A bar diversion tracking method based on target detection

Abstract

The present invention discloses a bar diversion tracking method based on target detection, which belongs to the field of intelligent manufacturing of steel products. The bar diversion tracking method comprises: establishing the underlying logic for diverting and tracking the bars based on the cold detection signal and the steel pusher propulsion signal; establishing a visual diversion tracking model based on the target detection algorithm; combining the underlying logic and the visual diversion tracking model to clarify the whereabouts of each bar before collecting the cooling bed. The bar diversion tracking method provided by the present invention can realize automatic tracking of the whereabouts of bars in the collection area by combining the underlying logic signal with the visual target detection, with high accuracy and reliability, easy maintenance, and no need to modify the original production line.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing of steel products, and in particular to a bar diversion tracking method based on target detection. Background Art

[0002] At present, the bar industry has entered a new round of industrial upgrading. The bar industry is becoming more collectivized, specialized, large-scale and internationalized, and the industry's technological progress is accelerating. The bar industry is a basic industry in the national economy, and its position in the national economy is constantly improving. With the rapid development of the national economy, users have higher and higher requirements for the quality of bar products, and personalized and diversified demands are emerging in an endless stream. At the same time, the bar industry is also facing many problems. In the face of fierce market competition, the key to being invincible is to improve the quality of products, which requires enterprises to establish a complete quality assurance system.

[0003] As a manufacturing enterprise, production is the foundation of the enterprise. Only production data can truly reflect the production status of the enterprise. Real-time tracking of production status is the key to realizing enterprise information management. For bar production, it is of great significance to improve product quality and trace each bar in the production process.

[0004] Collection is one of the processes on the bar production line. After rolling, shearing, sawing and other processes, the bars are put on the fixed-length collection cooling bed. After the bars from the upstream production line are transported in rows to the entrance of the collection cooling bed by the conveyor roller, they are randomly diverted into the collection cooling bed. At this time, it is necessary to record the whereabouts of the bars, which is a key link to achieve bar-by-bar tracking. Summary of the invention

[0005] After the bars from the upstream production line are transported in rows to the entrance of the collection cooling bed via conveyor rollers, they are randomly diverted into the collection cooling bed. At this time, the whereabouts of the bars need to be recorded. To address this problem, the present invention provides a bar diversion tracking method based on target detection, which combines the underlying logic signal with visual target detection to realize automatic tracking of the whereabouts of the bars in the collection area.

[0006] To solve the above technical problems, the embodiments of the present invention provide the following solutions:

[0007] A bar diversion tracking method based on target detection comprises the following steps:

[0008] S1: Establish the underlying logic for bar diversion and tracking based on the cold inspection signal and the pusher advance signal;

[0009] S2: Establish a visual diversion tracking model based on the target detection algorithm;

[0010] S3: By combining the underlying logic and the visual diversion tracking model, the destination of each bar is determined before being collected on the cooling bed.

[0011] Preferably, the underlying logic of establishing the diversion tracking of the bars based on the cold detection signal and the steel pusher advancement signal means that the bars from the upstream production line will randomly enter the 1#, 2#, ..., N# collection cooling beds arranged in sequence, and when the bars pass through the tracking area, the numbering information of the bar sequence is obtained through the cold detection signal and the steel pusher advancement signal, including:

[0012] Through the cold inspection signal at the entrance of the collecting cooling bed on the transport roller, it is clear whether there is a bar sequence arriving at each collecting cooling bed entrance;

[0013] The actual material information of each collection cooling bed is obtained through the push signal of the steel pusher at the entrance of each collection cooling bed;

[0014] After the steel pushing action is completed, the cold detection signal at the entrance of the collection cooling bed detects that the bar sequence disappears, indicating that the group of bar sequences has entered the collection cooling bed.

[0015] Preferably, the numbering information of the bar sequence refers to the bars moving in rows on the transport roller, one row is called a group of sequences, and the numbering information of a group of bar sequences includes the number of each bar in the group of bar sequences and the arrangement order of each bar.

[0016] Preferably, the target detection algorithm includes:

[0017] An industrial camera is installed above the transport roller to collect real-time status images of the transport roller in front of the cooling bed;

[0018] By using a target detection algorithm, target detection is performed on the state image collected in real time, taking each group of bar sequences as a target;

[0019] The arrangement order of each group of bar sequences is obtained according to the detected coordinates, and the numbering information of each group of bar sequences is clarified by comparing with the upstream production plan;

[0020] A loading end line is set in the status image of the transport roller.

