Further preferably, the above-mentioned single-classification support vector machine algorithm adopts a radial basis kernel function, and optimizes the kernel parameter γ and the penalty parameter ν by a grid search or cross-validation method to determine the optimal anomaly recognition model.

[0062] Single-class support vector machines can use different kernel functions to map data to high-dimensional space. The RBF kernel function is a commonly used kernel function that can effectively process nonlinearly separable data. The reason for selecting the RBF kernel function in this embodiment is that it has good generalization ability and flexibility and can adapt to various data distributions. The formula of the RBF kernel function is as follows:

[0063] K(x,y)=exp(-γ*||xy||2)

[0064] Where x and y are two data points, ||xy||2 is the square of their Euclidean distance, and γ is the kernel parameter that controls the width of the RBF kernel function.

[0065] Kernel parameter γ (Gamma): The γ value determines the influence range of the RBF kernel function. A smaller γ value indicates a larger influence range, and the model will be smoother and prone to underfitting; a larger γ value indicates a smaller influence range, and the model will be more complex and prone to overfitting. Therefore, choosing an appropriate γ value is crucial.

[0066] Penalty parameter ν (Nu): ν controls the sensitivity of the model to outliers. It indicates the upper limit of the proportion of training data that is allowed to be considered as outliers, and also indicates the lower limit of the proportion of support vectors. A smaller ν value means that the model is more sensitive to outliers and is prone to misclassifying normal data points as abnormal; a larger ν value means that the model is more tolerant to outliers and is prone to misclassifying abnormal data points as normal.

[0067] The grid search in this step is a hyperparameter optimization method that finds the best parameter value by trying different parameter combinations. For OC-SVM, you can use grid search to try different γ and ν values ​​and select the best combination based on the performance of the model.

[0068] Cross-validation is a model evaluation method that divides the data set into multiple subsets, uses one of the subsets as the test set and the remaining subsets as the training set in turn, and the final performance indicator is the average of multiple test results. Cross-validation can more accurately evaluate the generalization ability of the model and avoid overfitting.

[0069] Specifically, the above optimization process is as follows:

[0070] 1) Select RBF kernel function: First, determine to use RBF kernel function as the kernel function of One-Class SVM.

[0071] 2) Define parameter range: Define a reasonable search range for γ and ν. For example, you can set the range of γ to [0.001, 1000] and the range of ν to [0.01, 0.5].

[0072] 3) Grid search or cross validation: Use grid search or cross validation methods to try different combinations of γ and ν within the defined parameter range. For each combination, train an OC-SVM model and evaluate its performance using cross validation.

[0073] 4) Selecting the best parameters: Select the best performing values ​​of γ and ν and use these values ​​to train the final anomaly recognition model.

[0074] Through this optimization method, the optimal kernel parameter γ and penalty parameter ν can be found, thereby improving the accuracy and generalization ability of the One-ClassSVM model, enabling it to more effectively identify abnormal iron-adding situations that do not appear in the abnormal iron-adding image data.

[0075] Step S205: deploy the trained iron exchange monitoring model and the abnormality recognition model into the actual production environment, conduct real-time monitoring of the unmanned iron exchange process, and provide information about the iron exchange process and alarm prompts.

[0076] Different from the above step S204, this step uses both the iron exchange monitoring model and the abnormality recognition model to monitor the unmanned iron exchange process in real time and provide the iron exchange process and alarm prompts. This involves the comprehensive use of two models. In this embodiment, the master-slave collaboration mode can be used for monitoring:

[0077] Main model (iron addition monitoring model): This model is trained based on normal and abnormal iron addition data, and is mainly responsible for identifying known normal and abnormal iron addition situations, such as molten iron splashing, abnormal position relationship, and excessive speed. It can classify the current iron addition situation and determine whether an alarm is needed based on the preset threshold. For example, if the degree of molten iron splashing exceeds the threshold, an alarm of "abnormal iron addition-severe splashing" is issued.

[0078] Auxiliary model (abnormal identification model - OC-SVM): This model is trained only on normal iron exchange data and is mainly responsible for identifying unknown abnormal situations, that is, those abnormal situations that have not appeared in the training data. It learns the normal iron exchange pattern and determines whether the current iron exchange situation deviates from the normal pattern. If the degree of deviation exceeds a certain threshold, an "unknown abnormality" alarm is issued.

