A method and device for intelligent operation and maintenance scheduling based on 3D modeling

Abstract

The application discloses a kind of method and device for intelligent operation and maintenance scheduling based on 3D modeling, comprising the following steps: obtaining the real-time data of each device in the region to be operated and maintained;Set operation and maintenance requirements and constraint conditions;According to the preset 3D model of the region to be operated and maintained, the real-time data of each device, operation and maintenance requirements and constraint conditions, generate operation and maintenance scheduling plan.The application accurately represents the position, layout and mutual relationship of each device in the region to be operated and maintained by three-dimensional modeling of the region to be operated and maintained, and when performing operation and maintenance scheduling, the position, layout and mutual relationship of each device in the region to be operated and maintained are taken as part of the data basis of the optimization algorithm according to the three-dimensional modeling of the region to be operated and maintained, and the obtained operation and maintenance scheduling plan has more reasonable task arrangement and time allocation, improves operation and maintenance efficiency, reduces maintenance time and energy loss.

Description

Technical Field

[0001] This invention relates to the field of station operation and maintenance technology, and more specifically, to a method and apparatus for intelligent operation and maintenance scheduling based on 3D modeling. Background Technology

[0002] New energy power plants typically consist of multiple devices and components, and there are complex interrelationships among these devices and components.

[0003] Traditional operation and maintenance scheduling for new energy power plants is usually based on manual planning and experience, lacking systematicity and intelligence, which easily leads to problems such as unreasonable task allocation and conflicting maintenance schedules, affecting the stable operation of the plant. At the same time, new energy power plants themselves are characterized by complexity and large scale, including a wide variety of equipment, variable operating conditions, and complex influencing factors, which brings challenges to operation and maintenance scheduling.

[0004] With the rapid development and application of new energy technologies, the number and scale of new energy power stations are constantly increasing. These stations cover various energy forms such as solar, wind, and hydropower, and their equipment is complex and large-scale. Traditional operation and maintenance scheduling methods can no longer meet the complexity and real-time requirements of new energy power station operation.

[0005] Currently, the solutions to the operation and maintenance scheduling problem of new energy power plants mainly fall into the following two categories:

[0006] 1. Intelligent scheduling method for operation and maintenance: By using intelligent scheduling and optimization algorithms, such as genetic algorithms and simulated annealing algorithms, the operation and maintenance tasks of new energy power plants can be optimized and scheduled to improve operation and maintenance efficiency and performance.

[0007] 2. Data-driven operation and maintenance management approach: By analyzing and modeling a large amount of operation and maintenance data, real-time decision support and optimization solutions are provided to improve the operation and maintenance management level of the site.

[0008] Existing technologies have the following shortcomings in adapting to the increasingly complex operation and maintenance scheduling of new energy power plants:

[0009] Existing operation and maintenance scheduling methods are often based on two-dimensional plan diagrams, which cannot accurately reflect the three-dimensional structure of the site. The lack of accurate representation of the site's three-dimensional structure may result in scheduling results that do not conform to the actual situation, affecting the operation and maintenance effect. Summary of the Invention

[0010] One objective of this invention is to provide a method for intelligent operation and maintenance scheduling based on 3D modeling, which solves the technical problem that existing operation and maintenance scheduling methods lack accurate representation of three-dimensional structures, resulting in scheduling results that may not conform to the actual situation and affect the operation and maintenance effect; another objective of this invention is to provide a device for intelligent operation and maintenance scheduling based on 3D modeling.

[0011] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0012] The first aspect of this invention provides a method for intelligent operation and maintenance scheduling based on 3D modeling, comprising the following steps:

[0013] Obtain real-time data for each device in the area to be scheduled for maintenance;

[0014] Set up operation and maintenance requirements and constraints;

[0015] Based on the preset 3D model of the area to be maintained, the real-time data of each device, the maintenance requirements and constraints, an maintenance schedule plan is generated.

[0016] Among the aforementioned technical methods, precise 3D modeling of the area to be scheduled for maintenance can accurately represent the location, layout, and interrelationships of equipment and components in the area, providing a more accurate data foundation for maintenance scheduling. At the same time, with the help of intelligent optimization algorithms, reasonable task arrangement and time allocation can be achieved, improving maintenance efficiency and reducing maintenance time and energy loss.

[0017] Furthermore, the setting of operation and maintenance requirements and constraints shall include at least one of the following:

[0018] 1) Set the priority of different operation and maintenance tasks;

[0019] 2) Set restrictions for different devices in the area to be scheduled for maintenance;

[0020] 3) Set optimization goals for the areas to be scheduled for maintenance;

[0021] 4) Configure the allocation of human resources, including the number of personnel and skill requirements for different operation and maintenance tasks;

[0022] 5) Set security requirements and standards for operation and maintenance tasks;

[0023] 6) Set the weights for different optimization objectives.

