Bridge steel bar component manufacturing scheduling method

Abstract

The invention provides a bridge reinforcement component construction scheduling method, which comprises the following steps of: collecting construction period and completion period data through an API (Application Program Interface) or database connection, and establishing data connection with factory processing equipment to obtain operation state information. And splitting the reinforcing steel bar component by using the three-dimensional model processing tool, generating a material list, allocating tasks to the processing equipment according to the construction period, and conveying materials. After machining is completed, a high-definition industrial camera is used for collecting an excess material image, excess materials are scheduled to a proper machining task, and the material utilization rate is increased. The management platform continuously collects processing real-time data, predicts the processing completion time, adjusts the production process according to the processing completion time, and guarantees the production progress. In the transportation link, a high-definition camera is installed at a goods delivery transportation station of a truck, transportation of reinforcing steel bar components is monitored through the image recognition technology, once errors are found, an alarm is given immediately, an error correction process is started, and accurate transportation is ensured. According to the method, full-process efficient scheduling management of bridge reinforcing steel bar component manufacturing is realized.

Description

Technical Field

[0001] The present invention relates to the field of manufacturing of steel bar components, and particularly to a manufacturing scheduling method for bridge steel bar components. Background Art

[0002] In the production management of steel bar components, there are also many problems. Due to the large structural differences in the steel bar components for bridge construction, it is easy to have situations such as mixing of steel bar components and misdelivery of goods during the production process, resulting in a decline in the construction progress. Moreover, the production management of steel bar components in multiple regions is chaotic, and there is a problem of mismatch between the construction period and the production progress, such as the premature manufacturing of steel bar components for late construction, while the required steel bar components are not produced in time at the positions in urgent need of construction.

[0003] In the transportation link, there is a lack of effective monitoring means, and it is difficult to monitor the transportation status of steel bar components in real time. Once a transportation error occurs, it cannot be discovered and corrected in time, affecting the construction progress and quality. In addition, the existing technologies also have deficiencies in aspects such as processing equipment management, surplus material handling, production progress prediction and adjustment, and it is urgent to have a new manufacturing scheduling method for bridge steel bar components to solve these problems. Summary of the Invention

[0004] The main purpose of the present invention is to provide a manufacturing scheduling method for bridge steel bar components to solve the problems that the existing technologies also have deficiencies in aspects such as processing equipment management, surplus material handling, production progress prediction and adjustment.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is: a manufacturing scheduling method for bridge steel bar components, and the method includes: S1. Using a management platform, through an API interface or database connection, collect construction period and completion period data from a construction project management system and an engineering progress record database; S2. Establish a data connection between the management platform and various processing equipment in the factory to obtain the operating status information of the equipment in real time; S3. With the aid of a three-dimensional model processing tool, split the designed steel bar components into steel bar blocks and steel bar meshes according to the structural characteristics and design specifications, and generate a material list using a data table; S4. Allocate tasks to the selected processing equipment in sequence according to the construction period and completion period data in step S1, and transport the generated material list and the sorted materials to the corresponding positions of the processing equipment; S5. Use a high-definition industrial camera to collect images of the surplus materials generated during processing, and schedule the surplus materials to appropriate steel bar component processing tasks; S6. The management platform continuously collects and processes the real-time data of the processing equipment during the processing, predicts the processing completion time of the steel bar parts, and adjusts the entire production process according to the processing completion time. S7. Install high-definition cameras at the truck shipping and transportation workstations, use image recognition technology to monitor the transported steel bar parts in real time, and immediately send an alarm signal and start the error correction process if transportation errors or sequence errors are found.

[0006] In the preferred solution, the management platform collects the construction period and completion period data of each construction location on the public network or internal and external networks, uses the Bloom filter deduplication algorithm to clean and organize the data in combination with the time range and format check, and stores the processed data in the management platform database.

[0007] In the preferred solution, the processing equipment includes a numerical control steel bar sawing and threading production line, a numerical control bending equipment, a steel bar mesh flexible manufacturing production line, a steel bar sheet flexible manufacturing production line, and a steel bar block flexible manufacturing production line. Obtain the operating status information of the equipment, including the processing progress percentage and the remaining processing time. Use the Hungarian algorithm to select processing equipment for the steel bar parts, and preferentially arrange the equipment with the shortest remaining processing time for processing.

[0008] In the preferred solution, use the pandas library in the data table generation tool Python to organize the material information required for the split steel bar blocks and steel bar meshes into a structured table form. The content in the table form includes detailed data on the steel bar specifications, quantities, and dimensions. Send the material information table to the selected processing equipment control system and the processing personnel operation terminal through the network transfer protocols FTP and HTTP.

[0009] In the preferred solution, the specific method of step S4 is as follows: S41. According to the construction period and completion period data, use the task assignment algorithm based on time window and resource constraints to calculate the task urgency , where is the completion deadline of task , is the current time, which is used to quantify the task urgency Combined with the available processing time window and processing capacity of the processing equipment, sort the tasks from high to low according to the task urgency and assign them to the earliest available equipment; S42. Determine the construction sequence based on the construction project plan, deadline requirements, and improved critical path method, construct the construction process network, and perform forward calculation , , where: For the process Duration, used to calculate the earliest start and end times of the process; Backward calculation 、 , determine the critical path, which consists of processes with a total float of 0, and determines the shortest project duration; S43. Adopt the priority queue algorithm to sort tasks according to the priority function , where 、 are weight coefficients and , is the task construction sequence number. Determine the priority by comprehensively considering the task urgency and construction sequence, and assign tasks to processing equipment in order; S44. The processing equipment executes tasks according to the scheduling order. The blanking process controls the blanking length according to , where is the required blanking length, is the cutting precision error, ensuring the blanking length accuracy; The bending process controls the bending angle and radius according to 、 , 、 are the designed bending angle and radius, is the bending precision, ensuring the bending precision; The welding process controls the welding parameters according to the welding quality evaluation formula , 、 、 are weight coefficients, 、 、 are the welding current, voltage and time.

[0010] In the preferred solution, the specific method of step S5 is: S51. After the processing equipment completes the processing of the steel bar parts, use a high-definition industrial camera to collect the image of the remaining material according to the preset shooting parameters and angles. Adopt the median filtering algorithm to denoise the collected image, and remove discrete noise points such as salt-and-pepper noise in the image through the formula , providing an accurate data basis for subsequent edge detection, where , is the pixel value within the neighborhood window centered on the pixel point , is the denoised pixel value; S52. Apply the Hough transform to the preprocessed image for edge detection. In the Cartesian coordinate system, the straight line equation Converted to the Hough space as , where is the perpendicular distance from the origin to the line, is the angle between the perpendicular line and the axis. By accumulating votes in the Hough space to find the peak point, the line parameters in the image are obtained. After detecting the line, based on the line endpoint coordinates and , using the formula to calculate the length of the remaining material , and determining the width of the remaining material according to the geometric relationship, so as to obtain the size information of the remaining material; S53. Construct an evaluation model for the production requirements of other steel bar parts, considering the required steel bar length for each steel bar part , quantity and the allowable dimensional error range . Calculate the urgency of each steel bar part's demand for the remaining material through the formula , and quantify the urgency of each steel bar part's demand for the remaining material; S54. Take the size information, quantity of the remaining material and the urgency of each steel bar part as the input of the genetic algorithm. Encode the remaining material allocation scheme using an integer array, and evaluate the quality of the allocation scheme through the fitness function . is the quantity of the remaining material allocated to the steel bar part , is the required steel bar length of the steel bar part , is the actual available length of the remaining material allocated to the steel bar part ; Use the roulette wheel selection method, perform crossover operations with a crossover probability and perform mutation operations with a mutation probability . After multiple generations of iterative optimization, select the scheme corresponding to the chromosome with the highest fitness and schedule the remaining material to the appropriate steel bar part processing tasks to achieve efficient use of materials.

