Intelligent equipment of multi-angle steel combination production line and control method

Abstract

The invention relates to an intelligent device and a control method for a multi-angle-steel combined production line, and belongs to the technical field of angle steel products.Real-time data are integrated into an Internet of Things platform, real-time machining data information is obtained through the Internet of Things platform, and a machining anomaly recognition model is constructed based on multi-scale machining parameter features; and abnormal recognition is conducted on the machining parameter data information in each machining process through the machining abnormal recognition model, machining detection is conducted on the angle steel in the machining process, and the angle steel in the machining process is marked according to the machining detection result. According to the method, the Internet of Things technology and the adversarial neural network are fused, the historical index factors corresponding to the processing parameters are generated in combination, training is carried out through the adversarial neural network, the processing abnormal condition caused by coupling between the parameters can be recognized, the processing parameter abnormal area can be quickly and accurately positioned, and the processing accuracy is improved. And the situation that machining is continued due to abnormity can be avoided, and machining defective products are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of angle steel production, and particularly to an intelligent device and a control method for a multi-angle steel merging production line. Background Art

[0002] Angle steel is a carbon structural steel, which is suitable for the construction field and can be used to fix different buildings to play a role in fixing angles. Angle steel can be composed of various different load-bearing members according to different structural needs, and can also be used as connectors between members. It is widely used in various building structures and engineering structures, such as roof beams, bridges, transmission towers, hoisting and transportation machinery, ships, industrial furnaces, reaction towers, container racks, cable trench supports, power pipe fittings, busbar support installation, and warehouse shelves, etc. Angle steel belongs to carbon structural steel for construction, which is a section steel with a simple cross-section and is mainly used for metal components and the frames of factories, etc. In use, it is required to have good weldability, plastic deformation performance, and certain mechanical strength. The raw material billet for producing angle steel is a low-carbon square steel billet, and the finished angle steel is delivered in a hot-rolled formed, normalized or hot-rolled state. Nowadays, the angle steel production equipment is gradually transferred to intelligent production, but abnormal situations will also occur during each process of the current angle steel production equipment, resulting in unreasonable processing parameter indicators of the angle steel production equipment, thus leading to a large number of defective products. Moreover, there is a certain potential influence relationship between processing parameters, and different combinations of processing parameters will lead to different processing results, which will reduce the accuracy of abnormal identification of processing parameters. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent device and a control method for a multi-angle steel merging production line.

[0004] To achieve the above object, the technical solution adopted by the present invention is as follows: In a first aspect of the present invention, an intelligent device for a multi-angle steel merging production line is provided, including: A feeding module, which transports the angle steel to be processed to the conveying module through the feeding module, and conveys the angle steel to be processed to the processing module through the conveying module. After processing by the processing module, the processed angle steel is unloaded through the unloading module; A detection module, which performs processing detection on the angle steel during the processing process and marks the angle steel during the processing process according to the processing detection results; An Internet of Things platform, which transmits the real-time data of the feeding module, the conveying module, the processing module, and the unloading module to the Internet of Things platform, and performs abnormal identification on the real-time data through the Internet of Things platform.

[0005] In a second aspect of the present invention, a control method for an intelligent device of a multi-angle steel merging production line is provided, including the following steps: Integrate the real-time data of the feeding module, conveying module, processing module, and discharging module into the Internet of Things platform, and obtain real-time processing data information through the Internet of Things platform; Construct a processing anomaly recognition model based on the real-time processing data information; Perform anomaly recognition on the processing parameter data information in each processing process through the processing anomaly recognition model; Through anomaly recognition, conduct processing detection on the angle steel during the processing process, and mark the angle steel during the processing process according to the processing detection results.

[0006] Furthermore, in the control method of intelligent devices for multiple angle steel merging production lines, integrating the real-time data of the feeding module, conveying module, processing module, and discharging module into the Internet of Things platform, and obtaining real-time processing data information through the Internet of Things platform, specifically: Obtain the file size information of the real-time data of the feeding module, conveying module, processing module, and discharging module, construct several information transmission channels, randomly select several information transmission channels for information transmission, and conduct transmission tests on the information transmission channels based on the file size information of the real-time data; Through the information transmission test, obtain the real-time information transmission rate information, obtain the preset information transmission rate threshold, and determine whether the real-time information transmission rate information is greater than the preset information transmission rate threshold; When the real-time information transmission rate information is greater than the preset information transmission rate threshold, perform information transmission according to the current several information transmission channels; When the real-time information transmission rate information is not greater than the preset information transmission rate threshold, reset several information transmission channels for information transmission, integrate the data into the Internet of Things platform, and obtain real-time processing data information through the Internet of Things platform.