[0024] Furthermore, before generating the operation and maintenance schedule plan, the following steps are also included:

[0025] Based on the 3D model of the area to be maintained and scheduled, the real-time data of each device, the maintenance requirements and constraints, a multi-objective optimization algorithm is selected from a preset multi-objective optimization algorithm library to generate the maintenance schedule plan. The preset multi-objective optimization algorithm library includes a variety of multi-objective optimization algorithms.

[0026] Among the aforementioned technical methods, a multi-objective optimization algorithm is used to search for the optimal solution by combining the user-defined objective function and constraints, thereby obtaining an operation and maintenance scheduling plan that satisfies multiple objectives. This optimization plan comprehensively considers the trade-offs between different objectives, meets the site's operation and maintenance needs and constraints, and achieves more efficient and reliable operation and maintenance.

[0027] Furthermore, the various multi-objective optimization algorithms include the NSGA-II algorithm, the SPEA2 algorithm, and the MOEA / D algorithm.

[0028] Furthermore, the step of generating an operation and maintenance schedule plan based on the preset 3D model of the area to be operated and maintained, real-time data of each device, operation and maintenance requirements, and constraints includes:

[0029] Based on the 3D model of the area to be maintained and scheduled, calculate the difficulty coefficient of reaching each device in the area to be maintained and scheduled.

[0030] Based on the aforementioned difficulty coefficient, real-time data of each device, operation and maintenance requirements, and constraints, the selected multi-objective optimization algorithm is used to solve for the optimization result.

[0031] The optimization results are then converted into an actual operation and maintenance scheduling plan to obtain the operation and maintenance scheduling plan.

[0032] Furthermore, the calculation of the difficulty coefficient for reaching each device in the area to be scheduled for maintenance includes:

[0033] min D=(∑ h∈H ∑ e∈E (sinA*α)∑ t∈T )*β

[0034] In the formula, D is the difficulty coefficient of reaching each device in the area to be maintained and scheduled; h is the set of relative heights of the target maintenance devices; e is the set of location factors, representing the parameter factors formed by the sum of comprehensive environmental factors of the device's location; A is the angle between the relative height of the target maintenance device and the plane; α is the conversion factor; t is the set of weather factors; and β is the final conversion factor.

[0035] Furthermore, the preset 3D model of the area to be scheduled for maintenance includes:

[0036] Obtain three-dimensional data of the internal structure of the area to be maintained and scheduled and the distribution of equipment in the area to be maintained and scheduled. The three-dimensional data includes the actual three-dimensional coordinates of each equipment in the area to be maintained and scheduled and the real environment in which each equipment is located.

[0037] The acquired 3D data is preprocessed, cleaned, and transformed to obtain preprocessed 3D data;

[0038] The preprocessed 3D data is modeled to generate a 3D model of the area to be scheduled for maintenance.

[0039] Furthermore, acquiring real-time data for each device in the area to be scheduled for maintenance includes:

[0040] Sensors are installed on each device in the area to be maintained and scheduled. The sensors acquire real-time parameters and indicators of each device, including temperature, humidity, pressure, current and voltage.

[0041] Data cleaning is performed on the real-time parameters and indicators of each device.

[0042] Information is extracted and processed from the cleaned real-time parameters and indicators to generate key parameters and indicators, which serve as real-time data for each device.

[0043] Furthermore, it also includes the following steps:

[0044] The generated operation and maintenance schedule plan is visualized and provides real-time monitoring and dynamic adjustment functions.

[0045] A second aspect of the present invention also provides a system for intelligent operation and maintenance scheduling based on 3D modeling, comprising:

[0046] The 3D modeling module constructs a 3D model of the site based on its three-dimensional layout structure. The 3D model of the site includes the actual three-dimensional coordinates of each piece of equipment in the site and the real environment in which each piece of equipment is located.

[0047] The data acquisition module acquires real-time data of each device in the area to be maintained and scheduled.

[0048] A constraint module, which sets operation and maintenance requirements and constraints;

[0049] The scheduling generation module generates an operation and maintenance schedule plan based on the preset 3D model of the area to be scheduled for operation and maintenance, the real-time data of each device, the operation and maintenance requirements and constraints.

