An abnormality detection method and device for a blast furnace thermocouple and a storage medium

Abstract

The application provides an abnormality detection method and device of a blast furnace thermocouple and a storage medium, and the method comprises the following steps: S1, selecting a plurality of thermocouples in a blast furnace that need to be subjected to abnormality detection, periodically collecting temperature measurement data for a predetermined time length to obtain a temperature measurement data sequence of each thermocouple temperature measurement point; S2, grouping the selected plurality of thermocouples according to installation position attributes, and packing the obtained temperature measurement data sequence of each thermocouple temperature measurement point according to the grouping to obtain a two-dimensional array representing the temperature measurement data of each group of thermocouple temperature measurement points; and S3, for each two-dimensional array, using an isolation forest algorithm to train the temperature measurement data to obtain an abnormality score of each temperature measurement point, comparing the abnormality score with a predetermined abnormality score threshold, and determining an abnormal temperature measurement point in each group of temperature measurement points according to a comparison result. By using the above technical solution, an abnormal temperature measurement point can be found online and quickly.

Description

Technical Field

[0001] This invention relates to the field of blast furnace ironmaking detection technology, and in particular to a method, device and storage medium for detecting abnormalities in blast furnace thermocouples. Background Technology

[0002] Blast furnaces, as crucial equipment in steel production, incur enormous construction and maintenance costs, making their longevity a top priority for ironmaking professionals. Generally, achieving a long blast furnace lifespan involves two main challenges: the hearth and bottom are prone to burn-through, and the belly, waist, and lower part of the furnace have limited lifespan. To understand the working condition and erosion status of these areas, thermocouples are typically installed in the hearth and bottom lining and furnace cooling equipment to monitor temperature. Especially in the construction of large blast furnaces, hundreds of thermocouple temperature measurement points are buried in the hearth and bottom area; this online temperature measurement method has become the primary means of monitoring and calculating the erosion status of the hearth and bottom.

[0003] However, due to the large number of thermocouples embedded from the furnace body to the bottom, and the complexity of instrument and wiring installation, wiring errors and instability frequently occur at various blast furnace sites. Furthermore, the long operating time of blast furnaces, large temperature variations, and numerous interfering factors during production lead to thermocouple breakage and melting during use. The failure of some thermocouples due to various reasons is detrimental to the actual operation of the blast furnace. Because there are so many temperature measurement points, checking or observing the condition of all thermocouples during blast furnace maintenance is extremely labor-intensive. Therefore, a detection method is needed to quickly and automatically identify abnormal thermocouple temperature measurement points. Summary of the Invention

[0004] The embodiments of the present invention provide a method, device and storage medium for detecting abnormalities in blast furnace thermocouples, so as to quickly detect abnormal thermocouple temperature measuring points.

[0005] To achieve the above objectives, on the one hand, a method for detecting abnormalities in blast furnace thermocouples is provided, comprising the following steps:

[0006] S1: Select multiple thermocouples in the blast furnace that need to be detected for abnormalities, and periodically collect temperature measurement data for a predetermined duration at the temperature measurement points of the multiple thermocouples to obtain the temperature measurement data sequence of each thermocouple temperature measurement point.

[0007] S2: The selected multiple thermocouples are grouped according to their installation location attributes, and the temperature measurement data sequences of each thermocouple temperature measurement point are packaged according to the group to obtain one or more two-dimensional arrays representing the temperature measurement data of each group of thermocouple temperature measurement points. Among them, one two-dimensional array corresponds to one group of thermocouple temperature measurement points, each row of the two-dimensional array contains the temperature measurement data of each thermocouple temperature measurement point in the corresponding group at the same time, and each column of the two-dimensional array contains the temperature measurement data of the same thermocouple temperature measurement point at different times.

[0008] S3: For each of the obtained two-dimensional arrays, the isolated forest algorithm is used to train the temperature measurement data in the two-dimensional array. The temperature measurement data in each column of the two-dimensional array is used as different samples in the training isolated forest, and the temperature measurement data in each row is used as different features in the training isolated forest. The abnormal score of each temperature measurement point is obtained. The abnormal score is compared with the predetermined abnormal score threshold. The abnormal temperature measurement points in each group of temperature measurement points are determined according to the comparison result.