[0011] In the optimal solution, the specific method of step S6 is as follows: S61. The management platform continuously collects data such as the quantity of processed steel bars and processing speed during the processing through the real-time data interface with the processing equipment. represents time, and constructs a time series data set and . is the number of data collection time points; S62. Process the data of the quantity of processed steel bars using the grey prediction model (GM(1,1)), specifically including: Through the formula ( ) perform a first-order cumulative generation on the original sequence of the quantity of processed steel bars to obtain the sequence , so as to weaken the randomness of the data and highlight the data trend, facilitating subsequent modeling and analysis; Based on the cumulative generation sequence construct , where is the development coefficient reflecting the data development trend, is the grey action quantity reflecting the data driving factors; Adopt the least squares method and calculate the parameters through the formula and to provide parameter support for prediction; Solve the prediction formula from the whiting differential equation for predicting the future cumulative generated quantity of processed steel bars; For the predicted cumulative generation sequence , perform a subtraction generation through the formula to obtain the predicted value sequence of the actual quantity of processed steel bars; For the total quantity of steel bars in the steel bar parts , set the current time as , the prediction time step as , when , determine the predicted completion time to provide a key basis for production monitoring and adjustment; Set the early warning threshold and the delay warning threshold for the processing progress. When the predicted completion time meets , trigger an early warning to notify relevant personnel to prepare for the subsequent process; when , trigger a delay warning, and the management platform notifies the personnel to adjust the production plan. The trigger conditions of the warning mechanism are uniformly represented by the formula ; When the delay warning is triggered, adopt a production adjustment algorithm, specifically including: S63. Calculate the schedulable priority of each device through the formula Wei: , comprehensively considering the remaining processing capacity of the device, the current task priority and the device adjustment cost, where , , is a weight coefficient, and ; S63. According to the schedulable priority of the equipment, transfer some tasks of the equipment with a lagging processing progress to the equipment with a higher schedulable priority, or, on the premise of ensuring the processing quality, adjust the processing speed according to the formula and the relationship between the processing time to increase the processing speed so as to shorten the processing time and accelerate the overall production progress.

[0012] In the preferred solution, the specific method of step S7 is as follows: Pre-store the standard shape feature data of the steel bar parts and the corresponding transport vehicle number information in the management platform. The shape of the steel bar parts is represented by the feature vector , and at the same time load the object detection algorithm of the OpenCV library, the KMP string matching algorithm, and the structural similarity index algorithm; Use a high-definition camera to collect images of the transport station in real time, and use the adaptive histogram equalization algorithm to enhance the image contrast and improve the recognition rate of the steel bar parts and the transport vehicle number, so as to provide high-quality images for subsequent processing; Use the object detection algorithm in the OpenCV library to detect the steel bar parts and the transport vehicle number. For the detected steel bar parts, extract the shape feature vector , and for the transport vehicle number, extract the character information ; Use the KMP algorithm to compare the extracted transport vehicle number with the correct number recorded in the management platform, and efficiently judge whether the numbers match by calculating the partial match table $PMT$ of ; Use the structural similarity index algorithm to calculate the similarity of the shape feature vectors of the steel bar parts , where , are the means, , are the standard deviations, is the covariance, , is a constant, set the similarity threshold , and judge whether the shapes match; The management platform maintains the transport sequence queue , obtains the expected sequence number of the steel bar parts and the actually detected sequence number , and judges whether the transport sequence is correct by comparing the two; ​If the number comparison fails, the shape similarity is lower than the threshold, or the transportation sequence is incorrect, the management platform issues an alarm signal and initiates an error correction process, takes corresponding measures according to the error type, and evaluates the error severity according to the error severity evaluation formula to determine the error correction priority, , , are weight coefficients and , is the Kronecker function.

[0013] In the preferred solution, the steel bar components are transported to the construction location and then installed. During the construction process, the processing sequence scheduling, surplus material processing, processing progress monitoring, and transportation monitoring steps are cyclically executed. After all the steel bar components at the construction location are constructed and pass the quality inspection, the construction task is determined to be completed.

[0014] The present invention provides a manufacturing scheduling method for bridge steel bar components. In terms of construction efficiency, this method uses the management platform to collect construction time data, reasonably schedules processing equipment and task sequences, and closely coordinates the processing of steel bar components with the construction progress. For example, the construction sequence is determined based on the critical path method, and the priority queue algorithm is used to sort processing tasks, avoiding construction delays, greatly shortening the construction period, and improving the overall construction efficiency.

[0015] Regarding construction quality, the processing equipment strictly performs processing operations according to the material information form, and precisely controls parameters using specific formulas in each process. For example, the cutting length is controlled in the cutting process, the bending accuracy is ensured in the bending process, and the welding quality is ensured in the welding process, thereby effectively guaranteeing the processing quality of the steel bar components and improving the overall structural stability and safety of the bridge.

[0016] In terms of resource utilization, image acquisition equipment and related algorithms are used to process processing surplus materials. The size information of the surplus materials is obtained through the Hough transform, and the genetic algorithm is used to find the optimal surplus material allocation plan, and the surplus materials are scheduled to appropriate steel bar component processing tasks, improving the material utilization rate and reducing the production cost.

[0017] In terms of production management, the management platform collects processing equipment data in real time, uses the grey prediction model to predict the processing completion time, and sets a threshold range to trigger the warning mechanism. When the predicted time exceeds the threshold, relevant personnel are notified in a timely manner to adjust the production plan, such as reallocating tasks according to the equipment schedulable priority or adjusting processing parameters, ensuring that the production process proceeds on time, and enhancing the scientific nature and accuracy of production management.

[0018] In the transportation monitoring process, high-definition cameras are installed at the transportation workstations. Combining image recognition technology, string matching algorithms, and image similarity algorithms, the steel bar components being transported are monitored in real time. Once a transportation error or sequence error is detected, an alarm signal is immediately issued and the error correction process is initiated to ensure that the steel bar components are accurately transported to the designated construction location, reducing construction delays caused by transportation problems.