[0079] Collaborative work: The two models analyze the real-time camera images at the same time and perform collaborative analysis according to the following three situations:

[0080] Case 1: The main model identifies a known abnormality. If the main model identifies a known abnormality, such as "abnormal iron mixing - severe splashing", it will directly issue a corresponding alarm and take corresponding measures according to the preset strategy, such as stopping the iron mixing operation. At this time, the output of the auxiliary model can be used as a reference, but it does not play a decisive role.

[0081] Case 2: The primary model does not identify an abnormality, but the auxiliary model does. If the primary model believes that the current iron exchange situation is normal, but the auxiliary model identifies a large deviation from the normal pattern, an "unknown abnormality" alarm will be issued to prompt the operator to pay attention and conduct further inspections. This can serve as an additional safety guarantee to prevent unknown risks.

[0082] Case 3: Both models do not identify anomalies. If both models believe that the current iron exchange situation is normal, the iron exchange operation will continue.

[0083] From the above, it can be seen that this collaborative working mode can combine the advantages of the two models to improve the reliability and safety of the system. The main model is responsible for identifying known anomalies, and the auxiliary model is responsible for identifying unknown anomalies, thereby covering a more comprehensive range of abnormal situations, realizing comprehensive monitoring of the unmanned iron-adding process, and ultimately promoting the popularization and application of unmanned iron-adding technology for converters.

[0084] The above embodiments discuss the method of using the iron monitoring model and the abnormality recognition model for monitoring. However, relying solely on image information may be limited by some environmental factors, such as lighting changes, camera occlusion, etc. Therefore, in order to improve the reliability and robustness of the system, the embodiments of the present application further consider the solution of multi-model fusion, combining the image recognition model (iron monitoring model) with the sensor-based model. Specifically, Figure 3 As shown, the unmanned iron addition monitoring method for a converter molten iron tank based on artificial intelligence in this embodiment may include the following steps:

[0085] Step S301: acquiring historical image data of the iron adding process of the converter molten iron tank, wherein the historical image data includes normal iron adding image data and abnormal iron adding image data.

[0086] Step S302: annotating and extracting features from the historical image data, wherein the features include the degree of molten iron splashing, the relative position of the molten iron ladle and the converter, the angular velocity of the molten iron ladle, the time when the molten iron starts to flow out, and the time when the molten iron stops flowing out.

[0087] Step S303: Establish a database based on the extracted features, and use the database to train an iron addition monitoring model, so that the iron addition monitoring model learns to identify and judge normal iron addition, abnormal iron addition, the beginning and end of the molten iron flow out of the molten iron tank, the normal and abnormal positional relationship between the molten iron tank and the converter, and the normal and abnormal rotation speed of the molten iron tank.

[0088] The above steps S301-S303 are the same as steps S101-S103 in the above embodiment, and will not be further described here.

[0089] Step S304: deploy the trained iron addition monitoring model and the abnormality recognition model into the actual production environment, and use sensors to obtain the weight, position, temperature and vibration data of the molten iron tank during the iron addition process of the converter iron tank, and based on the weight, position, temperature and vibration data of the molten iron tank and the monitoring results of the iron addition monitoring model, conduct a comprehensive analysis of the abnormal conditions in the iron addition process, and according to the analysis results, conduct real-time monitoring of the unmanned iron addition process and provide iron addition process and alarm prompts.

[0090] Unlike step S104, this step also uses sensor data for comprehensive analysis when actually monitoring the iron mixing process. Image data can intuitively reflect the macroscopic situation in the iron mixing process, such as molten iron splashing, positional relationship, etc. Sensor data can provide more detailed and quantitative information, such as weight change, temperature change, vibration amplitude, etc. Some abnormal conditions may not be easy to detect in image data, but can be reflected by sensor data. For example, abnormal vibration inside the molten iron tank may indicate damage or failure of certain components, even if there is no obvious abnormal performance in the image. Through comprehensive analysis, these potential abnormalities can be discovered early, and measures can be taken in time to avoid accidents. Therefore, this embodiment combines the two for comprehensive analysis, which can more comprehensively and accurately judge the abnormal conditions in the iron mixing process and reduce false alarms and missed reports. In addition, combined with sensor data, more abundant alarm information can be provided, such as "molten iron tank temperature is too high", "abnormal vibration", etc., to help operators judge the type and severity of abnormalities faster and more accurately, and take corresponding measures.

