Railway box girder manufacturing and erecting integrated intelligent production scheduling system

Abstract

The invention relates to the field of artificial intelligence, in particular to a railway box girder manufacturing and erecting integrated intelligent production scheduling system, which comprises a data acquisition and management subsystem used for acquiring construction data in real time and storing and processing the data; the intelligent production scheduling subsystem is used for generating a production scheduling plan based on the standardized basic data set, the production scheduling plan comprises a beam manufacturing plan and a beam erecting plan, the risk of the plan implementation process is predicted, and the plan is dynamically adjusted; the monitoring management subsystem is used for tracking and managing the construction process in real time and monitoring the production condition; the execution management subsystem is used for compiling an execution plan based on the production scheduling plan and completing task distribution of the execution plan; the interaction subsystem comprises a user interface module and is used for a user to know the production condition and manage production tasks, and intelligent management and optimal configuration of the whole process from beam manufacturing to beam erecting are achieved by integrating advanced data collection, algorithm optimization, real-time adjustment and user interface design.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence, in particular to a railway box girder manufacturing and erecting integrated intelligent production scheduling system. BACKGROUND

[0002] In railway engineering construction, the prefabrication and erection of box girders are important links, and their construction progress and completion quality directly affect the quality of the entire project. The traditional production scheduling of railway box girders is mainly based on manual experience, but with the continuous expansion of railway construction scale and the increasing improvement of construction precision, manual production scheduling is low in efficiency, difficult to quickly respond to changes in production demand, and prone to negligence or errors, resulting in unreasonable production plans and affecting construction precision and quality. In addition, the traditional manual production scheduling method has limited real-time computing capability, and in the face of sudden situations such as equipment failure and material shortage, it cannot be flexibly adjusted to achieve optimal allocation of resources, resulting in project delay or resource waste. SUMMARY

[0003] In view of the defects in the prior art, the present application provides a railway box girder manufacturing and erecting integrated intelligent production scheduling system, which realizes intelligent management and optimal allocation of the whole process from girder manufacturing to girder erection by integrating advanced data acquisition, optimization algorithm, real-time adjustment and user interface design.

[0004] In order to solve the above technical problems, the present application solves the problems by the following technical scheme:

[0005] A railway box girder manufacturing and erecting integrated intelligent production scheduling system, comprising:

[0006] A data acquisition and management subsystem for real-time acquisition of construction data and storage and processing of the data, and initialization of a device resource pool based on the acquired data to generate a standardized basic data set; an intelligent production scheduling subsystem for generating a production scheduling plan based on the standardized basic data set, the production scheduling plan including a girder manufacturing plan and a girder erection plan, predicting risks in the implementation process, and dynamically adjusting the plan; a monitoring and management subsystem for real-time tracking and management of the construction process and monitoring of production conditions; an execution management subsystem for preparing an execution plan based on the production scheduling plan and completing task allocation of the execution plan; and an interactive subsystem including a user interface module for user to understand production conditions and manage production tasks.

[0007] By means of the present application, manual intervention is reduced by automation, information processing speed is accelerated, and real-time progress of the process is ensured, thereby improving production scheduling efficiency; a detailed beam manufacturing and erecting plan is automatically generated by using an optimization algorithm, avoiding errors caused by manual calculation, improving data accuracy, and ensuring data authenticity and reliability; specific conditions of each process during production are recorded in detail, and historical data are quickly queried and deeply analyzed to facilitate post-project review, thereby enhancing the traceability of construction data; resource utilization is improved by optimizing resource allocation, thereby reducing waste and cost; real-time monitoring and dynamic adjustment of production scheduling are realized, ensuring smooth construction process and improving the quality of the final product.

[0008] As a preferred, the data acquisition and management subsystem comprises: a data acquisition module for acquiring construction data in real time, including acquiring work point configuration data, beam type setting data, pedestal configuration data and construction progress data, storing and processing the data; a pedestal information management module for integrating information of pedestal types, quantities, positions and use states, and generating an equipment resource pool.

