Intelligent material distribution control system and method for duct piece mold based on computer vision

Abstract

The invention provides a duct piece mold intelligent material distribution control system and method based on computer vision. The system comprises a network camera, an image processing and algorithm module, a material distribution control module and a data storage and management module. The network camera collects image information of cloth in a mold in real time, the image processing and algorithm module processes and analyzes the image information, and the cloth control module automatically adjusts operation parameters of cloth equipment according to a judgment result of the image processing and algorithm module. And the data storage and management module is respectively connected with the network camera, the image processing and algorithm module and the material distribution control module, and is used for storing and managing data in the material distribution process. According to the technical scheme, the problems that in the prior art, a duct piece mold is low in distribution amount precision, low in efficiency and dependent on manpower are solved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control, specifically to an intelligent material placement control system and method for pipe segment molds based on computer vision. Background Art

[0002] Currently, the control of material distribution in tunnel segment molds relies on manual visual inspection, which suffers from high subjectivity and low precision. Excessive material distribution leads to waste, while insufficient distribution affects product quality. Furthermore, manual monitoring is difficult to implement continuously and stably 24 hours a day, lacking real-time data recording and analysis capabilities. No solution has yet been found in the existing technology that combines the YOLO algorithm with a network camera for controlling the material distribution in tunnel segment molds.

[0003] Therefore, there is a need for a computer vision-based intelligent material distribution control system and method for pipe segment molds that can improve production efficiency, increase material distribution accuracy, and reduce manual labor intensity. Summary of the Invention

[0004] The main objective of this invention is to provide a computer vision-based intelligent material distribution control system and method for segment molds, in order to solve the problems of low material distribution accuracy, low efficiency, and reliance on manual labor in the prior art.

[0005] To achieve the above objectives, this invention provides a computer vision-based intelligent material placement control system for pipe segment molds, comprising: a network camera, an image processing and algorithm module, a material placement control module, and a data storage and management module; the network camera acquires real-time image information of the material placement inside the mold, the image processing and algorithm module processes and analyzes the image information, the material placement control module automatically adjusts the operating parameters of the material placement equipment based on the judgment results of the image processing and algorithm module, and the data storage and management module is connected to the network camera, the image processing and algorithm module, and the material placement control module respectively to store and manage data during the material placement process.

[0006] Furthermore, the image processing and algorithm module integrates the YOLO algorithm to identify and locate the fabric area in the image, and calculate the area and volume parameters of the fabric. The image processing and algorithm module compares the calculation results with the preset fabric quantity standard to determine whether the fabric quantity meets the standard.

[0007] Furthermore, the operating parameters include: fabric speed, fabric time, and fabric flow rate.

[0008] Furthermore, the fabric control module communicates with the fabric equipment by sending control signals.

[0009] This invention also provides a computer vision-based intelligent material placement control method for segment molds, which specifically includes the following steps:

[0010] S1. After the system starts, it performs initialization settings, including: setting the parameters of the network camera, loading the YOLO algorithm model, and presetting the fabric parameters.

[0011] S2, the network camera collects image information of the fabric inside the pipe segment mold in real time, and transmits the image data to the image processing and algorithm module.

[0012] S3, the image processing and algorithm module, performs preprocessing, target detection, feature extraction and analysis on the acquired images, calculates the area and volume parameters of the fabric, and determines whether the amount of fabric meets the fabric quantity standard.

[0013] S4. Based on the judgment results of the image processing and algorithm module, the fabric control module automatically adjusts the operating parameters of the fabric equipment.

[0014] S5, during the fabric laying process, the data storage and management module stores and manages relevant data in real time, including fabric images, calculation results, and operating parameters.

[0015] S6. The system continuously executes steps S1 to S5 in a loop, monitoring the material distribution inside the segment mold in real time to ensure that the material distribution meets the requirements of the segment forming process.

