A direct current arc furnace and detection system

Abstract

The present application relates to the technical field of chemical detection data processing, and provides a direct current electric arc furnace and a detection system, which aims to solve the problem that the existing direct current electric arc furnace cannot detect the chemical substances in the furnace in real time, resulting in the inability to timely predict and warn the equipment state.The concentration data of the chemical substances in the furnace and other basic data are collected in real time by a data acquisition unit, the data is preprocessed and feature extracted by a detection unit, a knowledge base is constructed by a data processing unit, fault data is called to generate chemical detection substances, the chemical substances in the furnace are detected, real-time electrical equipment adjustment and maintenance data are generated according to the detection results, and the equipment operation state is optimized.The present application realizes real-time detection of the chemical substances in the direct current electric arc furnace, improves the prediction and warning capability of the equipment state, and enhances the pertinence of fault handling.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of chemical detection data processing, and particularly relates to a direct current electric arc furnace and a detection system. BACKGROUND

[0002] The direct current electric arc furnace is a smelting equipment using direct current for heating. The working principle of the direct current electric arc furnace is to convert electric energy into heat energy, and to melt ore or metal raw materials through the high-temperature action of an electric arc. Compared with an alternating current electric arc furnace, the direct current electric arc furnace adopts direct current in power supply. The direct current power supply form makes the electric arc more stable, which is conducive to the control of the smelting process and improves the smelting efficiency. The direct current electric arc furnace is widely used in fields such as electric arc smelting and steel smelting, and is one of the important equipment indispensable in modern metallurgical industry.

[0003] The existing direct current electric arc furnace usually uses an alternating current power supply for power supply, and has the problem of low power efficiency. In addition, due to the large fluctuation of the electric arc generated by the alternating current, an additional cooling device, a detection device and a monitoring device need to be provided to complete the monitoring and adjustment of the direct current electric arc furnace through multiple device equipment, so as to realize the stable operation of the direct current electric arc furnace. However, in the actual use process of the existing direct current electric arc furnace, the chemical substances in the direct current electric arc furnace cannot be detected, which leads to the problem that the situation of each device of the direct current electric arc furnace cannot be timely predicted and warned. To solve this technical problem, the present application provides a direct current electric arc furnace and a detection system. SUMMARY

[0004] In view of the deficiencies in the prior art, the present application provides a direct current electric arc furnace and a detection system to solve the problem that the existing direct current electric arc furnace cannot detect the chemical substances in the direct current electric arc furnace in the actual use process, which leads to the problem that the situation of each device of the direct current electric arc furnace cannot be timely predicted and warned.

[0005] To solve the above technical problems, the specific technical solutions of the present application are as follows:

[0006] In a first aspect, the present application provides a direct current electric arc furnace, comprising:

[0007] a data acquisition unit configured to acquire direct current electric arc furnace basic data;

[0008] a detection unit configured to preprocess the direct current electric arc furnace basic data to obtain a direct current electric arc furnace basic data feature group;

[0009] The state detection unit is configured to establish an operation state detection model of the DC arc furnace based on a set of DC arc furnace basic data features, extract features of the DC arc furnace collected in real time and input the features into the operation state detection model of the DC arc furnace to generate a DC arc furnace state detection result, wherein the DC arc furnace state detection result includes a normal state of the DC arc furnace, a pre-warning state of the DC arc furnace and a fault state of the DC arc furnace.

[0010] The pre-warning unit is configured to trigger a DC arc furnace pre-warning process when the DC arc furnace state detection result is the pre-warning state of the DC arc furnace, and trigger a DC arc furnace fault detection process when the DC arc furnace state detection result is the fault state of the DC arc furnace.

[0011] The data processing unit is configured to acquire DC arc furnace operation history data, construct a DC arc furnace knowledge base, retrieve fault data corresponding to the fault state of the DC arc furnace, obtain real-time fault data, extract data features from the real-time fault data, match the obtained real-time fault feature data in the DC arc furnace knowledge base to obtain real-time fault feature correlation data, wherein the real-time fault feature correlation data includes historical chemical substance detection data and historical electrical equipment adjustment and maintenance data, generate chemical detection substances based on the historical chemical substance detection data, detect the DC arc furnace using the chemical detection substances to obtain a DC arc furnace chemical detection result, match the DC arc furnace chemical detection result with the historical electrical equipment adjustment and maintenance data to obtain real-time electrical equipment adjustment and maintenance data, and send the real-time electrical equipment adjustment and maintenance data to a device end of the DC arc furnace.

[0012] Further, the data acquisition unit of the DC arc furnace is further configured to:

[0013] The data acquisition unit initiates a data collection request to a sensor in the DC arc furnace to request real-time data of chemical substances in the furnace, wherein a request message body carries an address of the data acquisition unit, an address of the sensor, a time range of requested data and a requested data type, the requested data type includes temperature, pressure and chemical component concentration, the sensor responds to the request and returns original detection data of the DC arc furnace.

[0014] Further, the detection unit of the DC arc furnace is further configured to:

[0015] The detection unit receives original detection data from the sensor, removes repeated, invalid or format error data, calibrates the cleaned data, and labels temperature data, pressure data and chemical component concentration data according to characteristics of the detection data.

[0016] Further, the data processing unit of the DC arc furnace is further configured to:

[0017] Collecting the data of the chemical substances in the furnace, identifying the type, concentration and change trend of the chemical substances in the furnace through a preset algorithm model;

[0018] Receiving and setting the threshold value, constructing an anomaly detection model, detecting the type, concentration and change trend of the chemical substances in the furnace using the anomaly detection model, obtaining the anomaly detection result of the chemical substances in the furnace, and alarming the data beyond the normal range to prompt the existing equipment failure or safety hazard.

[0019] Based on the historical data and the current data, the future trend of the state of the chemical substances in the furnace and the equipment operation is predicted.

[0020] Further, the data processing unit of the direct current electric arc furnace is further used for:

[0021] The historical chemical substance detection data is called from the direct current electric arc furnace knowledge base, the obtained historical chemical substance detection data is preprocessed, and the preprocessed historical chemical substance detection data is obtained;

[0022] The preprocessed historical chemical substance detection data is analyzed by using a preset algorithm model, and the chemical substances in the direct current electric arc furnace and the characteristics of the direct current electric arc furnace are identified;

[0023] According to the chemical substances in the direct current electric arc furnace and the characteristics of the direct current electric arc furnace, matching is performed in the direct current electric arc furnace knowledge base, and corresponding chemical detection substances are prepared.

[0024] The chemical detection substances are applied to the to-be-detected parts of the direct current electric arc furnace, the to-be-detected parts of the direct current electric arc furnace include the furnace and the furnace wall of the direct current electric arc furnace, and the reaction data of the chemical detection substances and the chemical substances in the direct current electric arc furnace are collected;

[0025] The reaction data of the chemical detection substances and the chemical substances in the direct current electric arc furnace are extracted, the type of the chemical substances in the direct current electric arc furnace, the concentration of the chemical substances in the direct current electric arc furnace and the color data of the chemical substances in the direct current electric arc furnace are obtained, the type of the chemical substances in the direct current electric arc furnace, the concentration of the chemical substances in the direct current electric arc furnace and the color data of the chemical substances in the direct current electric arc furnace are compared and analyzed with the preset chemical detection standard, and the chemical detection result is obtained;

[0026] The running data after the real-time electrical equipment adjustment and maintenance data of the equipment end of the direct current electric arc furnace is collected to obtain adjusted running data. The adjusted running data is compared with preset standard data of the direct current electric arc furnace. If the adjusted running data is not within the preset standard data of the direct current electric arc furnace, a distillation algorithm is used to optimize the real-time electrical equipment adjustment and maintenance data. The optimized real-time electrical equipment adjustment and maintenance data is sent to the equipment end of the direct current electric arc furnace.

[0027] In a second aspect, the present application provides a direct current electric arc furnace detection system, which is applied to the direct current electric arc furnace, and comprises a server end, a data acquisition end and a direct current electric arc furnace equipment end, wherein the server end is in communication connection with the data acquisition end and the direct current electric arc furnace equipment end respectively.

[0028] The server end comprises:

[0029] A data acquisition unit is configured to acquire the direct current electric arc furnace basic data.

[0030] A detection unit is configured to preprocess the direct current electric arc furnace basic data to obtain a direct current electric arc furnace basic data feature group.

[0031] A state detection unit is configured to establish a direct current electric arc furnace running state detection model based on the direct current electric arc furnace basic data feature group, extract features of the real-time collected direct current electric arc furnace and input the features into the direct current electric arc furnace running state detection model to generate a direct current electric arc furnace state detection result, wherein the direct current electric arc furnace state detection result comprises a direct current electric arc furnace normal state, a direct current electric arc furnace early warning state and a direct current electric arc furnace fault state.

[0032] An early warning unit is configured to trigger a direct current electric arc furnace early warning process when the direct current electric arc furnace state detection result is the direct current electric arc furnace early warning state, and trigger a direct current electric arc furnace fault detection process when the direct current electric arc furnace state detection result is the direct current electric arc furnace fault state.

