Zinc ingot auxiliary material automatic storage identification system and method, device and medium

Abstract

The present invention provides an automatic warehousing identification system for zinc ingot auxiliary materials, including: a behavior identification module: identifying the movement operation of a material transport vehicle, judging whether there are zinc ingot auxiliary materials on the material transport vehicle by characteristics, outputting the judgment result and sending corresponding instructions to the identification area synchronous movement module; the identification area synchronous movement module: performing synchronous operation after receiving the corresponding instructions sent by the behavior identification module; the zinc ingot auxiliary material label identification module: identifying the zinc ingot auxiliary materials on the material transport vehicle while the identification area synchronous movement module is operating; the identification information intelligent processing module: collecting the data sets of the processing cycle and the continuous reception and centralized processing mode within the processing cycle and performing corresponding processing. The present invention realizes automatic identification of the warehousing process of zinc ingot auxiliary materials of the hot-dip galvanizing unit, achieves the accuracy of ingot identification, and the recognition rate meets the use requirements in the scene that meets the technical conditions, thereby improving the warehousing efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of zinc ingot auxiliary material processing, and in particular to an automatic warehousing identification system and method, device and medium for zinc ingot auxiliary materials. Background Art

[0002] Hot-dip galvanizing (galvanizing) is also called hot-dip galvanizing and hot-dip galvanizing: it is an effective way to prevent metal corrosion, mainly used in metal structural facilities in various industries. It is to immerse the rust-free steel parts in molten zinc liquid at about 500 degrees Celsius, so that the zinc layer adheres to the surface of the steel components, thereby achieving the purpose of corrosion protection. With the rapid development of high-voltage power transmission, transportation, and communications, the requirements for the protection of steel parts are getting higher and higher, and the demand for hot-dip galvanizing is also increasing.

[0003] Zinc ingots are the main raw material for hot-dip galvanizing units. They have the problems of high consumption, heavy weight per piece, messy site, low warehouse management accuracy, and difficulty in managing by piece. Therefore, it is common for ingots to be mixed up in the warehouse cycle, the batches used are chaotic, the source of use cannot be traced by piece, quality problems are difficult to analyze after they occur, and manual collection of warehouse information by piece is costly and inefficient.

[0004] After searching, the patent document CN112053122A discloses an intelligent management method for the raw material database of hydraulic supports, which integrates, matches, retrieves and calls the R&D, process, quality inspection and inventory information through the raw material database of hydraulic supports, including: inventory management: digital visualization management of materials in logistics warehouses; quality inspection: factory inspection, data analysis of test data archiving; R&D: design strength, material selection recommendation; process: process matching material selection, parent material welding material selection; production: cutting and production according to the comprehensive information in the database. However, the prior art only states the process of inputting, stacking and entering data into the database, and cannot solve the problem of targeted identification and management of zinc ingot auxiliary materials. Moreover, in this technical field, there is no corresponding record of the automatic warehousing identification of zinc ingot auxiliary materials for hot-dip galvanizing units.

[0005] Therefore, in order to meet the needs of improving the management of steel enterprises and improve the management accuracy and efficiency of zinc ingot warehousing, it is necessary to focus on the warehousing of zinc ingot auxiliary materials of hot-dip galvanizing units, and research and develop automatic warehousing identification systems and devices to improve production efficiency in order to meet business needs. Summary of the invention

[0006] In view of the defects in the prior art, the purpose of the present invention is to provide a zinc ingot auxiliary material automatic warehousing identification system and method, device, and medium, which realizes automatic identification of the warehousing process, thereby improving warehousing efficiency, reducing data errors, increasing the completeness of auxiliary material information, and realizing the informatization of related data.

[0007] According to the present invention, a zinc ingot auxiliary material automatic storage identification system is provided, comprising:

[0008] Behavior recognition module: identifies the movement of the material transport vehicle, determines whether there are zinc ingot auxiliary materials on the material transport vehicle by characterizing them, outputs the judgment result and sends corresponding instructions to the synchronous movement module in the recognition area;

[0009] Identification area synchronous movement module: performs synchronous operation after receiving the corresponding instructions sent by the behavior recognition module;

[0010] Zinc ingot auxiliary material label identification module: It identifies the zinc ingot auxiliary materials on the transport vehicle while the synchronous mobile module in the identification area is operating;

[0011] Identification information intelligent processing module: collects data sets in the processing cycle and the continuous reception and centralized processing mode within the processing cycle and performs corresponding processing.