[0009] By means of the present application, the data acquisition module uses Internet of Things (IoT) technology to acquire real-time field information through sensors, RFID (Radio-Frequency Identification) tags, cameras and other intelligent devices, and to collect various types of data related to production scheduling, including but not limited to work point configuration, beam type setting, pedestal configuration, process setting and construction period arrangement, and to transmit them to a cloud server for storage and processing. Specific application scenarios include a steel bar processing workshop, a mixing station and a beam field, ensuring real-time and comprehensive data acquisition and providing accurate resource allocation basis for subsequent production scheduling. The pedestal information management module specifically manages information of beam manufacturing pedestals, including types, quantities, positions, use states and the like, and updates the latest pedestal information in real time to provide accurate data support for production scheduling plan generation, assist management personnel in reasonably allocating resources, and improve utilization.

[0010] As a preferred, the intelligent production scheduling subsystem comprises: an intelligent production scheduling module for generating a production scheduling plan based on standardized basic data sets and optimization algorithms, the production scheduling plan including a beam manufacturing plan and a beam erecting plan; a beam AI scheduling module for predicting risks in the beam manufacturing process and correcting the beam manufacturing plan, and continuously optimizing the beam manufacturing plan; a feasibility analysis module for evaluating whether the production scheduling plan meets safety standards and satisfies resource limitations, and indicating potential risks of the production scheduling plan and improvement directions of the production scheduling plan.

[0011] By the present application, advanced optimization algorithms such as genetic algorithm and ant colony algorithm are used to generate detailed beam manufacturing and erecting plans, AI technology is used to predict various variables that may be encountered during beam manufacturing (such as weather changes, equipment performance, worker skill level, etc.), and measures are taken in advance to deal with them, thereby comprehensively optimizing multiple objectives and predicting risks to ensure the scientificity and feasibility of the production scheduling plan and reduce construction delays. Among them, the beam AI scheduling module can continuously learn and optimize its own algorithm, gradually improving the prediction accuracy and production scheduling effect.

[0012] As a preferred, the intelligent production scheduling module is specifically used for: optimizing pedestal task allocation and construction period arrangement based on genetic algorithm; optimizing beam moving distance and transportation cost based on ant colony algorithm.

[0013] By the present application, the genetic algorithm is used to optimize the allocation of pedestal tasks, reasonably allocate the tasks of pedestals, avoid resource idling or overload, and ensure that the task load U i of any pedestal is close to the average value, i.e. the average load of all pedestals N is the number of pedestals, and the production scheduling plan meets the overall construction period requirement, beam type, pedestal and process specific requirement, and ensures that the total time consumption t i of all processes or tasks does not exceed the total construction period T total , i.e. The ant colony algorithm is used to optimize the beam moving path, select the shortest path (i, j), and update the pheromone concentration τ ij to reflect the path quality, so as to select the shortest path to reduce the transportation cost. By combining the genetic algorithm and the ant colony algorithm, the global resource balanced allocation and the local path optimization are cooperated, the transportation cost is effectively reduced, and the construction period is shortened.

[0014] As a preferred, the genetic algorithm is used to optimize the allocation of pedestal tasks and the arrangement of construction period, including:

[0015] The fitness function is used to evaluate the pros and cons of the production scheduling plan, wherein: g i (x) is the i-th optimization objective, and the optimization objectives include minimizing the beam moving distance, balancing the pedestal tasks, and meeting the construction period requirement; ω i is a weight coefficient.

[0016] By the present application, the genetic algorithm is used to optimize the allocation of pedestal tasks, and the priority of the optimization objective is flexibly adjusted to adapt to different engineering scene requirements, so as to generate an optimal production scheduling plan.

[0017] As a preferred, the genetic algorithm is used to optimize the allocation of pedestal tasks and the arrangement of construction period, and further includes:

[0018] The selection operation is adopted to select the parent production scheduling plan according to the probability of the fitness value, wherein: P(x i) is the production scheduling plan x i The probability of being selected; N is the population size, indicating the number of currently generated production scheduling plans; f(x i ) is the fitness value of the production scheduling plan x i ;

[0019] The crossover operation is adopted, the production scheduling plan with higher fitness value is selected as the parent production scheduling plan, the child production scheduling plan is generated through the parent production scheduling plan, x new1 =α1x parent1 +(1-α1)x parent2 , wherein: α1 is a crossover coefficient, α1=0.5; x parent1 and x parent2 are the parent production scheduling plan, indicating the parent production scheduling plan; x new1 is the child production scheduling plan;

[0020] The mutation operation is adopted, the random disturbance is introduced to the production scheduling plan, the production scheduling plan after mutation is generated, x new2 =x old +Δx, wherein: Δx is a random disturbance; x new2 is the production scheduling plan after mutation; x old is the production scheduling plan.