[0033] A data processing unit is configured to acquire direct current electric arc furnace running historical data, construct a direct current electric arc furnace knowledge base, call fault data corresponding to the direct current electric arc furnace fault state to obtain real-time fault data, extract data features of the real-time fault data, match the obtained real-time fault feature data in the direct current electric arc furnace knowledge base to obtain real-time fault feature correlation data, use the real-time fault feature correlation data to detect the direct current electric arc furnace, and obtain a direct current electric arc furnace chemical detection result. The direct current electric arc furnace chemical detection result is matched with historical electrical equipment adjustment and maintenance data to obtain real-time electrical equipment adjustment and maintenance data, which is sent to the equipment end of the direct current electric arc furnace.

[0034] Further, the direct current electric arc furnace detection system, the data acquisition unit is further used for:

[0035] The data acquisition unit initiates a data collection request to the sensor in the direct current electric arc furnace, requests to acquire real-time data of the chemical substance in the furnace, the request message carries the data acquisition unit address, the sensor address, the time range of the requested data and the requested data type, the requested data type includes temperature, pressure and chemical composition concentration, the sensor responds to the request and returns the original detection data of the direct current electric arc furnace.

[0036] Further, the direct current electric arc furnace detection system, the detection unit is further used for:

[0037] The detection unit receives the original detection data from the sensor, removes the repeated, invalid or format error data, calibrates the cleaned data, and labels the temperature data, pressure data and chemical composition concentration data according to the characteristics of the detection data.

[0038] Further, the direct current electric arc furnace detection system, the data processing unit is further used for:

[0039] Collecting the chemical substance data in the furnace, identifying the type, concentration and change trend of the chemical substance in the furnace through a preset algorithm model;

[0040] Receiving and setting a threshold value, constructing an anomaly detection model, detecting the type, concentration and change trend of the chemical substance in the furnace using the anomaly detection model, obtaining the anomaly detection result of the chemical substance in the furnace, and alarming the data exceeding the normal range to prompt the existing equipment failure or safety hazard.

[0041] Based on the historical data and the current data, the future trend of the chemical substance state in the furnace and the equipment operation is predicted.

[0042] Further, the direct current electric arc furnace detection system, the data processing unit is further used for:

[0043] The historical chemical substance detection data is called from the direct current electric arc furnace knowledge base, the obtained historical chemical substance detection data is preprocessed, and the preprocessed historical chemical substance detection data is obtained;

[0044] The preprocessed historical chemical substance detection data is analyzed by using a preset algorithm model, and the chemical substance in the direct current electric arc furnace and the characteristics of the direct current electric arc furnace are identified;

[0045] According to the chemical substance in the direct current electric arc furnace and the characteristics of the direct current electric arc furnace, the direct current electric arc furnace knowledge base is matched to obtain the corresponding chemical detection substance.

[0046] The chemical detection substance is applied to the to-be-detected part of the direct current electric arc furnace, the to-be-detected part of the direct current electric arc furnace including an inner part of the direct current electric arc furnace and a wall part of the direct current electric arc furnace, reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace are collected, and the reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace are collected;

[0047] Data feature extraction is performed on the reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace, to obtain the type, concentration and color data of the chemical substance in the direct current electric arc furnace, and the type, concentration and color data of the chemical substance in the direct current electric arc furnace are compared and analyzed with the preset chemical detection standard to obtain the chemical detection result;

[0048] The running data of the direct current electric arc furnace after the real-time electrical equipment adjustment and maintenance data of the equipment end are collected to obtain the adjusted running data, the running data of the adjusted running data is compared with the preset standard data of the direct current electric arc furnace, if the adjusted running data is not in the preset standard data of the direct current electric arc furnace, the real-time electrical equipment adjustment and maintenance data are optimized by using a distillation algorithm, and the optimized real-time electrical equipment adjustment and maintenance data are sent to the equipment end of the direct current electric arc furnace.

[0049] The beneficial effects of the present application are as follows:

[0050] The present application realizes real-time detection of the chemical substance in the direct current electric arc furnace: the existing direct current electric arc furnace cannot directly detect the chemical substance in the furnace, which leads to the inability to accurately grasp the chemical environment in the furnace. The present application can collect and process the concentration data of the chemical substance in the furnace in real time through the data acquisition unit and the detection unit, including temperature, pressure, chemical component concentration, etc. Real-time detection of the chemical substance in the furnace enables the operator to timely understand the status in the furnace, providing a data basis for subsequent fault prediction and early warning.

[0051] The present application realizes the improvement of the prediction and early warning ability of the equipment state: due to the inability to detect the chemical substance in the furnace, the existing direct current electric arc furnace cannot predict and warn the equipment state. The present application establishes and runs a running state detection model based on the real-time collected chemical substance data in the furnace and other basic data through the state detection unit, which can accurately identify the running state of the direct current electric arc furnace. When the equipment state is abnormal or is about to be abnormal, the early warning unit can timely trigger the early warning process to remind the operator to take measures, effectively avoiding the occurrence or expansion of faults.

[0052] The present application enhances the pertinence of equipment failure handling: existing direct current electric arc furnaces often lack pertinence in failure handling, resulting in low processing efficiency. The present application constructs a direct current electric arc furnace knowledge base through a data processing unit, stores historical failure data and adjustment and maintenance data. When equipment fails, the data processing unit can retrieve relevant knowledge to generate real-time electrical equipment adjustment and maintenance data, optimizing equipment operating conditions. This failure handling method based on historical and real-time data makes the handling measures more targeted and effective, improving equipment reliability.

[0053] The present application improves production efficiency and reduces maintenance costs: due to the inability to predict and warn of equipment status, existing direct current electric arc furnaces often need to be shut down for maintenance when a failure occurs, resulting in low production efficiency. The present application can take timely measures to avoid unnecessary downtime by real-time monitoring and warning mechanisms before equipment status becomes abnormal. At the same time, targeted failure handling measures reduce the frequency of equipment failure and maintenance costs, improving overall production efficiency.

[0054] The present application introduces advanced data detection and analysis technology in the field of direct current electric arc furnaces, promoting technological innovation in this field. Real-time monitoring and data analysis provide strong support for the optimal design and intelligent control of direct current electric arc furnaces, promoting the upgrading and development of the entire industry.

[0055] In summary, the beneficial effects of the present application mainly include real-time detection of chemical substances in direct current electric arc furnaces, improved equipment status prediction and warning capabilities, enhanced equipment failure handling pertinence and effectiveness, improved production efficiency and reduced maintenance costs, and promotion of technological innovation and industrial upgrading. These beneficial effects not only solve the problems of existing direct current electric arc furnaces, but also provide more reliable and efficient technical support for their application in the metallurgical industry. BRIEF DESCRIPTION OF DRAWINGS

[0056] To more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed in the embodiments. Obviously, other drawings can also be obtained by those skilled in the art without creative labor on the premise of the drawings.

[0057] Figure 1 The functional module schematic diagram of the direct current electric arc furnace provided by the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below in combination with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application. The technical solutions provided by each embodiment of the present application are described in detail below in combination with the drawings.

[0059] In order to better understand the purpose of the present application, the present application will be further described in detail below.

[0060] The present application realizes real-time detection of chemical substances in a direct current electric arc furnace by the following steps:

[0061] Data acquisition unit: The data acquisition unit initiates a data collection request to the sensor in the direct current electric arc furnace, requesting to obtain real-time data of chemical substances in the furnace. The request message body carries the data acquisition unit address, sensor address, time range of requested data and requested data type (including temperature, pressure, chemical composition concentration, etc.). The sensor responds to the request and returns the original detection data of the direct current electric arc furnace.

[0062] Detection unit: The detection unit receives the original detection data from the sensor, removes duplicate, invalid or format error data, calibrates the cleaned data to ensure the accuracy and consistency of the data.

[0063] According to the characteristics of the detection data, the temperature data, pressure data and chemical composition concentration data are labeled, which facilitates subsequent data processing and analysis.

[0064] Data feature extraction: The detection unit extracts data features from the preprocessed data to obtain a set of basic data features of the direct current electric arc furnace, including chemical substance concentration features, etc.

[0065] Data processing unit: The data processing unit can collect chemical substance data in the furnace, identify the type, concentration and trend of the chemical substances in the furnace through a preset algorithm model. An anomaly detection model is constructed to detect the type, concentration and trend of the chemical substances in the furnace, and an alarm is given when the data exceeds the normal range, prompting the existence of equipment failure or safety hazards. Through these steps, the present application can realize real-time detection of chemical substances in the direct current electric arc furnace, providing accurate data support for subsequent fault prediction, early warning and processing.

[0066] The early warning unit does not directly establish an operating state detection model based on the real-time collected chemical substance data in the furnace, but the state detection unit is responsible for this task. The following is the logical reasoning process:

[0067] The role of the state detection unit: The state detection unit is responsible for establishing and running the operating state detection model of the DC electric arc furnace based on the DC electric arc furnace basic data feature set (including electrical parameter features, temperature features, arc stability features, chemical substance concentration features, etc.).