[0007] Furthermore, in the control method of intelligent devices for multiple angle steel merging production lines, constructing a processing anomaly recognition model based on the real-time processing data information specifically includes: Construct a processing anomaly recognition model based on a generative adversarial network, obtain the processing parameter data information in each processing process from the real-time processing data information, and construct multi-scale processing parameter features based on the processing parameter data information in each processing process; Introduce a Bayesian network, set the influencing factors of processing parameter indicators, use the influencing factors of processing parameter indicators as the dependent variable, regard the multi-scale processing parameter features as independent events, and input the dependent variable and the independent events into the Bayesian network; Construct a multi-parameter optimization objective function based on the independent events, input the multi-parameter optimization objective function into a Bayesian network, and obtain the potential relationship between the multi-parameter optimization objective function and the dependent variable; Input the potential relationship between the multi-parameter optimization objective function and the dependent variable into the processing anomaly recognition model for training to obtain a processing anomaly recognition model that meets expectations.

[0008] Further, in the control method of intelligent devices in multiple angle steel merging production lines, the processing parameter data information in each processing process is identified for anomalies through the processing anomaly recognition model, specifically including: Obtain the processing parameter data information in each processing process, and input the processing parameter data information in each processing process into the processing anomaly recognition model; The generator predicts the abnormal parameters based on the processing parameter data information in the processing process to obtain an initial parameter recognition result; Input the initial parameter recognition result into the discriminator for judgment. The discriminator judges whether to accept the initial parameter recognition result. If accepted, output the initial parameter recognition result; When the initial parameter recognition result is a preset parameter recognition result, output an abnormal parameter recognition result. When the initial parameter recognition result is not a preset parameter recognition result, output a normal parameter recognition result.

[0009] Further, in the control method of intelligent devices in multiple angle steel merging production lines, the angle steel in the processing process is inspected through anomaly recognition, specifically: Through anomaly recognition, obtain abnormal processing parameter data information, set a processing parameter data evaluation index, and judge whether the abnormal processing parameter data information is greater than the processing parameter data evaluation index; When the abnormal processing parameter data information is greater than the processing parameter data evaluation index, the corresponding angle steel is scrapped; When the abnormal processing parameter data information is not greater than the processing parameter data evaluation index, angle steel that can be repaired normally is generated, and a processing inspection result is output based on the scrapped angle steel and the angle steel that can be repaired normally.

[0010] Further, in the control method of intelligent devices in multiple angle steel merging production lines, the angle steel in the processing process is marked according to the processing inspection result, specifically including: If the processing inspection result is for the scrapped angle steel, the scrapped angle steel is marked and centrally processed; Statistically count the quantity information of angle steels scrapped and processed within a preset time, set a quantity threshold for the angle steels scrapped and processed, and determine whether the quantity information of the angle steels scrapped and processed within the preset time is greater than the quantity threshold of the angle steels scrapped and processed; When the quantity information of the angle steels scrapped and processed within the preset time is greater than the quantity threshold of the angle steels scrapped and processed, control the intelligent devices of multiple angle steel merging production lines to stop working; When the quantity information of the angle steels scrapped and processed within the preset time is not greater than the quantity threshold of the angle steels scrapped and processed, maintain the normal operation of the intelligent devices of multiple angle steel merging production lines.