[0009] Preferably, in the anomaly detection method, the selected thermocouple is not limited to thermocouples embedded in the blast furnace throat, furnace body, furnace waist, furnace belly, furnace hearth, and furnace bottom areas.

[0010] Preferably, in the anomaly detection method, the grouping according to the installation location attributes of the thermocouples includes: grouping all multiple thermocouples according to the height, angle and / or insertion depth of the thermocouples.

[0011] Preferably, in the anomaly detection method, the grouping according to the installation location attributes of the thermocouples includes: grouping thermocouples with the same height and insertion depth into one group, wherein the temperature measuring points in each group are different only in angle.

[0012] Preferably, in the anomaly detection method, the number of thermocouple temperature measuring points in each group is greater than or equal to 3, and thermocouple temperature measuring points that cannot be grouped are discarded.

[0013] Preferably, in the anomaly detection method, step S2 involves packaging the obtained temperature measurement data sequences from each thermocouple temperature measurement point into groups, including:

[0014] The thermocouple temperature measurement data sequences in the same group are stacked sequentially in chronological order to form a two-dimensional array. This two-dimensional array contains the temperature measurement data sequences of all thermocouple temperature measurement points in the corresponding group.

[0015] Preferably, in the anomaly detection method, the selected thermocouples are all thermocouples within a selected area, and the number of selected thermocouples is greater than or equal to 3, wherein the thermocouples within the selected area include:

[0016] Multiple thermocouples with the same height and insertion depth but different angles are installed in the cooling wall of the blast furnace.

[0017] All furnace hearth temperature measuring thermocouples;

[0018] All thermocouples on the sidewalls of the furnace hearth, layers 5 to 13;

[0019] Among all the thermocouples on the sidewalls of layers 5 to 13 of the furnace hearth, there are multiple thermocouples of the same height and insertion depth but different angles; or

[0020] All furnace body temperature measuring thermocouples.

[0021] On the other hand, an apparatus for detecting anomalies in blast furnace thermocouples is provided, comprising a memory and a processor, wherein the memory stores at least one program, which is executed by the processor to implement any of the methods described above.

[0022] In another aspect, a computer-readable storage medium is provided, wherein at least one program is stored therein, the at least one program being executed by a processor to implement any of the methods described above.

[0023] The above technical solution has the following technical effects:

[0024] The technical solution of this invention involves periodically collecting thermocouple data, grouping the collected data according to the installation location of the thermocouples, packaging the temperature measurement data of the same group of thermocouples to obtain a corresponding two-dimensional array for each group, using the temperature measurement data of each column in the two-dimensional array as different samples in the training independent forest, and using the temperature measurement data of each row as different features in the training independent forest. The isolated forest algorithm is used to train the temperature measurement data in the two-dimensional array, which can quickly detect abnormal temperature measurement points online due to various reasons such as wiring errors, aging lines, instrument damage, or network failures. It is applicable to the abnormal detection needs of a large number of thermocouple devices and helps the on-site equipment maintenance work of blast furnaces. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating an anomaly detection method for blast furnace thermocouple temperature measurement data according to an embodiment of the present invention.

[0026] Figure 2 This is a schematic diagram of the structure of an anomaly detection device for blast furnace thermocouple temperature measurement data according to an embodiment of the present invention. Detailed Implementation

[0027] To further illustrate the various embodiments, the present invention provides accompanying drawings. These drawings are part of the disclosure of the present invention, primarily used to illustrate the embodiments and to explain the operating principles of the embodiments in conjunction with the relevant descriptions in the specification. With reference to these drawings, those skilled in the art should be able to understand other possible implementations and the advantages of the present invention. Components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0028] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments.

[0029] In the process of realizing this invention, the inventors discovered that due to wiring errors, aging lines, instrument damage, or network failures, thermocouple temperature measuring points in blast furnaces may exhibit abnormal data. Moreover, the temperature measuring data of abnormal thermocouple temperature measuring points may show different numerical ranges or fluctuation patterns compared to those of normal thermocouple temperature measuring points that are adjacent or close in location. Therefore, the inventors of this invention utilize this point to propose a technical solution for detecting abnormal thermocouple temperature measuring points in blast furnaces.