[0068] The data acquisition unit collects the concentration data of the chemical substances in the furnace and other basic data (such as electrical parameter data, temperature data, etc.) in real time. The detection unit pre-processes and extracts features from these data to obtain real-time DC electric arc furnace feature data.

[0069] Establishment of the operating state detection model: The state detection unit uses the DC electric arc furnace basic data feature set and corresponding operating state labels in the historical data set to train the operating state detection model through machine learning or deep learning algorithms (such as support vector machines, random forests, neural networks, etc.). The model can identify the normal state, pre-warning state and fault state of the DC electric arc furnace.

[0070] Real-time state detection: The real-time DC electric arc furnace feature data collected is input into the operating state detection model. The model generates the state detection results of the DC electric arc furnace according to the input feature data.

[0071] Triggering of the pre-warning unit: When the state detection result output by the state detection unit is a pre-warning state or a fault state, the pre-warning unit is triggered. The pre-warning unit triggers the corresponding pre-warning process or fault detection process according to the pre-warning or fault state, such as sending a pre-warning signal, recording pre-warning information, starting a fault troubleshooting program, etc.

[0072] Therefore, the pre-warning unit does not directly establish the operating state detection model, but relies on the model established by the state detection unit through historical data and real-time data to identify the operating state of the DC electric arc furnace, and triggers the corresponding pre-warning or fault handling process when needed.

[0073] In a first aspect, the present application provides a DC electric arc furnace, comprising:

[0074] A data acquisition unit for acquiring DC electric arc furnace basic data, including electrical parameter data, temperature data, arc stability data, chemical substance concentration data, cooling system data, and equipment state data;

[0075] Data acquisition unit of the DC electric arc furnace

[0076] Data acquisition basic data range: The data acquisition unit is used to acquire the basic data of the direct current electric furnace, including but not limited to electrical parameter data (such as current, voltage, power factor, etc.), temperature data (such as furnace temperature, cooling water temperature, etc.), arc stability data (such as arc length, arc voltage fluctuation, etc.), chemical concentration data (such as furnace gas composition concentration, melt composition concentration, etc.), cooling system data (such as cooling water flow, pressure, etc.), and equipment state data (such as electrode position, furnace door opening and closing state, etc.).

[0077] In order to accurately acquire the above data, the data acquisition unit needs to interact with various types of sensors. For example, electrical parameter data can be obtained through current transformers and voltage sensors; temperature data can be obtained through thermocouples or infrared thermometers; arc stability data can be obtained through arc sensors or image recognition technology; chemical concentration data can be obtained through gas analyzers or spectrometers; cooling system data can be obtained through flow meters and pressure sensors; and equipment state data can be obtained through limit switches and proximity switches. The layout of the sensors should fully consider the furnace environment and measurement requirements.

[0078] The data acquisition unit needs to establish a stable communication connection with the sensors, and can use standard industrial communication protocols (such as Modbus, Profibus, etc.) or custom protocols for data transmission. At the same time, in order to cope with the differences in data format and transmission rate of different sensors, the data acquisition unit has data format conversion and buffering mechanism.

[0079] During data acquisition, due to sensor failure, communication interference and other factors, the data may be incomplete or incorrect. Therefore, the data acquisition unit detects the integrity of the data through the internal preset data verification and error handling mechanism, which includes improving the accuracy of the data through redundant sensors, data comparison verification and other methods.

[0080] The data acquisition unit, as the data source of the detection system, needs to closely cooperate with other units (such as the detection unit, the state detection unit, the early warning unit, and the data processing unit). For example, the detection unit needs to obtain preprocessed data from the data acquisition unit for feature extraction; the state detection unit needs to establish and update the running state detection model based on the data provided by the data acquisition unit; the early warning unit and the data processing unit need to perform fault early warning and adjustment and maintenance decision based on the data provided by the data acquisition unit.

[0081] The entire detection system forms a closed-loop feedback mechanism from data acquisition to state detection, early warning, and processing. The data acquisition unit serves as the foundation, enabling data input for subsequent steps; the detection unit and state detection unit process and analyze data, providing a basis for early warning and processing; the early warning unit and data processing unit take appropriate measures based on the analysis results to achieve safe and stable operation of the direct current electric arc furnace.

[0082] The detection unit is used to preprocess the direct current electric arc furnace basic data to obtain preprocessed direct current electric arc furnace basic data, and to extract data features from the preprocessed direct current electric arc furnace basic data to obtain a direct current electric arc furnace basic data feature group, which includes electrical parameter features, temperature features, arc stability features, chemical substance concentration features, cooling system features, and equipment state features.

[0083] Data cleaning: The detection unit first receives basic data from the data acquisition unit. The data cleaning process includes removing duplicate data, handling missing values (such as filling in missing values using interpolation), identifying and correcting outliers (such as setting thresholds based on statistical methods or domain knowledge).

[0084] Data calibration: To address the precision differences between different sensors, data calibration is performed to ensure that all data is compared on the same scale and standard. For example, temperature compensation is performed on temperature data, and zero drift correction is performed on electrical parameter data.

[0085] Data normalization / standardization: To eliminate the dimensional differences between different features and improve the efficiency of subsequent feature extraction and model training, data normalization or standardization is performed.

[0086] Data normalization / standardization not only helps to improve model training efficiency, but also enhances the generalization ability of the model.

[0087] Based on domain knowledge and statistical analysis, features that significantly affect the operation of the electric arc furnace are selected from the preprocessed data. For example, current, voltage, and power factor are selected as electrical parameter features, furnace temperature and cooling water temperature are selected as temperature features, arc length and arc voltage fluctuation are selected as arc stability features, etc.

[0088] Feature dimensionality reduction: For high-dimensional data, principal component analysis (PCA), linear discriminant analysis (LDA), and other methods are used for feature dimensionality reduction to reduce computational complexity while preserving key information.

[0089] Feature engineering: According to specific application scenarios, new features need to be constructed. For example, arc power fluctuation rate is calculated as a new feature of arc stability, or furnace heat flow distribution is calculated based on temperature gradient, etc.

[0090] The detection unit serves as a bridge between the data acquisition unit and the subsequent analysis unit (such as the state detection unit), playing a role of connecting the past and the future. Through preprocessing and feature extraction of the raw data, it provides data support for subsequent state monitoring and fault warning.

[0091] After the data acquisition unit provides the raw data, the detection unit first performs preprocessing, and then performs feature extraction, converting high-dimensional and complex raw data into low-dimensional and easily analyzed feature vectors. These feature vectors are then input into the state detection unit to establish and update the operating state detection model, realizing real-time state monitoring and fault warning of the electric furnace. The entire process forms a closed-loop feedback mechanism from data acquisition to state monitoring.

[0092] The state detection unit is used to establish an operating state detection model of the direct current electric furnace based on the direct current electric furnace basic data feature set. The operating state detection model of the direct current electric furnace is used to identify the operating state of the direct current electric furnace. The real-time collected direct current electric furnace is subjected to feature extraction to obtain real-time direct current electric furnace feature data. The real-time direct current electric furnace feature data is input into the operating state detection model of the direct current electric furnace. The operating state detection model of the direct current electric furnace generates a direct current electric furnace state detection result. The direct current electric furnace state detection result includes a direct current electric furnace state normal state, a direct current electric furnace state warning state, and a direct current electric furnace state fault state.

[0093] According to the operating characteristics and monitoring requirements of the direct current electric furnace, a suitable machine learning or deep learning algorithm is selected as the basis of the operating state detection model. For example, support vector machines (SVM), random forests, neural networks, etc. can be selected.

[0094] Feature engineering: Before establishing the model, further feature selection, feature transformation or feature construction are performed on the direct current electric furnace basic data feature set to extract the most useful information for operating state identification.

[0095] Model training: The direct current electric furnace basic data feature set and the corresponding operating state labels in the historical data set are used to train the selected algorithm to obtain the operating state detection model. During the training process, cross-validation, grid search, etc. can be used to optimize the model parameters and improve the model performance.

[0096] The real-time collected direct current electric furnace data is preprocessed and feature extracted to obtain real-time direct current electric furnace feature data.

[0097] Model input and output: The real-time direct current electric furnace feature data is input into the operating state detection model. The model generates a direct current electric furnace state detection result based on the input feature data. The detection result can include direct current electric furnace state normal, warning or fault, etc.

[0098] Result processing and feedback: Process and analyze the state detection results generated by the model, such as triggering corresponding alarm mechanisms or maintenance measures according to early warning or fault states. At the same time, feedback the detection results to system users or operators so that they can timely understand the running state of the direct current electric arc furnace.

[0099] Normal state: When all operating parameters of the direct current electric arc furnace are within the normal range and there is no abnormal fluctuation or trend, it is determined as normal state.

[0100] Early warning state: When some operating parameters of the direct current electric arc furnace appear slight abnormalities or trend changes, but have not reached the fault threshold, it is determined as early warning state. Early warning state aims to discover potential problems in advance to take preventive measures.