[0016] Furthermore, step S3 specifically includes the following steps:

[0017] S3.1, preprocess the acquired raw images, including image enhancement, noise reduction and normalization operations;

[0018] S3.2, Use the YOLO algorithm to perform target detection on the preprocessed image, identify the fabric region in the image, and determine the location and bounding box of the fabric region;

[0019] S3.3, extract and analyze features of the detected fabric area, and calculate parameters such as the area, volume, and shape of the fabric;

[0020] S3.4, compare the calculated fabric parameters with the preset fabric quantity standard to determine whether the fabric quantity meets the standard; if the fabric quantity is insufficient, notify the fabric control module to increase the fabric quantity; if the fabric quantity is excessive, notify the fabric control module to reduce the fabric quantity.

[0021] The present invention has the following beneficial effects:

[0022] Improving fabric application accuracy: By utilizing the YOLO algorithm and webcam, the amount of fabric applied to the segment mold is accurately detected and controlled, which greatly improves the accuracy of fabric application, reduces the occurrence of too much or too little fabric, and improves the production quality of segments.

[0023] Improved production efficiency: The system can automate fabric distribution, reduce manual intervention, improve production efficiency, and shorten the production cycle.

[0024] Reduced labor intensity: It avoids workers having to concentrate on observation and operation for long periods of time, thus reducing labor intensity and improving work comfort and safety.

[0025] Data recording and analysis: The system can record and analyze detailed data on the fabric production process, providing strong support for production process optimization and quality traceability.

[0026] Highly adaptable: The system parameters and configuration can be flexibly adjusted according to different segment molds and material requirements, exhibiting strong adaptability and versatility. Attached Figure Description

[0027] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0028] Figure 1 A flowchart of a computer vision-based intelligent material placement control method for segment molds according to the present invention is shown. Detailed Implementation

[0029] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] A computer vision-based intelligent fabric placement control system for tunnel segment molds includes: a network camera, an image processing and algorithm module, a fabric placement control module, and a data storage and management module. The network camera acquires real-time images of the fabric inside the mold. The image processing and algorithm module processes and analyzes the image information. Based on the judgment results of the image processing and algorithm module, the fabric placement control module automatically adjusts the operating parameters of the fabric placement equipment. The data storage and management module is connected to the network camera, image processing and algorithm module, and fabric placement control module respectively, storing and managing data during the fabric placement process. The network camera is installed above the tunnel segment mold or at a suitable location to acquire real-time images of the fabric inside the mold. The network camera should have high resolution, high frame rate, and good light adaptability to ensure clear and accurate capture of the fabric's state. It is used to store and manage relevant data during the fabric placement process, such as fabric images, calculation results, and operating parameters. Analysis and mining of this data can provide strong support for production process optimization and quality control. The data storage and management module can be implemented using a database management system for convenient data storage, retrieval, and analysis. Specifically, the image processing and algorithm module is responsible for processing and analyzing the images acquired by the network camera. The image processing and algorithm module integrates the YOLO algorithm to identify and locate fabric regions in images, and calculates the area and volume parameters of the fabric. The image processing and algorithm module compares the calculation results with the preset fabric quantity standard to determine whether the fabric quantity meets the standard.

[0031] Specifically, the operating parameters include: fabric speed, fabric time, and fabric flow rate.

[0032] Specifically, the fabric control module communicates with the fabric equipment by sending control signals. Based on the judgment results of the image processing and algorithm module, the fabric control module automatically adjusts the operating parameters of the fabric equipment, such as fabric speed, fabric time, and fabric flow rate, to achieve precise control of the amount of fabric.

[0033] The following is a detailed description of how to install and debug the system provided by this invention:

[0034] Webcam Installation: Choose a suitable installation location to ensure the webcam can clearly and comprehensively capture images of the fabric inside the tunnel lining mold. During installation, pay attention to the camera's angle, height, and stability to avoid blurry images or obstructions. After installation, adjust the camera parameters, such as focal length, aperture, and exposure time, to obtain the best image capture results.

[0035] Device Connection and Communication: Ensure proper connection of devices such as network cameras, image processing and algorithm modules, fabric control modules, data storage and management modules, and human-machine interfaces, and guarantee their ability to communicate. Connections can be made via wired or wireless methods, such as Ethernet or Wi-Fi.

