A revocation method based on AI analysis and double repeated tracking logic

Abstract

The application provides a revocation method based on AI analysis and double repeated verification of tracking logic, and belongs to the technical field of intelligent manufacturing of steel products. The method comprises the following steps: based on the material number information identified by the identification device at the entrance of the tracking area, the equipment action signal in the tracking area, the roller running signal and the cold and hot detection signal, a bottom layer logic for tracking the material is established, and a real-time tracking picture is formed; based on the video picture obtained by the on-site camera, the AI analysis system analyzes the video, and obtains the crane feeding and discharging signal and the material position information; when the online material is judged to have the abnormal lifting-off situation of material clamping, the material number information is put into the revocation cache; before the production is reported, the revocation cache is compared with the material completion information in the production control system, and the revocation cache is updated. The application can accurately, reliably and effectively monitor and count the abnormal offline revocation situation of the material in the tracking area.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology for steel products, and in particular to a method for revocation based on AI analysis and a dual-core logic for tracking each item. Background Technology

[0002] Material tracking is fundamental to achieving precise control, quality traceability, and refined energy management in steel pipe production. The tracking system ensures that the entire production line is under relatively strict information control by acquiring information from sensors installed on the production line. This allows operators and managers to obtain precise production information on each material on the production line, including its location, processes, and completion status. By linking the data generated during the production process with each material, the system can grasp the working status of the production line and identify existing problems, providing a strong reference for subsequent production planning and production line improvement.

[0003] To identify problems and factors detrimental to production on the production line, it is crucial to pay close attention to the production information of materials that have been removed from the line due to abnormal circumstances. Therefore, a method is needed to accurately and effectively track the removal of materials and obtain their production information. Summary of the Invention

[0004] To address the aforementioned problems, the present invention aims to provide a revocation method based on AI analysis and item-by-item tracking logic with dual cores, in order to solve the problems of accurate acquisition and timely statistical confirmation of information on revoked materials.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] A deregistration method based on AI analysis and branch-by-branch tracking logic with dual core duplication includes the following steps:

[0007] S1: Based on the material number information identified by the identification equipment at the entrance of the tracking area, the action signals of the equipment in the tracking area, the roller conveyor operation signals and the cold and hot detection signals, the underlying logic for tracking materials is established, and a real-time tracking screen is formed by the tracking system for each component.

[0008] S2: Based on the video footage obtained by the on-site camera, the AI ​​analysis system analyzes the video to obtain the overhead crane loading and unloading signals and material position information;

[0009] S3: When the system determines that an online material is abnormally removed due to a material jam, the material number information is placed into the lifting cache.

[0010] S4: Before production is reported, the cancellation cache is compared with the material completion information in the production control system. The cancellation cache is updated according to the material completion information in the production control system, and the cancellation record is confirmed and submitted.

[0011] Optionally, in step S1, establishing the underlying logic for tracking materials includes:

[0012] S11: By tracking the entry identification device of the tracking area, the time and order in which materials arrive at the entry of the tracking area in batches are obtained, and the batch to which the material belongs is determined by comparing with the upstream production plan, thereby obtaining the material number information;

[0013] S12: By using the roller conveyor operation signal and the cold and heat detection signal, it is possible to determine whether the material is moving and its position on the roller conveyor, thus forming a real-time tracking screen;

[0014] S13: By tracking the equipment action signals at the area exit, confirm the order in which materials arrive at the area exit in batches, so as to connect the material number information with the downstream process.

[0015] Optionally, the real-time tracking screen in step S12 is formed by determining the arrival of the material at the corresponding sensor installation point through on-site hot and cold detection signals. Between the corresponding sensor installation points, the roller speed information obtained by the roller conveyor running signal is integrated over time to calculate the position of the material on the roller conveyor, thereby forming a real-time tracking screen. When the material passes the next sensor installation point, the calculated material position and the real-time tracking screen are corrected according to the sensor hot and cold detection signals.

[0016] Optionally, in step S2, the AI ​​analysis system uses industrial cameras configured within the tracking area to obtain monitoring images covering the production line area, and delineates the roller conveyor area in the monitoring images.

[0017] Optionally, the AI ​​analysis system processes the acquired video using a target detection algorithm, using the overhead crane hook as the target of the algorithm detection, and thereby obtains the overhead crane positioning signal when the hook enters the roller conveyor area; it uses the online material as the target of the algorithm detection, and thereby obtains the coordinates and coordinate changes of the material within the tracking range, i.e., its movement; it communicates with the item-by-item tracking system described in S1, and matches the material monitored by the AI ​​analysis system with the material number information obtained by the item-by-item tracking system.

[0018] Optionally, in step S3, the conditions for determining that a material jamming or abnormal lifting situation has occurred specifically include judgment condition 1 and judgment condition 2.