[0101] Fault state: When one or more operating parameters of the direct current electric arc furnace exceed the normal range, or appear obvious abnormal fluctuations or trends, it is determined as fault state. Fault state needs to take immediate maintenance or shutdown measures to avoid causing more serious consequences.

[0102] Normal state is the ideal state of the direct current electric arc furnace operation, and is also the goal pursued by the state detection system.

[0103] Early warning state is one of the important functions of the state detection system, which can reduce the occurrence and impact of faults by discovering potential problems in advance.

[0104] Fault state is the most undesirable situation in the operation of the direct current electric arc furnace, but the state detection system can timely discover and alarm, which helps to reduce the loss caused by faults.

[0105] The state detection unit is the core part of the direct current electric arc furnace running state detection system, responsible for establishing and running the running state detection model, and realizing real-time and accurate identification of the running state of the direct current electric arc furnace.

[0106] Firstly, the basic data of the direct current electric arc furnace is obtained and preprocessed through the data acquisition unit and the detection unit, and the feature data is extracted.

[0107] Then, the feature data is input into the running state detection model in the state detection unit, and the model generates state detection results according to the input data.

[0108] Finally, the state detection results are processed and analyzed, and corresponding measures are taken or feedback to the user to ensure the safe and stable operation of the direct current electric arc furnace.

[0109] The whole process forms a closed-loop system from data acquisition to state detection, which provides a strong guarantee for production efficiency and safety by identifying the running state of the direct current electric arc furnace in real time and accurately.

[0110] an early warning unit configured to trigger an early warning process when the DC arc furnace state detection result is a DC arc furnace state early warning state, and trigger a DC arc furnace fault detection process when the DC arc furnace state detection result is a DC arc furnace state fault state;

[0111] According to the operating characteristics and safety standards of the DC arc furnace, specific conditions for triggering the early warning state are preset. These conditions can include abnormal fluctuations, exceeding the preset range or trend changes of certain key operating parameters, etc.

[0112] Early warning process triggering: When the DC arc furnace state detection result output by the state detection unit is an early warning state, the early warning unit immediately triggers the early warning process. The early warning process can include sending early warning signals to the operator or control system, recording early warning time, early warning reasons and other related information, and taking appropriate preventive measures according to the early warning level.

[0113] Early warning signal transmission: Early warning signals can be transmitted to operators or control systems in various ways, such as sound alarms, light indicators, SMS notifications, system pop-ups, etc., to ensure that operators can receive early warning information in a timely manner and respond.

[0114] The setting of early warning conditions is the basis for the work of the early warning unit, and reasonable early warning conditions can ensure that the early warning process is triggered in time when potential problems occur in the equipment. The triggering of the early warning process is the core function of the early warning unit, which can prompt operators to take preventive measures to avoid equipment failure or expansion by timely and accurate transmission of early warning information. The transmission method of the early warning signal should be selected according to the actual use scene and demand to ensure that the early warning information can be quickly and accurately conveyed to the relevant personnel.

[0115] Fault condition setting: Similarly, according to the operating characteristics and safety standards of the DC arc furnace, specific conditions for triggering the fault state are preset. These conditions are usually more stringent than the early warning conditions, such as serious deviation of key operating parameters from the normal range, obvious signs of equipment failure, etc.

[0116] Fault detection process triggering: When the DC arc furnace state detection result output by the state detection unit is a fault state, the early warning unit immediately triggers the fault detection process. The fault detection process can include stopping the equipment operation, sending a fault alarm signal, starting the fault troubleshooting program, recording the fault time, fault type and other related information, and taking appropriate maintenance or emergency repair measures according to the fault level.

[0117] Fault alarm and handling: Fault alarm signals should be delivered to the operator or control system in a conspicuous manner, such as emergency stop indication, sound and light alarm, system emergency pop-up, etc., to ensure that the operator can immediately realize the severity of the fault and take appropriate handling measures.

[0118] The setting of fault conditions is the key to ensuring that the equipment can be shut down in time and trigger the fault handling process when serious problems occur. The triggering of the fault detection process is the core function of the early warning unit when the equipment fails. By quickly and accurately delivering fault information, it can prompt the operator to take maintenance or emergency repair measures in time and reduce the loss caused by the fault.

[0119] The early warning unit is part of the DC furnace operation state detection and early warning system, responsible for identifying the early warning and fault state of the DC furnace, and triggering the corresponding handling process.

[0120] First, the state detection unit detects the operation state of the DC furnace in real time and outputs the state detection result.

[0121] Then, the early warning unit identifies the early warning or fault state of the DC furnace according to the state detection result, and triggers the corresponding early warning or fault detection process.

[0122] Next, the early warning or fault detection process ensures the safe and stable operation of the equipment through the sending of alarm signals, the recording of relevant information, the taking of preventive measures or maintenance measures, etc.

[0123] Finally, through process connection, information sharing and process optimization, etc., the efficiency and accuracy of early warning and fault handling are continuously improved.

[0124] The whole process forms a closed-loop system from state detection to early warning or fault handling, which provides a strong guarantee for the safe and stable operation of the equipment by identifying and handling the operation state of the DC furnace in real time and accurately.

[0125] The data processing unit is used to obtain the operating history data of the direct current electric arc furnace, construct a direct current electric arc furnace knowledge base, call the fault data corresponding to the fault state of the direct current electric arc furnace, take the fault data corresponding to the fault state of the direct current electric arc furnace as real-time fault data, perform data feature extraction on the real-time fault data, obtain real-time fault feature data, match the real-time fault feature data in the direct current electric arc furnace knowledge base, obtain real-time fault feature association data, the real-time fault feature association data includes historical chemical substance detection data and historical electrical equipment adjustment and maintenance data, generate a chemical detection substance based on the historical chemical substance detection data, detect the direct current electric arc furnace using the chemical detection substance, obtain a direct current electric arc furnace chemical detection result, match the direct current electric arc furnace chemical detection result with the historical electrical equipment adjustment and maintenance data, obtain real-time electrical equipment adjustment and maintenance data, send the real-time electrical equipment adjustment and maintenance data to the equipment end of the direct current electric arc furnace, collect operating data of the equipment end of the direct current electric arc furnace after executing the real-time electrical equipment adjustment and maintenance data, obtain adjusted operating data, compare the operating data of the adjusted operating data with preset direct current electric arc furnace standard data, if the adjusted operating data is not within the preset direct current electric arc furnace standard data, optimize the real-time electrical equipment adjustment and maintenance data using a distillation algorithm, and send the optimized real-time electrical equipment adjustment and maintenance data to the direct current electric arc furnace equipment end.

[0126] The data processing unit is connected with the control system or sensor network of the direct current electric arc furnace, and obtains the operating history data of the direct current electric arc furnace in real time or periodically, including but not limited to temperature, current, voltage, chemical substance content, equipment operating state, etc.

[0127] Knowledge base construction: based on the obtained operating history data, the data processing unit constructs a direct current electric arc furnace knowledge base, which contains normal operating data, historical fault data, fault handling schemes, chemical substance detection data, electrical equipment adjustment and maintenance data, etc., providing data support for subsequent fault analysis and handling.

[0128] Fault data calling: when the direct current electric arc furnace fails, the data processing unit calls the fault data corresponding to the fault state from the knowledge base, including historical fault cases, fault phenomena, fault causes, etc.

[0129] Data feature extraction: perform data feature extraction on the called fault data, such as statistical analysis, trend analysis, frequency spectrum analysis, etc., to obtain real-time fault feature data for subsequent fault matching and handling.

[0130] Fault feature matching: match the real-time fault feature data in the direct current electric arc furnace knowledge base, find similar historical fault cases, and obtain real-time fault feature association data, including historical chemical substance detection data and historical electrical equipment adjustment and maintenance data.

[0131] Chemical detection substance generation: Based on historical chemical detection data, generate a list or formula of chemical detection substances for chemical detection of the direct current electric arc furnace to verify or determine the cause of the fault.

[0132] Chemical detection result acquisition: Detect the direct current electric arc furnace using the generated chemical detection substances to obtain the chemical detection results of the direct current electric arc furnace, such as chemical content, reaction products, etc.

[0133] Fault feature matching is a bridge connecting the current fault with historical fault cases, and through matching, similar fault handling solutions or experiences can be found. The generation and detection of chemical detection substances are important means to verify the cause of the fault, especially when the fault is related to chemical substances.

[0134] Match the chemical detection results of the direct current electric arc furnace with historical electrical equipment adjustment and maintenance data to find similar adjustment and maintenance cases and obtain real-time electrical equipment adjustment and maintenance data.

[0135] Adjustment and maintenance data transmission: Transmit the real-time electrical equipment adjustment and maintenance data to the device end of the direct current electric arc furnace to guide the device to perform corresponding adjustments or maintenance.

[0136] Post-adjustment operation data collection: Collect the operation data after the device end of the direct current electric arc furnace executes the real-time electrical equipment adjustment and maintenance data to obtain post-adjustment operation data.

[0137] Data comparison and optimization: Compare the post-adjustment operation data with the preset direct current electric arc furnace standard data. If the post-adjustment operation data is not within the preset range, use the distillation algorithm to optimize the real-time electrical equipment adjustment and maintenance data to improve the accuracy and effectiveness of the adjustment and maintenance.