[0021] Preferably, the visual diversion tracking model takes a single set of bar sequences as an object, as shown in formula (1):

[0022] Seq((x,y),C,D) (1)

[0023] Among them, (x, y) represents the position coordinates of the lower edge center of the target detection bounding box of the bar sequence in the image, which corresponds to the actual position on the tracking area. The positive direction of the x-axis is the roller transport direction, and the positive direction of the y-axis points to the collection cooling bed; C is the numbering information of the bar sequence; D is the collection cooling bed number of the final flow direction of the bar, which is initialized to None.

[0024] Preferably, the setting of a feeding termination line in the state image of the transport roller means artificially setting a feeding termination line in the collected state image. If the position of a group of bar sequences in the real-time state image of the transport roller exceeds the feeding termination line, as shown in formula (2):

[0025] y≥y T (2)

[0026] where y T is the ordinate of the loading termination line, it is considered that the group of bar sequences has been collected and cooled on the cooling bed.

[0027] Preferably, the destination of each bar is clarified before the collection cooling bed, which means that different bar sequences from the upstream production line will randomly enter the 1#, 2#, ..., N# collection cooling beds arranged in sequence, and the destination of each group of bar sequences is clarified by combining the target detection algorithm with the underlying logic signal, and the bar number, arrangement order and destination information in the bar sequence are output.

[0028] Preferably, the target detection algorithm is combined with the underlying logic signal, including:

[0029] After the cold inspection signal is triggered, the status image of the transport roller is collected in real time;

[0030] After the pusher push signal is triggered, the target detection algorithm is used to detect the state image collected in real time, taking each group of bar sequences as the target. The arrangement order between each group of bar sequences is obtained according to the detected coordinates, and the numbering information of each group of bar sequences is clarified by comparing with the upstream production plan.

[0031] According to the push signal of the steel pusher, it is clear which cooling bed is collecting the bars;

[0032] After the position of a group of bar sequences in the real-time status image crosses the loading termination line, the destination of the group of bar sequences is determined, and the collection cooling bed number D of the final flow of the bars is assigned at this time;

[0033] When the cold detection signal detects that the bar disappears, it is determined that the group of bar sequence has been collected on the cooling bed, and the number information of the group of bar sequence is output at this time.

[0034] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0035] The bar diversion tracking method based on target detection provided by the present invention realizes the diversion tracking of the bar by combining the target detection algorithm with the underlying logic signal. The bars move in rows in front of the collection cooling bed and are randomly diverted into the collection cooling bed. At this time, the flow direction of the bars needs to be recorded. The method of the present invention combines the underlying logic signal with the visual target detection to realize the automatic tracking of the destination of the bars in the collection area. It has clear logic, high accuracy and reliability, and is easy to maintain without changing the original production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0037] Figure 1 is a flow chart of a bar diversion tracking method based on target detection provided by an embodiment of the present invention;

[0038] Figure 2a-2b It is a schematic diagram of time T and time T+1 in the process of collecting the cooling bed charge provided by an embodiment of the present invention;

[0039] Figure 3 is a schematic diagram of the installation position of the target detection camera provided by an embodiment of the present invention;

[0040] Figure 4 It is a detailed flowchart of bar diversion tracking combined with the target detection method provided by an embodiment of the present invention and the underlying logic signal. DETAILED DESCRIPTION

[0041] 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.

[0042] The embodiment of the present invention provides a bar diversion tracking method based on target detection, such as Figure 1 As shown, the method comprises the following steps:

[0043] S1: Establish the underlying logic for bar diversion and tracking based on the cold inspection signal and the pusher advance signal;

[0044] S2: Establish a visual diversion tracking model based on the target detection algorithm;

[0045] S3: By combining the underlying logic and the visual diversion tracking model, the destination of each bar is determined before being collected on the cooling bed.

[0046] like Figure 2a-2b As shown, in the embodiment of the present invention, the bars from the upstream production line will randomly enter the 1#, 2#, and 3# collection cooling beds arranged in sequence. The underlying logic of establishing the diversion tracking of the bars based on the cold detection signal and the steel pusher advancement signal means that when the bars pass through the tracking area, the numbering information of the bar sequence is obtained through the cold detection signal and the steel pusher advancement signal, including:

[0047] like Figure 2a As shown, at time T, through the cold detection signal at the entrance of the collecting cooling bed on the transport roller, it can be known that the bar sequence has arrived at the entrances of the 1#, 2#, and 3# collecting cooling beds;

[0048] like Figure 2b As shown, at time T+1, through the push signal of the steel pusher at the entrance of each collecting cooling bed, it can be known that the 2# and 3# cooling beds are loading;

[0049] After the steel pushing action is completed, the cold detection signal at the entrance of the collection cooling bed detects that the bar sequence disappears, indicating that the group of bar sequences has entered the collection cooling bed.