[0019] It realizes the efficient management and precise control of the entire process of manufacturing bridge steel bar components, improves construction efficiency and quality, reduces costs, enhances the scientific nature of production management and the accuracy of transportation, and strongly promotes the development of the bridge construction industry. Brief Description of the Drawings

[0020] The present invention will be further described below in conjunction with the drawings and embodiments: Figure 1 It is the manufacturing scheduling flowchart of the bridge steel bar components of the present invention; Detailed Embodiments Embodiment 1 As Figure 1 shown, a method for manufacturing and scheduling bridge steel bar components, the method includes: S1. Using the management platform, through the API interface or database connection, collect the construction period and completion period data from the construction project management system and the project progress record database; S2. The management platform establishes a data connection with various processing equipment in the factory to obtain the real-time operation status information of the equipment in real time; S3. With the help of three-dimensional model processing tools, the designed steel bar components are disassembled into steel bar blocks and steel bar meshes according to the structural characteristics and design specifications, and a material list is generated using a data table; S4. Assign tasks to the selected processing equipment in sequence according to the construction period and completion period data in step S1, and transport the generated material list and the sorted materials to the corresponding positions of the processing equipment; S5. Use a high-definition industrial camera to collect images of the production waste generated during processing, and schedule the waste to the appropriate steel bar component processing tasks; S6. The management platform continuously collects the real-time data of the processing equipment during the processing process, predicts the processing completion time of the steel bar components, and adjusts the entire production process according to the processing completion time; S7. Install high-definition cameras at the truck shipping and transportation workstations, and use image recognition technology to monitor the steel bar components being transported in real time. When a transportation error or sequence error is found, an alarm signal is immediately issued, and the error correction process is initiated.

[0021] In the preferred solution, the management platform collects the construction period and completion period data of each construction location in the public network or the internal and external networks, and uses the Bloom filter deduplication algorithm to clean and organize the data in combination with the time range and format check, and stores the processed data in the management platform database.

[0022] In the preferred solution, the processing equipment includes a numerically controlled steel bar sawing and threading production line, a numerically controlled bending equipment, a flexible manufacturing production line for steel bar meshes, a flexible manufacturing production line for steel bar sheets, and a flexible manufacturing production line for steel bar blocks; Obtain the operating status information of the equipment, including the processing progress percentage and the remaining processing time; Use the Hungarian algorithm to select processing equipment for steel bar components, and preferentially arrange the equipment with the shortest remaining processing time for processing.

[0023] In the preferred solution, use the pandas library in the data table generation tool Python to organize the material information required for the split steel bar blocks and steel bar meshes into a structured table form; The content in the table form includes detailed data on steel bar specifications, quantities, and dimensions; Send the material information table to the control system of the selected processing equipment and the operation terminal of the processing personnel through the network transmission protocols FTP and HTTP.

[0024] The steps of the manufacturing scheduling method for bridge steel bar components specifically include: 1. Construction time data collection and collation: Use the management platform in the public network or the internal and external networks to collect the construction period and completion period data of each construction location by interacting with the construction project management system, the project progress record database, etc. Adopt the Bloom filter deduplication algorithm, combine the set time range, format check and other rules to clean and organize the collected data, remove invalid data and duplicate data, and store the processed data in the database of the management platform to provide an accurate time basis for subsequent scheduling.

[0025] 2. Processing equipment status monitoring and selection: The management platform establishes a data connection with various processing equipment in the factory (such as numerically controlled steel bar sawing and threading production lines, numerically controlled bending equipment, flexible manufacturing production lines for steel bar meshes, flexible manufacturing production lines for steel bar sheets, flexible manufacturing production lines for steel bar blocks, etc., specifically determined according to the processing requirements of different steel bar components), and obtains the operating status information of the equipment in real time, including the processing progress percentage, the remaining processing time, etc. Use the Hungarian algorithm to select the most suitable processing equipment for each steel bar component according to the remaining processing time of the equipment and the processing tasks of the steel bar components, and preferentially arrange the equipment with the shortest remaining processing time for processing to improve the overall production efficiency.

[0026] 3. Reinforcement Component Disassembly and Material Information Sorting: With the help of 3D model processing tools, disassemble the designed reinforcement components into reinforcement blocks and reinforcement meshes according to structural characteristics and design specifications. Use data table generation tools (such as the pandas library in Python) to sort the material information required for the disassembled reinforcement blocks and reinforcement meshes into a structured table form, including detailed data such as the specifications, quantities, and dimensions of the reinforcement bars. Through network transmission protocols (such as FTP, HTTP), send the material information table to the control system of the selected processing equipment and the operation terminals of the processing personnel to ensure that both the processing personnel and the equipment can obtain accurate processing information.

[0027] 4. Processing Sequence Scheduling and Task Execution: Determine the construction sequence of the reinforcement components based on the overall plan of the construction project, the requirements of the construction period, and the critical path method. Use the priority queue algorithm to sort the processing tasks of the reinforcement components by comprehensively considering factors such as the sequence of construction and the urgency of the construction period. The processing equipment executes the processing tasks according to the scheduling sequence. During the processing, strictly perform the processing operations of the reinforcement bars according to the requirements in the material information table, such as cutting, bending, and welding of the reinforcement bars, to ensure the processing quality of the reinforcement components.

[0028] 5. Scrap Collection, Analysis, and Scheduling: After the processing equipment completes the processing of the reinforcement components, use an image acquisition device (high-definition industrial camera) to collect images of the scraps generated during processing. Perform edge detection on the collected scrap images through image processing algorithms such as the Hough transform to obtain the size information of the scraps. Transmit the size information of the scraps to the scheduling device. The scheduling device uses a genetic algorithm to find the optimal scrap allocation plan based on the current production requirements of other reinforcement components and the size and quantity of the scraps, and schedule the scraps to the appropriate reinforcement component processing tasks to achieve efficient use of materials and reduce production costs.

[0029] 6. Processing Progress Prediction and Monitoring: The management platform continuously collects real-time data during the processing of the processing equipment, such as the number of processed reinforcement bars and the processing speed. Use the grey prediction model to analyze and process these data to predict the completion time of the reinforcement component processing. At the same time, set a reasonable threshold range for the processing progress. When the predicted completion time exceeds this threshold range, the management platform automatically triggers an early warning mechanism to notify the relevant personnel to adjust the production plan in a timely manner to ensure that the entire production process proceeds on time.

[0030] 7. Transportation Monitoring and Error Handling: Install high-definition cameras at the transportation workstations and use image recognition technology to monitor the transported steel bar components in real time. Compare the shape information of the steel bar components recognized by the cameras and the vehicle numbers with the data recorded in the management platform. String matching algorithm is used for the vehicle numbers, and image similarity algorithm is used for the shapes. If it is found that the transported steel bar components do not match the records or the transportation sequence is incorrect, the management platform immediately issues an alarm signal and initiates an error correction process to notify the relevant personnel for handling, ensuring that the steel bar components are accurately transported to the designated construction location.

[0031] 8. Construction Process Cycle and End Judgment: After the steel bar components are transported to the construction location, the construction personnel carry out the installation construction according to the construction sequence. During the construction process, steps such as processing sequence scheduling, surplus material handling, processing progress monitoring, and transportation monitoring are continuously cycled. When the construction of the steel bar components at all construction locations is completed and passes the quality inspection, it is determined that the construction task of the entire bridge steel bar components is completed.