[0138] Optimized data transmission: Transmit the optimized real-time electrical equipment adjustment and maintenance data to the device end of the direct current electric arc furnace to guide the device to perform adjustments or maintenance again.

[0139] The matching of adjustment and maintenance data is the key to the effectiveness of the adjustment or maintenance measures, and through matching, similar adjustment and maintenance experiences or solutions can be found. The transmission and execution of adjustment and maintenance data are the actual operation links of fault handling, which need to ensure the accuracy of the data and the timeliness of the execution. The collection and comparison of post-adjustment operation data are important basis for verifying the effectiveness of adjustment and maintenance, and through comparison, the effectiveness of adjustment and maintenance measures can be evaluated.

[0140] The application of the distillation algorithm is an effective means to optimize the adjustment and maintenance data, which can improve the accuracy and efficiency of the adjustment and maintenance.

[0141] The data processing unit is a core part of a direct current electric furnace data processing and fault processing system, responsible for acquiring and processing operation history data of the direct current electric furnace, constructing a knowledge base, and calling relevant data for fault analysis, detection and processing in a fault state, thereby providing strong support for stable operation of the direct current electric furnace.

[0142] Firstly, the data processing unit acquires operation history data of the direct current electric furnace in real time or periodically through a data acquisition method, and constructs a knowledge base.

[0143] Then, in a fault state, the data processing unit calls fault data from the knowledge base, and extracts data features to obtain real-time fault feature data.

[0144] Next, the data processing unit matches the real-time fault feature data in the knowledge base to obtain real-time fault feature correlation data, and generates a chemical detection substance based on historical chemical substance detection data, thereby detecting the direct current electric furnace.

[0145] Subsequently, the data processing unit matches the chemical detection result with historical electrical equipment adjustment and maintenance data to obtain real-time electrical equipment adjustment and maintenance data, and sends the data to the direct current electric furnace equipment end for execution.

[0146] Finally, the data processing unit collects the adjusted operation data, and compares the data with preset direct current electric furnace standard data, if the data does not meet the expectation, the data processing unit optimizes the real-time electrical equipment adjustment and maintenance data using a distillation algorithm, and sends the data to the equipment end for execution again.

[0147] The whole process forms a closed-loop system from data acquisition to fault processing, which provides strong guarantee for stable operation of the equipment by processing and analyzing operation data of the direct current electric furnace in real time and accurately. Meanwhile, by continuously optimizing the adjustment and maintenance data, the efficiency and accuracy of fault processing are improved.

[0148] Specifically, the data acquisition unit of the direct current electric furnace is further used for:

[0149] The data acquisition unit initiates a data collection request to a sensor in the direct current electric furnace, requests to acquire real-time data of chemical substances in the furnace, and a request message body carries a data acquisition unit address, a sensor address, a time range of requested data and a requested data type, the requested data type includes temperature, pressure and chemical composition concentration, the sensor responds to the request and returns original detection data of the direct current electric furnace.

[0150] The data acquisition unit address is used for identifying the data acquisition unit initiating the request, so as to identify the request source by the sensor or other parts of the system.

[0151] The sensor address is used for specifying the sensor responding to the request, so as to acquire data from the correct sensor.

[0152] Time range of requested data: specifies the time period of data that needs to be collected, which can be real-time data or a time range of historical data.

[0153] Data type requested: specifies the type of data that needs to be collected, including but not limited to temperature, pressure, chemical composition concentration, etc., to meet the data needs in different scenarios.

[0154] After the sensor receives the data collection request, it executes the corresponding data collection task according to the information in the request message body.

[0155] After the sensor collects the data, it packages the data into a response message and returns it to the data acquisition unit that initiated the request.

[0156] The returned raw detection data includes but is not limited to temperature values, pressure values, chemical composition concentration values, etc., which are determined according to the requested data type.

[0157] Specifically, the detection unit of the direct current electric arc furnace according to the present application is also used for:

[0158] The detection unit receives raw detection data from the sensor, removes duplicate, invalid or format error data, calibrates the cleaned data, and labels temperature data, pressure data and chemical composition concentration data according to the characteristics of the detection data.

[0159] The detection unit is responsible for receiving raw detection data from the sensor in real time or periodically. The received data types include but are not limited to temperature data, pressure data, chemical composition concentration data, etc.

[0160] The detection unit has a data cleaning module built-in, which is responsible for removing duplicate data, invalid data and format error data in the received raw detection data. Duplicate data is caused by repeated sending of the sensor or data transmission error; invalid data is caused by sensor failure or environmental interference; format error data is caused by encoding error or decoding error in the data transmission process. The data cleaning module automatically identifies and removes these bad data through pre-set algorithms or rules, ensuring the accuracy of subsequent processing.

[0161] The detection unit is provided with a data calibration module, which is responsible for calibrating the cleaned data.

[0162] The calibration process includes linear calibration, nonlinear calibration, temperature compensation, pressure compensation, etc., which are determined according to the characteristics of the sensor and the properties of the detection data.

[0163] The data calibration module processes the cleaned data through pre-set calibration parameters or algorithms to ensure the accuracy and consistency of the data.

[0164] The detection unit is built-in with a data labeling module, which is responsible for labeling the calibrated data.

[0165] The labeling content includes but is not limited to the type of data (such as temperature, pressure, chemical composition concentration, etc.), collection time, sensor number, etc.

[0166] The data labeling module automatically adds labeling information to the calibrated data through preset labeling rules or algorithms, facilitating subsequent data analysis and processing.

[0167] Specifically, the data processing unit of the direct current electric arc furnace is also used for:

[0168] Collecting the data of the chemical substances in the furnace, identifying the types, concentrations and trends of the chemical substances in the furnace through a preset algorithm model;

[0169] Receiving and setting threshold values, constructing an anomaly detection model, detecting the types, concentrations and trends of the chemical substances in the furnace using the anomaly detection model, obtaining the anomaly detection results of the chemical substances in the furnace, and alarming the data beyond the normal range to prompt the existing equipment failure or safety hazard.

[0170] Based on historical data and current data, predicting the future trends of the chemical substance state and equipment operation in the furnace.

[0171] The data processing unit is responsible for collecting the original data of the chemical substances in the furnace in real time or periodically, including but not limited to temperature, pressure, chemical composition concentration, etc.

[0172] The data processing unit is built-in with a preset algorithm model, which is based on machine learning, deep learning or statistical analysis, and can identify the types, concentrations and trends of the chemical substances in the furnace.

[0173] The algorithm model learns the characteristic patterns of the chemical substances by training historical data, so as to accurately identify newly collected data.

[0174] By identifying the types, concentrations and trends of the chemical substances, the chemical environment in the furnace can be understood in a timely manner, providing a basis for subsequent anomaly detection and prediction.

[0175] The data processing unit is provided with a threshold setting module, which is responsible for receiving and setting the normal range threshold values of the types, concentrations and trends of the chemical substances in the furnace.

[0176] Based on the set threshold values, the data processing unit constructs an anomaly detection model, which can monitor the state of the chemical substances in the furnace in real time and compare it with the threshold values.

[0177] When the state of the chemical substances in the furnace is detected to be beyond the normal range, the anomaly detection model triggers an alarm mechanism to prompt the existing equipment failure or safety hazard.

[0178] The data processing unit is built-in with a prediction model that predicts the future trend of the chemical substance state and equipment operation condition in the furnace based on historical data and current data using time series analysis, machine learning or deep learning methods. The prediction model can consider various factors such as changes in temperature, pressure, and chemical composition concentration in the furnace, as well as equipment operation time, load, etc., to improve the accuracy of the prediction. The prediction results can be displayed in the form of charts, reports, etc., to facilitate operators to intuitively understand the future trend of the chemical substance state and equipment operation condition in the furnace.

[0179] The data processing unit first collects the original data of the chemical substance in the furnace, then identifies it through a pre-set algorithm model to obtain the type, concentration and trend of the chemical substance. Based on the set threshold, the data processing unit constructs an anomaly detection model to monitor the state of the chemical substance in the furnace in real time and timely discover and alarm abnormal state. The data processing unit predicts the future trend of the chemical substance state and equipment operation condition in the furnace based on historical data and current data through the prediction model to provide decision support for operators.

[0180] In summary, the data processing unit and data processing method of the direct current electric arc furnace according to the present application realize comprehensive monitoring of the chemical substance state and equipment operation condition in the direct current electric arc furnace through the steps of chemical substance data collection, identification, detection and prediction.

[0181] Specifically, the data processing unit of the direct current electric arc furnace according to the present application is also used for:

[0182] Retrieving historical chemical substance detection data from the direct current electric arc furnace knowledge base, preprocessing the obtained historical chemical substance detection data to obtain preprocessed historical chemical substance detection data;

[0183] Using a pre-set algorithm model to analyze the preprocessed historical chemical substance detection data, identifying the chemical substance in the direct current electric arc furnace and the characteristics of the direct current electric arc furnace;

[0184] Matching the chemical substance in the direct current electric arc furnace and the characteristics of the direct current electric arc furnace in the direct current electric arc furnace knowledge base to obtain the corresponding chemical detection substance.