[0012] Preferably, the behavior recognition module identifies the feature source by collecting the video signal of the material transport vehicle, and detects whether the material transport vehicle is put into storage and whether there are zinc ingot auxiliary materials on the material transport vehicle.

[0013] Preferably, when it is detected that the material transport vehicle has entered the warehouse and has material, multiple instructions are output based on the identification of the behavioral characteristics of the material transport vehicle; the multiple instructions include the material transport vehicle entry start instruction, the material transport vehicle current relative position instruction, the entry identification boundary instruction and the empty instruction.

[0014] Preferably, the operations of the identification area synchronous movement module after receiving the corresponding instruction include:

[0015] When receiving the instruction to start the material transport vehicle entering the warehouse, the driving device is started to move;

[0016] When receiving the current relative position instruction of the material transport vehicle, it moves synchronously with the position of the material transport vehicle;

[0017] When receiving the instruction of the material transport vehicle to enter the warehouse and identify the boundary, the synchronous movement is stopped;

[0018] When receiving the empty command, the drive device is controlled to return to the initial position.

[0019] Preferably, the identification information intelligent processing module processes data in the following modes:

[0020] When receiving the start instruction of the material carrier entering the warehouse, the processing cycle is started, the data cache is created, and the incoming data begins to be received;

[0021] When a null instruction is received, the current processing cycle ends, the data cache is intelligently processed through the algorithm, the recognition result data set is generated and written into the database, and then the data cache is cleared.

[0022] According to the present invention, a method for automatically identifying zinc ingot auxiliary materials entering storage comprises the following steps:

[0023] Behavior recognition step: recognize the motion operation of the material transport vehicle, determine whether there are zinc ingot auxiliary materials on the material transport vehicle by characterizing them, output the judgment result and send the corresponding command;

[0024] Recognition area synchronous movement step: after receiving the corresponding instruction sent by the behavior recognition step, perform the synchronous operation;

[0025] Zinc ingot auxiliary material label identification step: while the synchronous movement step in the identification area is operating, the zinc ingot auxiliary materials on the material transport vehicle are identified;

[0026] Identify the steps of intelligent processing of information: collect the data sets of the processing cycle and the continuous reception and centralized processing mode within the processing cycle and perform corresponding processing.

[0027] According to a computer-readable storage medium storing a computer program provided by the present invention, the steps of the above method are implemented when the computer program is executed by a processor.

[0028] An automatic storage identification device for zinc ingot auxiliary materials provided according to the present invention comprises the above-mentioned automatic storage identification system for zinc ingot auxiliary materials or the above-mentioned computer-readable storage medium storing a computer program.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. The present invention realizes automatic identification of the zinc ingot auxiliary material warehousing process of the hot-dip galvanizing unit, achieves the accuracy of ingot identification, and the recognition rate meets the use requirements in scenarios that meet the technical conditions, improves the warehousing efficiency, reduces manual operation and costs, reduces data errors, increases the completeness of auxiliary material information, and realizes the informatization of related data.

[0031] 2. The present invention can realize various operation conditions through the various instructions sent by the behavior recognition module to ensure the completeness of the effect.

[0032] 3. The present invention is responsible for overall control through the behavior recognition module, which communicates with each module. The start and end of the recognition cycle are determined and instructions are issued by it, and other modules can complete their respective functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0034] Figure 1 It is a flow chart of the system modules in the present invention;

[0035] Figure 2 It is a schematic diagram of the technical solution of the working area in the present invention. DETAILED DESCRIPTION

[0036] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0037] like Figure 1 and Figure 2 As shown, the present invention provides a zinc ingot auxiliary material automatic storage identification system, comprising:

[0038] Behavior recognition module: identifies the movement of the material transport vehicle, determines whether there are zinc ingot auxiliary materials on the material transport vehicle by characterizing them, outputs the judgment result and sends corresponding instructions to the synchronous movement module in the recognition area;

[0039] Identification area synchronous movement module: performs synchronous operation after receiving the corresponding instructions sent by the behavior recognition module;

[0040] Zinc ingot auxiliary material label identification module: It identifies the zinc ingot auxiliary materials on the transport vehicle while the synchronous mobile module in the identification area is operating;

[0041] Identification information intelligent processing module: collects data sets in the processing cycle and the continuous reception and centralized processing mode within the processing cycle and performs corresponding processing.