[0032] Embodiment 2 Further described in combination with Embodiment 1, the specific method of step S4 is as follows: S41. According to the construction period and completion period data, use the task assignment algorithm based on time window and resource constraints to calculate the task urgency , where is the completion period of task , is the current time, used to quantify the task urgency Combined with the available processing time window and processing capacity of the processing equipment, sort the tasks according to the task urgency from high to low and assign them to the earliest available equipment; S42. Determine the construction sequence based on the construction project plan, deadline requirements, and improved critical path method, construct a construction process network, and perform forward calculation , , where: is the duration of process , used to calculate the earliest start and end times of the process; Perform backward calculation , , determine the critical path, which is composed of processes with total float equal to 0, and determines the shortest project duration; S43. Use the priority queue algorithm to sort the tasks according to the priority function , where , are weight coefficients and , is task The construction sequence number determines the priority by comprehensively considering the task urgency and construction sequence, and tasks are allocated to processing equipment in sequence; S44. The processing equipment executes tasks according to the scheduling sequence, and the blanking process is carried out according to Controlling the blanking length, where is the required blanking length, is the cutting precision error to ensure the blanking length precision; The bending process is carried out according to 、 Controlling the bending angle and radius, 、 are the designed bending angle and radius, is the bending precision to ensure the bending precision; The welding process controls the welding parameters according to the welding quality evaluation formula where 、 、 are the weight coefficients, 、 、 are the welding current, voltage and time.

[0033] Detailed steps of step S4: 1. Task allocation algorithm: According to the construction period and completion period data collected in step S1, a task allocation algorithm based on time window and resource constraint (TWRC - Task Allocation Algorithm based on TimeWindow and Resource Constraint) is adopted.

[0034] First, for each steel bar component task Calculate the time urgency , and the formula is as follows: ; Where represents the completion deadline of task , represents the current time. The closer the value of

[0035] is to 0, the more urgent the task is. This formula quantifies the time urgency of each task by calculating the proportion of the remaining time in the total project duration, providing an important basis for subsequent task allocation. Considering the equipment resource constraint: For the selected processing equipment , determine its available time window for processing, as well as the processing capacity of the equipment

[0036] Task Assignment Strategy: Sort tasks according to the degree of time urgency from high to low. For each task , on the premise of meeting the equipment time window and processing capacity, assign it to the earliest available equipment . If the current equipment cannot meet the task requirements, look for the next available equipment.

[0037] 2. Construction Sequence Determination Algorithm: Determine the construction sequence of steel bar components based on the overall planning of the construction project, construction period requirements, and the critical path method. Use the improved critical path method (MCPM - Modified Critical Path Method).

[0038] Regard each processing procedure of the steel bar components as a node, and regard the sequence relationship between procedures as an edge to construct a directed acyclic graph (DAG - Directed Acyclic Graph). Each node n contains the start time , end time , latest start time and latest end time .

[0039] Calculate the time parameters of the procedures: Forward calculation of the earliest start time and earliest end time: ; , where is the duration of procedure .

[0040] These two formulas determine the earliest time when each procedure can start and end without affecting subsequent procedures by gradually calculating the earliest start and end times of each procedure starting from the starting node.

[0041] Backward calculation of the latest start time and latest end time: ;

[0042] These two formulas calculate the latest start and end times of each procedure backward from the end node, determining the latest time when each procedure can start and end without delaying the overall project duration.

[0043] The critical path is the path composed of all procedures with a total float of 0, and the total float . The procedures on the critical path determine the shortest duration of the entire project. By finding the critical path, it is clear which procedure delays will directly affect the progress of the entire project.

[0044] 3. Processing task sequencing algorithm: The priority queue algorithm is adopted to comprehensively consider factors such as the construction sequence and the urgency of the construction period, and sort the processing tasks of the steel bar components.

[0045] Define the priority function: For each task Define the priority , the formula is as follows:

[0046] Among them, and are weight coefficients, and , which can be adjusted according to the actual project situation. represents the serial number of task in the construction sequence. The smaller the serial number, the earlier the construction sequence. is the time urgency calculated previously. This formula comprehensively considers the time urgency and construction sequence of the task. By adjusting the weight coefficients, the influence of both on the priority can be flexibly balanced.

[0047] Priority queue operation: Insert all tasks into the priority queue according to the priority . The tasks with higher priority are arranged in the front of the queue. Each time, the task with the highest priority is taken out from the queue and assigned to the processing equipment for processing.

[0048] 4. Processing equipment executes tasks: The processing equipment executes the processing tasks according to the scheduling sequence. During the processing, the steel bar processing operations are strictly carried out according to the requirements in the material information table, such as the cutting, bending, welding and other processes of the steel bars, to ensure the processing quality of the steel bar components.

[0049] Cutting process: According to the steel bar specifications and length requirements in the material information table, use the numerical control steel bar sawing equipment for cutting. When controlling the cutting length, consider the cutting precision error of the equipment , the control range of the actual cutting length is:

[0050] Among them, is the steel bar cutting length required in the material information table. This formula ensures that the cutting length is within the allowable error range and guarantees the dimensional accuracy of the steel bar components.

[0051] Bending process: For the steel bars that need to be bent, according to the bending angle and bending radius required by the design, use the numerical control bending equipment for bending operation. During the bending process, consider the bending precision of the equipment , the actual bending angle and bending radius The control range is: ; ; These two formulas ensure that the bending angle and bending radius meet the design requirements, ensuring the shape accuracy of the steel bar parts.

[0052] In the welding process, to ensure the welding quality, according to the specifications of the steel bars and the requirements of the welding process, control the welding current , welding voltage and welding time . Use the welding quality evaluation formula , where , , are the weight coefficients determined according to the welding process and the steel bar material. By adjusting the welding parameters, make the value within a suitable range to ensure the welding quality. This formula provides a basis for the control of the welding process by quantifying the relationship between the welding parameters and the welding quality.

[0053] Example 3 Combined with Example 1 for further illustration, the specific method of step S5 is as follows: S51. After the processing equipment completes the processing of the steel bar parts, use a high-definition industrial camera to collect the image of the remaining material according to the preset shooting parameters and angles, and use the median filtering algorithm to denoise the collected image. Remove the discrete noise points such as salt-and-pepper noise in the image through the formula to provide an accurate data basis for subsequent edge detection, where , is the pixel value within the neighborhood window centered on the pixel point , is the pixel value after denoising; S52. Apply the Hough transform to the preprocessed image for edge detection. The straight-line equation in the Cartesian coordinate system is converted to the Hough space as , where is the perpendicular distance from the origin to the straight line, is the angle between the perpendicular line and the axis. By accumulating votes in the Hough space to find the peak point to obtain the straight-line parameters in the image. After detecting the straight line, according to the straight-line endpoint coordinates and , use the formula to calculate the length of the remaining material, and determine the width of the remaining material according to the geometric relationship, so as to obtain the size information of the remaining material; S53. Construct an evaluation model for the production requirements of other steel bar parts, considering each steel bar part The required steel bar length , quantity And the allowable dimensional error range , and calculate the urgency of the demand for surplus materials for each steel bar part through the formula , quantifying the urgency of the demand for surplus materials for each steel bar part; S54. Take the dimensional information, quantity Of the surplus materials and the urgency of the demand for each steel bar part As the input of the genetic algorithm, encode the surplus material allocation scheme using an integer array, and evaluate the pros and cons of the allocation scheme through the fitness function , Is the quantity of surplus materials allocated to the steel bar part , Is the steel bar part The required steel bar length, Is the actual available length of the surplus materials allocated to the steel bar part ; Use the roulette wheel selection method, perform crossover operations with the crossover probability And perform mutation operations with the mutation probability . After multi-generation iterative optimization, select the scheme corresponding to the chromosome with the highest fitness and schedule the surplus materials to the appropriate steel bar part processing tasks to achieve efficient utilization of materials.