[0021] Through the application, the selection, crossover and mutation operations are used to further optimize the generated production scheduling plan, increase the diversity of the generated production scheduling plan, avoid the algorithm from falling into local optimum, and improve the robustness of the scheme of the production scheduling plan.

[0022] As preferred, the moving beam transportation distance and transportation cost are optimized based on the ant colony algorithm, including optimizing the moving beam transportation distance and transportation cost according to the pheromone updating rule and path selection probability of the ant colony algorithm:

[0023] Pheromone updating, τ ij (t+1)=(1-ρ)τ ij (t)+Δτ ij , wherein: τ ij is the pheromone concentration on the path (i,j), the path (i,j) is the moving beam path from the beam manufacturing pedestal i to the beam storage pedestal j; ρ is the pheromone volatilization coefficient; Δτ ij is the pheromone increment, wherein Q is a constant, d ij is the distance of the path (i,j);

[0024] Path selection probability, wherein P ij is the probability of selecting the path (i,j); η ij is the heuristic information, α and β are parameters for controlling the relative importance of pheromone and heuristic information, α=1, β=2.

[0025] By the present application, the shortest transportation path can be quickly converged to by using the ant colony algorithm, and the shortest transportation path is used to significantly reduce the cost of moving beams.

[0026] As preferred, the monitoring management subsystem comprises: a real-time adjustment module for monitoring the production process and recording the production situation, and adjusting the production scheduling in real time when a sudden situation occurs, the sudden situation including equipment failure and material shortage; a progress management module for tracking the state of each process of the construction process in real time and recording the time stamp, triggering an alarm when there is a delayed process, and generating improvement suggestions; a dynamic adjustment module for optimizing algorithm parameters and optimizing production scheduling based on historical execution data.

[0027] By the present application, real-time monitoring and adaptive adjustment of the construction process can be realized to ensure the stability of plan execution: by implementing the adjustment module, the production scheduling is dynamically adjusted according to the actual situation in the production process to respond to sudden situations such as equipment failure and material shortage, rapidly re-evaluate the current production state and propose solutions such as deploying standby equipment or notifying the procurement department to supplement materials; by the progress management module, the progress of beam manufacturing and erecting is tracked and managed, the state of each process of beam manufacturing and erecting, i.e., "not started", "in progress", "completed", is updated in real time, and by recording specific time stamps, alarms are issued for delayed processes and improvement suggestions are provided to ensure that the project can be completed on time and avoid increased construction costs due to delays; the dynamic adjustment module has self-learning ability and can quickly respond to changes such as equipment failure and material shortage in the production process based on past experience, i.e., historical execution data, to timely adjust and optimize the production scheduling, thereby ensuring that the production process is in the best possible state.

[0028] As preferred, the execution management subsystem comprises: a production management module for supervising and evaluating each link of production based on the production scheduling; a beam erection plan compilation module for revising the beam erection plan based on historical execution data and production situation, and continuously optimizing the beam erection plan.

[0029] By the present application, the production management module can cover multiple aspects such as production process, production plan, production task management, etc., to improve the overall production and management level, set clear goals and evaluation indicators for each production link, regularly assess performance, timely correct problems, and ensure efficient operation; the beam erection plan compilation module further compiles detailed beam erection plans by combining the latest construction site situation and historical execution data, covering path planning, construction period arrangement, work point arrangement, etc., and the beam erection plan compilation module works with other related modules to ensure the consistency and coordination of beam manufacturing and erection plans, and to improve the efficiency of task execution and the coordination of beam erection processes.

[0030] As preferred, the user interface module comprises: a drag-and-drop task adjustment interface for user to manually modify task priority or allocation scheme; a chart display page for displaying construction progress and resource distribution; a mobile application for user to access the railway box girder erection integrated intelligent production scheduling system in real time and push alerts.