[0019] Judgment condition 1 is established based on the information characteristics generated during the time period from when the material experiences a jamming abnormality to when it is lifted away by the overhead crane, specifically including:

[0020] Criterion 1: In step S2, the AI ​​analysis system detects that the material coordinates remain stationary for a longer period of time than a set time threshold and issues an alarm signal.

[0021] Criterion 2: In step S2, the AI ​​analysis system detects that the overhead crane has arrived in the production line area corresponding to the material and sends an overhead crane arrival signal to the system;

[0022] When any one of the criteria 1-2 is met, the material is considered to satisfy criterion 1.

[0023] Judgment condition 2 is established based on the information characteristics generated when the next material on the production line arrives at that position after the material has actually left the production line.

[0024] When the material stops at the real-time tracking screen formed by the material position confirmed by the equipment action signal, roller conveyor running signal and cold and hot detection signal collected in the tracking area in step S1, and the real-time tracking screen position of the next material coincides with that of the material, it indicates that the material has actually been lifted away and the next material has reached the position where it was lifted away; at this time, the material is considered to meet judgment condition 2.

[0025] When conditions 1 and 2 are met simultaneously, the system determines that a material has been abnormally removed from its support and places the material number information of that material into the removal cache.

[0026] Optionally, in step S4, the material completion information is the actual completion record in the production control system. On-site operators manually verify the revocation cache based on this information. After comparing it with the material completion information, the completed material number information that has not been actually revoked in the revocation cache is removed, so as to realize the correspondence between the revocation cache and the material completion information. The final revocation record is formed and submitted based on the revocation cache after manual confirmation.

[0027] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects:

[0028] The method provided by this invention combines the logic of item-by-item tracking with the application of an AI video analysis system. With the dual core of the two, it can accurately, reliably and effectively monitor and statistically analyze the abnormal removal and cancellation of materials in the tracking area without making significant modifications to the production line in the tracking area or affecting the normal production process. This allows relevant operators and managers to conveniently query the material number information and process of the abnormally cancelled material, and facilitates the investigation and analysis of optimization problems in the production line based on the cancellation records. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1This is a flowchart of the revocation method based on AI analysis and branch-by-branch tracking logic dual-core provided in the embodiments of the present invention;

[0031] Figure 2 This is a detailed flowchart illustrating the revocation method for specific materials based on AI analysis and item-by-item tracking logic dual-core processing provided in this embodiment of the invention. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0033] Embodiments of the present invention provide a revocation method based on AI analysis and branch-by-branch tracking logic with dual cores, such as... Figure 1 As shown, the method includes the following steps:

[0034] S1: Based on the material number information identified by the identification equipment at the entrance of the tracking area, the action signals of the equipment in the tracking area, the roller conveyor operation signals and the cold and hot detection signals, the underlying logic for tracking materials is established, and a real-time tracking screen is formed by the tracking system for each component.

[0035] S2: Based on the video footage obtained by the on-site camera, the AI ​​analysis system analyzes the video to obtain the overhead crane loading and unloading signals and material position information;

[0036] S3: When the system determines that an online material is abnormally removed due to a material jam, the material number information is placed into the lifting cache.

[0037] S4: Before production is reported, the cancellation cache is compared with the material completion information in the production control system. The cancellation cache is updated according to the material completion information in the production control system, and the cancellation record is confirmed and submitted.

[0038] Furthermore, in step S1, establishing the underlying logic for tracking materials includes:

[0039] S11: By tracking the entry identification device of the tracking area, the time and order in which materials arrive at the entry of the tracking area in batches are obtained, and the batch to which the material belongs is determined by comparing with the upstream production plan, thereby obtaining the material number information;

[0040] S12: By using the roller conveyor operation signal and the cold and heat detection signal, it is possible to determine whether the material is moving and its position on the roller conveyor, thus forming a real-time tracking screen;

[0041] S13: By tracking the equipment action signals at the area exit, confirm the order in which materials arrive at the area exit in batches, so as to connect the material number information with the downstream process.

[0042] By establishing material tracking logic through the above process, a real-time tracking screen of material movement on the production line is generated.

[0043] In this embodiment of the invention, the formation of the real-time tracking screen in step S12 is achieved by determining the arrival of the material at the corresponding sensor installation point through on-site hot and cold detection signals. Between the corresponding sensor installation points, the roller speed information obtained by the roller conveyor running signal is integrated over time to calculate the position of the material on the roller conveyor, thereby forming a real-time tracking screen. When the material passes the next sensor installation point, the calculated material position and the real-time tracking screen are corrected according to the sensor hot and cold detection signals.