[0011] The present invention solves the defects existing in the background technology and has the following beneficial effects: The present invention integrates the real-time data of the feeding module, conveying module, processing module, and discharging module into the Internet of Things platform, and obtains real-time processing data information through the Internet of Things platform; constructs a processing anomaly recognition model based on multi-scale processing parameter features; performs anomaly recognition on the processing parameter data information in each processing process through the processing anomaly recognition model; through anomaly recognition, performs processing detection on the angle steels in the processing process, and marks the angle steels in the processing process according to the processing detection results. The present invention combines the Internet of Things technology and the adversarial neural network, and trains through the adversarial neural network by combining the corresponding historical index factors generated by each processing parameter, can identify the processing anomaly situations caused by the coupling between parameters, can quickly and accurately locate the area where the processing parameters are abnormal, thus can avoid the situation of continuing processing due to anomalies, and reduce the generation of processing defective products. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0013] Figure 1 Shows a structural schematic diagram of the intelligent devices of multiple angle steel merging production lines; Figure 2 Shows a method flow chart of the control method of the intelligent devices of multiple angle steel merging production lines. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] In order to more clearly understand the above-mentioned objects, features, and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0015] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0016] The first aspect of the present invention provides an intelligent device for a multi-angle steel merging production line, including: As Figure 1 shown, the first aspect of the present invention provides an intelligent device for a multi-angle steel merging production line, including: A feeding module 10, through which the angle steel to be processed is transported to the conveying module, and the angle steel to be processed is conveyed to the processing module through the conveying module. After being processed by the processing module, the processed angle steel is unloaded through the discharging module; Several detection modules 20, which perform processing detection on the angle steel during the processing through the detection modules and mark the angle steel during the processing according to the processing detection results; An Internet of Things platform, which transmits the real-time data of the feeding module 10, the conveying module 40, several processing modules 50, and the discharging module 30 to the Internet of Things platform, and performs anomaly recognition on the real-time data through the Internet of Things platform.

[0017] It should be noted that the present invention combines the Internet of Things technology and the adversarial neural network, and generates the corresponding historical index factors by combining various processing parameters and training through the adversarial neural network, which can identify the processing anomalies caused by the coupling between parameters, quickly and accurately locate the area where the processing parameters are abnormal, so as to avoid the situation of continuing processing due to anomalies and reduce the generation of processing defective products.

[0018] As Figure 2 shown, the second aspect of the present invention provides a control method for an intelligent device of a multi-angle steel merging production line, including the following steps: S102: Integrate the real-time data of the feeding module, the conveying module, the processing module, and the discharging module into the Internet of Things platform, and obtain the real-time processing data information through the Internet of Things platform; S104: Construct a processing anomaly recognition model based on the real-time processing data information; S106: Perform anomaly recognition on the processing parameter data information in each processing process through the processing anomaly recognition model; S108: Through anomaly recognition, the angle steel during the processing is subjected to processing detection, and the angle steel during the processing is marked according to the processing detection results.

[0019] It should be noted that the present invention combines the Internet of Things technology and the adversarial neural network, and thus generates the corresponding historical index factors by combining various processing parameters and trains them through the adversarial neural network. It can identify the processing anomalies caused by the coupling between parameters, quickly and accurately locate the area where the processing parameters are abnormal, thus preventing the situation of continuing processing due to anomalies and reducing the generation of processing defective products. The real-time processing data includes the processing parameter data of the equipment (such as the motor speed during drilling, the motor speed during milling, the feed speed, etc.), the drawing parameters of the angle steel (the influencing factors of the processing index, such as roughness, the positioning accuracy of the hole position, the size of the hole position, the processing accuracy of the hole position, etc.) and other data.

[0020] Further, in the control method of the intelligent equipment of multiple angle steel merging production lines, the real-time data of the loading module, the conveying module, the processing module and the unloading module are integrated into the Internet of Things platform, and the real-time processing data information is obtained through the Internet of Things platform. Specifically: Obtain the file size information of the real-time data of the loading module, the conveying module, the processing module and the unloading module, construct several information transmission channels, randomly select several information transmission channels for information transmission, and perform transmission tests on the information transmission channels based on the file size information of the real-time data; Through the information transmission test, obtain the real-time information transmission rate information, and obtain the preset information transmission rate threshold, and judge whether the real-time information transmission rate information is greater than the preset information transmission rate threshold; When the real-time information transmission rate information is greater than the preset information transmission rate threshold, perform information transmission according to the current several information transmission channels; When the real-time information transmission rate information is not greater than the preset information transmission rate threshold, reset several information transmission channels for information transmission, integrate the data into the Internet of Things platform, and obtain the real-time processing data information through the Internet of Things platform.

[0021] It should be noted that the information transmission channels include Bluetooth transmission, wifi transmission, wired transmission and other methods. When the real-time information transmission rate information is greater than the preset information transmission rate threshold, it means that the data can be quickly transmitted to the Internet of Things platform. When the real-time information transmission rate information is not greater than the preset information transmission rate threshold, reset several information transmission channels for information transmission, integrate the data into the Internet of Things platform, and obtain the real-time processing data information through the Internet of Things platform, which can realize the rapid reading of the data.