[0185] Applying the chemical detection substance to the detection part of the direct current electric arc furnace, the detection part of the direct current electric arc furnace including the furnace and the furnace wall of the direct current electric arc furnace, collecting the reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace, the reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace;

[0186] The data feature extraction is performed on the reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace to obtain the type of the chemical substance in the direct current electric arc furnace, the concentration of the chemical substance in the direct current electric arc furnace, and the color data of the chemical substance in the direct current electric arc furnace. The type of the chemical substance in the direct current electric arc furnace, the concentration of the chemical substance in the direct current electric arc furnace, and the color data of the chemical substance in the direct current electric arc furnace are compared and analyzed with the preset chemical detection standard to obtain the chemical detection result.

[0187] The data processing unit can retrieve historical chemical substance detection data from the direct current electric arc furnace knowledge base. The data in the knowledge base includes past detection records, chemical substance types, concentrations, colors, and reaction characteristics, etc. The retrieved historical chemical substance detection data is preprocessed, such as cleaning, denoising, and normalization, to eliminate abnormal values, missing values, or noise in the data, to obtain preprocessed historical chemical substance detection data.

[0188] The data processing unit uses a preset algorithm model, such as a machine learning algorithm, a statistical analysis method, or a pattern recognition technique, to perform data analysis on the preprocessed historical chemical substance detection data.

[0189] Through data analysis, the types of chemical substances in the direct current electric arc furnace, the concentration distribution, and the operating characteristics of the direct current electric arc furnace, such as temperature changes and pressure fluctuations, are identified.

[0190] According to the identified chemical substances in the direct current electric arc furnace and the characteristics of the direct current electric arc furnace, the data processing unit matches in the direct current electric arc furnace knowledge base to select or prepare corresponding chemical detection substances. The selection or preparation of the chemical detection substance needs to consider its reaction characteristics with the target chemical substance, detection sensitivity, safety, and other factors.

[0191] The matching and preparation of the chemical detection substance is a key step in chemical detection, which directly affects the accuracy and reliability of the detection. The matching process in the knowledge base needs to be based on accurate chemical substance and characteristic information to ensure that the selected or prepared chemical detection substance is applicable.

[0192] The prepared chemical detection substance is applied to the detection site of the direct current electric arc furnace, including the furnace and the furnace wall, etc.

[0193] The data processing unit collects the reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace in real time or periodically, including the types, concentrations, colors, and reaction times of the reaction products, etc.

[0194] The data processing unit is built-in with a data feature extraction module to extract features from the collected reaction data of the chemical detection substance and the chemical substances in the DC smelting furnace. Through feature extraction, the types, concentrations, and colors of the chemical substances in the DC smelting furnace are obtained. The extracted data are compared and analyzed with the preset chemical detection standard to obtain the chemical detection results, including whether the chemical substances are abnormal, whether the concentrations exceed the standard, and whether the colors change, etc.

[0195] Data feature extraction is one of the key steps of chemical detection, which needs to extract useful information from complex reaction data. The setting of chemical detection standard needs to be based on industry specifications, equipment requirements, and safety standards, etc. to ensure the accuracy and reliability of the detection results.

[0196] The data processing unit first retrieves historical chemical substance detection data and pre-processes them to provide accurate basic data for subsequent data analysis. Through preset algorithm models, the pre-processed data are analyzed to accurately identify the chemical substances and features in the DC smelting furnace. According to the identified chemical substances and features, suitable chemical detection substances are selected or prepared in the knowledge base. The chemical detection substances are applied to the detection site, and reaction data are collected in real time or periodically to ensure the timeliness and accuracy of the data. The reaction data are extracted for features and compared with the preset standard to obtain accurate chemical detection results.

[0197] In summary, the data processing unit and the chemical detection method of the DC smelting furnace according to the present application realize comprehensive detection of the chemical substances in the DC smelting furnace through the steps of historical data retrieval, data analysis, chemical detection substance preparation, application, reaction data collection, and data feature extraction.

[0198] In a second aspect, the present application provides a DC smelting furnace detection system applied to the DC smelting furnace, comprising a server end, a data acquisition end, and a DC smelting furnace equipment end, the server end being respectively in communication connection with the data acquisition end and the DC smelting furnace equipment end.

[0199] The server end comprises:

[0200] The data acquisition unit acquires DC smelting furnace basic data, including electrical parameter data, temperature data, arc stability data, chemical substance concentration data, cooling system data, and equipment state data.

[0201] The detection unit pre-processes the direct-current electric arc furnace basic data to obtain pre-processed direct-current electric arc furnace basic data, and extracts data features from the pre-processed direct-current electric arc furnace basic data to obtain a direct-current electric arc furnace basic data feature group, which includes electrical parameter features, temperature features, arc stability features, chemical substance concentration features, cooling system features, and equipment state features.

[0202] The state detection unit establishes a direct-current electric arc furnace operation state detection model based on the direct-current electric arc furnace basic data feature group, which is used to identify the operation state of the direct-current electric arc furnace. The real-time collected direct-current electric arc furnace is subjected to feature extraction to obtain real-time direct-current electric arc furnace feature data, which is input into the direct-current electric arc furnace operation state detection model. The direct-current electric arc furnace operation state detection model generates a direct-current electric arc furnace state detection result, which includes a direct-current electric arc furnace state normal state, a direct-current electric arc furnace state warning state, and a direct-current electric arc furnace state fault state.

[0203] The warning unit triggers a direct-current electric arc furnace warning process when the direct-current electric arc furnace state detection result is a direct-current electric arc furnace state warning state, and triggers a direct-current electric arc furnace fault detection process when the direct-current electric arc furnace state detection result is a direct-current electric arc furnace state fault state.

[0204] The data processing unit obtains direct-current electric arc furnace operation history data, constructs a direct-current electric arc furnace knowledge base, retrieves fault data corresponding to the direct-current electric arc furnace state fault state, and uses the fault data as real-time fault data. Data feature extraction is performed on the real-time fault data to obtain real-time fault feature data, which is matched in the direct-current electric arc furnace knowledge base to obtain real-time fault feature association data, including historical chemical substance detection data and historical electrical equipment adjustment and maintenance data. The historical chemical substance detection data is used to generate a chemical detection substance, which is used to detect the direct-current electric arc furnace to obtain a direct-current electric arc furnace chemical detection result. The direct-current electric arc furnace chemical detection result is matched with the historical electrical equipment adjustment and maintenance data to obtain real-time electrical equipment adjustment and maintenance data, which is sent to the equipment end of the direct-current electric arc furnace. The operation data of the equipment end of the direct-current electric arc furnace after executing the real-time electrical equipment adjustment and maintenance data is obtained as adjusted operation data. The adjusted operation data is compared with preset direct-current electric arc furnace standard data. If the adjusted operation data is not within the preset direct-current electric arc furnace standard data, the real-time electrical equipment adjustment and maintenance data is optimized using a distillation algorithm, and the optimized real-time electrical equipment adjustment and maintenance data is sent to the direct-current electric arc furnace equipment end.

[0205] Specifically, the DC arc furnace detection system provided by the application, the data acquisition unit is further used for:

[0206] The data acquisition unit initiates a data collection request to the sensor in the DC arc furnace, requests to acquire real-time data of chemical substances in the furnace, and the request message body carries the data collection unit address, sensor address, time range of requested data, and requested data type, the requested data type includes temperature, pressure, and chemical component concentration, the sensor responds to the request and returns the original detection data of the DC arc furnace.

[0207] Specifically, the DC arc furnace detection system provided by the application, the detection unit is further used for:

[0208] The detection unit receives the original detection data from the sensor, removes repeated, invalid, or format error data, calibrates the cleaned data, and labels the temperature data, pressure data, and chemical component concentration data according to the characteristics of the detection data.

[0209] Specifically, the DC arc furnace detection system provided by the application, the data processing unit is further used for:

[0210] Collecting the data of chemical substances in the furnace, identifying the type, concentration, and change trend of the chemical substances in the furnace through a preset algorithm model;

[0211] Receiving and setting a threshold value, constructing an anomaly detection model, detecting the type, concentration, and change trend of the chemical substances in the furnace using the anomaly detection model, obtaining the anomaly detection result of the chemical substances in the furnace, and alarming the data exceeding the normal range to prompt the existing equipment failure or safety hazard.

[0212] Based on historical data and current data, predicting the future trend of the state of chemical substances in the furnace and the operation of the equipment.

[0213] Specifically, the DC arc furnace detection system provided by the application, the data processing unit is further used for:

[0214] Retrieving historical chemical substance detection data from the DC arc furnace knowledge base, preprocessing the obtained historical chemical substance detection data, and obtaining preprocessed historical chemical substance detection data;

[0215] Using a preset algorithm model to analyze the preprocessed historical chemical substance detection data, identifying the chemical substances in the DC arc furnace and the characteristics of the DC arc furnace;

[0216] According to the chemical substances in the DC arc furnace and the characteristics of the DC arc furnace, matching in the DC arc furnace knowledge base to obtain the corresponding chemical detection substances.