[0050] Furthermore, the numbering information of the bar sequence refers to the bars moving in rows on the transport roller, one row is called a group of sequences, and the numbering information of a group of bar sequences includes the number of each bar in the group of bar sequences and the arrangement order of each bar.

[0051] Furthermore, the target detection algorithm includes:

[0052] like Figure 3 As shown, an industrial camera is set up above the transport roller to collect the status images of the three transport rollers in front of the cooling bed in real time;

[0053] By using a target detection algorithm, target detection is performed on the state image collected in real time, taking each group of bar sequences as a target;

[0054] like Figure 2a As shown, the arrangement order of the three groups of bar sequences is obtained according to the detected coordinates, and the numbering information of each group of bar sequences is clarified by comparing with the upstream production plan;

[0055] A loading end line is set in the status image of the transport roller.

[0056] Furthermore, the visual diversion tracking model takes a single set of bar sequences as the object, as shown in formula (1):

[0057] Seq((x,y),C,D) (1)

[0058] Among them, (x, y) represents the position coordinates of the lower edge center of the target detection bounding box of the bar sequence in the image, which corresponds to the actual position on the tracking area. The positive direction of the x-axis is the roller transport direction, and the positive direction of the y-axis points to the collection cooling bed; C is the numbering information of the bar sequence; D is the collection cooling bed number of the final flow direction of the bar, which is initialized to None.

[0059] Furthermore, if Figure 2b As shown, the setting of a feeding termination line in the state image of the transport roller refers to artificially setting a feeding termination line in the collected state image. At this time, in the real-time image of the transport roller, the positions of the two groups of bar sequences at the 2# and 3# cooling beds cross the feeding termination line, as shown in formula (2):

[0060] y ≥ y T (2)

[0061] where y T is the ordinate of the loading termination line, it is considered that the two bar sequences have been collected and cooled on the cooling bed.

[0062] Furthermore, the described process of clarifying the destination of each bar before collecting the cooling bed means that different bar sequences from the upstream production line will randomly enter the 1#, 2#, and 3# collecting cooling beds arranged in sequence, and the destination of each group of bar sequences will be clarified through the combination of the target detection algorithm and the underlying logic signal, and the information such as the bar number, arrangement order, and destination in the bar sequence will be output.

[0063] like Figure 4 As shown, the embodiment of the present invention takes two bar sequences on the transport roller table being simultaneously placed on different collection cooling beds as an example, and tracks the flow direction of the bars by combining the target detection algorithm with the underlying logic signal, specifically including:

[0064] After the cold inspection signal is triggered, the status image of the transport roller is collected in real time;

[0065] After the pusher push signal is triggered, the target detection algorithm is used to detect the state image collected in real time, taking each group of bar sequences as the target. The arrangement order between the three groups of bar sequences is obtained according to the detected coordinates, and the number information of each group of bar sequences is clarified by comparing with the upstream production plan.

[0066] Through the pusher advance signal, it can be known that the 2# and 3# cooling beds are loading bars;

[0067] In the real-time status image, after the positions of the two groups of bar sequences cross the feeding termination line, by comparing the x-coordinates of the visual diversion tracking model of the two groups of bar sequences, it can be seen that the two groups of bar sequences enter the 2# and 3# cooling beds respectively. At this time, the collection cooling bed number D of the final flow direction of the bars is assigned;

[0068] When the 2# and 3# cold detection signals detect that the bars disappear, it is determined that the bar sequences at the two locations have been collected on the cooling bed, and the numbering information of the two groups of bar sequences is output at this time.

[0069] The target detection-based bar diversion tracking method provided by the present invention combines the underlying logic signal with visual target detection to realize automatic tracking of the whereabouts of the bars in the collection area. It has clear logic, high accuracy and reliability, and is easy to maintain without changing the original production line.

[0070] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0071] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0072] As used herein, the term "nominal / nominal" refers to an expected or target value for a characteristic or parameter of a component or process operation set during the design phase of a production or manufacturing process, as well as a range of values ​​above and / or below the expected value. The range of values ​​may be due to slight variations in the manufacturing process or tolerances. As used herein, the term "approximately" indicates a value of a given quantity that may vary based on a particular technology node associated with the subject semiconductor device. Based on a particular technology node, the term "approximately" may indicate a value of a given quantity that varies, for example, within 5%-15% of the value (e.g., ±5%, ±10%, or ±15% of the value).

[0073] It will be understood that the meaning of “on,” “over,” and “above” in this disclosure should be interpreted in the broadest manner, so that “on” means not only “directly on” something, but also includes the meaning of being “on” something with intervening features or layers therebetween, and “on” or “over” means not only “on” or “above” something, but also includes the meaning of being “on” or “above” something with no intervening features or layers therebetween.

