A method for detecting local nodules in a blast furnace, an electronic device and a storage medium

Abstract

The present invention relates to the technical field of blast furnace ironmaking, and in particular to a method for detecting local nodules in blast furnaces, electronic equipment and storage media. The method comprises the following steps: obtaining historical data of the thickness of each part of the furnace wall within a certain period of time, wherein the historical data is time series data; filtering the historical data of the thickness of each part of the furnace wall to generate second time series data of each part of the furnace wall; analyzing the second time series data of each part of the furnace wall to determine whether nodules occur; analyzing the parts where nodules occur, and merging them when the merging conditions are met. This method can detect local nodules earlier by monitoring the furnace thickness in real time, analyzing the thickness change trend of each part, discovering excessively thickened parts and merging them, and taking timely treatment measures to ensure safe production.

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace ironmaking, and in particular to a blast furnace local nodule detection method, electronic equipment and storage medium. Background Art

[0002] When the blast furnace is in operation, the charge enters the blast furnace from the top of the furnace, and the gas flows from the bottom to the top. At high temperature, it is mixed with coke and burned to convert the charge into molten iron, which gradually drips from the top to the bottom. However, under certain conditions, such as frequent and large-scale temperature fluctuations near the furnace wall, a lot of charge powder, and increased alkalinity of the furnace wall, it will cause the charge, solvent and other substances to adhere to the furnace wall, and form nodules over time. The furnace nodules may be distributed on one side of the furnace wall, or they may be ring-shaped and seriously damage the shape of the blast furnace wall. The charge at the nodule site descends slowly, and the gas flow does not rise smoothly, resulting in suspended material and collapsed material, affecting normal production and even shortening the normal service life of the blast furnace. In addition, due to the closed structure of the blast furnace and the particularity of its operation, it is very troublesome and risky to deal with the furnace nodules. Therefore, the key to nodules is prevention, timely discovery and timely treatment to avoid a serious problem. Real-time monitoring of the furnace thickness, analysis of the thickness change trend of each part, discovery of excessively thickened parts and merging them, can detect local nodules earlier, and timely take treatment measures to ensure safe production. Summary of the invention

[0003] The purpose of the present invention is to provide a method for detecting local nodules in a blast furnace, an electronic device and a storage medium, which can detect nodules at an early stage and take treatment measures in time to ensure safe production.

[0004] To achieve the above object, the first aspect of the present invention provides a method for detecting local nodules in a blast furnace, comprising the following steps:

[0005] Step S1, obtaining historical data of the thickness of each part of the furnace wall within a certain period of time, wherein the historical data is time series data;

[0006] Step S2, filtering the historical data of the thickness of each part of the furnace wall to generate second time series data of each part of the furnace wall;

[0007] Step S3, analyzing the second time series data of each part of the furnace wall to determine whether nodule formation occurs;

[0008] Step S4: Analyze the sites where nodules occur and merge them when the merging conditions are met.

[0009] Furthermore, the filtering process in step S2 is to filter the historical data of furnace wall thickness using a sliding window filtering algorithm, which specifically includes:

[0010] (1) Assume that the historical data set is X{x1,x2,x3,…,x n}, set the window queue with a length of k;

[0011] (2) Take the first k data of X and input them into the window queue, and calculate the filtered data as

[0012]

[0013] (3) The window moves back one position and updates the window queue, which is (x2, x3, ..., x k+1}, calculate the filtered value again according to the above formula;

[0014] (4) Continue to move the window backward until it reaches the end of the set X, generating the second time series data Y (y1, y2, y3, ...}).

[0015] Furthermore, in order to maintain the consistency of the data length before and after filtering, the second time series data Y is expressed as (y1, y2, y3, ..., y n-k+1 ,y n-k+2 , …, y n}, where y1 to y n-k+1 is obtained by filtering, y n-k+2 =x n-k+2 , ..., y n =x n .

[0016] Furthermore, the method for determining whether nodulation occurs in step S3 is specifically as follows:

[0017] (1) Set the thickness change threshold to δ and the thickness threshold to δ T , set the time period to T;

[0018] (2) Traverse the second time series data and set the two adjacent data as y m ,y m+1 ,like

[0019] y m >δ T

[0020] and

[0021] |y m+1 -y m |<δ

[0022] Then time m is temporarily set as the starting point of nodulation;

[0023] (3) Search backward from the starting point of the nodule until the

[0024] |y m+j -y m+j+1 |>δ

[0025] Then the time m+j+1 is considered as the end point of nodule formation;

[0026] (4) If it exists

[0027] (j+1)ΔT>T

[0028] Among them, ΔT is the sampling period, then it is considered that nodulation has indeed occurred;

[0029] (5) If no nodule endpoint is found, and

[0030] (nm)ΔT>T

[0031] It is considered that nodulation has occurred;

[0032] (6) Writing nodule data into a nodule list, wherein the nodule data includes the start time, end time, nodule location and nodule thickness of the nodule.