[0050] Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

[0051] This invention accurately represents the location, layout, and interrelationships of each device in the area to be scheduled for maintenance by creating a 3D model of the area. When scheduling maintenance, the location, layout, and interrelationships of each device in the area are used as part of the data foundation for the optimization algorithm based on the 3D model of the area. The resulting maintenance scheduling plan has a more reasonable task arrangement and time allocation, improving maintenance efficiency and reducing maintenance time and energy loss. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 A schematic diagram of the intelligent operation and maintenance scheduling method based on 3D modeling provided in an embodiment of the present invention;

[0054] Figure 2 A detailed flowchart of the intelligent operation and maintenance scheduling method based on 3D modeling provided in this embodiment of the invention;

[0055] Figure 3 This is a schematic diagram of the 3D modeling process provided in an embodiment of the present invention;

[0056] Figure 4 This is a schematic diagram of the real-time data capture process of the sensor provided in an embodiment of the present invention;

[0057] Figure 5 A schematic diagram of an intelligent operation and maintenance scheduling device based on 3D modeling provided in an embodiment of the present invention. Detailed Implementation

[0058] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this patent.

[0059] To better illustrate this embodiment, some parts in the accompanying drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions;

[0060] It will be understood by those skilled in the art that certain well-known structures and their descriptions may be omitted in the accompanying drawings.

[0061] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0062] Example 1

[0063] This invention provides a method for intelligent operation and maintenance scheduling based on 3D modeling, such as... Figure 1 As shown, it includes the following steps:

[0064] Obtain real-time data for each device in the area to be scheduled for maintenance;

[0065] Set up operation and maintenance requirements and constraints;

[0066] Based on the preset 3D model of the area to be maintained, the real-time data of each device, the maintenance requirements and constraints, an maintenance schedule plan is generated.

[0067] In this embodiment, a precise 3D model is performed on the area to be scheduled for maintenance. The position, layout, and relationships between the devices in the area to be scheduled for maintenance are represented in the form of a 3D model. When optimizing the maintenance scheduling plan, the position, layout, and relationships between the devices in the area to be scheduled for maintenance are used as part of the data source for the optimization algorithm. The maintenance scheduling plan has a more reasonable task arrangement and time allocation, which improves maintenance efficiency and solves the technical problem in the prior art that the lack of accurate representation of the three-dimensional structure may lead to scheduling results that do not conform to the actual situation.

[0068] Example 2

[0069] This embodiment, based on embodiment 1, continues to disclose the following content, specifically as follows: Figure 2 As shown, the process includes data acquisition and modeling steps, operation and maintenance requirements and constraint setting steps, multi-objective optimization steps, operation and maintenance scheduling plan generation steps, and visualization and real-time monitoring steps, among which:

[0070] The data acquisition and modeling process includes two steps: 3D site modeling and real-time sensor data acquisition. The specific workflow for 3D site modeling is as follows: Figure 3 As shown, it includes the following steps:

[0071] The system acquires three-dimensional data of the internal structure and equipment distribution of the area to be maintained and scheduled. The three-dimensional data includes the actual three-dimensional coordinates of each piece of equipment in the area to be maintained and scheduled and the real environment in which each piece of equipment is located. In a specific embodiment, the system uses technical means including laser measurement or camera imaging to acquire the three-dimensional data of the internal structure and equipment distribution of the area to be maintained and scheduled.

[0072] The acquired 3D data is preprocessed, cleaned, and transformed to obtain preprocessed 3D data;

[0073] The preprocessed 3D data is modeled to generate a 3D model of the area to be maintained and scheduled. In a specific embodiment, the 3D data of the area to be maintained and scheduled is modeled using software such as 3D reconstruction and model editing to generate a 3D model of the area to be maintained and scheduled.

[0074] The specific process for real-time data acquisition from the sensor is as follows: Figure 4 As shown, it includes the following steps:

[0075] Sensors are installed on each device in the area to be maintained and scheduled. The sensors acquire real-time parameters and indicators of each device, including temperature, humidity, pressure, current and voltage.

[0076] Data cleaning is performed on the real-time parameters and indicators of each device.

[0077] Information is extracted and processed from the cleaned real-time parameters and indicators to generate key parameters and indicators, which serve as real-time data for each device.

[0078] In a further embodiment, in the operation and maintenance requirements and constraint settings, the user can set various requirements and constraints for the operation and maintenance schedule according to actual needs, including:

[0079] 1) Set the priority of different operation and maintenance tasks; for example, emergency repair tasks may need to be handled with priority, while routine inspection tasks may have a lower priority, because prioritizing emergency repair tasks can ensure the continuity of power supply.