[0054] Detailed steps of step S5: 1. Surplus material image acquisition and preprocessing: After the processing equipment completes the processing of steel bar parts, a high-definition industrial camera acquires images of the surplus materials according to the preset shooting parameters and angles. Since the acquired images may be disturbed by noise, preprocessing is required. Use the median filtering algorithm to denoise the images. For each pixel point In the image, its pixel value After median filtering is the median of the pixel values in the neighborhood window centered on this pixel point (for example Or Window).

[0055] Assume that the set of pixel values in the neighborhood window is , where , then: ; By taking the median of the neighboring pixels, discrete noise points such as salt-and-pepper noise in the image are effectively removed, making the image smoother and providing a more accurate data basis for subsequent edge detection.

[0056] 2. Edge Detection and Size Calculation of Scrap Based on Hough Transform: The preprocessed image is subjected to edge detection using the Hough transform. The Hough transform is a method for detecting geometric shapes in an image. For line detection, in the Cartesian coordinate system, the line equation is , and when converted to the Hough space, it becomes (where is the perpendicular distance from the origin to the line, and is the angle between the perpendicular line and the axis).

[0057] For each edge point in the image, it corresponds to a sine curve in the Hough space. By accumulating votes in the Hough space, peak points are found, and the values corresponding to these peak points represent the line parameters in the image.

[0058] After detecting the line, based on the detected endpoint coordinates and , the length and width of the scrap are calculated. If multiple parallel lines form the boundary of the scrap, the width is determined according to the geometric relationship. This formula is used to calculate the line length, thereby obtaining the size information of the scrap and providing accurate data for subsequent scrap allocation.

[0059] 3. Scrap Demand Assessment: For the production demands of other steel bar components, a demand assessment model is constructed. Consider the required steel bar length , quantity , and the allowable dimensional error range for each steel bar component . Calculate the demand urgency of each steel bar component for the scrap, and the formula is as follows: ; Among them, the numerator represents the total required length of the steel bar for the steel bar component , and the denominator represents the total required length of the steel bar for all steel bar components. This formula quantifies the demand urgency of each steel bar component for the scrap by considering the required length, quantity, and dimensional error range of each steel bar component. The higher the demand urgency, the more urgent the demand for the scrap by this component.

[0060] 4. Scrap Allocation Based on Genetic Algorithm: The size information (length , width , etc.) and quantity of the scrap, as well as the demand urgency As the input of the genetic algorithm.

[0061] Encode the leftover material allocation plan into a chromosome. For example, it can be represented by an integer array, and each element in the array represents the quantity of leftover material allocated to different steel bar parts.

[0062] Design a fitness function $Fitness$ to evaluate the quality of each chromosome (i.e., the leftover material allocation plan). The formula is as follows:

[0063] Among them, is the quantity of leftover material allocated to the steel bar part ; is the required quantity of the steel bar part ; is the required steel bar length of the steel bar part ; is the actual available length of the leftover material allocated to the steel bar part (considering the matching situation between the leftover material size and the required size of the steel bar part). This formula comprehensively considers the matching degree between the allocated quantity and the required quantity of the leftover material, the urgency of the demand, and the fitting degree between the leftover material size and the required size of the steel bar part. The higher the fitness function value, the better the leftover material allocation plan.

[0064] Genetic operations: Adopt the roulette wheel selection method. According to the fitness value of the chromosome, the higher the fitness of the chromosome, the greater the probability of being selected for genetic operations. Assume the population size is , and the fitness of chromosome is , then its selection probability is: ; By calculating the selection probability of each chromosome, chromosomes with high fitness have a greater chance to participate in the reproduction of the next generation, simulating the mechanism of survival of the fittest in natural selection.

[0065] Select two chromosomes for crossover operation with a certain crossover probability , and exchange some of their genes to generate new offspring chromosomes. For example, single-point crossover is to randomly select a crossover point on the chromosome and exchange the gene segments after this point of the two chromosomes.

[0066] Mutate the genes of the chromosome with a certain mutation probability , randomly change the values of the genes, introduce new genetic information, and prevent the algorithm from falling into a local optimal solution.

[0067] Continuously repeat the selection, crossover, and mutation operations. After multiple generations of evolution, select the chromosome with the highest fitness as the final waste material allocation plan. Schedule the waste materials into the appropriate steel bar component processing tasks according to this plan to achieve efficient utilization of materials.

[0068] Example 4 Further described in combination with Example 1, the specific method of step S6 is as follows: S61. The management platform continuously collects data such as the quantity of processed steel bars , processing speed etc. during the processing through the real-time data interface with the processing equipment, represents time, and constructs a time series data set and , is the number of data collection time points; S62. Use the grey prediction model (GM(1,1)) to process the data of the quantity of processed steel bars, specifically including: Through the formula ( ) perform a first-order accumulation generation on the original sequence of the quantity of processed steel bars to obtain the sequence to weaken the randomness of the data and highlight the data trend for subsequent modeling and analysis; Based on the accumulated generation sequence construct , where is the development coefficient reflecting the data development trend, is the grey action quantity reflecting the data driving factor; Adopt the least squares method, and calculate the parameters through the formula and to provide parameter support for prediction; Solve the prediction formula from the whitening differential equation for predicting the future accumulated quantity of processed steel bars; For the predicted accumulated generation sequence , perform a subtraction generation through the formula to obtain the predicted value sequence of the actual quantity of processed steel bars; For the total quantity of steel bars of the steel bar component, set the current time as , the prediction time step as , when , determine the predicted processing completion time to provide a key basis for production monitoring and adjustment; Set an early warning threshold for the processing progress and the delay warning threshold When the predicted processing completion time meets an early warning is triggered to notify relevant personnel to prepare for subsequent processes; when a delay warning is triggered, and the management platform notifies personnel to adjust the production plan. The trigger conditions for the warning mechanism are uniformly represented by the formula ; When a delay warning is triggered, a production adjustment algorithm is adopted, specifically including: S63. Through the formula Wei: Calculate the schedulable priority of each device , comprehensively considering the remaining processing capacity of the device, the current task priority, and the device adjustment cost, where , , are weight coefficients and ; S63. According to the schedulable priority of the device, transfer some tasks of the devices with lagging processing progress to the devices with high schedulable priority, or, on the premise of ensuring processing quality, adjust the processing speed according to the formula and the relationship between the processing speed and the processing time to increase the processing speed so as to shorten the processing time and speed up the overall production progress.

[0069] Detailed steps of step S6: The management platform continuously collects various data during the processing through the real-time data interface with the processing equipment, such as the number of processed steel bars , the processing speed , etc., where represents time. Organize the collected data to construct a time series data set and , is the number of time points for data collection.