[0091] The sensor data here include the weight, position, temperature and vibration data of the molten iron tank, and the corresponding sensors are weight sensor, position sensor, temperature sensor and vibration sensor. Among them, the weight sensor can monitor the weight change of the molten iron tank in real time, so as to more accurately judge the molten iron outflow status and end time, and avoid the image recognition model from misjudging that iron is being added after the molten iron has run out. The position sensor can accurately measure the relative position of the molten iron tank and the converter, and make up for the error in position judgment of image recognition, especially when the camera viewing angle is limited or the picture is blurred. The temperature sensor can monitor the temperature of the molten iron, and can determine whether the molten iron has reached the predetermined temperature, and whether there are abnormal conditions such as overheating. The vibration sensor can monitor the vibration of the molten iron tank and the converter, and can determine whether there are abnormal conditions such as splashing and spilling of molten iron, and serve as a supplement and verification of the image recognition model.

[0092] The comprehensive analysis method in this step can be implemented in a variety of ways, such as setting thresholds, weighted average or logical judgment. Setting thresholds refers to setting thresholds for the output results of the sensor data and the iron addition monitoring model respectively. If any data source exceeds the threshold, an alarm will be triggered. For example, if the iron addition monitoring model identifies that the molten iron splashes severely, or the sensor detects that the molten iron tank vibrates violently, an alarm will be triggered and the iron addition operation will be stopped. Weighted average refers to assigning different weights to the sensor data and the output results of the iron addition monitoring model based on experience or experimental results, and then performing weighted average to obtain a comprehensive score, and judging whether to trigger an alarm based on the comprehensive score. Logical judgment refers to designing more complex logical judgment rules based on the output results of the sensor data and the iron addition monitoring model. For example, if the iron addition monitoring model identifies that the position of the molten iron tank is abnormal, and the sensor detects that the weight of the molten iron tank suddenly drops, it is judged that the molten iron tank is tilted too much and an alarm is triggered.

[0093] As can be seen from the above, the artificial intelligence-based converter molten iron tank unmanned iron addition monitoring method provided by the present invention can more comprehensively identify and judge various abnormal situations, including molten iron splashing, abnormal position relationship, excessive speed, abnormal weight, abnormal temperature, and abnormal vibration, etc. Once an abnormality is found, the system will immediately issue an alarm to prompt the operator to take measures to avoid accidents and ensure production safety.

[0094] The artificial intelligence-based unmanned converter iron tank iron addition monitoring methods in the above-mentioned embodiments can only provide an alarm function after an abnormality occurs. However, if an early warning function can be provided during the monitoring process, the safety of production can be further improved, accidents can be further avoided, and the safety of production can be further guaranteed. Figure 1 and Figure 3 In the corresponding embodiment, when the iron addition monitoring model is used for actual monitoring, the following steps may also be included: issuing an early warning based on the positional relationship between the molten iron ladle and the converter and the rotation speed of the molten iron ladle identified by the iron addition monitoring model, including: if the distance between the mouth of the molten iron ladle and the converter furnace mouth exceeds a set threshold, issuing a first early warning signal; if the incremental speed of the rotation speed of the molten iron ladle exceeds a set threshold, issuing a second early warning signal.

[0095] Through the above steps, this embodiment can give an early warning before the abnormality occurs, thereby avoiding the occurrence of the abnormality, and thus directly avoiding the occurrence of related accidents, so that the unmanned iron addition technology of the converter can be promoted and applied.

[0096] like Figure 4The structure diagram of an unmanned converter iron tank iron addition monitoring device based on artificial intelligence provided by an embodiment of the present application is shown, and the device includes: a historical data acquisition unit 410, a feature extraction unit 420, a model training unit 430 and a model deployment unit 440, which are connected in sequence. Among them:

[0097] The historical data acquisition unit 410 is used to acquire historical image data of the iron adding process of the converter molten iron tank, wherein the historical image data includes normal iron adding image data and abnormal iron adding image data.

[0098] The feature extraction unit 420 is used to annotate and extract features from the historical image data, wherein the features include the degree of molten iron splashing, the relative position of the molten iron ladle and the converter, the angular velocity of the molten iron ladle, the time when the molten iron starts to flow out, and the time when the molten iron stops flowing out.

[0099] The model training unit 430 is used to establish a database based on the extracted features, and use the database to train the iron addition monitoring model, so that the iron addition monitoring model can learn to identify and judge normal iron addition, abnormal iron addition, the beginning and end of the molten iron flow out of the molten iron tank, the normal and abnormal positional relationship between the molten iron tank and the converter, and the normal and abnormal rotation speed of the molten iron tank.