[0033] Furthermore, the nodule site merging conditions in step S4 are specifically:

[0034] Assume that the start time of the two nodules is T1 and T2 respectively, and the locations of the nodules are {p1, q1, r1} and {p2, q2, r2} respectively. If the condition is satisfied

[0035] ①|T1-T2|<Δt

[0036] ②

[0037] Among them, Δt is the set time threshold, ΔL is the set distance threshold, and the two nodules are merged.

[0038] Furthermore, the nodule site merging operation in step S4 is specifically as follows:

[0039] (1) The minimum time of the nodulation start at the two locations is taken as the start time;

[0040] (2) The maximum of the two nodule ending times is taken as the ending time;

[0041] (3) Nodule thickness is the maximum of the two nodule thicknesses;

[0042] (4) The nodule position with the maximum nodule thickness is taken as the nodule position after merging;

[0043] (5) Add the two nodules before the merger to the member list of the nodule after the merger;

[0044] (6) Update the nodule list, add the merged nodule data to the nodule list, and delete the original two nodule data from the nodule list.

[0045] The second aspect of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for detecting local nodules in a blast furnace as described in any scheme of the first aspect of the present invention.

[0046] The third aspect of the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes, the steps in the method for detecting local nodules in a blast furnace as described in any scheme of the first aspect of the present invention are implemented.

[0047] The present invention achieves the following technical effects:

[0048] The method monitors the furnace thickness in real time, analyzes the thickness variation trend of each part, finds and merges the excessively thickened parts, and can detect local nodules at an early stage, thereby taking timely treatment measures to ensure safe production. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a general flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0050] To further illustrate the various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, a person of ordinary skill in the art should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0051] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.

[0052] like Figure 1 As shown, the present invention proposes an application example of a method for detecting local nodules in a blast furnace. The method can continuously monitor the thickness of the blast furnace wall and find the nodule location by analyzing the thickness change trend of each part. The method includes the following steps:

[0053] Step S1, obtaining historical data of the thickness of each part of the furnace wall within half an hour.

[0054] Step S2: Filter the thickness history data to remove small disturbances and generate second time series data (which can be displayed in the form of thickness data curve or other data). The filtering process is as follows:

[0055] The sliding window filtering algorithm is used to filter the historical data. The window length is set to 4. The historical data set is X{x1, x2, x3, ..., x n},but

[0056] (1) Set the window queue length to 4;

[0057] (2) Take the first 4 data of X and input them into the window queue, and calculate the filtered data as

[0058]

[0059] (3) The window moves backward one position and updates the window queue to {x2, x3, …, x5}. The filtered value y2 is calculated again according to the above formula.

[0060] (4) Continue to move the window backward until it reaches the end of the set X, generating the second time series data Y(y1, y2, y3, ...}.

[0061] In this embodiment, in order to ensure the consistency of the data length before and after filtering, the second time series data Y is processed in the following manner: when the sliding window reaches the end of the data, the filtering process is stopped, that is, the data on the edge are not involved in the filtering. In this way, the second time series data Y formed is represented as (y1, y2, y3, ..., y n-k+1 ,y n-k+2 , …, y n}, where y1 to y n-k+1 is obtained by filtering, y n-k+2 =x n-k+2 , ..., y n =x n .

[0062] Step S3, analyzing the second time series data generated after filtering of each part, traversing the second time series data and performing the following operations:

[0063] (1) Set the thickness change threshold as δ, set the time period as T, T is the nodule time threshold, when the nodule time length reaches time T, it is considered that the part has a nodule;

[0064] (2) Traverse the filtered data list and set two adjacent data as y m ,y m+1 ,like

[0065] y m >δ T

[0066] and

[0067] |y m+1 -y m |<δ

[0068] Then m is tentatively defined as the nodule starting point;

[0069] (3) Search backward from the starting point of the nodule until the

[0070] |y m+j -y m+j+1 |>δ

[0071] Then m+j+1 is considered to be the end point of nodulation; that is, nodulation has occurred and the nodule has fallen off.

[0072] (4) If it exists

[0073] (j+1)ΔT>T

[0074] Among them, ΔT is the sampling period, then it is considered that nodulation has indeed occurred;

[0075] (5) If no nodule endpoint is found, and

[0076] (nm)ΔT>T

[0077] It is considered that nodules have occurred and exist;

[0078] (6) Writing nodule data into a nodule list, wherein the nodule data includes the start time, end time, nodule location and nodule thickness of the nodule.