[0070] Use the grey prediction model (GM(1,1)) to analyze and process the data of the number of processed steel bars to predict the processing completion time of the steel bar parts. The GM(1,1) model is a prediction method based on grey system theory. It weakens the randomness of the data and mines the potential laws of the data by performing accumulation generation and other processing on the original data.

[0071] Perform a first-order accumulation generation (1 - AGO) on the original sequence of the number of processed steel bars to obtain a new sequence , and the formula is: ; Its function is to make the original data show a certain regularity through accumulation operation, which is convenient for subsequent model establishment and analysis. After the accumulation generation, the trend of the data becomes more obvious, which is conducive to capturing the internal characteristics of the data.

[0072] Based on the accumulated generating sequence , construct the whitenization differential equation: , where is the development coefficient, reflecting the development trend of the data; is the grey action quantity, reflecting the driving factors of the data. This equation describes the change trend of the accumulated generating sequence and is one of the core equations of the GM(1,1) model.

[0073] Estimate the parameters and using the least squares method. Let , then: ; where , . Calculate the values of the parameters and through this formula, providing parameter support for subsequent prediction.

[0074] The prediction formula can be obtained from the solution of the whitenization differential equation: In is the value of the predicted accumulated generating sequence at time. This formula is used to predict the quantity of processed steel bars generated by accumulation at future times. By predicting the accumulated generating sequence and then performing inverse accumulation generation (IAGO), the predicted value of the actual quantity of processed steel bars can be obtained.

[0075] Perform inverse accumulation generation on the predicted accumulated generating sequence to obtain the predicted sequence of the quantity of processed steel bars , and the formula is: , restoring the predicted value of the accumulated generation to the predicted value of the actual quantity of processed steel bars, so as to obtain the predicted quantity of processed steel bars at each time point.

[0076] Let the total quantity of steel bars of the steel bar component be , and calculate the predicted processing completion time according to the predicted sequence of the quantity of processed steel bars . By gradually accumulating the predicted quantity of processed steel bars, when the accumulated value reaches or exceeds , the corresponding time point is the predicted processing completion time. Let be the current time, be the predicted time step, then: when , , by continuously accumulating the predicted quantity of processed steel bars, find the time point that meets the total steel bar quantity requirement, thereby determining the predicted processing completion time, providing a key basis for the monitoring and adjustment of the production process.

[0077] Set a reasonable threshold range for the processing progress, including the early warning threshold and the delay warning threshold. . The early warning threshold represents the time limit when the processing progress may be completed in advance, and the delay warning threshold represents the time limit when the processing progress may be completed with a delay. When the predicted processing completion time meets the following conditions, trigger the corresponding warning mechanism: If , trigger an early warning and notify relevant personnel to make preparations for subsequent processes in advance; If , trigger a delay warning, and the management platform automatically notifies relevant personnel to adjust the production plan in a timely manner, such as increasing equipment, adjusting the processing technology, or reallocating tasks, etc.

[0078] The trigger condition formula of the warning mechanism can be uniformly expressed as: ; It clarifies the warning status under different processing completion time situations, enabling the management platform to respond in a timely manner according to the prediction results, ensuring that the entire production process proceeds on time.

[0079] When a delay warning is triggered, use a production adjustment algorithm to adjust the production process. This algorithm considers various factors, such as the schedulability of equipment, the availability of personnel, and the priority of tasks, etc. Calculate the schedulable priority of each equipment , and the formula is:

[0080] Among them, , , are weight coefficients, and , which are adjusted according to the actual production situation. The remaining processing capacity represents the quantity of steel bars that the equipment can still process in the current state, and the total processing capacity is the maximum processing capacity of the equipment; the current task priority is determined according to the urgency of the task and the impact on the entire production process; the equipment adjustment cost includes the time required for the equipment to switch tasks, the cost of replacing tools, etc. This formula comprehensively considers the remaining processing capacity of the equipment, the current task priority, and the equipment adjustment cost. By adjusting the weight coefficients, the schedulable priority of the equipment can be flexibly determined, and the equipment with a high schedulable priority is preferentially selected for task adjustment.

[0081] Reallocate tasks or adjust processing parameters according to the schedulable priority of the equipment. For example, transfer some tasks from the equipment with a lagging processing progress to the equipment with a high schedulable priority for processing, or adjust the processing speed and the relationship of processing time According to the formula , on the premise of ensuring the processing quality, appropriately increase the processing speed to shorten the processing time , thereby accelerating the overall production progress.

[0082] Example 5 Further described in combination with Example 1, the specific method of step S7 is as follows: Pre-store the standard shape feature data of the steel bar parts and the corresponding transport vehicle number information in the management platform. The shape of the steel bar parts is represented by a feature vector , and at the same time load the object detection algorithm of the OpenCV library, the KMP string matching algorithm, and the structural similarity index algorithm; Use a high-definition camera to collect images of the transport station in real time, and use the adaptive histogram equalization algorithm to enhance the image contrast and improve the recognition rate of the steel bar parts and the transport vehicle number, providing high-quality images for subsequent processing; Use the object detection algorithm in the OpenCV library to detect the steel bar parts and the transport vehicle number. For the detected steel bar parts, extract the shape feature vector , and for the transport vehicle number, extract the character information ; Use the KMP algorithm to compare the extracted transport vehicle number with the correct number recorded in the management platform , and efficiently judge whether the numbers match by calculating the partial match table $PMT$ of; Use the structural similarity index algorithm to calculate the similarity of the shape feature vectors of the steel bar parts , where , are the means, , are the standard deviations, is the covariance, , is a constant, set the similarity threshold , and judge whether the shapes match; The management platform maintains the transport order queue , obtain the expected sequence number of the steel bar parts and the actually detected sequence number , and judge whether the transport order is correct by comparing the two; If the number comparison fails, the external shape similarity is lower than the threshold, or the transportation order is incorrect, the management platform issues an alarm signal and initiates an error correction process, takes corresponding measures according to the error type, and evaluates according to the error severity assessment formula to determine the error correction priority, , , where are weight coefficients and , is the Kronecker function.

[0083] The detailed calculation steps of step S7 are as follows: In the management platform, the standard external shape feature data (such as dimensions, shapes, etc.) of each steel bar part and the corresponding transport vehicle number information are pre - stored. For the external shape features of the steel bar parts, they are represented by feature vectors. For example , where represents different feature dimensions, such as length, width, bending angle, etc. At the same time, relevant models and algorithms for image recognition are loaded, such as the object detection model based on the OpenCV library, the KMP algorithm for number comparison, and the Structural Similarity Index (SSIM) algorithm for external shape comparison.

[0084] The high - definition camera performs real - time image acquisition of the transportation station at the set frame rate. The acquired images may have problems such as uneven illumination and noise, so pre - processing is required. First, the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm is used to enhance the contrast of the image. The formula is as follows: For each pixel point in the image, its pixel value after CLAHE processing is obtained by performing histogram equalization on the local area centered on this pixel point. The specific implementation process is to divide the image into multiple small blocks, calculate the histogram of each small block, then perform the equalization operation, and finally merge the processed small blocks into a complete image through bilinear interpolation.