[0100] The model deployment unit 440 is used to deploy the trained iron exchange monitoring model into the actual production environment, to monitor the unmanned iron exchange process in real time and to provide the iron exchange process and alarm prompts.

[0101] Preferably, the prompts of the above-mentioned iron adding process include: iron adding preparation stage, iron adding start stage and iron adding end stage; the alarm prompts include: severe molten iron splashing, excessive position deviation of the molten iron tank and excessive speed of the molten iron tank.

[0102] Preferably, the above-mentioned device also includes: an abnormality recognition unit, which is used to train an abnormality recognition model based on the normal iron-adding image data in the historical image data using a single-classification support vector machine algorithm to identify abnormal iron-adding situations that do not appear in the abnormal iron-adding image data.

[0103] As an embodiment of the present invention, the above-mentioned single-classification support vector machine algorithm adopts a radial basis kernel function, and optimizes the kernel parameter γ and the penalty parameter ν by a grid search or cross-validation method to determine the optimal anomaly recognition model.

[0104] Preferably, the above-mentioned device also includes: a sensor unit, which is used to obtain the weight, position, temperature and vibration data of the molten iron tank during the iron adding process of the converter molten iron tank by using a sensor, and a comprehensive analysis unit, which is used to conduct a comprehensive analysis of abnormal conditions in the iron adding process based on the weight, position, temperature and vibration data of the molten iron tank and the monitoring results of the iron adding monitoring model.

[0105] Preferably, the above-mentioned device also includes an early warning unit for issuing an early warning based on the positional relationship between the molten iron ladle and the converter and the rotation speed of the molten iron ladle identified by the iron addition monitoring model, including: if the distance between the mouth of the molten iron ladle and the converter furnace mouth exceeds a set threshold, a first early warning signal is issued; if the incremental speed of the rotation speed of the molten iron ladle exceeds the set threshold, a second early warning signal is issued.

[0106] The detailed description of each of the above units can be found in the corresponding description in the aforementioned method embodiment, which will not be further elaborated here.

[0107] It can be seen from the above technical scheme that the artificial intelligence-based converter molten iron tank unmanned iron addition monitoring device provided by the present invention monitors various states of the iron addition process in real time through an artificial model, identifies normal / abnormal iron addition, the positional relationship between the molten iron tank and the converter, the rotation speed of the molten iron tank, etc., and issues an alarm when an abnormal situation occurs, thereby avoiding safety accidents and ensuring the safety of unmanned operation. It fills the gap of the existing unmanned iron addition system lacking a complete monitoring system and promotes the popularization and application of converter unmanned iron addition technology.

[0108] Figure 5 is a schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 5 The electronic device shown is a general data processing device, which includes a general computer hardware structure, which at least includes a processor 801 and a memory 802. The processor 801 and the memory 802 are connected via a bus 803. The memory 802 is suitable for storing one or more instructions or programs executable by the processor 801. The one or more instructions or programs are executed by the processor 801 to implement the steps in the above-mentioned artificial intelligence-based converter iron ladle unmanned iron addition monitoring method.

[0109] The processor 801 may be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 801 executes the commands stored in the memory 802 to execute the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 803 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 804 and the display device and the input / output (I / O) device 805. The input / output (I / O) device 805 may be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output (I / O) device 805 is connected to the system via an input / output (I / O) controller 806.

[0110] The memory 802 may store software components such as an operating system, a communication module, an interaction module, and an application program. Each of the modules and applications described above corresponds to a set of executable program instructions that implement one or more functions and methods described in the embodiments of the invention.

[0111] An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based unmanned iron addition monitoring method for a converter iron molten ladle are implemented.

[0112] An embodiment of the present invention also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned artificial intelligence-based converter iron tank unmanned iron addition monitoring method.

[0113] In summary, the artificial intelligence-based converter molten iron tank unmanned iron addition monitoring method and device provided by the present invention monitors various states of the iron addition process in real time through an artificial model, identifies normal / abnormal iron addition, the positional relationship between the molten iron tank and the converter, the rotation speed of the molten iron tank, etc., and issues an alarm when an abnormal situation occurs, thereby avoiding safety accidents and ensuring the safety of unmanned operation. It fills the gap of the existing unmanned iron addition system lacking a complete monitoring system and promotes the popularization and application of converter unmanned iron addition technology.