[0030] Example 1:

[0031] Figure 1 This is a flowchart illustrating an abnormal detection method for blast furnace thermocouples according to an embodiment of the present invention. Figure 1 The abnormal detection method for blast furnace thermocouples in this embodiment includes the following steps:

[0032] S1. Select multiple thermocouples in the blast furnace that need to be detected for abnormalities, and periodically collect temperature measurement data for a predetermined duration at the temperature measurement points of multiple thermocouples to obtain the temperature measurement data sequence of each thermocouple temperature measurement point.

[0033] This step is the data acquisition step. Taking a 2500m... 3 Taking a blast furnace as an example, thermocouples that need to be detected for anomalies in the blast furnace are selected, and temperature data is collected periodically for a predetermined period of time. The scope of thermocouples for anomaly detection is not limited to thermocouples buried in areas such as the blast furnace body, waist, belly, hearth, and bottom.

[0034] For example, all thermocouples within a selected area can be selected for anomaly testing, with the number of thermocouple measuring points being greater than or equal to 3. The thermocouples within the selected area include, but are not limited to: multiple thermocouples with the same installation height and insertion depth but different angles in the cooling wall of the blast furnace body; all furnace hearth temperature-measuring thermocouples; or all furnace body temperature-measuring thermocouples, etc. Preferably, all temperature-measuring thermocouples on the 5th to 13th layers of the furnace hearth sidewalls are selected, or multiple thermocouples with the same height and insertion depth but different angles are selected from all temperature-measuring thermocouples on the 5th to 13th layers of the furnace hearth sidewalls. In other embodiments, multiple adjacent or closely located thermocouples, such as those with a distance of less than a predetermined distance between each pair, can be selected as the thermocouples to be tested for anomalies.

[0035] Periodically collecting temperature data for a predetermined duration involves collecting temperature data from all selected thermocouples within a specific collection period. Ultimately, each thermocouple acquires a sequence of temperature values ​​of equal length, ordered chronologically. For example, the predetermined duration could be 7 days, with temperature data from the most recent 7 days collected at preset collection periods such as 20 seconds or 1 hour. The predetermined duration can also be other values, not limited to days, but also including hours.

[0036] S2: The selected multiple thermocouples are grouped according to their installation location attributes, and the temperature measurement data sequences of each thermocouple temperature measurement point are packaged according to the group to obtain one or more two-dimensional arrays representing the temperature measurement data of each group of thermocouple temperature measurement points. Among them, one two-dimensional array corresponds to one group of thermocouple temperature measurement points, each row of the two-dimensional array contains the temperature measurement data of each thermocouple temperature measurement point in the corresponding group at the same time, and each column of the two-dimensional array contains the temperature measurement data of the same thermocouple temperature measurement point at different times.

[0037] This step is a data processing step. The grouping based on the thermocouple's installation location attributes includes grouping all multiple thermocouples according to their height, angle, and / or insertion depth. For example, among the selected thermocouples, temperature measuring points at the same height and insertion depth can be grouped together, so that the temperature measuring points in each group differ only in their angle. Preferably, for the thermocouples measuring the temperature on the side walls of the furnace cylinder layers 5 to 13, they are grouped according to their measuring point location being on the same layer, i.e., at the same height and insertion depth, with the temperature measuring points in each group differing only in their angle.

[0038] In other embodiments, multiple thermocouples that are adjacent or close in location, such as those selected where the distance between each pair is less than a predetermined distance, can be grouped together.

[0039] Grouping requires ensuring that each group contains at least three thermocouple temperature measurement points, discarding any unnecessary points that cannot be grouped. The aforementioned temperature measurement data sequences are packaged according to grouping. This means that after grouping all thermocouples, the temperature measurement data sequences within the same group are stacked sequentially in chronological order to form a two-dimensional array. After this operation, each group of temperature measurement points will obtain a two-dimensional array containing all the temperature measurement values ​​of the thermocouples within that group. Each column in the two-dimensional array represents the data sequence of a specific temperature measurement point.

[0040] S3: For each of the obtained two-dimensional arrays, the Isolation Forest algorithm is used to train the temperature measurement data in the two-dimensional array. The temperature measurement data in each column of the two-dimensional array is used as different samples in the training independent forest, and the temperature measurement data in each row is used as different features in the training independent forest to obtain the anomaly score of each temperature measurement point. The anomaly score is compared with the predetermined anomaly scoring threshold, and the abnormal temperature measurement points in each group of temperature measurement points are determined according to the comparison result.