[0042] Specifically, the behavior recognition module includes a video acquisition device, an embedded behavior recognition submodule and a bracket. The video acquisition device acquires video signals as input, and uses video recognition methods based on artificial intelligence to identify the source through key video features in the video stream, detect whether the material transport vehicle is in the warehouse and the speed of the material transport vehicle, and overall identify the material transport vehicle. Sports For identification. The material transport vehicle is affixed with a number label of a specified format as a key video feature identification source for behavior identification. The feature judgment of zinc ingot auxiliary materials in the video stream is used to obtain the detection result of whether there is material. In the case of detecting that there is material entering the warehouse, according to the behavioral characteristics of the material transport vehicle, a variety of instructions are output to other modules, including: material transport vehicle entry start instruction, material transport vehicle current relative position instruction, entry identification boundary instruction and empty instruction.

[0043] The synchronous movement module of the identification area includes a bracket, a guide rail, a stepper motor and a mounting base for the zinc ingot auxiliary material label identification module. The bracket plays a role in fixing the position and meets the requirements of the identification height. The base is placed on the guide rail and can move horizontally. It is controlled by a stepper motor. The zinc ingot auxiliary material label identification module is installed on the base. When receiving the start instruction of the loading and unloading vehicle entering the warehouse from the material transport vehicle behavior identification module, start the small stepper motor and prepare to move; when receiving the current relative position instruction of the material transport vehicle from the material transport vehicle behavior identification module, control the small stepper motor to keep synchronous movement with the position of the material transport vehicle; when receiving the instruction of the loading and unloading vehicle reaching the boundary of the warehouse entry identification from the material transport vehicle behavior identification module, stop synchronous movement; when receiving the empty instruction from the material transport vehicle behavior identification module, return to the initial position (the initial position is the starting position of the warehouse entry identification area) by controlling the small stepper motor.

[0044] The zinc ingot auxiliary material label recognition module includes a high-definition camera and an embedded QR code recognition, parsing and data transmission subsystem. The zinc ingot auxiliary material label recognition module is installed on the base of the synchronous moving module in the recognition area. When the material transport vehicle behavior recognition module receives the material transport vehicle entry start instruction, the high-definition camera is started to take pictures; the picture is taken, the QR code in it is automatically recognized, and it is parsed into data and sent to the recognition information intelligent processing module; when the material transport vehicle behavior recognition module receives the material transport vehicle has reached the entry identification boundary instruction, stop taking pictures and identification.

[0045] The identification information intelligent processing module uses the processing cycle characteristics, adopts the method of continuous reception within the cycle and centralized processing at the end. When receiving the start instruction of the material transport vehicle behavior identification module, the processing cycle is started, the data cache is created, and the incoming data is received; when receiving the empty instruction of the material transport vehicle behavior identification module, the current processing cycle is ended, the data cache is intelligently processed through the algorithm, the identification result data set is generated and written into the database, and finally the data cache is cleared. The material number (ingot number) of the identification result is displayed on the screen through the dot matrix display screen with matching prompts, which is convenient for viewing and verification.

[0046] The core technical route of the present invention uses video and image camera equipment as the main physical carriers for observation, identification and detection, and uses the main technical means of image recognition in artificial intelligence to collaborate as a whole to achieve automatic identification and data collection and storage of the warehousing process, providing management support for the relevant manufacturing management system MES.

[0047] Specifically, the environmental technical plan of the work area is set to operate the automatic storage identification system for zinc ingot auxiliary materials, such as Figure 2 As shown:

[0048] The present invention sets an identification working area with a length of 2 to 4 meters, 3 meters is recommended, and the side spacing of the material transport vehicle identification is recommended to have a width of 1 meter, which should not exceed 1.5 meters at most, and single-sided identification is adopted.

[0049] A QR code is attached to the side section of zinc ingot auxiliary materials, which is required to be greater than or equal to 2cm*2cm; the maximum vertical height of the loading vehicle is 3 ingots, and the maximum horizontal width is 3 ingots (according to the specifications of commercially available standard ingots); the maximum passing speed of the vehicle is 1.5 meters per second; the roads in the working area are flat, without potholes or other abnormal road conditions that affect the passing of the vehicle; only one vehicle should pass through in each recognition cycle; in outdoor scenes, shading, rain, and snow facilities should be provided to avoid affecting the recognition accuracy (but such facilities are not within the scope of this invention); in indoor scenes, the recognition side should avoid strong light interference and dust interference with visibility less than 5 meters.