[0036] System debugging: The entire system is debugged to check the functionality of each module, the stability of data transmission, and the accurate execution of control commands. During debugging, different fabric conditions can be simulated to test and optimize the system's performance.

[0037] The following is a detailed explanation of how the system provided by this invention operates and is maintained:

[0038] System Startup and Operation: After completing hardware installation, software configuration, and training, the intelligent material placement system for the tunnel segment mold is started. The system will automatically perform initialization settings and begin real-time acquisition of material placement images within the tunnel segment mold, processing and analyzing them to achieve intelligent control of the material placement amount.

[0039] Operation Monitoring and Adjustment: During system operation, the system's operating status and material distribution are monitored in real time through a human-machine interface. If any abnormalities are detected or the material distribution does not meet requirements, timely adjustments and interventions are made. System parameters can be optimized and adjusted based on actual conditions to improve system performance and stability.

[0040] Data Backup and Analysis: Regularly back up the data in the data storage and management module to prevent data loss. Simultaneously, analyze and mine the stored data to summarize patterns and problems in the fabrication process, providing a basis for production process optimization and quality control.

[0041] Equipment maintenance and upkeep: Regularly maintain and service hardware such as network cameras, fabric processing equipment, and computers. Check the operating status of the equipment, clean the surfaces, and replace damaged parts. Ensure the normal operation of the equipment and extend its service life.

[0042] like Figure 1 The intelligent material placement control method for tunnel segment molds based on computer vision, as shown, specifically includes the following steps:

[0043] S1. After the system starts, it performs initialization settings, including: setting the parameters of the network camera, loading the YOLO algorithm model, and presetting the fabric parameters.

[0044] S2, the network camera collects image information of the fabric inside the pipe segment mold in real time, and transmits the image data to the image processing and algorithm module.

[0045] S3, the image processing and algorithm module, performs preprocessing, target detection, feature extraction and analysis on the acquired images, calculates the area and volume parameters of the fabric, and determines whether the amount of fabric meets the fabric quantity standard.

[0046] S4. Based on the judgment results of the image processing and algorithm module, the fabric control module automatically adjusts the operating parameters of the fabric equipment to achieve precise control of the amount of fabric.

[0047] S5, during the fabric laying process, the data storage and management module stores and manages relevant data in real time, including fabric images, calculation results, and operating parameters.

[0048] S6. The system continuously executes steps S1 to S5 in a loop, monitoring the material distribution inside the segment mold in real time to ensure that the material distribution meets the requirements of the segment forming process.

[0049] Specifically, step S3 includes the following steps:

[0050] S3.1 Preprocesses the acquired raw images, including image enhancement, noise reduction, and normalization operations, to improve image quality and clarity, facilitating subsequent target detection and recognition.

[0051] S3.2, The YOLO algorithm is used to perform target detection on the preprocessed image, identifying the fabric region in the image and determining the location and bounding box of the fabric region. The YOLO algorithm achieves rapid target detection by dividing the image into multiple grids, with each grid responsible for predicting a certain number of bounding boxes and corresponding class probabilities.

[0052] Step S3.3 extracts and analyzes features from the detected fabric area, calculating parameters such as the fabric's area, volume, and shape. Image processing and computer vision methods, such as edge detection, morphological processing, and template matching, can be used to extract the fabric's feature information.

[0053] S3.4, compare the calculated fabric parameters with the preset fabric quantity standard to determine whether the fabric quantity meets the standard; if the fabric quantity is insufficient, notify the fabric control module to increase the fabric quantity; if the fabric quantity is excessive, notify the fabric control module to reduce the fabric quantity.

[0054] The software configuration and training methods involved in the method provided by this invention will be described in detail below:

[0055] YOLO Algorithm Model Training: A large number of images of pipe segment mold fabric are collected as a training dataset, and the fabric regions in the images are labeled. The labeled dataset is used to train the YOLO algorithm model, adjusting the model's parameters to improve its detection accuracy and precision. The training process can be performed on a high-performance computer using deep learning frameworks (such as PyTorch, TensorFlow, etc.).