[0044] Furthermore, in step S2, the AI ​​analysis system uses industrial cameras configured within the tracking area to obtain monitoring images covering the production line area, and delineates the roller conveyor area in the monitoring images.

[0045] The AI ​​analysis system processes the acquired video using a target detection algorithm, using the overhead crane hook as the target of the algorithm to obtain the overhead crane positioning signal when the hook enters the roller conveyor area; it also uses the online material as the target of the algorithm to obtain the coordinates and coordinate changes of the material within the tracking range, i.e., its movement; and it communicates with the individual tracking system in S1 to match the material monitored by the AI ​​analysis system with the material number information obtained by the individual tracking system.

[0046] Furthermore, in step S3, the conditions for determining that a material jamming or abnormal lifting situation has occurred specifically include judgment condition 1 and judgment condition 2;

[0047] Judgment condition 1 is established based on the information characteristics generated during the time period from when the material experiences a jamming abnormality to when it is lifted away by the overhead crane, specifically including:

[0048] Criterion 1: In step S2, the AI ​​analysis system detects that the material coordinates remain stationary for a longer period of time than a set time threshold and issues an alarm signal.

[0049] Criterion 2: In step S2, the AI ​​analysis system detects that the overhead crane has arrived in the production line area corresponding to the material and sends an overhead crane arrival signal to the system;

[0050] When any one of the criteria 1-2 is met, the material is considered to satisfy criterion 1.

[0051] Judgment condition 2 is established based on the information characteristics generated when the next material on the production line arrives at that position after the material has actually left the production line.

[0052] When the material stops at the real-time tracking screen formed by the material position confirmed by the equipment action signal, roller conveyor running signal and cold and hot detection signal collected in the tracking area in step S1, and the real-time tracking screen position of the next material coincides with that of the material, it indicates that the material has actually been lifted away and the next material has reached the position where it was lifted away; at this time, the material is considered to meet judgment condition 2.

[0053] When conditions 1 and 2 are met simultaneously, the system determines that a material has been abnormally removed from its support and places the material number information of that material into the removal cache.

[0054] Furthermore, in step S4, the material completion information is the actual completion record in the production control system; the on-site operator manually verifies the revocation cache based on this information, compares it with the material completion information, removes the completed material number information that has not been actually revoked from the revocation cache, realizes the correspondence between the revocation cache and the material completion information, and forms the final revocation record based on the manually confirmed revocation cache and submits it.

[0055] like Figure 2 As shown, this embodiment of the invention takes the example of a piece of material stuck on the conveyor roller conveyor and then being lifted off by an overhead crane, after which the production line continues to operate. Through a dual-core approach of AI analysis and piece-by-piece tracking logic, the information of the lifted material is locked, specifically including:

[0056] The real-time position of the material running on the roller conveyor is confirmed by the tracking system described in step S1 and the AI ​​analysis system described in step S2, forming a tracking screen.

[0057] When the material stops on the roller conveyor for more than a set time threshold, the track-by-track system described in step S1 issues an alarm signal based on the detected material stagnation time; the AI ​​video analysis system described in step S2 issues an alarm signal based on the detected material coordinates stagnation time in the image.

[0058] When the crane hook for lifting materials is detected to be in the designated roller conveyor area within the monitoring screen, the AI ​​video analysis system described in step S2 issues a crane arrival alarm signal.

[0059] After the material was lifted off the crane and the production line resumed normal operation, the real-time position calculated by the individual tracking system based on the roller conveyor speed did not change, and the image of the material remained in the tracking screen.

[0060] When the next material screen overlaps with the screen of the material that has been lifted, and the location information of the next material in the item-by-item tracking system passes through the location of the lifted material, the system will put the material number information of the lifted material into the lifting cache if one of the three alarm signals mentioned above is detected.

[0061] After the batch of materials is processed, before reporting to production, all material number information placed in the revocation cache in the aforementioned manner is manually compared and verified with the actual completion record in the production control system. The completed material number information that has not been actually revoked in the revocation cache is removed to achieve the correspondence between the revocation cache and the completion record. The final revocation record is formed and submitted based on the revocation cache after manual confirmation.

[0062] The method provided by this invention combines the logic of item-by-item tracking with the application of an AI video analysis system. With the dual core of the two, it can accurately, reliably and effectively monitor and statistically analyze the abnormal removal and cancellation of materials in the tracking area without making significant modifications to the production line in the tracking area or affecting the normal production process. This allows relevant operators and managers to conveniently query the material number information and process of the abnormally cancelled material, and facilitates the investigation and analysis of optimization problems in the production line based on the cancellation records.

[0063] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0064] The use of terms such as "an embodiment," "an embodiment," "an exemplary embodiment," and "some embodiments" in the specification indicates that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the art.