[0085] The purpose of this step is to improve the clarity of the image, enhance the recognition of the steel bar parts and the transport vehicle numbers in the image, and provide better image quality for subsequent object detection and feature extraction.

[0086] Use the object detection algorithm in the OpenCV library (such as Haar cascade detector or deep - learning object detection models, such as YOLO, Faster R - CNN, etc.) to detect the steel bar parts and the transport vehicle numbers in the pre - processed image.

[0087] Taking the deep learning object detection model as an example, the model learns the feature representations of steel bar parts and transport vehicle numbers by training on a large number of annotated image data. During detection, the model performs forward propagation calculations on the input image and outputs the positions (such as bounding box coordinates ) and categories (steel bar parts or transport vehicle numbers) of the detected objects.

[0088] For the detected steel bar parts, their external shape features are extracted and also represented by a feature vector ; for the transport vehicle numbers, their character information is extracted .

[0089] 4. Number comparison algorithm**: The KMP (Knuth - Morris - Pratt) algorithm is used to compare the character information of the extracted transport vehicle numbers with the correct numbers recorded in the management platform . The core of the KMP algorithm is to use the partial match table (PMT - Partial Match Table) to reduce unnecessary character comparisons.

[0090] First, calculate the partial match table $PMT$ of the correct number , where $PMT[i]$ represents the length of the longest same prefix and suffix of the substring composed of the first characters.

[0091] Then, during the comparison process, let be the current comparison position of , and be the current comparison position of . When , and increase simultaneously; when , , until or . If reaches the length, it means the number matching is successful; otherwise, the number comparison fails.

[0092] This algorithm can efficiently perform string matching, quickly determine whether the transport vehicle number is correct, and reduce the time complexity of comparing characters one by one.

[0093] The structural similarity index (SSIM) algorithm is used to calculate the similarity between the external shape feature vector of the detected steel bar parts and the standard external shape feature vector recorded in the management platform . The SSIM algorithm comprehensively considers the brightness, contrast, and structural information of the image, and the formula is as follows: ; Where, and are the means of the feature vectors and respectively, and are their standard deviations respectively, is their covariance, , is a constant used to maintain stability ( , are constants, is the dynamic range of pixel values).

[0094] The closer the SSIM value is to 1, the more similar the shapes of the steel bar components represented by the two feature vectors are. By setting a similarity threshold (such as ), when , it is considered that the shape of the steel bar component does not match the record.

[0095] The management platform maintains a transportation sequence queue , recording the theoretical transportation sequence of each steel bar component. When it is detected that a steel bar component starts to be transported, obtain its expected sequence number in the queue, and at the same time record the actually detected sequence number (the actual transportation sequence can be determined by timestamp or other means).

[0096] By comparing and to judge whether the transportation sequence is correct. If , it is determined that the transportation sequence is incorrect.

[0097] If the number comparison fails, the shape similarity is lower than the threshold, or the transportation sequence is incorrect, the management platform immediately issues an alarm signal. The alarm signal can be notified to relevant personnel through text messages, system pop-ups, etc.

[0098] At the same time, start the error correction process. According to the type of error, different correction measures are taken. For example, if it is a number error, query the management platform records to determine the correct transportation vehicle; if the shape does not match, check the production records of the steel bar components to judge whether there are production errors or confusions, and adjust the transportation arrangements in a timely manner; if the transportation sequence is incorrect, re-plan the transportation route and sequence to ensure that subsequent transportation is carried out in the correct order.

[0099] To quantify the priority of error correction, define an error severity evaluation formula: ; Among them, , , are weight coefficients (and , which can be adjusted according to the actual situation), and are used to represent the importance degrees of different error types; is the Kronecker Delta function. When , , otherwise . The larger the Severity value is, the more serious the error is, and the errors with higher Severity values are preferentially processed.

[0100] In the preferred solution, after the steel bar component is transported to the construction location, installation construction is carried out. During the construction process, the steps of processing sequence scheduling, surplus material handling, processing progress monitoring, and transportation monitoring are cyclically executed. After the construction of the steel bar components at all construction locations is completed and the quality inspection is qualified, it is determined that the construction task is ended.

[0101] The above embodiments are only the preferred technical solutions of the present invention and should not be regarded as limitations on the present invention. The protection scope of the present invention should be the technical solutions recorded in the claims, including the equivalent replacement solutions of the technical features in the technical solutions recorded in the claims. That is, the equivalent replacement improvements within this scope are also within the protection scope of the present invention.

Claims

1. A method for manufacturing and scheduling bridge steel bar components, characterized by: The method includes: S1. Use the management platform to collect construction deadline and completion deadline data from the construction project management system and project progress record database through API interface or database connection; S2. The management platform establishes data connection with various processing equipment in the factory to obtain the operating status information of the equipment in real time; S3. With the help of 3D model processing tools, the designed steel bar components are split into steel bar blocks and steel meshes according to structural characteristics and design specifications, and a material list is generated using a data table; S4, assigning tasks to the selected processing equipment in sequence according to the construction deadline and completion deadline data in step S1, and transporting the generated material list and materials to the corresponding processing equipment locations after sorting; S5. Use high-definition industrial cameras to collect images of the remaining materials produced during processing, and dispatch the remaining materials to appropriate steel bar component processing tasks; S6. The management platform continuously collects real-time data of the processing equipment during the processing, predicts the processing completion time of the steel bar parts, and adjusts the entire production process according to the processing completion time; S7. Install high-definition cameras at the truck shipping and transportation stations, and use image recognition technology to monitor the transported steel bar components in real time. If transportation errors or sequence errors are found, an alarm signal will be immediately issued and the error correction process will be initiated.

2. A method for manufacturing and scheduling bridge steel bar components according to claim 1, characterized in that: The management platform collects the construction period and completion period data of each construction location on the public network or the intranet and the intranet, uses the Bloom filter deduplication algorithm combined with the time range and format check to clean and organize the data, and stores the processed data in the management platform database.

3. According to the method for manufacturing and scheduling bridge steel bar components as described in claim 1, it is characterized by: Processing equipment includes CNC steel bar sawing and threading production lines, CNC bending equipment, steel mesh flexible manufacturing production lines, steel sheet flexible manufacturing production lines, and steel block flexible manufacturing production lines; Obtain the equipment's operating status information, including processing progress percentage and remaining processing time; The Hungarian algorithm is used to select processing equipment for steel bar components, giving priority to equipment with the shortest remaining processing time.

4. The method for manufacturing and scheduling bridge steel bar components according to claim 1 is characterized by: Use the pandas library in Python, a data table generation tool, to organize the material information required for the split steel blocks and steel mesh into a structured table format; The content in the form of a table contains detailed data on steel bar specifications, quantity, and dimensions; The material information form is sent to the selected processing equipment control system and the processing personnel operation terminal through the network transmission protocol FTP and HTTP.