[0022] Among them, this method may further include: Obtain the data size information of the data to be recognized generated by the current processing production line, and obtain the real-time data recognition ability characteristic data of the Internet of Things platform, and determine whether the data size information of the data to be recognized generated by the current processing production line is greater than the real-time data recognition ability characteristic data of the Internet of Things platform; When the data size information of the data to be recognized generated by the current processing production line is greater than the real-time data recognition ability characteristic data of the Internet of Things platform, configure the data to be recognized generated by the current processing production line according to the real-time data recognition ability characteristic data of the Internet of Things platform; Through configuration, configure the Internet of Things platform to be able to recognize data with the maximum data size, and perform data recognition in the order of the time stamps; When the data size information of the data to be recognized generated by the current processing production line is not greater than the real-time data recognition ability characteristic data of the Internet of Things platform, keep the quantity of the data to be recognized generated by the current processing production line unchanged.

[0023] It should be noted that due to the existence of a certain data processing capacity of the Internet of Things platform, the real-time data recognition ability of the Internet of Things platform is limited. The real-time data recognition ability characteristic data of the Internet of Things platform includes the data size data that can be recognized within a unit time, the quantity information of the data that can be recognized within a predetermined time, etc. Through this method, the Internet of Things platform can be configured to recognize data with the maximum data size according to the data recognition ability of the Internet of Things platform, so as to ensure the normal operation rate of the Internet of Things platform and avoid the collapse of the Internet of Things platform.

[0024] In addition, obtaining the real-time data recognition ability characteristic data of the Internet of Things platform specifically includes: Obtain the data recognition ability characteristic data of the Internet of Things platform service terminal in each working environment through big data, and construct a data recognition ability characteristic prediction model based on a deep neural network; Input the data recognition ability characteristic data of the Internet of Things platform service terminal in each working environment into the data recognition ability characteristic prediction model for training, and obtain a data recognition ability characteristic prediction model that meets the expectations; Obtain the working environment information of the area where the current Internet of Things platform service terminal is located, and input the working environment information of the area where the current Internet of Things platform service terminal is located into the data recognition ability characteristic prediction model that meets the expectations for prediction; Through prediction, obtain the real-time data recognition ability characteristic data of the Internet of Things platform, and output the real-time data recognition ability characteristic data of the Internet of Things platform.

[0025] It should be noted that the characteristic data of the data recognition ability of the Internet of Things platform service terminal is different under different working environments (such as temperature and humidity). Through this method, it is possible to further improve the normal operation rate of the Internet of Things platform and avoid the collapse of the Internet of Things platform, and improve the control accuracy of the Internet of Things platform in identifying abnormal parameters.

[0026] Furthermore, in the control method of intelligent devices in a multi-angle steel merging production line, a processing anomaly recognition model is constructed based on real-time processing data information, specifically including: Construct a processing anomaly recognition model based on a generative adversarial network, obtain the processing parameter data information in each processing process from the real-time processing data information, and construct multi-scale processing parameter features based on the processing parameter data information in each processing process; Introduce a Bayesian network, set the influencing factors of processing parameter indicators, use the influencing factors of processing parameter indicators as the dependent variable, regard the multi-scale processing parameter features as independent events, and input the dependent variable and independent events into the Bayesian network; Construct a multi-parameter optimization objective function based on independent events, input the multi-parameter optimization objective function into the Bayesian network, and obtain the potential relationship between the multi-parameter optimization objective function and the dependent variable; Input the potential relationship between the multi-parameter optimization objective function and the dependent variable into the processing anomaly recognition model for training to obtain a processing anomaly recognition model that meets the expectations.

[0027] It should be noted that the influencing factors of processing parameter indicators include factors such as crack factors, deformation factors, and dimensional deviations. Among them, the multi-parameter optimization objective function satisfies the following relationship: ; Among them, is the correlation probability value calculated by the Bayesian method, taking values of 0 or 1. 0 indicates non-correlation, and 1 indicates correlation; represents the i-th dependent variable; represents the correction coefficient, taking a value of 0.1; represents the real-time data of the i-th processing parameter.

[0028] It should be noted that when is 1, it means that the current processing parameter data is not related to , that is, the current processing parameter will not generate the index factors of the situation (such as cracks and dimensional deviations). By continuously storing such data and counting the index factors that appear in each processing parameter, a data set is constructed, and the data set corresponding to the potential relationship between the multi-parameter optimization objective function and the dependent variable is input into the processing anomaly recognition model for training to obtain a processing anomaly recognition model that meets the expectations.