[0031] Through the present application, an intuitive and easy-to-use user interface is designed to simplify the operation process, so as to ensure that various users can easily get started, wherein the drag-and-drop layout can allow users to intuitively arrange various tasks, the chart display can help managers quickly understand the overall progress and real-time resource information, and the mobile application is designed to facilitate relevant personnel to access the system anytime and anywhere, thereby improving work efficiency.

[0032] The present system realizes intelligent management of the whole process of railway box girder erection through the coordinated operation of five subsystems of data acquisition, intelligent production scheduling, real-time monitoring, task execution and user interaction.

[0033] Based on the multi-objective optimization of genetic algorithm and ant colony algorithm, AI risk prediction and dynamic adjustment mechanism, the problems of low efficiency, large error and resource waste of traditional manual production scheduling are solved.

[0034] Through real-time data acquisition and adaptive adjustment mechanism, rapid response to unexpected problems is realized to ensure the continuity of construction.

[0035] The intuitive and easy-to-use drag-and-drop interface and chart display, as well as multi-end support, realize the transparency of production scheduling process and the convenience of user interaction. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 Figure 1 is a schematic diagram of the overall architecture of a railway box girder erection integrated intelligent production scheduling system according to the present application. DETAILED DESCRIPTION

[0037] In order to further understand the content of the present application, the present application will be described in detail in conjunction with the embodiments. It should be understood that the embodiments are only used to explain and not to limit the present application.

[0038] Embodiment 1

[0039] As shown in Figure 1 , the present embodiment provides a railway box girder erection integrated intelligent production scheduling system, which comprises:

[0040] The data acquisition and management subsystem is used for real-time acquisition of construction data and storage and processing of the data, and initializing a device resource pool based on the acquired data, and generating a standardized basic data set; the intelligent scheduling subsystem is used for generating a scheduling plan based on the standardized basic data set, the scheduling plan including a beam manufacturing plan and a beam erecting plan, and predicting a risk in a plan implementation process, and dynamically adjusting the plan; the monitoring and management subsystem is used for real-time tracking and management of a construction process, and monitoring production conditions; the execution management subsystem is used for preparing an execution plan based on the scheduling plan, and completing task allocation of the execution plan; and the interactive subsystem includes a user interface module, and is used for user understanding of production conditions and management of production tasks.

[0041] Through the embodiment, manual intervention is reduced by using an automated means, information processing speed is accelerated, and real-time grasp of a process progress is ensured, thereby improving scheduling efficiency; a detailed beam manufacturing and beam erecting plan is automatically generated by using an optimization algorithm, errors caused by manual calculation are avoided, data accuracy is improved, and data authenticity and reliability are ensured; specific conditions of each process in a production process are recorded in detail, and fast query and deep analysis of historical data are supported, so as to facilitate post review of a project, and construction data traceability is enhanced; resource utilization is improved by optimizing resource allocation, thereby reducing waste and cost; real-time monitoring and dynamic adjustment of a scheduling plan are realized, a construction process is ensured to be smooth, and final product quality is improved.

[0042] In the embodiment, the data acquisition and management subsystem includes a data acquisition module, a pedestal information management module, and the like. The data acquisition module is used for real-time acquisition of construction data, including acquisition of work point configuration data, beam type setting data, pedestal configuration data, and construction progress data, and storage and processing of the data; the pedestal information management module is used for integrating information of pedestal types, quantities, positions, and use states, and generating a device resource pool.

[0043] The data acquisition module uses Internet of Things (IoT) technology, and real-time field information is acquired by using intelligent devices such as sensors, RFID tags, and cameras, various types of data related to scheduling are acquired, including but not limited to work point configuration, beam type setting, pedestal configuration, process setting, and construction period arrangement, and the like, and the data is transmitted to a cloud server for storage and processing. Specific application scenarios include a steel bar processing workshop, a mixing station, and a beam field, and real-time and comprehensive data acquisition is ensured, thereby providing accurate resource allocation basis for subsequent scheduling. The pedestal information management module is specially used for managing information of beam manufacturing pedestals, including types, quantities, positions, use states, and the like, and real-time updates of the latest pedestal information are provided, accurate data support is provided for generation of a scheduling plan, resource allocation is reasonably assisted by management personnel, and utilization is improved.

