Blast furnace process furnace condition detection method and device

Abstract

The invention provides a blast furnace process furnace condition detection method and device, which can be used in the technical field of artificial intelligence, and the method comprises the following steps: obtaining blast furnace process data; performing data mining on the blast furnace process data to obtain furnace condition index data; through the pre-constructed furnace condition state detection model, the furnace condition is detected according to the furnace condition index data, the furnace condition detection result is obtained, the blast furnace process data can be obtained in real time, data mining is carried out, automatic furnace condition detection is achieved, and the objectivity, accuracy and data stability of the detection result are improved; data is acquired in real time for analysis and detection, and the detection timeliness is improved; the furnace condition is automatically detected, and the detection efficiency and the data utilization rate are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, in particular to the field of artificial intelligence technology, and more particularly to a method and device for detecting a blast furnace process condition. Background Art

[0002] Blast furnace process condition analysis is a crucial process control link in the steel industry. It has a significant impact on the stability, efficiency and product quality of the blast furnace smelting process. Traditional blast furnace condition analysis mainly relies on the operator's experience and offline data analysis. Operators judge and analyze the furnace condition by observing the external indicators and operating parameters of the blast furnace, as well as the data obtained by sampling and analysis. However, this method is based on manual experience as the main method for furnace condition detection, which is highly dependent on the operator's experience and feeling, and is subjective and unstable, which can easily lead to errors and delays in furnace condition control; offline sampling and laboratory analysis have the problem of data feedback lag and poor timeliness; the amount of data generated during the operation of the blast furnace is huge, and the traditional manual analysis and processing methods are inefficient and cannot fully mine the valuable information in the data. Summary of the invention

[0003] One object of the present invention is to provide a blast furnace process condition detection method, which can obtain blast furnace process data in real time and perform data mining, realize automatic furnace condition detection, improve the objectivity, accuracy and data stability of the detection results; obtain data in real time for analysis and detection, improve the timeliness of detection; automatically perform furnace condition detection, improve detection efficiency and data utilization. Another object of the present invention is to provide a blast furnace process condition detection device. Another object of the present invention is to provide a computer readable medium. Another object of the present invention is to provide a computer device.

[0004] In order to achieve the above objectives, the present invention discloses a method for detecting a blast furnace process condition, comprising:

[0005] Obtain blast furnace process data;

[0006] Conduct data mining on blast furnace process data to obtain furnace condition index data;

[0007] Through the pre-built furnace condition detection model, the furnace condition detection is carried out according to the furnace condition index data to obtain the furnace condition detection result.

[0008] Preferably, data mining is performed on the blast furnace process data to obtain furnace condition index data, including:

[0009] Conducting correlation data mining on blast furnace process data to obtain furnace condition index data; or,

[0010] Extract features from blast furnace process data to obtain furnace condition features;

[0011] The furnace condition characteristics and preset furnace condition target variables are determined as furnace condition index data.

[0012] Preferably, the blast furnace process data is mined for associated data to obtain furnace condition index data, including:

[0013] The blast furnace process data is mined through association rule mining algorithm to obtain frequent item sets, which are then determined as furnace condition index data.

[0014] Preferably, the blast furnace process data is mined for associated data to obtain furnace condition index data, including:

[0015] The blast furnace process data is clustered by cluster analysis algorithm to obtain data clustering results, which are then determined as furnace condition index data.

[0016] Preferably, before data mining is performed on the blast furnace process data to obtain furnace condition index data, the method further includes:

[0017] Perform data cleaning on blast furnace process data to obtain cleaned process data;

[0018] The missing value processing is performed on the cleaned process data to obtain the preprocessed blast furnace process data.

[0019] Preferably, the method further comprises:

[0020] Obtain historical process data;

[0021] Through historical process data, the preset big data analysis model is trained to build an initial detection model. The big data analysis model includes decision tree model, support vector machine model, random forest model, linear programming model, genetic algorithm model and neural network model;

[0022] Through the optimization algorithm, the initial detection model is optimized and the furnace condition detection model is constructed.

[0023] Preferably, after performing furnace condition detection according to furnace condition index data by using a pre-built furnace condition detection model to obtain a furnace condition detection result, the method further includes:

[0024] If the furnace condition detection result is an abnormal result, a furnace condition warning message is generated according to the furnace condition detection result;

[0025] The furnace condition warning message is sent to the user terminal through the preset warning method.