[0029] Further, in the control method of intelligent equipment for a multi-angle steel merging production line, the processing parameter data information in each processing flow is identified for anomalies through a processing anomaly identification model, specifically including: Obtain the processing parameter data information in each processing flow, and input the processing parameter data information in each processing flow into the processing anomaly identification model; The generator predicts the abnormal parameters based on the processing parameter data information in the processing flow to obtain the initial parameter identification result; Input the initial parameter identification result into the discriminator for judgment. The discriminator determines whether to accept the initial parameter identification result. If accepted, output the initial parameter identification result; When the initial parameter identification result is the preset parameter identification result, output the abnormal parameter identification result. When the initial parameter identification result is not the preset parameter identification result, output the normal parameter identification result.

[0030] Further, in the control method of intelligent equipment for a multi-angle steel merging production line, the angle steel in the processing process is inspected through anomaly identification, specifically: Through anomaly identification, obtain the abnormal processing parameter data information, and set the evaluation index of the processing parameter data. Determine whether the abnormal processing parameter data information is greater than the evaluation index of the processing parameter data; When the abnormal processing parameter data information is greater than the evaluation index of the processing parameter data, the corresponding angle steel is scrapped; When the abnormal processing parameter data information is not greater than the evaluation index of the processing parameter data, angle steel that can be normally repaired is generated, and the processing inspection result is output based on the scrapped angle steel and the angle steel that can be normally repaired.

[0031] It should be noted that there are two cases of anomalies. One is the repairable case (such as the case where the angle steel has a negative dimensional deviation), and the other is the non-repairable case (such as cracks). That is, when the abnormal processing parameter data information is greater than the evaluation index of the processing parameter data, the corresponding angle steel is scrapped. When the abnormal processing parameter data information is not greater than the evaluation index of the processing parameter data, angle steel that can be normally repaired is generated, and the processing inspection result is output based on the scrapped angle steel and the angle steel that can be normally repaired.

[0032] Further, in the control method of intelligent equipment for a multi-angle steel merging production line, the angle steel in the processing process is marked according to the processing inspection result, specifically including: If the processing inspection result is for the scrapped angle steel, the scrapped angle steel will be marked and centrally processed; Statistically count the quantity information of angle steels scrapped and processed within a preset time, set a quantity threshold for the angle steels scrapped and processed, and determine whether the quantity information of the angle steels scrapped and processed within the preset time is greater than the quantity threshold for the angle steels scrapped and processed; When the quantity information of the angle steels scrapped and processed within the preset time is greater than the quantity threshold for the angle steels scrapped and processed, control the intelligent devices of multiple angle steel merging production lines to stop working; When the quantity information of the angle steels scrapped and processed within the preset time is not greater than the quantity threshold for the angle steels scrapped and processed, maintain the normal operation of the intelligent devices of multiple angle steel merging production lines.

[0033] It should be noted that through this method, a large number of abnormal angle steels can be detected in a timely manner, so as to control the operation of the intelligent devices of multiple angle steel merging production lines and improve the rationality of control.

[0034] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0035] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0036] In addition, in each embodiment of the present invention, the various functional units can all be integrated in one processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit; the above integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0037] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs and other various media that can store program codes.

[0038] Alternatively, if the above integrated units of the present invention are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the various embodiments of the present invention. And the aforementioned storage medium includes: mobile storage devices, ROM, RAM, magnetic disks, or optical discs and other various media that can store program codes.

[0039] The above are only the specific implementation manners of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An intelligent device for a multi-angle steel merging production line, characterized in that, Including: A feeding module that transports the angle steel to be processed to a conveying module through the feeding module, conveys the angle steel to be processed to a processing module through the conveying module, and discharges the processed angle steel through a discharging module after processing; A detection module that performs processing detection on the angle steel during the processing through the detection module and marks the angle steel during the processing according to the processing detection result; An Internet of Things platform that transmits the real-time data of the feeding module, the conveying module, the processing module, and the discharging module to the Internet of Things platform and performs anomaly identification on the real-time data through the Internet of Things platform.

2. A control method for an intelligent device of a multi-angle steel merging production line, characterized in that, Including the following steps: Integrate the real-time data of the feeding module, the conveying module, the processing module, and the discharging module into the Internet of Things platform, and obtain real-time processing data information through the Internet of Things platform; Construct a processing anomaly identification model based on the real-time processing data information; Perform anomaly identification on the processing parameter data information in each processing process through the processing anomaly identification model; Through anomaly identification, perform processing detection on the angle steel during the processing and mark the angle steel during the processing according to the processing detection result.