[0114] The preferred embodiments of the present invention have been described above with reference to the accompanying drawings. Many features and advantages of these embodiments are clear from this detailed description, and therefore the claims are intended to cover all such features and advantages of these embodiments that fall within their true spirit and scope. In addition, since many modifications and changes are readily apparent to those skilled in the art, the embodiments of the present invention are not intended to be limited to the precise structure and operation illustrated and described, but all suitable modifications and equivalents that fall within their scope may be included.

[0115] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0119] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An artificial intelligence-based method for monitoring the unmanned iron addition in a converter molten iron tank, characterized in that: The method comprises: Acquire historical image data of the iron adding process of the converter molten iron tank, wherein the historical image data includes normal iron adding image data and abnormal iron adding image data; Annotating and extracting features from the historical image data, wherein the features include the degree of molten iron splashing, the relative position of the molten iron ladle and the converter, the angular velocity of the molten iron ladle, the time when the molten iron starts to flow out, and the time when the molten iron stops flowing out; A database is established based on the extracted features, and the database is used to train an iron addition monitoring model, so that the iron addition monitoring model learns to identify and judge normal iron addition, abnormal iron addition, the start and end of the iron outflow from the molten iron tank, the normal and abnormal positional relationship between the molten iron tank and the converter, and the normal and abnormal rotation speed of the molten iron tank; The trained iron exchange monitoring model is deployed in the actual production environment to monitor the unmanned iron exchange process in real time and provide iron exchange process and alarm prompts.

2. The unmanned iron addition monitoring method for a converter molten iron tank based on artificial intelligence as claimed in claim 1, characterized in that: The prompts of the iron adding process include: the iron adding preparation stage, the iron adding start stage and the iron adding end stage; the alarm prompts include: severe molten iron splashing, excessive deviation of the position of the molten iron tank and excessive speed of the molten iron tank.

3. The unmanned iron addition monitoring method for a converter molten iron tank based on artificial intelligence as claimed in claim 1, characterized in that: The method further includes: based on the normal iron-adding image data in the historical image data, using a single-classification support vector machine algorithm to train an abnormality recognition model to recognize abnormal iron-adding situations that do not appear in the abnormal iron-adding image data.

4. The unmanned iron addition monitoring method for a converter molten iron tank based on artificial intelligence as claimed in claim 3 is characterized in that: The single-class support vector machine algorithm adopts a radial basis kernel function and optimizes the kernel parameter γ and the penalty parameter ν by a grid search or cross-validation method to determine the optimal anomaly recognition model.

5. The unmanned iron addition monitoring method for a converter molten iron tank based on artificial intelligence as claimed in claim 1, characterized in that: The method also includes: using sensors to obtain the weight, position, temperature and vibration data of the molten iron tank during the iron adding process of the converter molten iron tank, and based on the weight, position, temperature and vibration data of the molten iron tank and the monitoring results of the iron adding monitoring model, comprehensively analyzing abnormal conditions in the iron adding process.

6. The unmanned iron addition monitoring method for a converter molten iron tank based on artificial intelligence as claimed in claim 1, characterized in that: The method also includes: issuing an early warning based on the positional relationship between the molten iron ladle and the converter and the rotation speed of the molten iron ladle identified by the iron addition monitoring model, including: issuing a first early warning signal if the distance between the mouth of the molten iron ladle and the converter furnace mouth exceeds a set threshold, and issuing a second early warning signal if the incremental speed of the rotation speed of the molten iron ladle exceeds a set threshold.

7. An unmanned iron addition monitoring device for a converter molten iron tank based on artificial intelligence, characterized in that: The device comprises: A historical data acquisition unit, used to acquire historical image data of the iron adding process of the converter molten iron tank, wherein the historical image data includes normal iron adding image data and abnormal iron adding image data; A feature extraction unit, used for annotating and extracting features from the historical image data, wherein the features include the degree of molten iron splashing, the relative position of the molten iron ladle and the converter, the angular velocity of the molten iron ladle, the time when the molten iron starts to flow out, and the time when the molten iron stops flowing out; A model training unit is used to establish a database based on the extracted features, and use the database to train an iron addition monitoring model, so that the iron addition monitoring model learns to identify and judge normal iron addition, abnormal iron addition, the start and end of the iron outflow from the molten iron tank, the normal and abnormal positional relationship between the molten iron tank and the converter, and the normal and abnormal rotation speed of the molten iron tank; The model deployment unit is used to deploy the trained iron exchange monitoring model into the actual production environment, to monitor the unmanned iron exchange process in real time and to provide iron exchange process and alarm prompts.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images