[0044] In this embodiment, the intelligent production scheduling subsystem includes: an intelligent production scheduling module, configured to generate a production scheduling plan based on a standardized basic data set and an optimization algorithm, the production scheduling plan including a beam manufacturing plan and a beam erecting plan; a beam manufacturing AI scheduling module, configured to predict risks in a beam manufacturing process and correct the beam manufacturing plan, and continuously optimize the beam manufacturing plan; and a feasibility analysis module, configured to evaluate whether the production scheduling plan meets safety standards and satisfies resource limitations, and indicate potential risks of the production scheduling plan and an improvement direction of the production scheduling plan.

[0045] By this embodiment, advanced optimization algorithms such as genetic algorithms and ant colony algorithms are used to generate detailed beam manufacturing and erecting plans, and AI technology is used to predict various variables (such as weather changes, equipment performance, worker skill levels, etc.) that may be encountered during beam manufacturing, and to take measures in advance, thereby comprehensively optimizing multiple objectives and predicting risks to ensure the scientificity and feasibility of the production scheduling plan and reduce construction delays. The beam manufacturing AI scheduling module can continuously learn and optimize its own algorithm, gradually improving prediction accuracy and production scheduling effectiveness.

[0046] In this embodiment, the intelligent production scheduling module is specifically configured to: optimize pedestal task allocation and construction period arrangement based on a genetic algorithm; and optimize beam moving distance and transportation cost based on an ant colony algorithm.

[0047] By this embodiment, the genetic algorithm is used to optimize pedestal task allocation, reasonably allocate pedestal tasks, avoid resource idling or overload, and ensure that the task load U i of any pedestal is close to the average value, i.e., the average load of all pedestals N is the number of pedestals, and the production scheduling plan meets the overall construction period requirement, beam type, pedestal and process specific requirements, and ensures that the total time consumption t i of all processes or tasks does not exceed the total construction period T total , i.e. The ant colony algorithm is used to optimize the beam moving path, select the shortest path (i, j), and update the pheromone concentration τ ij to reflect the path quality, thereby selecting the shortest path to reduce transportation cost. By combining the genetic algorithm and the ant colony algorithm, global resource balanced allocation and local path optimization are coordinated, transportation cost is effectively reduced, and the construction period is shortened.

[0048] In this embodiment, the genetic algorithm is used to optimize pedestal task allocation and construction period arrangement, including:

[0049] A fitness function is used to evaluate the pros and cons of the production scheduling plan, wherein: g i (x) is the i-th optimization objective, and the optimization objectives include minimizing beam moving distance, balancing pedestal tasks, and meeting construction period requirements; and ω i is a weight coefficient.

[0050] The fitness function f(x) is used to evaluate the pros and cons of the scheduling plan, and the evaluation object includes multiple optimization objectives, including minimizing beam transportation distance, balancing pedestal tasks, and meeting time limit requirements, g i (x) refers to the i-th optimization objective, for example, g1(x) is the objective of minimizing beam transportation distance to measure transportation cost, g2(x) is the objective of balancing pedestal tasks to avoid resource idling or overload, and g3(x) is the objective of meeting time limit requirements to ensure that the plan meets the overall time limit, and the importance of each optimization objective is adjusted by adjusting the weight coefficient ω i If the time limit requirement is the most important, ω3 can be set to be larger, and if the transportation cost is the key, ω1 can be set to be larger.

[0051] Through the embodiment, the genetic algorithm is used to optimize the pedestal task allocation, and the priority of the optimization objective is flexibly adjusted to adapt to different engineering scene requirements to generate an optimal scheduling plan.