[0026] The present invention also discloses a blast furnace process condition detection device, comprising:

[0027] Real-time data acquisition unit, used to acquire blast furnace process data;

[0028] A data mining unit is used to perform data mining on blast furnace process data to obtain furnace condition index data;

[0029] The furnace condition detection unit is used to perform furnace condition detection according to furnace condition index data through a pre-built furnace condition detection model to obtain a furnace condition detection result.

[0030] Preferably, the data mining unit is specifically used to perform associated data mining on blast furnace process data to obtain furnace condition index data; or, perform feature extraction on blast furnace process data to obtain furnace condition features; and determine the furnace condition features and preset furnace condition target variables as furnace condition index data.

[0031] Preferably, the data mining unit is specifically used to mine the blast furnace process data through an association rule mining algorithm to obtain frequent item sets, and determine the frequent item sets as furnace condition index data.

[0032] Preferably, the data mining unit is specifically used to cluster the blast furnace process data through a cluster analysis algorithm to obtain data clustering results, and determine the data clustering results as furnace condition index data.

[0033] Preferably, the device further comprises:

[0034] A data cleaning unit is used to clean the blast furnace process data to obtain cleaned process data;

[0035] The data filling unit is used to process missing values ​​of the cleaned process data to obtain pre-processed blast furnace process data.

[0036] Preferably, the device further comprises:

[0037] A historical data acquisition unit, used for acquiring historical process data;

[0038] A model training unit is used to train a preset big data analysis model through historical process data to build an initial detection model. The big data analysis model includes a decision tree model, a support vector machine model, a random forest model, a linear programming model, a genetic algorithm model, and a neural network model;

[0039] The model optimization unit is used to optimize the initial detection model through an optimization algorithm and construct a furnace condition detection model.

[0040] Preferably, the device further comprises:

[0041] The warning message generating unit is used to generate a furnace condition warning message according to the furnace condition detection result if the furnace condition detection result is an abnormal result;

[0042] The furnace condition warning unit is used to send the furnace condition warning message to the user terminal through a preset warning method.

[0043] The present invention also discloses a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.

[0044] The present invention also discloses a computer device, including a memory and a processor, wherein the memory is used to store information including program instructions, the processor is used to control the execution of program instructions, and the processor implements the above method when executing the program.

[0045] The present invention also discloses a computer program product, including a computer program / instruction, and the method described above is implemented when the computer program / instruction is executed by a processor.

[0046] The present invention acquires blast furnace process data; performs data mining on the blast furnace process data to obtain furnace condition index data; performs furnace condition detection according to the furnace condition index data through a pre-constructed furnace condition state detection model to obtain a furnace condition detection result, and can acquire blast furnace process data in real time and perform data mining to realize automatic furnace condition detection, thereby improving the objectivity, accuracy and data stability of the detection result; acquires data in real time for analysis and detection, thereby improving the timeliness of detection; and automatically performs furnace condition detection to improve detection efficiency and data utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A flow chart of a blast furnace process condition detection method provided by an embodiment of the present invention;

[0049] Figure 2 A flow chart of another blast furnace process condition detection method provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the structure of a blast furnace process condition detection device provided by an embodiment of the present invention;

[0051] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] It should be noted that the blast furnace process condition detection method and device disclosed in the present application can be used in the field of artificial intelligence technology, and can also be used in any field outside the field of artificial intelligence technology. The application field of the blast furnace process condition detection method and device disclosed in the present application is not limited.

[0054] In order to facilitate the understanding of the technical solution provided by the present application, the relevant contents of the technical solution of the present application are described below. The blast furnace is a device that reduces iron ore to molten iron, with a complex smelting process and variable process parameters, such as ore composition, charge ratio, fuel combustion status, etc. In order to achieve the safety, stability and efficiency of blast furnace smelting, it is very important to accurately monitor and timely analyze the blast furnace condition. The goal of modern blast furnace process condition analysis is to use advanced technologies such as big data technology, machine learning and artificial intelligence to achieve real-time monitoring, abnormality detection and optimization control of blast furnace conditions. By real-time collection and analysis of various data in the blast furnace smelting process, including temperature, pressure, flow, chemical composition and other parameters, the operating status of the blast furnace can be fully understood, abnormal conditions can be discovered in time, and corresponding adjustments and optimization measures can be made. Blast furnace condition analysis based on big data can provide accurate, real-time and comprehensive data support, help operators quickly understand the operation of the blast furnace, and make scientific decisions based on data analysis results. By establishing a mathematical model and prediction model for the blast furnace, key indicators in the blast furnace smelting process can be predicted and optimized to improve production efficiency and product quality stability. At the same time, data mining and intelligent algorithms can also be used to discover the rules and associations hidden in big data, providing new ideas and methods for optimizing blast furnace smelting. Therefore, the research and development and application of blast furnace condition analysis technology based on big data are of great significance and have broad application prospects. It can improve the intelligence level of blast furnace smelting process, optimize process control strategies, improve production efficiency and product quality, and achieve sustainable development of the steel industry.