3. The control method of the intelligent device for a multi-angle steel merging production line according to claim 2, characterized in that, Integrate the real-time data of the feeding module, the conveying module, the processing module, and the discharging module into the Internet of Things platform, and obtain real-time processing data information through the Internet of Things platform. Specifically: Obtain the file size information of the real-time data of the feeding module, the conveying module, the processing module, and the discharging module, construct several information transmission channels, randomly select several information transmission channels for information transmission, and perform transmission tests on the information transmission channels based on the file size information of the real-time data; Through the information transmission test, obtain the real-time information transmission rate information, obtain a preset information transmission rate threshold, and determine whether the real-time information transmission rate information is greater than the preset information transmission rate threshold; When the real-time information transmission rate information is greater than the preset information transmission rate threshold, perform information transmission according to the current several information transmission channels; When the real-time information transmission rate information is not greater than the preset information transmission rate threshold, reset several information transmission channels for information transmission, integrate the data into the Internet of Things platform, and obtain real-time processing data information through the Internet of Things platform.

4. The control method of the intelligent device of a multi-angle steel merging production line according to claim 2, characterized in that, Constructing a processing anomaly identification model based on the real-time processing data information specifically includes: Construct a processing anomaly identification model based on a generative adversarial network, obtain the processing parameter data information in each processing process from the real-time processing data information, and construct multi-scale processing parameter features based on the processing parameter data information in each processing process; Introduce a Bayesian network, set the influencing factors of processing parameter indicators, use the influencing factors of processing parameter indicators as dependent variables, regard the multi-scale processing parameter features as independent events, and input the dependent variables and the independent events into the Bayesian network; Construct a multi-parameter optimization objective function based on the independent events, input the multi-parameter optimization objective function into the Bayesian network, and obtain the potential relationship between the multi-parameter optimization objective function and the dependent variable. Input the potential relationship between the multi-parameter optimization objective function and the dependent variable into the machining anomaly recognition model for training to obtain a machining anomaly recognition model that meets expectations.

5. The control method of an intelligent device for a multi-angle steel merging production line according to claim 2, characterized in that, Perform anomaly recognition on the machining parameter data information in each machining process through the machining anomaly recognition model, specifically including: Obtain the machining parameter data information in each machining process and input the machining parameter data information in each machining process into the machining anomaly recognition model; The generator predicts the abnormal parameters based on the machining parameter data information in the machining process to obtain the initial parameter recognition result; Input the initial parameter recognition result into the discriminator for judgment. The discriminator judges whether to accept the initial parameter recognition result. If accepted, output the initial parameter recognition result; When the initial parameter recognition result is the preset parameter recognition result, output the abnormal parameter recognition result. When the initial parameter recognition result is not the preset parameter recognition result, output the normal parameter recognition result.

6. The control method of an intelligent device for a multi-angle steel merging production line according to claim 2, characterized in that, Through anomaly recognition, perform machining inspection on the angle steel during the machining process, specifically: Through anomaly recognition, obtain the abnormal machining parameter data information and set the machining parameter data evaluation index, and judge whether the abnormal machining parameter data information is greater than the machining parameter data evaluation index; When the abnormal machining parameter data information is greater than the machining parameter data evaluation index, scrap the corresponding angle steel; When the abnormal machining parameter data information is not greater than the machining parameter data evaluation index, generate angle steel that can be normally repaired, and output the machining inspection result based on the scrapped angle steel and the angle steel that can be normally repaired.

7. The control method of an intelligent device for a multi-angle steel merging production line according to claim 2, characterized in that, Mark the angle steel during the machining process according to the machining inspection result, specifically including: If the machining inspection result is the scrapped angle steel, mark the scrapped angle steel and centrally process the scrapped angle steel; Count the quantity information of the scrapped angle steel within the preset time, set the quantity threshold of the scrapped angle steel, and judge whether the quantity information of the scrapped angle steel within the preset time is greater than the quantity threshold of the scrapped angle steel; When the quantity information of the scrapped angle steel within the preset time is greater than the quantity threshold of the scrapped angle steel, control the intelligent equipment of multiple angle steel merging production lines to stop working; When the quantity information of the scrapped angle steel within the preset time is not greater than the quantity threshold of the scrapped angle steel, maintain the normal operation of the intelligent equipment of multiple angle steel merging production lines.

Images