[0217] The chemical detection substance is applied to the to-be-detected part of the direct current electric arc furnace, the to-be-detected part of the direct current electric arc furnace including the furnace interior of the direct current electric arc furnace and the furnace wall of the direct current electric arc furnace, reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace are collected, and the reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace are collected;

[0218] The reaction data of the chemical detection substance and the chemical substance in the direct current electric arc furnace are subjected to data feature extraction, to obtain the type, concentration and color data of the chemical substance in the direct current electric arc furnace, and the type, concentration and color data of the chemical substance in the direct current electric arc furnace are compared and analyzed with the preset chemical detection standard to obtain the chemical detection result.

[0219] The technical scheme of the present application effectively solves the problem that the existing direct current electric arc furnace cannot detect the chemical substance in the furnace during actual use, and thus cannot timely predict and warn the state of each device.

[0220] The existing direct current electric arc furnace lacks a means for directly detecting the chemical substance in the furnace in real time, resulting in an inability to accurately grasp the chemical environment in the furnace. Due to the inability to detect the chemical substance in the furnace, it is impossible to predict the working state of the device according to the changes in the chemical substance, and it is also impossible to timely warn when the device state is abnormal.

[0221] Solution approach of the technical scheme of the present application:

[0222] The data acquisition unit initiates a data collection request to the sensor in the direct current electric arc furnace and acquires various basic data including chemical substance concentration data. The detection unit pre-processes and extracts features from the acquired basic data, including chemical substance concentration features. Through data cleaning, calibration and feature extraction, noise and invalid data are removed, and key features are extracted, providing high-quality data for subsequent state detection. The state detection unit establishes and runs a running state detection model based on the extracted feature data to identify the running state of the direct current electric arc furnace. The model can automatically learn the relationship between the chemical substance concentration and other features in the furnace and the device running state through machine learning or deep learning algorithms, thereby achieving accurate identification of the state.

[0223] When the state detection unit identifies a warning or fault state, the warning unit triggers the corresponding warning or fault detection process. By monitoring the chemical substance concentration and other key indicators in the furnace in real time, the warning unit can timely issue a warning before the device state becomes abnormal, providing sufficient time for the operator to take measures to avoid the occurrence or expansion of faults.

[0224] A direct current electric arc furnace knowledge base is constructed to store historical chemical substance detection data. When a device fails, the failure data is retrieved to generate chemical detection substances to detect the chemical substances in the furnace. Based on the detection results and historical data, real-time electrical device adjustment and maintenance data are generated to optimize the device operating state. The construction of the knowledge base provides rich historical data support for data analysis. Through the application of chemical detection substances, the types and concentrations of chemical substances in the furnace can be directly detected to accurately determine the device state. The generated adjustment and maintenance data can specifically address device problems to improve the reliability and stability of the device.

[0225] The technical scheme of the present application realizes real-time detection of chemical substances in a direct current electric arc furnace and accurate prediction of the device state through close cooperation of multiple links such as data acquisition, detection, state recognition, early warning, and data processing. This scheme not only solves the problem of the existing direct current electric arc furnace that cannot detect the chemical substances in the furnace, but also realizes the safe and stable operation of the device through early warning and adjustment and maintenance processes, effectively improving production efficiency and reducing maintenance costs.

[0226] The model and construction steps, uses, and model parameters involved in the present application are as follows:

[0227] Operating state detection model:

[0228] Construction steps:

[0229] Data collection: Collect basic data of the direct current electric arc furnace, including electrical parameters, temperature, arc stability, chemical substance concentration, cooling system data, and device state data.

[0230] Data preprocessing: Clean, calibrate, and feature extract the collected data to form a feature data set.

[0231] Model selection: Select appropriate machine learning or deep learning algorithms (such as support vector machines, random forests, neural networks, etc.) as the model basis.

[0232] Feature engineering: Further select, transform, or construct the feature data set to extract the most useful information for operating state recognition.

[0233] Model training: Use the feature data in the historical data set and the corresponding operating state labels to train the model, and optimize the model parameters through cross-validation, grid search, etc.

[0234] Use of operating state detection model: Used to identify the operating state of the direct current electric arc furnace in real time, including normal state, early warning state, and failure state.

[0235] Running state detection model parameters: specific parameters of machine learning or deep learning algorithms (such as the number of neural network layers, node number, learning rate, etc.). Parameters used in feature selection, transformation or construction process.

[0236] Abnormality detection model construction steps:

[0237] Data collection: collect the types, concentrations and trends of chemical substances in the furnace.

[0238] Threshold setting: set the normal range threshold of the furnace chemical substance data according to historical data and actual operation experience.

[0239] Abnormality detection model construction: based on the set threshold, construct the abnormality detection model.

[0240] Use of abnormality detection model: used for real-time monitoring of the state of chemical substances in the furnace, and compared with the threshold, when the data exceeds the normal range, trigger an alarm, prompt the existence of equipment failure or safety hazard.

[0241] Model parameters of abnormality detection model: normal range threshold of furnace chemical substance data.

[0242] Prediction model construction steps:

[0243] Data collection: collect historical data and current data, including changes in furnace temperature, pressure, chemical composition concentration, and equipment running time, load, etc.

[0244] Model selection: select appropriate time series analysis, machine learning or deep learning algorithm as the basis of the prediction model.

[0245] Model training: use historical data and current data to train the prediction model, optimize model parameters to improve prediction accuracy.

[0246] Use of prediction model: used for predicting the future trend of furnace chemical substance state and equipment operation, providing decision support for operators.

[0247] Prediction model parameters: specific parameters of time series analysis, machine learning or deep learning algorithms.

[0248] Historical data and current data used to train the model.

[0249] When using distillation algorithm to optimize real-time electrical equipment adjustment and maintenance data, the specific steps can be summarized as follows:

[0250] Determine the target of knowledge distillation: clarify the target of distillation algorithm, that is, to improve the accuracy and effectiveness of real-time electrical equipment adjustment and maintenance data, and make it closer to the preset standard data of direct current electric furnace.

[0251] Teacher model construction: Select or construct a superior-performing teacher model. In this scenario, the teacher model can be a model based on historical best electrical equipment adjustment and maintenance data and DC furnace operating status, which can accurately predict and adjust the equipment status. The teacher model should have high accuracy and generalization ability, and can serve as a reference standard for real-time electrical equipment adjustment and maintenance data optimization.

[0252] Prepare student model: The student model is the real-time electrical equipment adjustment and maintenance data model that needs to be optimized.

[0253] Initialize the parameters of the student model, which come from preliminary adjustment and maintenance data or simple rule-based models.

[0254] Data preparation: Prepare training data for distillation, including historical best electrical equipment adjustment and maintenance data, corresponding DC furnace operating status data, and current real-time electrical equipment adjustment and maintenance data.

[0255] Knowledge distillation process:

[0256] Prediction phase: First, let the teacher model predict the training data to get the teacher model's prediction results.

[0257] Learning phase: Then, let the student model also predict these training data and compare its prediction results with the teacher model's prediction results.

[0258] Loss calculation: Calculate the difference between the student model's prediction and the teacher model's prediction, i.e., the distillation loss. At the same time, the standard loss can also be calculated by combining the true labels of the original data.

[0259] Backpropagation and optimization: Through the backpropagation algorithm, the parameters of the student model are optimized according to the distillation loss and the standard loss.

[0260] Model evaluation and adjustment:

[0261] During the distillation process, the performance of the student model is regularly evaluated to ensure that the optimization direction is correct.

[0262] According to the evaluation results, adjust the hyperparameters in the distillation process, such as the weights of distillation loss and standard loss, learning rate, etc.

[0263] Output the optimized model: When the performance of the student model meets the expectations, stop the distillation process and output the optimized real-time electrical equipment adjustment and maintenance data model.

[0264] Deployment and application: Deploy the optimized model to the DC furnace equipment end to guide the actual electrical equipment adjustment and maintenance work.

[0265] Through these steps, the distillation algorithm can effectively transfer the knowledge of the teacher model to the student model, improve the accuracy and effectiveness of real-time electrical equipment adjustment and maintenance data, and thus optimize the operation state of the direct current smelting furnace.