[0050] One of the core technical solutions of the present invention is that the material transport vehicle behavior recognition module is responsible for overall control and communicates with each module. The start and end of the recognition cycle are determined and issued by it, and other modules cooperate to complete it.

[0051] The technical details of the video stream information material transport vehicle behavior recognition based on artificial intelligence technology in the present invention include the following:

[0052] (1) Obtaining image data of a material transport vehicle carrying zinc ingot auxiliary materials and having a color map on the vehicle body;

[0053] (2) performing enhancement processing, translation, rotation, filtering, flipping, scaling, etc. on the image data;

[0054] (3) Annotating the enhanced image data, and the obtained annotated data includes the coordinates of the four vertices of the zinc ingot and its category;

[0055] (4) Build a two-stage deep convolutional neural network to classify and regress the target, and output the predicted four vertex data of the zinc ingot;

[0056] (5) using a loss function to compare the labeled data and the predicted data of the image data, training the model parameters, and obtaining a final deep convolutional neural network model;

[0057] (6) inputting the image data to be tested into the deep convolutional neural network, and outputting the predicted data of the four vertices of the zinc ingot;

[0058] (7) Calculating the maximum horizontal width and maximum vertical width of the coordinates according to the predicted vertex data of the zinc ingot;

[0059] (8) Since the side of the zinc ingot is a square, calculate the ratio of the longitudinal width to the transverse width, and take the integer to get the number of zinc ingots on the material transport vehicle and store it in the database. The maximum number of zinc ingots does not exceed 3.

[0060] (9) Perform HSV color space conversion on the image. If the image contains the texture color within the set threshold, the vehicle body texture is detected, and then threshold segmentation is performed to obtain a binary image;

[0061] (10) Perform morphological processing on the binary image, erode and dilate to remove small interference areas, fill holes, and select the largest area as the mapping target;

[0062] (11) When three consecutive sampling photos contain the target, the vehicle is identified as entering the warehouse;

[0063] (12) Calculate the origin moment of the mapping area to obtain the center of mass;

[0064] (13) Continuously sample multiple images with a fixed sampling time. According to the moving distance of the centroid of the map and the actual scale, the moving speed of the car is obtained, and a signal is sent so that the synchronous motor moves at the same speed as the car;

[0065] (14) When reaching the end of the guide rail, the synchronous motor stops;

[0066] (15) When no mapped target is detected in three consecutive images, it is determined that the car has reached the storage boundary, a command is sent, the photo taking and recognition are stopped, an empty command is sent, and the synchronous motor returns to the initial position.

[0067] The details of the two-dimensional code recognition and parsing technology based on artificial intelligence technology in the present invention include the following:

[0068] (1) Obtaining QR code image data under different conditions;

[0069] (2) performing enhancement processing, translation, rotation, filtering, flipping, scaling, etc. on the image data;

[0070] (3) Annotating the enhanced two-dimensional code image data, and the obtained annotation data includes the coordinates of the four vertices of the two-dimensional code and the category;

[0071] (4) Build a two-stage deep convolutional neural network to classify and regress the target, and output the predicted four vertex data of the QR code;

[0072] (5) using a loss function to compare the labeled data and the predicted data of the image data, training the model parameters, and obtaining a final deep convolutional neural network model;

[0073] (6) Calculate the grayscale image of the sampled image, perform convolution using the Laplacian operator, and obtain the response variance. If the variance is within the set threshold, select the image as the key frame; otherwise, it is considered a blurred image and discarded.

[0074] (7) inputting the key frame image into the deep convolutional neural network and outputting the predicted data of the four vertices of the two-dimensional code;

[0075] (8) According to the predicted coordinates of the two-dimensional code vertices, the two-dimensional code area is cropped and the two-dimensional code is recognized;

[0076] (9) Identify the QR code and search the database. If there is identical information, it will not be counted in the database. If the information is different, the cropped QR code image and identification information will be stored in the database;

[0077] (10) If the QR code is not recognized, it is first stored in the local cache and processed and recognized after receiving the instruction that the vehicle has reached the storage boundary, so as to meet the real-time requirements;

[0078] (11) Using the principal component description method, the skewness of the cached two-dimensional code image is calculated and the corrected image is output;

[0079] (12) The corrected image is sent to the super-resolution model to increase the resolution by 8 times, recognized again, and output information;

[0080] (13) searching the database, if the database does not contain the above output information, the cropped two-dimensional code image and identification information are stored in the database;

[0081] (14) The identified information is transmitted to the dot matrix display screen for real-time display.