[0056] Image Processing and Algorithm Module Configuration: Configure the image processing and algorithm module according to actual needs, setting parameters for image preprocessing, target detection thresholds, and fabric parameter calculation methods. Simultaneously, load the trained YOLO algorithm model into this module to ensure its proper functioning.

[0057] Fabric control module configuration: Based on the type and performance of the fabric laying equipment, configure the fabric control module, setting the range and adjustment strategies for operating parameters such as fabric speed, fabric laying time, and fabric flow rate. Ensure that the fabric control module can accurately adjust the operating parameters of the fabric laying equipment based on the judgment results of the image processing and algorithm module.

[0058] Data storage and management module configuration: Select a suitable database management system and configure the data storage and management module, setting the database table structure, storage path, backup strategy, etc. Ensure this module can securely and stably store and manage relevant data from the fabric processing.

[0059] Of course, the above description is not intended to limit the present invention, and the present invention is not limited to the examples given above. Any changes, modifications, additions or substitutions made by those skilled in the art within the scope of the present invention should also fall within the protection scope of the present invention.

Claims

1. A computer vision-based intelligent material placement control system for tunnel segment molds, characterized in that, include: Network camera, image processing and algorithm module, fabric control module, and data storage and management module; The network camera captures real-time images of the fabric inside the mold. The image processing and algorithm module processes and analyzes the image information. Based on the judgment results of the image processing and algorithm module, the fabric control module automatically adjusts the operating parameters of the fabric-making equipment. The data storage and management module is connected to the network camera, the image processing and algorithm module, and the fabric control module respectively to store and manage the data during the fabric-making process.

2. The intelligent material placement control system for tunnel segment molds based on computer vision according to claim 1, characterized in that, The image processing and algorithm module integrates the YOLO algorithm to identify and locate fabric regions in images, and calculates the area and volume parameters of the fabric. The image processing and algorithm module compares the calculation results with the preset fabric quantity standard to determine whether the fabric quantity meets the standard.

3. The intelligent material placement control system for tunnel segment molds based on computer vision according to claim 1, characterized in that, Operating parameters include: fabric speed, fabric time, and fabric flow rate.

4. The intelligent material placement control system for tunnel segment molds based on computer vision according to claim 1, characterized in that, The fabric control module communicates with the fabric equipment by sending control signals.

5. A computer vision-based intelligent material placement control method for segment molds, characterized in that, The system according to any one of claims 1-4 specifically includes the following steps: S1. After the system starts, it performs initialization settings, including: setting the parameters of the network camera, loading the YOLO algorithm model, and presetting the fabric parameters; S2, the network camera collects image information of the fabric inside the pipe segment mold in real time, and transmits the image data to the image processing and algorithm module; S3, the image processing and algorithm module, performs preprocessing, target detection, feature extraction and analysis on the acquired images, calculates the area and volume parameters of the fabric, and determines whether the amount of fabric meets the fabric quantity standard. S4. Based on the judgment results of the image processing and algorithm module, the fabric control module automatically adjusts the operating parameters of the fabric equipment. S5, during the fabric laying process, the data storage and management module stores and manages relevant data in real time, including: fabric images, calculation results, and operating parameters; S6. The system continuously executes steps S1 to S5 in a loop, monitoring the material distribution inside the segment mold in real time to ensure that the material distribution meets the requirements of the segment forming process.

6. The intelligent material placement control method for tunnel segment molds based on computer vision according to claim 5, characterized in that, Step S3 specifically includes the following steps: S3.1, preprocess the acquired raw images, including image enhancement, noise reduction and normalization operations; S3.2, Use the YOLO algorithm to perform target detection on the preprocessed image, identify the fabric region in the image, and determine the location and bounding box of the fabric region; S3.3, extract and analyze features of the detected fabric area, and calculate parameters such as the area, volume, and shape of the fabric; S3.4, compare the calculated fabric parameters with the preset fabric quantity standard to determine whether the fabric quantity meets the standard; if the fabric quantity is insufficient, notify the fabric control module to add fabric. If there is too much fabric, notify the fabric control module to reduce the amount of fabric.

Images