[0074] Additionally, spatially relative terms such as "under," "beneath," "lower," "above," "upper," and the like may be used herein for descriptive convenience to describe the relationship of one element or feature to another element or features, as shown in the accompanying drawings. Spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the accompanying drawings. The device may be oriented in other ways, and the spatially relative descriptors used herein may be similarly interpreted accordingly.

[0075] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0076] A person skilled in the art will appreciate that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc.

[0077] 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 principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A bar diversion tracking method based on target detection, characterized in that: The following steps are involved: S1: Establish the underlying logic for bar diversion and tracking based on the cold inspection signal and the pusher advance signal; The underlying logic of establishing the diversion and tracking of the bars based on the cold detection signal and the steel pusher advancement signal means that the bars from the upstream production line will randomly enter the 1#, 2#, ..., N# collection cooling beds arranged in sequence. When the bars pass through the tracking area, the numbering information of the bar sequence is obtained through the cold detection signal and the steel pusher advancement signal, including: Through the cold detection signal at the entrance of the collecting cooling bed on the transport roller, it is clear whether there is a bar sequence arriving at the entrance of each collecting cooling bed; through the push signal of the steel pusher at the entrance of each collecting cooling bed, the actual material information of each collecting cooling bed is obtained; after the steel pushing action is completed, the cold detection signal at the entrance of the collecting cooling bed detects that the bar sequence disappears, indicating that the bar sequence has entered the collecting cooling bed; The numbering information of the bar sequence refers to the bars moving in rows on the transport roller, one row is called a group of sequences, and the numbering information of a group of bar sequences includes the number of each bar in the group of bar sequences and the arrangement order of each bar; S2: Establish a visual diversion tracking model based on the target detection algorithm; The target detection algorithm includes: An industrial camera is set up above the transport roller to collect the state image of the transport roller in front of the cooling bed in real time; the state image collected in real time is subjected to target detection with each group of bar sequences as the target through the target detection algorithm; the arrangement order between each group of bar sequences is obtained according to the detected coordinates, and the numbering information of each group of bar sequences is clarified by comparing with the upstream production plan; a loading termination line is set in the state image of the transport roller; The visual diversion tracking model takes a single set of bar sequences as the object, as shown in formula (1): Seq((x,y),C,D) (1) Among them, (x, y) represents the position coordinates of the lower edge center of the target detection bounding box of the bar sequence in the image, which corresponds to the actual position on the tracking area. The positive direction of the x-axis is the roller conveying direction, and the positive direction of the y-axis points to the collection cooling bed; C is the numbering information of the bar sequence; D is the collection cooling bed number of the final flow direction of the bar, which is initialized to None; The said setting of a feeding termination line in the state image of the transport roller means artificially setting a feeding termination line in the collected state image. If the position of a group of bar sequences in the real-time state image of the transport roller exceeds the feeding termination line, as shown in formula (2): y≥y T (2) where y T is the ordinate of the loading termination line, it is considered that the group of bar sequences has been collected and cooled on the cooling bed; S3: By combining the underlying logic and the visual diversion tracking model, the destination of each bar is determined before being collected on the cooling bed.

2. The bar diversion tracking method based on target detection according to claim 1 is characterized in that: The described process of clarifying the destination of each bar before collecting the cooling bed means that different bar sequences from the upstream production line will randomly enter the 1#, 2#, ..., N# collecting cooling beds arranged in sequence, and the destination of each group of bar sequences will be clarified through the combination of the target detection algorithm and the underlying logic signal, and the bar number, arrangement order and destination information in the bar sequence will be output.

3. The bar diversion tracking method based on target detection according to claim 2 is characterized in that: The target detection algorithm is combined with the underlying logic signal, including: After the cold inspection signal is triggered, the status image of the transport roller is collected in real time; After the pusher push signal is triggered, the target detection algorithm is used to detect the state image collected in real time, taking each group of bar sequences as the target. The arrangement order between each group of bar sequences is obtained according to the detected coordinates, and the numbering information of each group of bar sequences is clarified by comparing with the upstream production plan. According to the push signal of the steel pusher, it is clear which cooling bed is collecting the bars; After the position of a group of bar sequences in the real-time status image crosses the loading termination line, the destination of the group of bar sequences is determined, and the collection cooling bed number D of the final flow of the bars is assigned at this time; When the cold detection signal detects that the bar disappears, it is determined that the group of bar sequence has been collected on the cooling bed, and the number information of the group of bar sequence is output at this time.

Images