[0052] In the embodiment, the pedestal task allocation and the time limit arrangement are optimized based on the genetic algorithm, and further include:

[0053] The selection operation is adopted, and the parent scheduling plan is selected according to the probability of the fitness value, Wherein: P(x i ) is the probability of the scheduling plan x i being selected; N is the population size, indicating the number of scheduling plans currently generated; f(x i ) is the fitness value of the scheduling plan x i ;

[0054] The crossover operation is adopted, the scheduling plan with a higher fitness value is selected as the parent scheduling plan, the child scheduling plan is generated through the parent scheduling plan, x new1 = α1x parent1 + (1-α1) x parent2 , wherein: α1 is the crossover coefficient, α1 = 0.5; x parent1 and x parent2 are the parent scheduling plans, indicating the parent scheduling plans; x new1 is the child scheduling plan;

[0055] The mutation operation is adopted, random disturbance is introduced to the scheduling plan to generate a mutated scheduling plan, x new2 = x old + Δx, wherein: Δx is random disturbance; x new2 is the mutated scheduling plan; x old is the scheduling plan.

[0056] In the selection operation, the population size N can be determined according to the computing resources and the scheduling complexity, for example, N can be set to 50, and the fitness value f(x i) is calculated by the fitness function, which is used to reflect the pros and cons of each production plan during the selection operation.

[0057] In the crossover operation, the parent production plan can be selected from the current generated population with higher fitness, and then a new production plan, i.e. the child production plan, is generated by using the crossover operation to mix the task allocation scheme of the better parent plan.

[0058] In the mutation operation, a random disturbance Δx can be used to adjust the task allocation or beam moving path, and the generated production plan is added with random disturbance to introduce diversity, for example, randomly allocating the tasks of a certain pedestal to another pedestal, or adjusting the beam moving path to reduce the transportation distance.

[0059] Through the embodiment, the selection, crossover and mutation operations are used to further optimize the generated production plan, increase the diversity of the generated production plan, avoid the algorithm from falling into local optimum, and improve the robustness of the production plan scheme.

[0060] In the embodiment, the ant colony algorithm is used to optimize the beam moving distance and transportation cost, including optimizing the beam moving distance and transportation cost according to the pheromone update rule and path selection probability of the ant colony algorithm:

[0061] Pheromone update, τ ij (t+1) = (1-ρ)τ ij (t) + Δτ ij Where: τ ij is the pheromone concentration on the path (i, j), the path (i, j) is the beam moving path from the beam manufacturing pedestal i to the beam storage pedestal j; ρ is the pheromone evaporation coefficient; Δτ ij is the pheromone increment, Where Q is a constant, d ij is the distance of the path (i, j);

[0062] Path selection probability, Where: P ij is the probability of selecting the path (i, j); η ij is the heuristic information, α and β are parameters that control the relative importance of pheromone and heuristic information, α = 1, β = 2.

[0063] Pheromone increment Δτ ij is calculated according to the beam moving distance and the task completion condition, and is inversely proportional to the distance d ij of the path (i, j), the distance d ij of the path (i, j) is calculated according to the set row and column numbers of the pedestals and the distance between the pedestals, and the heuristic information η ijThe role is to guide ants to select shorter paths, and the distance d of path (i, j) ij is inversely proportional.

[0064] Through this embodiment, using the ant colony algorithm, the shortest transportation path can be quickly converged to, and the shortest transportation path is used to significantly reduce the cost of moving beams.

[0065] In this embodiment, the monitoring and management subsystem includes: a real-time adjustment module for monitoring the production process and recording the production situation, and adjusting the production scheduling plan in real time when a sudden situation occurs, including equipment failure and material shortage; a progress management module for tracking the state of each process of the construction process in real time and recording the time stamp, triggering an alarm when there is a delayed process, and generating improvement suggestions; a dynamic adjustment module for optimizing algorithm parameters and optimizing production scheduling plan based on historical execution data.

[0066] Through this embodiment, real-time monitoring and adaptive adjustment of the construction process can be realized to ensure the stability of plan execution: by implementing the adjustment module, the production scheduling plan is dynamically adjusted according to the actual situation in the production process, sudden situations such as equipment failure and material shortage are dealt with, the current production state is quickly re-evaluated and a solution is proposed, such as deploying standby equipment or notifying the procurement department to supplement materials; through the progress management module, the progress of beam manufacturing and erecting is tracked and managed, the state of each process of beam manufacturing and erecting, i.e. “not started”, “in progress”, “completed”, is updated in real time, and by recording specific time stamps, alarms are sent for delayed processes and improvement suggestions are provided to ensure that the project can be completed on time and avoid increased construction costs due to delays; the dynamic adjustment module has self-learning ability and can quickly respond to changes such as equipment failure and material shortage in the production process based on past experience, i.e. historical execution data, to timely adjust and optimize the production scheduling plan, thereby ensuring that the production process is in the best possible state.