[0055] In order to achieve the purpose of intelligent and efficient analysis of blast furnace conditions, this application uses a distributed data warehouse to uniformly summarize the production information, quality information, inspection and testing information and other data of key positions during the operation of the blast furnace, and cleans and processes the data during the data access process, and then completes the data stratification and partitioning for different purposes. After completing data aggregation, cleaning processing and stratification and partitioning, based on data, big data analysis technology is used for in-depth analysis and data mining, to understand the characteristics and changing trends of furnace condition data, and according to the current furnace condition data, predict the changing trend of furnace condition, provide optimization suggestions, etc., aiming to use big data analysis and inference machine algorithms to improve the accuracy, real-time and comprehensiveness of blast furnace condition analysis, and realize the safe, high-quality and low-consumption production of blast furnaces.

[0056] The following takes a blast furnace process condition detection device as an example to illustrate the implementation process of the blast furnace process condition detection method provided by the embodiment of the present invention. It is understandable that the execution subject of the blast furnace process condition detection method provided by the embodiment of the present invention includes but is not limited to a blast furnace process condition detection device.

[0057] Figure 1 A flow chart of a blast furnace process condition detection method provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0058] Step 101: Obtain blast furnace process data.

[0059] Step 102: perform data mining on blast furnace process data to obtain furnace condition index data.

[0060] Step 103: Perform furnace condition detection according to furnace condition index data using a pre-built furnace condition detection model to obtain a furnace condition detection result.

[0061] In the technical solution provided by the embodiment of the present invention, blast furnace process data is acquired; data mining is performed on the blast furnace process data to obtain furnace condition index data; through a pre-constructed furnace condition state detection model, furnace condition detection is performed according to the furnace condition index data to obtain a furnace condition detection result, the blast furnace process data can be acquired in real time and data mining can be performed to realize automated furnace condition detection, thereby improving the objectivity, accuracy and data stability of the detection results; data is acquired in real time for analysis and detection to improve the timeliness of detection; furnace condition detection is performed automatically to improve detection efficiency and data utilization.

[0062] Figure 2 A flow chart of another blast furnace process condition detection method provided by an embodiment of the present invention is as follows: Figure 2 As shown, the method includes:

[0063] Step 201: Obtain blast furnace process data.

[0064] In the embodiment of the present invention, each step is performed by a blast furnace process condition detection device.

[0065] In an embodiment of the present invention, blast furnace process data during the operation of the blast furnace is collected in real time through sensors and monitoring equipment. The blast furnace process data includes but is not limited to the temperature, pressure, flow, raw material composition, ratio, gas composition, feed rate, and discharge rate inside the blast furnace.

[0066] In an embodiment of the present invention, data acquisition devices such as sensors and monitoring equipment collect blast furnace process data from different measurement points through an interface connected to the blast furnace system. The data type of the blast furnace process data includes but is not limited to semi-structured or unstructured data such as audio / video, pictures, and documents.

[0067] Furthermore, a storage and management system for blast furnace condition data is established to store, clean and organize the collected blast furnace process data to ensure the integrity and accuracy of the data. The embodiment of the present invention supports the storage and analysis of big data with distributed system infrastructure (Hadoop) as the core, and provides a variety of storage types according to different data usage scenarios to meet different data scales, data processing methods, data sharing methods, and storage cycle requirements. A mature and general data storage computing solution is adopted to plan the data storage layer to form a data warehouse architecture such as the source layer, data warehouse layer, and market layer. And the data capacity supports horizontal expansion. The data therein can be accessed, processed, analyzed, and transmitted.