Claims

1. A DC submerged arc furnace, characterized in that, include: The data acquisition unit is used to acquire basic data of the DC submerged arc furnace; The detection unit is used to preprocess the basic data of the DC submerged arc furnace to obtain the feature group of the basic data of the DC submerged arc furnace. The status detection unit is used to establish an operating status detection model for the DC submerged arc furnace based on the basic data feature group of the DC submerged arc furnace. It extracts features from the DC submerged arc furnace collected in real time and inputs them into the operating status detection model of the DC submerged arc furnace to generate DC submerged arc furnace status detection results. The DC submerged arc furnace status detection results include normal status, warning status, and fault status of the DC submerged arc furnace. The early warning unit is used to trigger the DC electric arc furnace early warning process when the DC electric arc furnace status detection result is a DC electric arc furnace status early warning state, and to trigger the DC electric arc furnace fault detection process when the DC electric arc furnace status detection result is a DC electric arc furnace status fault state. The data processing unit is used to acquire historical operating data of the DC submerged arc furnace, build a DC submerged arc furnace knowledge base, retrieve fault data corresponding to the fault status of the DC submerged arc furnace to obtain real-time fault data, extract data features from the real-time fault data, match the obtained real-time fault feature data with the DC submerged arc furnace knowledge base to obtain real-time fault feature association data, which includes historical chemical substance detection data and historical electrical equipment adjustment and maintenance data. Based on the historical chemical substance detection data, a list or formula of chemical testing substances is generated, and the DC submerged arc furnace is tested using the list or formula of chemical testing substances to obtain the chemical testing results of the DC submerged arc furnace. The chemical testing results of the DC submerged arc furnace are matched with the historical electrical equipment adjustment and maintenance data to obtain real-time electrical equipment adjustment and maintenance data, and the real-time electrical equipment adjustment and maintenance data is sent to the equipment end of the DC submerged arc furnace. Also used for: Collect data on chemical substances inside the furnace, and identify the types, concentrations, and trends of chemical substances inside the furnace through a preset algorithm model; Receive and set thresholds, build an anomaly detection model, use the anomaly detection model to detect the types, concentrations and changing trends of chemical substances in the furnace, obtain the anomaly detection results of chemical substances in the furnace, and alarm for data that exceeds the normal range, indicating the existence of equipment failure or safety hazards. Based on historical and current data, predict future trends in the state of chemical substances inside the furnace and the operation of the equipment.

2. The DC submerged arc furnace according to claim 1, characterized in that, The data acquisition unit is also used for: The data acquisition unit initiates a data acquisition request to the sensors inside the DC submerged arc furnace, requesting real-time data on the chemical substances inside the furnace. The request message body carries the address of the data acquisition unit, the address of the sensor, the time range of the requested data, and the data type of the requested data, which includes temperature, pressure, and chemical composition concentration. The sensor responds to the request and returns the raw detection data of the DC submerged arc furnace.

3. A DC submerged arc furnace according to claim 1, characterized in that, The detection unit is also used for: The detection unit receives raw detection data from the sensor, removes duplicate, invalid, or incorrectly formatted data, calibrates the cleaned data, and labels temperature data, pressure data, and chemical component concentration data according to the characteristics of the detection data.

4. A DC submerged arc furnace according to claim 1, characterized in that, The data processing unit is also used for: Historical chemical substance detection data are retrieved from the DC submerged arc furnace knowledge base. The retrieved historical chemical substance detection data is preprocessed to obtain preprocessed historical chemical substance detection data. A pre-defined algorithm model is used to analyze the pre-processed historical chemical substance detection data to identify the chemical substances in the DC electric arc furnace and the characteristics of the DC electric arc furnace. Based on the chemical substances inside the DC submerged arc furnace and the characteristics of the DC submerged arc furnace, the corresponding chemical detection substances are selected by matching them in the DC submerged arc furnace knowledge base. The chemical detection substance is applied to the detection area of ​​the DC submerged arc furnace, which includes the furnace interior and furnace wall. Reaction data between the chemical detection substance and the chemical substances in the DC submerged arc furnace are collected. Data features are extracted from the reaction data of chemical substances and chemical substances in the DC submerged arc furnace to obtain the types, concentrations, and colors of chemical substances in the DC submerged arc furnace. The data of types, concentrations, and colors of chemical substances in the DC submerged arc furnace are then compared and analyzed with preset chemical detection standards to obtain chemical detection results. The system collects operational data from the DC submerged arc furnace after real-time electrical equipment adjustment and maintenance. This results in adjusted operational data, which is then compared with preset standard data for the DC submerged arc furnace. If the adjusted operational data does not match the preset standard data, a distillation algorithm is used to optimize the real-time electrical equipment adjustment and maintenance data. The optimized real-time electrical equipment adjustment and maintenance data is then sent back to the DC submerged arc furnace.

5. A DC submerged arc furnace detection system, applied to a DC submerged arc furnace as described in any one of claims 1 to 4, characterized in that, include: The system consists of a server, a data acquisition terminal, and a DC submerged arc furnace equipment terminal. The server establishes communication connections with both the data acquisition terminal and the DC submerged arc furnace equipment terminal. The server-side includes: The data acquisition unit is used to acquire basic data of the DC submerged arc furnace; The detection unit is used to preprocess the basic data of the DC submerged arc furnace to obtain the feature group of the basic data of the DC submerged arc furnace. The status detection unit is used to establish an operating status detection model for the DC submerged arc furnace based on the basic data feature group of the DC submerged arc furnace. It extracts features from the DC submerged arc furnace collected in real time and inputs them into the operating status detection model of the DC submerged arc furnace to generate DC submerged arc furnace status detection results. The DC submerged arc furnace status detection results include normal status, warning status, and fault status of the DC submerged arc furnace. The early warning unit is used to trigger the DC electric arc furnace early warning process when the DC electric arc furnace status detection result is a DC electric arc furnace status early warning state, and to trigger the DC electric arc furnace fault detection process when the DC electric arc furnace status detection result is a DC electric arc furnace status fault state. The data processing unit is used to acquire historical operating data of the DC submerged arc furnace, build a DC submerged arc furnace knowledge base, retrieve fault data corresponding to the fault status of the DC submerged arc furnace to obtain real-time fault data, extract data features from the real-time fault data, match the obtained real-time fault feature data with the DC submerged arc furnace knowledge base to obtain real-time fault feature association data, which includes historical chemical substance detection data and historical electrical equipment adjustment and maintenance data. Based on the historical chemical substance detection data, a list or formula of chemical testing substances is generated, and the DC submerged arc furnace is tested using the list or formula of chemical testing substances to obtain the chemical testing results of the DC submerged arc furnace. The chemical testing results of the DC submerged arc furnace are matched with the historical electrical equipment adjustment and maintenance data to obtain real-time electrical equipment adjustment and maintenance data, and the real-time electrical equipment adjustment and maintenance data is sent to the equipment end of the DC submerged arc furnace. The data processing unit is also used for: Collect data on chemical substances inside the furnace, and identify the types, concentrations, and trends of chemical substances inside the furnace through a preset algorithm model; Receive and set thresholds, build an anomaly detection model, use the anomaly detection model to detect the types, concentrations and changing trends of chemical substances in the furnace, obtain the anomaly detection results of chemical substances in the furnace, and alarm for data that exceeds the normal range, indicating the existence of equipment failure or safety hazards. Based on historical and current data, predict future trends in the state of chemical substances inside the furnace and the operation of the equipment.

6. The DC submerged arc furnace detection system according to claim 5, characterized in that, The data acquisition unit is also used for: The data acquisition unit initiates a data acquisition request to the sensors inside the DC submerged arc furnace, requesting real-time data on the chemical substances inside the furnace. The request message body carries the address of the data acquisition unit, the address of the sensor, the time range of the requested data, and the data type of the requested data, which includes temperature, pressure, and chemical composition concentration. The sensor responds to the request and returns the raw detection data of the DC submerged arc furnace.

7. The DC submerged arc furnace detection system according to claim 5, characterized in that, The detection unit is also used for: The detection unit receives raw detection data from the sensor, removes duplicate, invalid, or incorrectly formatted data, calibrates the cleaned data, and labels temperature data, pressure data, and chemical component concentration data according to the characteristics of the detection data.

8. The DC submerged arc furnace detection system according to claim 5, characterized in that, The data processing unit is also used for: Historical chemical substance detection data are retrieved from the DC submerged arc furnace knowledge base. The retrieved historical chemical substance detection data is preprocessed to obtain preprocessed historical chemical substance detection data. A pre-defined algorithm model is used to analyze the pre-processed historical chemical substance detection data to identify the chemical substances in the DC electric arc furnace and the characteristics of the DC electric arc furnace. Based on the chemical substances inside the DC submerged arc furnace and the characteristics of the DC submerged arc furnace, the corresponding chemical detection substances are selected by matching them in the DC submerged arc furnace knowledge base. The chemical detection substance is applied to the detection area of ​​the DC submerged arc furnace, which includes the furnace interior and furnace wall. Reaction data between the chemical detection substance and the chemical substances in the DC submerged arc furnace are collected. Data features are extracted from the reaction data of chemical substances and chemical substances in the DC submerged arc furnace to obtain the types, concentrations, and colors of chemical substances in the DC submerged arc furnace. The data of types, concentrations, and colors of chemical substances in the DC submerged arc furnace are then compared and analyzed with preset chemical detection standards to obtain chemical detection results. The system collects operational data from the DC submerged arc furnace after real-time electrical equipment adjustment and maintenance. This results in adjusted operational data, which is then compared with preset standard data for the DC submerged arc furnace. If the adjusted operational data does not match the preset standard data, a distillation algorithm is used to optimize the real-time electrical equipment adjustment and maintenance data. The optimized real-time electrical equipment adjustment and maintenance data is then sent back to the DC submerged arc furnace.

Images