[0067] In this embodiment, the execution management subsystem includes: a production management module for supervising and evaluating each link of production based on the production scheduling plan; a beam erection plan compilation module for revising the beam erection plan based on historical execution data and production situation, and continuously optimizing the beam erection plan.

[0068] Through the embodiment, the production management module can cover multiple aspects such as production process, production plan, production task management, etc., to improve the overall production and management level, set clear goals and evaluation indexes for each production link, regularly evaluate performance, timely correct problems, and ensure efficient operation; the beam erection plan compilation module further compiles detailed beam erection plans by combining the latest construction site conditions and historical execution data, covering aspects such as path planning, construction period arrangement, work point arrangement, etc., and the beam erection plan compilation module works with other related modules to ensure consistency and coordination of beam fabrication and erection plans, and to improve task execution efficiency and coordination of beam erection processes.

[0069] In the embodiment, the user interface module includes: a drag-and-drop task adjustment interface for user to manually modify task priority or allocation scheme; a chart display page for displaying construction progress and resource distribution; a mobile application for user to access the railway box girder erection integrated intelligent production scheduling system in real time and push alerts.

[0070] Through the embodiment, an intuitive and easy-to-use user interface is designed to simplify the operation process to ensure that all types of users can easily get started, among which the drag-and-drop layout allows users to intuitively arrange tasks, and the chart display can help managers quickly understand the overall progress and real-time resource information, and the mobile application is designed to allow relevant personnel to access the system anytime and anywhere, thereby improving work efficiency.

[0071] The system realizes intelligent management of the whole process of railway box girder erection through the collaborative operation of five subsystems of data collection, intelligent production scheduling, real-time monitoring, task execution and user interaction:

[0072] Based on the multi-objective optimization of genetic algorithm and ant colony algorithm, AI risk prediction and dynamic adjustment mechanism, the problems of low efficiency, large error and resource waste in traditional manual production scheduling are solved;

[0073] Through real-time data collection and adaptive adjustment mechanism, rapid response to unexpected problems is realized to ensure the continuity of construction;

[0074] Intuitive and easy-to-use drag-and-drop interface and chart display, as well as multi-end support, realize transparent production scheduling process and convenient user interaction.

[0075] It is easy to understand that based on one or more embodiments provided in the present application, other embodiments can be obtained by combining, splitting, recombining, etc. of the embodiments of the present application, and these embodiments do not exceed the protection scope of the present application.

[0076] The above description of the present application and its embodiments is illustrative and not restrictive, and the examples shown are only part of the embodiments of the present application, and the actual structure is not limited thereto. Therefore, if a person skilled in the art is inspired by it, without departing from the spirit of the present application, similar structural modes and examples can be designed without creativity, and all should belong to the protection scope of the present application.

Claims

1. An integrated intelligent production scheduling system for railway box girder manufacturing and erection, comprising: The data collection and management subsystem is used to collect construction data in real time, store and process the data, initialize the equipment resource pool based on the collected data, and generate a standardized basic data set; The intelligent production scheduling subsystem is used to generate production schedules based on standardized basic data sets. The production schedules include beam fabrication and erection plans, as well as predict risks during plan implementation and dynamically adjust the plans. Monitoring and management subsystem, used to track and manage the construction process in real time and monitor production conditions; The execution management subsystem is used to prepare the execution plan based on the production schedule and complete the task allocation of the execution plan; The interactive subsystem includes a user interface module, which is used by users to understand production conditions and manage production tasks.

2. The railway box girder manufacturing and erection integrated intelligent production scheduling system according to claim 1, wherein: The data acquisition and management subsystem includes: The data acquisition module is used to collect construction data in real time, including work point configuration data, beam type setting data, pedestal configuration data and construction progress data, and store and process the data; The pedestal information management module is used to integrate information on pedestal type, quantity, location and usage status to generate an equipment resource pool.