5. The method for manufacturing and scheduling bridge steel bar components according to claim 1 is characterized by: Step S4 The specific method is: S41. According to the construction deadline and completion deadline data, a task allocation algorithm based on time windows and resource constraints is used to calculate the time urgency of the task. ,in, For the task The completion period, The current time, used to quantify the urgency of the task Combined with the processing time window of the processing equipment and processing capabilities , sort the tasks from high to low time urgency and assign them to the earliest available device; S42, determine the construction sequence based on the construction project planning, deadline requirements and the improved critical path method, build a construction process network, and calculate the construction process through forward calculation. , ,in: For process Duration, used to calculate the earliest start and end time of the process; Reverse calculation , , determine the critical path, by the total time difference The process composition of 0 determines the shortest construction period of the project; S43, use the priority queue algorithm to sort the tasks according to the priority function ,in , is the weight coefficient and , For the task The construction sequence number determines the priority by comprehensively considering the urgency of the task and the construction sequence, and assigns the task to the processing equipment in sequence; S44, processing equipment performs tasks according to the scheduling order, and the unloading process is Control the cutting length, where: To request the cutting length, To reduce the cutting accuracy error and ensure the cutting length accuracy; Bending process , Control the bend angle and radius, , To design the bending angle and radius, To ensure bending accuracy; Welding process based on welding quality evaluation formula Control welding parameters, , , is the weight coefficient, , , are welding current, voltage and time.

6. The method for manufacturing and scheduling bridge steel bar components according to claim 1 is characterized by: Step S5 The specific method is: S51. After the processing equipment completes the processing of steel bar parts, the high-definition industrial camera is used to collect the residual material image according to the preset shooting parameters and angles, and the median filtering algorithm is used to denoise the collected image. Remove discrete noise points such as salt and pepper noise in the image to provide accurate data basis for subsequent edge detection. , Pixel centered The pixel value in the neighborhood window, is the pixel value after denoising; S52, use Hough transform to detect the edge of the preprocessed image, and calculate the linear equation in the Cartesian coordinate system Transformed to Hough space: ,in, is the vertical distance from the origin to the line, For the vertical line The angle between the axes is obtained by accumulating votes in Hough space to find the peak point to obtain the straight line parameters in the image. After the straight line is detected, the coordinates of the straight line endpoints are calculated. and , using the formula Calculate the remaining length , and determine the remaining width based on the geometric relationship , so as to obtain the remaining material size information; S53. Build an evaluation model for the production demand of other steel bar components, considering the production demand of each steel bar component. Required steel bar length ,quantity And the allowable size error range , through the formula Calculate the urgency of the need for spare parts for each steel bar component , quantify the urgency of the demand for surplus materials for each steel bar component; S54, the size information and quantity of the remaining material And the urgency of demand for each steel bar component As the input of the genetic algorithm, an integer array is used to encode the surplus material allocation plan, and the fitness function Evaluate the merits of the allocation plan. Assigned to steel bar parts The amount of remaining material, It is a steel bar part Required steel bar length, Assigned to steel bar parts The actual usable length of the remaining material; Using roulette wheel selection method, crossover probability Perform crossover and mutation probability By performing mutation operations and after multiple generations of iterative optimization, the solution corresponding to the chromosome with the highest fitness is selected to dispatch the surplus materials to the appropriate steel bar component processing tasks, thus achieving efficient utilization of materials.

7. The method for manufacturing and scheduling bridge steel bar components according to claim 1 is characterized by: Step S6 The specific method is: S61. The management platform continuously collects the number of processed steel bars during the processing process through the real-time data interface with the processing equipment. , Processing speed And other data, Representing time and constructing time series datasets and , number of time points for data collection; S62. Use the grey prediction model (GM(1,1)) to process the processed steel bar quantity data, including: By formula ( ) for the original processed steel bar quantity sequence Perform an accumulation generation to obtain the sequence , to weaken the randomness of data, highlight data trends, and facilitate subsequent modeling and analysis; Generate sequences based on accumulation Build ,in The development coefficient reflects the development trend of data. The gray action quantity reflects the data driving factors; Using the least squares method, the formula Calculation parameters and , providing parameter support for prediction; Solving the prediction formula by the whitening differential equation , used to predict the number of processed steel bars that will be generated cumulatively in the future; Generate a sequence of cumulative predictions , through the formula Perform cumulative subtraction to obtain a sequence of predicted values ​​for the actual number of processed steel bars ; Total number of steel bars for steel bar parts , let the current time be , the prediction time step is ,when When the processing completion time is determined , providing key basis for production monitoring and adjustment; Set early warning thresholds for processing progress and delay warning thresholds , when the processing completion time is predicted satisfy When the early warning is triggered, relevant personnel are notified to prepare for the subsequent process; When a delay warning is triggered, the management platform notifies personnel to adjust the production plan. The triggering condition of the warning mechanism is determined by the formula Unified representation; When the delay warning is triggered, the production adjustment algorithm is used, including: S63, through the formula: Calculate the schedulable priority of each device , comprehensively considering the equipment's remaining processing capacity, current task priority, and equipment adjustment costs, among which , , is the weight coefficient and ; S63. Based on the schedulable priority of the equipment, transfer some tasks of the equipment with lagging processing progress to the equipment with high schedulable priority, or, under the premise of ensuring the processing quality, according to the formula Adjust processing speed and processing time Relationship between the two, improve processing speed To shorten processing time , speed up the overall production progress.

8. The method for manufacturing and scheduling bridge steel bar components according to claim 1 is characterized by: The specific method of step S7 is: The management platform pre-stores the standard shape feature data of steel bar parts and the corresponding transport vehicle number information. The shape of steel bar parts is represented by feature vectors. Indicates that the OpenCV library target detection algorithm, KMP string matching algorithm, and structural similarity index algorithm are loaded at the same time; High-definition cameras are used to collect images of the transport station in real time, and an adaptive histogram equalization algorithm is used to enhance image contrast, improve the recognition of steel bar components and transport vehicle numbers, and provide high-quality images for subsequent processing; Use the target detection algorithm in the OpenCV library to detect the steel bar parts and the transport vehicle number, and extract the shape feature vector of the detected steel bar parts , extract character information for the transport vehicle number ; Use KMP algorithm to extract the transport vehicle number The correct number recorded in the management platform Compare and calculate The partial matching table $PMT$ is used to efficiently determine whether the serial number matches; Calculate the similarity of the shape feature vector of steel bar parts using the structural similarity index algorithm ,in , is the mean, , is the standard deviation, is the covariance, , is a constant, setting the similarity threshold , determine whether the appearance matches; The management platform maintains the transportation sequence queue , get the expected sequence number of the steel bar component and the actual detected sequence number , by comparing the two, determine whether the transportation sequence is correct; If the number matching fails, the appearance similarity is lower than the threshold, or the transportation sequence is wrong, the management platform will issue an alarm signal and start the error correction process, take corresponding measures according to the error type, and evaluate the error severity according to the error severity evaluation formula. Determine error correction priorities, , , is the weight coefficient and , is the Kronecker function.

9. The method for manufacturing and scheduling bridge steel bar components according to claim 1, characterized in that: After the steel bar components are transported to the construction location, they are installed and constructed. During the construction process, the processing sequence scheduling, residual material processing, processing progress monitoring and transportation monitoring steps are executed in a loop. After the construction of the steel bar components at all construction locations is completed and the quality inspection is passed, the construction task is considered to be completed.

Images