[0068] Step 202: clean the blast furnace process data to obtain cleaned process data.

[0069] In the embodiment of the present invention, data cleaning includes removing noise data and abnormal data in the blast furnace process data to obtain cleaned process data.

[0070] In the embodiment of the present invention, cleaning the data can ensure the reliability and accuracy of the data.

[0071] Step 203: Process the missing values ​​of the cleaned process data to obtain pre-processed blast furnace process data.

[0072] As an optional solution, the missing values ​​of the cleaned process data are interpolated through an interpolation method to fill in the missing values ​​and obtain the preprocessed blast furnace process data.

[0073] It is worth noting that the missing data may also be filled by other missing value processing methods, which is not limited in the embodiment of the present invention.

[0074] In the embodiment of the present invention, missing value processing can ensure the integrity and consistency of data.

[0075] Furthermore, the blast furnace process data is converted and normalized so that data of different dimensions can be compared and analyzed, thereby improving data processing efficiency.

[0076] Step 204: perform data mining on the blast furnace process data to obtain furnace condition index data.

[0077] In an embodiment of the present invention, associated data mining is performed on blast furnace process data to obtain furnace condition index data; or, feature extraction is performed on blast furnace process data to obtain furnace condition features; the furnace condition features and preset furnace condition target variables are determined as furnace condition index data.

[0078] As an optional solution, the blast furnace process data is mined through an association rule mining algorithm to obtain frequent item sets, and the frequent item sets are determined as furnace condition index data. Among them, the association rule mining algorithm is the Apriori algorithm. Specifically, the blast furnace process data is mined for frequent item sets through the Apriori algorithm to obtain frequent item sets. The frequent item sets indicate which raw material components, ratios, temperatures, pressures and other process parameters frequently appear in combination, that is, the associations and rules between the process parameters that appear frequently in combination. For example, "blast furnace temperature is related to raw material ratio", "blast furnace pressure is related to raw material composition" and other rules with practical significance.

[0079] As another optional solution, the blast furnace process data is clustered by a cluster analysis algorithm to obtain data clustering results, and the data clustering results are determined as furnace condition index data. The cluster analysis algorithm is a K-means algorithm. Specifically, the blast furnace process parameters are clustered by the K-means algorithm, and similar blast furnace process parameters are clustered together to obtain data clustering results, which are the inherent connections and laws between process parameters such as raw material composition, ratio, temperature, and pressure.

[0080] As another optional solution, feature extraction is performed on blast furnace process data through a feature extraction algorithm to obtain furnace condition features, which include but are not limited to raw material composition features, ratio features, temperature features, and pressure features; the furnace condition features and preset furnace condition target variables are determined as furnace condition index data. The furnace condition target variables are set according to actual needs, and the embodiment of the present invention does not limit this. For example, furnace condition target variables include but are not limited to output and energy consumption.

[0081] In the embodiment of the present invention, based on the big data analysis technology, it is possible to comprehensively consider the correlation and influence between multiple furnace condition indicators, comprehensively analyze the operation of the blast furnace, and discover potential key factors and optimization space.

[0082] Step 205, perform furnace condition detection according to furnace condition index data through the pre-constructed furnace condition detection model to obtain a furnace condition detection result. If the furnace condition detection result is an abnormal result, continue to step 206; if the furnace condition detection result is a normal result, continue to step 201.

[0083] Specifically, the furnace condition index data is input into the furnace condition state detection model, and the furnace condition state is classified and predicted according to the furnace condition index data to obtain the furnace condition detection result. The furnace condition detection result includes an abnormal result or a normal result. The abnormal result indicates that the furnace condition of the blast furnace will be abnormal in the future, and the normal result indicates that the furnace condition of the blast furnace will be in a normal operating state in the future.

[0084] In an embodiment of the present invention, a furnace condition detection model is pre-constructed. Specifically, historical process data is obtained; a preset big data analysis model is trained through the historical process data to construct an initial detection model, and the big data analysis model includes a decision tree model, a support vector machine model, a random forest model, a linear programming model, a genetic algorithm model, and a neural network model; the initial detection model is optimized through an optimization algorithm to construct a furnace condition detection model. Among them, the historical process data can be obtained from various departments such as a database or a production line and a laboratory, and the historical process data includes but is not limited to the temperature, historical pressure, historical flow, historical raw material composition, historical ratio, historical gas composition, historical feed amount, and historical discharge amount inside the historical blast furnace. The optimization algorithm includes a cross-validation algorithm and a grid search algorithm; the initial detection model is optimized through the optimization algorithm, the model parameters are adjusted, and a furnace condition detection model is constructed to improve the accuracy and generalization ability of the model.