[0041] For example, for all the obtained two-dimensional arrays, the isolated forest algorithm is executed sequentially to train the temperature measurement points in the two-dimensional arrays respectively, and the abnormality scores of different temperature measurement points are obtained.

[0042] The isolated forest algorithm used is as follows:

[0043] a) Given an input 2D array X, the number of trees t, and the subsampling size r, initialize an isolated forest.

[0044] b) Set the tree height limit to l = ceiling(log2r), where ceiling() refers to rounding up;

[0045] c) For i = 1…t, perform the following operation in a loop:

[0046] Randomly sample X according to r to obtain subsampled data X';

[0047] Construct an isolated tree iTree(X',0,l) and execute iForest←iForest∪iTree(X′,0,l).

[0048] d) After the loop is complete, the isolated forest iForest is obtained, and the anomaly score of each sample is calculated.

[0049] The steps involved in constructing the isolated iTree in this isolated forest algorithm are as follows:

[0050] a) Given an input two-dimensional array X, the current tree height e, and a tree height limit l;

[0051] b) Determine if the condition is true: e≥l or|X|≤1, where X represents the sample size of X; if the condition is true, proceed to step c), otherwise proceed to step d);

[0052] c) Let X be the tail node, output the node, and then end;

[0053] d) Let Q be a list representing all features of X. Randomly select a feature q in Q, and take the maximum and minimum values ​​of all sample features q in X as boundaries, and randomly select a value p as the dividing point.

[0054] e) Collect samples in X whose feature q values ​​are less than p into a left set array X. l Collect samples in X whose feature q value is greater than p into a right set array X. r ;

[0055] f) Create a node inNode whose left subtree is iTree(X l The right subtree of the tree is iTree(X,e+1,l). r The node is defined as q, with a boundary value of p. The node is then output, and the process ends. The two subtrees are established by recursively calling this algorithm.

[0056] The anomaly score for each sample is calculated using the following formula:

[0057]

[0058] In the formula, x represents any sample; n represents the number of samples; Here, H() is the harmonic series, H(n-1) = ln(n-1) + ξ, where ξ is Euler's constant, c(n) represents the average path length of a binary tree constructed from n samples; h(x) = e(x) + c(T.size), where e(x) represents the number of boundaries that sample x experiences on its journey from the root node to a leaf node, T.size represents the number of samples that share a leaf node with sample x; E(h(x)) represents the mean of h(x) for the sample across all trees in the isolated forest.

[0059] The abnormality score obtained by the above formula has a range of -0.5 to 0.5.

[0060] When training the two-dimensional array using the isolated forest algorithm, it's important to note that each column in the array is considered a different sample, and each row is considered a different feature. Specifically, one column corresponds to one temperature measurement point, with different columns corresponding to different measurement points; each column contains all the data for that temperature measurement point within a predetermined time period; one row corresponds to the temperature measurement data of a group of thermocouple measurement points at a specific moment, and different rows correspond to temperature measurement data at different moments in the time series.

[0061] Specifically, a certain abnormality scoring threshold is pre-set for the characteristics of all thermocouple temperature measurement points. These characteristics can be the area where the thermocouple temperature measurement point is located, temperature change characteristics, etc. Then, based on the set threshold, abnormal samples are identified, thereby identifying abnormal temperature measurement points.

[0062] Preferably, the anomaly score threshold is set to -0.2. In the isolated forest algorithm, samples (i.e., temperature measurement points) with anomaly scores less than the pre-set score threshold are identified as abnormal samples, i.e., the corresponding temperature measurement points are abnormal temperature measurement points.

[0063] By following the steps above, you can complete the anomaly detection of any blast furnace thermocouple temperature measurement data.

[0064] Example 2:

[0065] The present invention also provides a device for detecting abnormalities in blast furnace thermocouples, such as... Figure 2 As shown, the device includes a processor 201, a memory 202, a bus 203, and a computer program stored in the memory 202 and executable on the processor 201. The processor 201 includes one or more processing cores. The memory 202 is connected to the processor 201 via the bus 203. The memory 202 is used to store program instructions. When the processor executes the computer program, it implements the steps in the above-described method embodiment of Embodiment 1 of the present invention.