[0079] Step S4: Analyze the nodule sites and merge them when the merging conditions are met. Traverse the nodule sites, set the start time of the two nodules to be T1 and T2 respectively, and the locations where the nodules occur to be {p1, q1, r1} and {p2, q2, r2} respectively. If the conditions are met

[0080] ①|T1-T2|<Δt

[0081] ②

[0082] Where Δt is the set time threshold, and ΔL is the set distance threshold, then the two nodules are merged. An implementation method of merging is given below:

[0083] (1) The minimum time of the nodulation start at the two locations is taken as the start time;

[0084] (2) The maximum of the two nodule ending times is taken as the ending time;

[0085] (3) Nodule thickness is the maximum of the two nodule thicknesses;

[0086] (4) The nodule position with the maximum nodule thickness is taken as the nodule position after merging;

[0087] (5) Add the two nodules before the merger to the member list of the nodule after the merger;

[0088] (6) Update the nodule list, add the merged nodule data to the nodule list, and delete the original two nodule data from the nodule list.

[0089] The method monitors the furnace thickness in real time, analyzes the thickness variation trend of each part, finds and merges the excessively thickened parts, and can detect local nodules at an early stage, thereby taking timely treatment measures to ensure safe production.

[0090] Based on the same inventive concept, another embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the method described in any of the above embodiments of the present application are implemented.

[0091] Based on the same inventive concept, another embodiment of the present application provides an electronic device. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes, the steps in the method described in any of the above embodiments of the present application are implemented.

[0092] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0093] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices or computer program products. Therefore, the present application can be implemented in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can be implemented in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, semiconductor storage, etc.) containing computer-usable program codes.

[0094] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal 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.

[0095] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including 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.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement 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.

[0097] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.

[0098] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

Claims

1. A method for detecting local nodules in a blast furnace, characterized in that: The following steps are involved: Step S1, obtaining historical data of the thickness of each part of the furnace wall within a certain period of time, wherein the historical data is time series data; Step S2, filtering the historical data of the thickness of each part of the furnace wall to generate second time series data of each part of the furnace wall; Step S3, analyzing the second time series data of each part of the furnace wall to determine whether nodule formation occurs; Step S4, analyzing the sites where nodules occur, and merging them when the merging conditions are met; in: The filtering process in step S2 is to filter the historical data of furnace wall thickness using a sliding window filtering algorithm, which specifically includes: (1) Assume that the historical data set is X{x1,x2,x3,…,x n }, set the window queue with a length of k; (2) Take the first k data of X and input them into the window queue, and calculate the filtered data as (3) The window moves back one position and updates the window queue, which is {x2, x3, …, x k+1 }, calculate the filtered value y2 again according to the above formula; (4) Continue to move the window backward until it reaches the end of the set X, generating the second time series data Y{y1,y2,y3,…}; The second time series data Y is represented by {y1, y2, y3, ..., y n-k+1 ,y n-k+2 ,…,y n }, where y1 to y n-k+1 is obtained by filtering, y n-k+2 =x n-k+2 , ..., y n =x n ; The method for determining whether nodulation occurs in step S3 is specifically as follows: (1) Set the thickness change threshold to δ and the thickness threshold to δ T , set the time period to T; (2) Traverse the second time series data and set the two adjacent data as y m ,y m+1 , if y m >δ T and |and m+1 -and m |<δ Then time m is temporarily set as the starting point of nodulation; (3) Search backward from the starting point of the nodule until the |and m+j -and m+j+1 |>δ Then the time m+j+1 is considered as the end point of nodule formation; (4) If it exists (j+1)ΔT>T Among them, ΔT is the sampling period, then it is considered that nodulation has indeed occurred; (5) If no nodule endpoint is found, and (nm)ΔT>T It is considered that nodulation has occurred; (6) writing nodule data into a nodule list, wherein the nodule data includes the start time, end time, nodule location and nodule thickness of the nodule; The specific conditions for combining nodule sites in step S4 are: Assume that the start time of the two nodules is T1 and T2 respectively, and the locations of the nodules are {p1, q1, r1} and {p2, q2, r2} respectively. If the condition is satisfied ①|T1-T2|<Δt ② Among them, Δt is the set time threshold, ΔL is the set distance threshold, and the two nodules are merged; The specific operation of merging nodules in step S4 is as follows: (1) The minimum time of the nodulation start at the two locations is taken as the start time; (2) The maximum of the two nodule ending times is taken as the ending time; (3) Nodule thickness is the maximum of the two nodule thicknesses; (4) The nodule position with the maximum nodule thickness is taken as the nodule position after merging; (5) Add the two nodules before the merger to the member list of the nodule after the merger; (6) Update the nodule list, add the merged nodule data to the nodule list, and delete the original two nodule data from the nodule list.

2. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for detecting local nodules in a blast furnace as claimed in claim 1 are implemented.

3. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When executed, the processor implements the steps in the method for detecting local nodules in a blast furnace as claimed in claim 1.

Images