[0085] Furthermore, the initial detection model can be optimized by adding training data to construct a furnace condition detection model.

[0086] It is worth noting that the specific selection of the big data analysis model can be selected according to actual detection requirements, and the embodiments of the present invention do not limit this.

[0087] In the embodiment of the present invention, by utilizing a big data analysis method and conducting in-depth mining and analysis of a large amount of historical process data, more subtle changes in furnace conditions and abnormal conditions can be discovered, and the operating status of the blast furnace can be accurately determined.

[0088] Furthermore, the furnace condition index data of each detection and the corresponding furnace condition detection results are input into the furnace condition state detection model for model update optimization to obtain an updated and optimized furnace condition state detection model, thereby continuously improving the accuracy of the furnace condition state detection model.

[0089] In the embodiment of the present invention, the inference engine algorithm is combined with the blast furnace process data collected in real time, and can monitor the changes of furnace condition indicators in real time, and make predictions based on historical data and models, so as to timely discover potential problems and take measures in advance for adjustment and optimization; through the reasoning and inference capabilities of the inference engine, it provides decision support and optimization suggestions for engineers, helping them to quickly and accurately evaluate the furnace condition and formulate corresponding operation strategies and optimization measures.

[0090] Step 206: Generate a furnace condition warning message according to the furnace condition detection result.

[0091] In the embodiment of the present invention, the furnace condition warning information includes but is not limited to furnace condition detection results and corresponding furnace condition index data.

[0092] Step 207: Send the furnace condition warning message to the user terminal through a preset warning method.

[0093] In the embodiment of the present invention, the warning method includes but is not limited to sound warning, visual warning or email.

[0094] Specifically, the furnace condition warning message is sent to the user terminal or displayed in a warning manner, so as to promptly inform the engineer of the furnace condition detection results, so that the engineer can take corresponding warning measures in time. The warning measures include but are not limited to adjusting the raw material ratio, temperature, pressure and other process parameters to ensure the stability and economy of the blast furnace process.

[0095] The present invention uses big data analysis technology to achieve real-time monitoring and prediction of blast furnace conditions, thereby improving the efficiency and accuracy of furnace condition control; based on machine learning and data mining technology, a furnace condition detection model is constructed, which can accurately predict future furnace conditions, timely warn of abnormal furnace conditions, and provide intelligent decision support to help engineers take corresponding regulatory measures; through real-time reasoning and prediction, the operation strategy of the blast furnace is optimized, the efficiency of steel production and product quality are improved, the intelligent management of blast furnace conditions is achieved, the stability and controllability of the steelmaking process are improved, the production cost is reduced, and the product quality is improved, which has important economic and social benefits.

[0096] It is worth noting that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. The user information in the embodiments of this application is obtained through legal and compliant channels, and the acquisition, storage, use, and processing of user information are authorized and agreed by the customer.

[0097] In the technical solution of the blast furnace process condition detection method provided by the embodiment of the present invention, blast furnace process data is obtained; data mining is performed on the blast furnace process data to obtain furnace condition index data; through a pre-constructed furnace condition state detection model, furnace condition detection is performed according to the furnace condition index data to obtain a furnace condition detection result, and the blast furnace process data can be obtained in real time and data mining can be performed to realize automated furnace condition detection, thereby improving the objectivity, accuracy and data stability of the detection results; data is obtained in real time for analysis and detection to improve the timeliness of detection; and furnace condition detection is performed automatically to improve detection efficiency and data utilization.

[0098] Figure 3 A schematic diagram of the structure of a blast furnace process condition detection device provided by an embodiment of the present invention, the device is used to perform the above-mentioned blast furnace process condition detection method, such as Figure 3 As shown, the device includes: a real-time data acquisition unit 11, a data mining unit 12 and a furnace condition detection unit 13.

[0099] The real-time data acquisition unit 11 is used to acquire blast furnace process data.

[0100] The data mining unit 12 is used to perform data mining on blast furnace process data to obtain furnace condition index data.