3. The railway box girder manufacturing and erection integrated intelligent production scheduling system according to claim 1, wherein: The intelligent production scheduling subsystem includes: Intelligent production scheduling module, used to generate production schedules based on standardized basic data sets and optimization algorithms. The production schedules include beam fabrication and erection plans. The AI-powered beam-making scheduling module is used to predict risks in the beam-making process, revise the beam-making plan, and continuously optimize it. The feasibility analysis module is used to evaluate whether the production schedule meets safety standards and resource constraints, and to point out potential risks and improvement directions of the production schedule.

4. The integrated intelligent production scheduling system for railway box girder manufacturing and erection according to claim 3, wherein: The intelligent production scheduling module is specifically used to: Optimize pedestal task allocation and construction schedule based on genetic algorithm; Optimize beam moving distance and transportation cost based on ant colony algorithm.

5. The railway box girder manufacturing and erection integrated intelligent production scheduling system according to claim 4, wherein: The optimization of pedestal task allocation and construction period arrangement based on genetic algorithm includes: Using fitness function Evaluate the quality of the production schedule, where: g i (x) is the i-th optimization objective, which includes minimizing the beam moving distance, balancing the platform task, and meeting the construction period requirements; ω i is the weight coefficient.

6. The railway box girder manufacturing and erection integrated intelligent production scheduling system according to claim 5, wherein: The optimization of pedestal task allocation and construction period arrangement based on genetic algorithm also includes: Adopt the selection operation and select the parent generation production plan according to the fitness value probability. Where: P(x i ) is the production schedule x i The probability of being selected; N is the population size, which indicates the number of production schedules currently generated; f(x i ) is the production schedule x i The fitness value of Using crossover operation, select the production schedule with higher fitness as the parent production schedule, and generate the child production schedule through the parent production schedule. new1 =α1x parent1 +(1-α1)x parent2 , where: α1 is the cross coefficient, α1 = 0.5; x parent1 and x parent2 Is the parent generation production schedule, indicating the parent generation production schedule; x new1 Schedule production for offspring; Using mutation operation, random disturbance is introduced into the production schedule to generate the mutated production schedule, x new2 =x old +Δx, where: Δx is a random perturbation; x new2 is the production schedule after the change; x old It is a production schedule.

7. The railway box girder manufacturing and erection integrated intelligent production scheduling system according to claim 4, wherein: The optimization of beam moving distance and transportation cost based on ant colony algorithm includes: Optimize the beam moving distance and transportation cost based on the pheromone update rules and path selection probability of the ant colony algorithm: Pheromone update, τ ij (t+1)=(1-ρ)τ ij (t)+Δτ ij , where: τ ij is the pheromone concentration on path (i, j), where path (i, j) is the beam moving path from beam production platform i to beam storage platform j; ρ is the pheromone volatility coefficient; Δτ ij is the pheromone increment, Where Q is a constant, d ij is the distance of path (i, j); Path selection probability, Where: P ij is the probability of choosing path (i, j); η ij is heuristic information, α and β are parameters that control the relative importance of pheromone and heuristic information, α = 1, β = 2.

8. The railway box girder manufacturing and erection integrated intelligent production scheduling system according to claim 1, wherein: The monitoring and management subsystem includes: A real-time adjustment module is used to monitor the production process and record production status, and adjust the production schedule in real time when unexpected situations occur, such as equipment failure and material shortages; The progress management module is used to track the status of each step of the construction process in real time and record timestamps. It triggers alarms when there are delayed steps and generates improvement suggestions. Dynamic adjustment module, used to optimize algorithm parameters and production scheduling based on historical execution data.

9. The railway box girder manufacturing and erection integrated intelligent production scheduling system according to claim 1, wherein: The execution management subsystem includes: Production management module, used to monitor and evaluate every aspect of production based on production scheduling; The beam erection plan preparation module is used to modify the beam erection plan based on historical execution data and production conditions, and continuously optimize the beam erection plan.

10. The railway box girder manufacturing and erection integrated intelligent production scheduling system according to claim 1, wherein: The user interface module includes: Drag-and-drop task adjustment interface, allowing users to manually modify task priorities or allocation plans; Chart display page, used to show construction progress and resource distribution; A mobile application that allows users to access the integrated intelligent scheduling system for railway box girder fabrication in real time and receive push alerts.

Images