[0065] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0066] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc.

[0067] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for revoking licenses based on AI analysis and a dual-core logic for tracking each license, characterized in that, Includes the following steps: S1: Based on the material number information identified by the identification equipment at the entrance of the tracking area, the action signals of the equipment in the tracking area, the roller conveyor operation signals and the cold and hot detection signals, the underlying logic for tracking materials is established, and a real-time tracking screen is formed by the tracking system for each component. S2: Based on the video footage obtained by the on-site camera, the AI ​​analysis system analyzes the video to obtain the overhead crane loading and unloading signals and material position information; S3: When the system determines that an online material is abnormally removed due to a material jam, the material number information is placed into the lifting cache. In step S3, the conditions for determining that a material jamming or abnormal lifting situation has occurred specifically include judgment condition 1 and judgment condition 2. Judgment condition 1 is established based on the information characteristics generated during the time period from when the material experiences a jamming abnormality to when it is lifted away by the overhead crane, specifically including: Criterion 1: In step S2, the AI ​​analysis system detects that the material coordinates remain stationary for a longer period of time than a set time threshold and issues an alarm signal. Criterion 2: In step S2, the AI ​​analysis system detects that the overhead crane has arrived in the production line area corresponding to the material and sends an overhead crane arrival signal to the system; When any one of the criteria 1-2 is met, the material is considered to satisfy criterion 1. Judgment condition 2 is established based on the information characteristics generated when the next material on the production line arrives at that position after the material has actually left the production line. When the material stops at the real-time tracking screen formed by the material position confirmed by the equipment action signal, roller conveyor running signal and cold and hot detection signal collected in the tracking area in step S1, and the real-time tracking screen position of the next material coincides with that of the material, it indicates that the material has actually been lifted away and the next material has reached the position where it was lifted away; at this time, the material is considered to meet judgment condition 2. When both conditions 1 and 2 are met, the system determines that a material has been abnormally removed from the support and places the material number information of the material into the lifting cache. S4: Before production is reported, the cancellation cache is compared with the material completion information in the production control system. The cancellation cache is updated according to the material completion information in the production control system, and the cancellation record is confirmed and submitted.

2. The revocation method based on AI analysis and branch-by-branch tracking logic dual-core as described in claim 1, characterized in that, In step S1, establishing the underlying logic for tracking materials includes: S11: By tracking the entry identification device of the tracking area, the time and order in which materials arrive at the entry of the tracking area in batches are obtained, and the batch to which the material belongs is determined by comparing with the upstream production plan, thereby obtaining the material number information; S12: By using the roller conveyor operation signal and the cold / hot detection signal, it is possible to determine whether the material is moving and its position on the roller conveyor, thus forming a real-time tracking screen; S13: By tracking the equipment action signals at the area exit, confirm the order in which materials arrive at the area exit in batches, so as to connect the material number information with the downstream process.

3. The revocation method based on AI analysis and branch-by-branch tracking logic dual-core as described in claim 2, characterized in that, The real-time tracking screen is formed in step S12 by determining the arrival of the material at the corresponding sensor installation point through the on-site cold and hot detection signal. Between the corresponding sensor installation points, the roller speed information obtained by the roller conveyor operation signal is integrated with time to calculate the position of the material on the roller conveyor, thereby forming a real-time tracking screen. When the material passes the next sensor installation point, the calculated material position and the real-time tracking screen are corrected according to the sensor cold and hot detection signal.

4. The revocation method based on AI analysis and branch-by-branch tracking logic dual-core as described in claim 1, characterized in that, In step S2, the AI ​​analysis system uses industrial cameras configured within the tracking area to obtain monitoring images covering the production line area, and delineates the roller conveyor area in the monitoring images.

5. The revocation method based on AI analysis and branch-by-branch tracking logic dual-core as described in claim 4, characterized in that, The AI ​​analysis system processes the collected video using a target detection algorithm, using the overhead crane hook as the target of the algorithm to obtain the overhead crane positioning signal when the hook enters the roller conveyor area; it also uses the online material as the target of the algorithm to obtain the coordinates and coordinate changes of the material within the tracking range, i.e., its movement; and it communicates with the individual tracking system described in S1 to match the material monitored by the AI ​​analysis system with the material number information obtained by the individual tracking system.

6. The revocation method based on AI analysis and branch-by-branch tracking logic dual-core as described in claim 1, characterized in that, In step S4, the material completion information is the actual completion record in the production control system. On-site operators manually verify the revocation cache based on this information. After comparing it with the material completion information, the completed material number information that has not been actually revoked in the revocation cache is removed, so as to realize the correspondence between the revocation cache and the material completion information. The final revocation record is formed and submitted based on the revocation cache after manual confirmation.

Images