[0101] The furnace condition detection unit 13 is used to perform furnace condition detection according to furnace condition index data through a pre-built furnace condition detection model to obtain a furnace condition detection result.

[0102] In an embodiment of the present invention, the data mining unit 12 is specifically used to perform associated data mining on blast furnace process data to obtain furnace condition index data; or, to perform feature extraction on blast furnace process data to obtain furnace condition features; and to determine the furnace condition features and preset furnace condition target variables as furnace condition index data.

[0103] In the embodiment of the present invention, the data mining unit 12 is specifically used to mine the blast furnace process data through an association rule mining algorithm to obtain frequent item sets, and determine the frequent item sets as furnace condition index data.

[0104] In the embodiment of the present invention, the data mining unit 12 is specifically used to cluster the blast furnace process data through a cluster analysis algorithm to obtain data clustering results, and determine the data clustering results as furnace condition index data.

[0105] In the embodiment of the present invention, the device further includes: a data cleaning unit 14 and a data filling unit 15 .

[0106] The data cleaning unit 14 is used to clean the blast furnace process data to obtain cleaned process data.

[0107] The data filling unit 15 is used to process missing values ​​of the cleaned process data to obtain pre-processed blast furnace process data.

[0108] In the embodiment of the present invention, the device further includes: a historical data acquisition unit 16 , a model training unit 17 and a model optimization unit 18 .

[0109] The historical data acquisition unit 16 is used to acquire historical process data.

[0110] The model training unit 17 is used to train the preset big data analysis model through historical process data to construct an initial detection model. The big data analysis model includes a decision tree model, a support vector machine model, a random forest model, a linear programming model, a genetic algorithm model and a neural network model.

[0111] The model optimization unit 18 is used to optimize the initial detection model through an optimization algorithm to construct a furnace condition detection model.

[0112] In the embodiment of the present invention, the device further includes: an early warning message generating unit 19 and a furnace condition early warning unit 20 .

[0113] The warning message generating unit 19 is used to generate a furnace condition warning message according to the furnace condition detection result if the furnace condition detection result is an abnormal result.

[0114] The furnace condition warning unit 20 is used to send a furnace condition warning message to a user terminal through a preset warning method.

[0115] In the scheme of the embodiment of the present invention, blast furnace process data is obtained; data mining is performed on the blast furnace process data to obtain furnace condition index data; through a pre-constructed furnace condition state detection model, furnace condition detection is performed according to the furnace condition index data to obtain a furnace condition detection result, the blast furnace process data can be obtained in real time and data mining can be performed to realize automated furnace condition detection, thereby improving the objectivity, accuracy and data stability of the detection results; data is obtained in real time for analysis and detection to improve the timeliness of detection; furnace condition detection is performed automatically to improve detection efficiency and data utilization.

[0116] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer device, and specifically, the computer device may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0117] An embodiment of the present invention provides a computer device, including a memory and a processor, the memory is used to store information including program instructions, the processor is used to control the execution of the program instructions, and when the program instructions are loaded and executed by the processor, the steps of the embodiment of the above-mentioned blast furnace process condition detection method are implemented. For a specific description, please refer to the embodiment of the above-mentioned blast furnace process condition detection method.

[0118] Reference below Figure 4 , which shows a schematic diagram of the structure of a computer device 600 suitable for implementing an embodiment of the present application.

[0119] like Figure 4 As shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate operations and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer device 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0120] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal feedback device (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed as needed as the storage section 608.

[0121] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 609, and / or installed from the removable medium 611.

[0122] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0123] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0124] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0125] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0127] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0128] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0129] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0130] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0131] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0132] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for detecting blast furnace process conditions, It is characterized in that The method comprises: Obtain blast furnace process data; Performing data mining on the blast furnace process data to obtain furnace condition index data; The furnace condition detection is performed according to the furnace condition index data by using the pre-constructed furnace condition detection model to obtain the furnace condition detection result.

2. The blast furnace process condition detection method according to claim 1, It is characterized in that The data mining of the blast furnace process data to obtain furnace condition index data includes: Performing associated data mining on the blast furnace process data to obtain furnace condition index data; or, Extracting features from the blast furnace process data to obtain furnace condition features; The furnace condition characteristics and preset furnace condition target variables are determined as the furnace condition index data.