[0066] Furthermore, as an executable solution, the device for detecting abnormalities in the blast furnace thermocouple can be a computer unit, which can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer unit may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above-described structure of the computer unit is merely an example and does not constitute a limitation on the computer unit. It may include more or fewer components, or combine certain components, or use different components. For example, the computer unit may also include input / output devices, network access devices, buses, etc., and this embodiment of the invention does not limit this.

[0067] Furthermore, as an executable solution, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the computer unit, connecting various parts of the entire computer unit via various interfaces and lines.

[0068] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the computer unit by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0069] Example 3:

[0070] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the embodiments of the present invention.

[0071] If the modules / units integrated in the computer unit are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0072] Although the invention has been specifically shown and described in conjunction with preferred embodiments, those skilled in the art should understand that various changes in form and detail may be made to the invention without departing from the spirit and scope of the invention as defined in the appended claims, all of which shall be within the scope of protection of the invention.

Claims

1. A method for detecting anomalies in blast furnace thermocouples, characterized in that, Includes the following steps: S1: Select multiple thermocouples in the blast furnace that need to be detected for abnormalities, and periodically collect temperature measurement data for a predetermined duration at the temperature measurement points of the multiple thermocouples to obtain the temperature measurement data sequence of each thermocouple temperature measurement point. S2: The selected multiple thermocouples are grouped according to their installation location attributes, and the temperature measurement data sequences of each thermocouple temperature measurement point are packaged according to the group to obtain one or more two-dimensional arrays representing the temperature measurement data of each group of thermocouple temperature measurement points. Among them, one two-dimensional array corresponds to one group of thermocouple temperature measurement points, each row of the two-dimensional array contains the temperature measurement data of each thermocouple temperature measurement point in the corresponding group at the same time, and each column of the two-dimensional array contains the temperature measurement data of the same thermocouple temperature measurement point at different times. S3: For each of the obtained two-dimensional arrays, the isolated forest algorithm is used to train the temperature measurement data in the two-dimensional array. The temperature measurement data in each column of the two-dimensional array is used as different samples in the training isolated forest, and the temperature measurement data in each row is used as different features in the training isolated forest. The abnormal score of each temperature measurement point is obtained. The abnormal score is compared with the predetermined abnormal score threshold. The abnormal temperature measurement points in each group of temperature measurement points are determined according to the comparison result.

2. The anomaly detection method according to claim 1, characterized in that, The selected thermocouples are not limited to those embedded in the throat, body, waist, belly, hearth, and bottom areas of the blast furnace.

3. The anomaly detection method according to claim 1, characterized in that, The grouping according to the installation location attributes of the thermocouples includes grouping all multiple thermocouples according to the height, angle and / or insertion depth of the thermocouples.

4. The anomaly detection method according to claim 3, characterized in that, The grouping according to the installation location attributes of thermocouples includes: grouping thermocouples with the same height and insertion depth into one group, with the only difference being the angle of the temperature measuring point in each group.

5. The anomaly detection method according to claim 1, characterized in that, If the number of thermocouple temperature measuring points in each group is greater than or equal to 3, discard the thermocouple temperature measuring points that cannot be grouped.

6. The anomaly detection method according to claim 1, characterized in that, In step S2, the temperature measurement data sequences obtained from each thermocouple temperature measurement point are packaged into groups and included as follows: The thermocouple temperature measurement data sequences in the same group are stacked sequentially in chronological order to form a two-dimensional array. This two-dimensional array contains the temperature measurement data sequences of all thermocouple temperature measurement points in the corresponding group.

7. The anomaly detection method according to claim 1, characterized in that, The selected thermocouples are all thermocouples within a selected area, and the number of selected thermocouples is greater than or equal to 3. The thermocouples within the selected area include: Multiple thermocouples with the same height and insertion depth but different angles are installed in the cooling wall of the blast furnace. All furnace hearth temperature measuring thermocouples; All thermocouples on the sidewalls of the furnace hearth, layers 5 to 13; Among all the thermocouples on the sidewalls of layers 5-13 of the furnace hearth, there are multiple thermocouples of the same height and insertion depth but different angles; or All furnace body temperature measuring thermocouples.

8. A device for detecting anomalies in blast furnace thermocouple temperature measurement data, characterized in that, It includes a memory and a processor, the memory storing at least one program, the at least one program being executed by the processor to implement the method as claimed in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The storage medium stores at least one program segment, which is executed by a processor to implement the method as described in any one of claims 1 to 7.

Images