[0082] The present invention has good feasibility, effectiveness and applicability for similar units and production lines in the domestic steel industry. The supporting systems and devices of the present invention are highly integrated, easy to deploy and use, and are particularly suitable for the process-based continuous production requirements of hot-dip galvanizing units in steel enterprises. At the same time, it has great radiation and reference for similar scenarios.

[0083] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, the system and its various devices, modules, and units provided by the present invention can be completely realized in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps to realize the same functions. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0084] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A zinc ingot auxiliary material automatic storage identification system, characterized in that: include: Behavior recognition module: identifies the movement of the material transport vehicle, determines whether there are zinc ingot auxiliary materials on the material transport vehicle by characterizing them, outputs the judgment result and sends corresponding instructions to the synchronous movement module in the recognition area; Identification area synchronous movement module: performs synchronous operation after receiving the corresponding instructions sent by the behavior recognition module; Zinc ingot auxiliary material label identification module: It identifies the zinc ingot auxiliary materials on the transport vehicle while the synchronous mobile module in the identification area is operating; Identification information intelligent processing module: collects data sets in the processing cycle and the continuous reception and centralized processing mode within the processing cycle and performs corresponding processing; The behavior recognition module identifies the feature source by collecting the video signal of the material transport vehicle, and detects whether the material transport vehicle is in storage and whether there is zinc ingot auxiliary material on the material transport vehicle; When it is detected that the material transport vehicle has entered the warehouse and has materials, various instructions are output based on the behavioral characteristics of the material transport vehicle; The multiple instructions include a material transport vehicle entry start instruction, a material transport vehicle current relative position instruction, an entry boundary identification instruction, and a null instruction; The operations of the identification area synchronous movement module after receiving the corresponding instruction include: When receiving the instruction to start the material transport vehicle entering the warehouse, the driving device is started to move; When receiving the current relative position instruction of the material transport vehicle, it moves synchronously with the position of the material transport vehicle; When receiving the instruction of the material transport vehicle to enter the warehouse and identify the boundary, the synchronous movement is stopped; When receiving the empty command, the drive device is controlled to return to the initial position.

2. The zinc ingot auxiliary material automatic storage identification system according to claim 1 is characterized in that: The identification information intelligent processing module processes data in the following modes: When receiving the start instruction of the material carrier entering the warehouse, the processing cycle is started, the data cache is created, and the incoming data begins to be received; When a null instruction is received, the current processing cycle ends, the data cache is intelligently processed through the algorithm, the recognition result data set is generated and written into the database, and then the data cache is cleared.

3. A method for automatically identifying zinc ingot auxiliary materials entering storage, characterized in that: The steps include: Behavior recognition step: recognize the motion operation of the material transport vehicle, determine whether there are zinc ingot auxiliary materials on the material transport vehicle by characterizing them, output the judgment result and send the corresponding command; Recognition area synchronous movement step: after receiving the corresponding instruction sent by the behavior recognition step, perform the synchronous operation; Zinc ingot auxiliary material label identification step: while the identification area synchronous movement step is operating, the zinc ingot auxiliary materials on the material transport vehicle are identified; Identify the steps of intelligent processing of information: collect the data sets of the processing cycle and the way of continuous reception and centralized processing within the processing cycle and process them accordingly; The behavior recognition step identifies the feature source by collecting the video signal of the material transport vehicle, and detects whether the material transport vehicle is in storage and whether there is zinc ingot auxiliary material on the material transport vehicle; When it is detected that the material transport vehicle has entered the warehouse and has materials, various instructions are output based on the behavioral characteristics of the material transport vehicle; The multiple instructions include a material transport vehicle entry start instruction, a material transport vehicle current relative position instruction, an entry boundary identification instruction, and a null instruction; The steps of the identification area synchronous movement step after receiving the corresponding instruction include: When receiving the instruction to start the material transport vehicle entering the warehouse, the driving device is started to move; When receiving the current relative position instruction of the material transport vehicle, it moves synchronously with the position of the material transport vehicle; When receiving the instruction of the material transport vehicle to enter the warehouse and identify the boundary, the synchronous movement is stopped; When receiving the empty command, the drive device is controlled to return to the initial position.

4. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 3 are implemented.

5. A zinc ingot auxiliary material automatic storage identification device, characterized in that: It includes the automatic storage identification system for zinc ingot auxiliary materials as described in claims 1-2 or the computer-readable storage medium storing a computer program as described in claim 4.

Images