3. The blast furnace process condition detection method according to claim 2, It is characterized in that The associated data mining of the blast furnace process data to obtain furnace condition index data includes: The blast furnace process data is mined by an association rule mining algorithm to obtain frequent item sets, and the frequent item sets are determined as furnace condition index data.

4. The blast furnace process condition detection method according to claim 2, It is characterized in that The associated data mining of the blast furnace process data to obtain furnace condition index data includes: The blast furnace process data is clustered by a cluster analysis algorithm to obtain a data clustering result, and the data clustering result is determined as the furnace condition index data.

5. The blast furnace process condition detection method according to claim 1, It is characterized in that Before performing data mining on the blast furnace process data to obtain furnace condition index data, the method further includes: Performing data cleaning on the blast furnace process data to obtain cleaned process data; Missing value processing is performed on the cleaned process data to obtain pre-processed blast furnace process data.

6. The blast furnace process condition detection method according to claim 1, It is characterized in that The method further comprises: Obtain historical process data; Using the historical process data, a preset big data analysis model is trained to construct an initial detection model, wherein the big data analysis model includes a decision tree model, a support vector machine model, a random forest model, a linear programming model, a genetic algorithm model, and a neural network model; The initial detection model is optimized by an optimization algorithm to construct the furnace condition detection model.

7. The blast furnace process condition detection method according to claim 1, It is characterized in that After the furnace condition detection is performed according to the furnace condition index data by using the pre-built furnace condition detection model to obtain the furnace condition detection result, the method further includes: If the furnace condition detection result is an abnormal result, generating a furnace condition warning message according to the furnace condition detection result; The furnace condition warning message is sent to the user terminal through a preset warning method.

8. A blast furnace process condition detection device, It is characterized in that The device comprises: Real-time data acquisition unit, used to acquire blast furnace process data; A data mining unit, used for performing data mining on the blast furnace process data to obtain furnace condition index data; The furnace condition detection unit is used to perform furnace condition detection according to the furnace condition index data through a pre-built furnace condition state detection model to obtain a furnace condition detection result.

9. The blast furnace process condition detection device according to claim 8, It is characterized in that The data mining unit is specifically used to perform associated data mining on the blast furnace process data to obtain furnace condition index data; or to perform feature extraction on the blast furnace process data to obtain furnace condition features; The furnace condition characteristics and preset furnace condition target variables are determined as the furnace condition index data.

10. The blast furnace process condition detection device according to claim 9, It is characterized in that The data mining unit is specifically used to mine the blast furnace process data through an association rule mining algorithm to obtain frequent item sets, and determine the frequent item sets as furnace condition index data.

11. The blast furnace process condition detection device according to claim 9, It is characterized in that The data mining unit is specifically used to cluster the blast furnace process data through a cluster analysis algorithm to obtain data clustering results, and determine the data clustering results as the furnace condition index data.

12. The blast furnace process condition detection device according to claim 8, It is characterized in that The device also includes: A data cleaning unit, used for cleaning the blast furnace process data to obtain cleaned process data; The data filling unit is used to process missing values ​​of the cleaned process data to obtain pre-processed blast furnace process data.

13. The blast furnace process condition detection device according to claim 8, It is characterized in that The device also includes: A historical data acquisition unit, used for acquiring historical process data; A model training unit, used to train a preset big data analysis model through the historical process data to construct an initial detection model, wherein the big data analysis model includes a decision tree model, a support vector machine model, a random forest model, a linear programming model, a genetic algorithm model and a neural network model; The model optimization unit is used to optimize the initial detection model through an optimization algorithm to construct the furnace condition detection model.

14. The blast furnace process condition detection device according to claim 8, It is characterized in that The device also includes: an early warning message generating unit, configured to generate an early warning message for a furnace condition according to the furnace condition detection result if the furnace condition detection result is an abnormal result; The furnace condition warning unit is used to send the furnace condition warning message to the user terminal through a preset warning method.

15. A computer readable medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the blast furnace process condition detection method described in any one of claims 1 to 7 is implemented.

16. A computer device comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. It is characterized in that When the program instructions are loaded and executed by the processor, the blast furnace process condition detection method described in any one of claims 1 to 7 is implemented.

17. A computer program product comprising a computer program / instructions, It is characterized in that When the computer program / instructions are executed by a processor, the blast furnace process condition detection method according to any one of claims 1 to 7 is implemented.

Images