[0080] 2) Set constraints for different devices in the area to be maintained / maintained; this ensures that the maintenance schedule meets the operational requirements of the devices in the area. For example, set available time windows for devices, maximum operating capacity, and relationships between devices. Setting available time windows for devices limits maintenance tasks to a specific time period within a day. Users can also set the maximum operating capacity of devices to avoid exceeding their load limits. Maintenance users can also set relationships between devices, such as requiring certain devices to be maintained or shut down simultaneously to ensure safety and coordination.

[0081] 3) Set optimization goals for the areas to be scheduled for maintenance; such as reducing energy consumption and optimizing power utilization. These energy consumption goals will be considered when generating the maintenance schedule to achieve effective energy management. For example, the system can schedule equipment operation time to minimize energy consumption and ensure that the operational needs of the areas to be scheduled for maintenance are met;

[0082] 4) Configure the allocation of human resources, including the number of personnel and skill requirements for different maintenance tasks; when generating maintenance schedules, personnel will be allocated reasonably based on these settings. For example, a maintenance task may require two electrical engineers and one mechanical engineer, while another inspection task may only require one operator. When scheduling maintenance, reasonable personnel allocation will be achieved based on these settings to meet the maintenance needs of the site;

[0083] 5) Establish security requirements and standards for maintenance tasks to ensure that maintenance schedules comply with relevant safety standards and regulations. This includes, for example, work time limits, workflows, and safety measures. Setting work time limits restricts the completion time of maintenance tasks. Developing workflows and corresponding safety measures ensures the safety and compliance of maintenance tasks.

[0084] 6) Set weights for different optimization objectives; users can also set weights for different optimization objectives. For example, users can set the relative importance of indicators such as maintenance costs, equipment downtime, and personnel working hours. These weights will be considered in the optimization algorithm to obtain an operation and maintenance scheduling solution that better meets the user's needs. For example, if reducing maintenance costs is more important than reducing equipment downtime, control of maintenance costs will be given priority.

[0085] In a further embodiment, the multi-objective optimization step includes an algorithm selection and parameter setting step and an algorithm activation and scheduling association step, wherein the algorithm selection and parameter setting step includes the following steps:

[0086] Based on the 3D model of the area to be maintained and scheduled, the real-time data of each device, the maintenance requirements, and the constraints, a multi-objective optimization algorithm is selected from a preset multi-objective optimization algorithm library to generate the maintenance schedule. The preset multi-objective optimization algorithm library includes various multi-objective optimization algorithms, such as the NSGA-II algorithm, the SPEA2 algorithm, and the MOEA / D algorithm. Each algorithm has its unique advantages and applicability. Users can select a suitable algorithm from the multi-objective optimization algorithm library according to the specific characteristics of the problem and the nature of the optimization objective.

[0087] In the algorithm activation and scheduling association steps, the multi-objective optimization algorithm is linked with the generation of the operation and maintenance scheduling plan. This ensures, on the one hand, that the optimization results can be directly applied to the scheduling plan generation process; and on the other hand, the association between the algorithm and historical scheduling plans provides a valid reference for the current algorithm activation. This includes the following steps:

[0088] 1. Set optimization goals. These goals are the various objectives among the requirements and constraints of the operation and maintenance scheduling mentioned above. For example, based on the actual needs of the area to be scheduled for operation and maintenance and the objectives of the operation and maintenance scheduling: maintenance costs, equipment downtime, energy utilization rate, etc. Specify their relative importance by setting weights for different optimization goals.

[0089] 2. Set constraints: Limit the available time window of the equipment, the relationship between the equipment, and the skill requirements of the personnel by setting the steps of the operation and maintenance requirements and constraints.

[0090] 3. Selecting a Multi-Objective Optimization Algorithm: In the multi-objective optimization module, you can choose a suitable multi-objective optimization algorithm for the current problem, such as NSGA-II, SPEA2, and MOEA / D. Choose an appropriate algorithm based on the nature and requirements of the problem. Specifically, if the problem involves large-scale equipment, multiple optimization objectives, and complex constraints, a more advanced algorithm, such as MOEA / D, may be necessary; if the problem is relatively simple, algorithms like NSGA-II or SPEA2 may be sufficient. Different algorithms have different applicability to different types of optimization objectives. For those focusing on quickly finding convergent solutions and good distribution, NSGA-II may be a better choice. Some algorithms may be more effective in handling specific types of constraints. For example, MOEA / D, using decomposition, can handle high-dimensional problems and numerous constraints well. Based on the analytical optimization results, the optimal solution is transformed into an actual operation and maintenance scheduling plan. By comprehensively considering the optimization objectives and constraints, an optimal operation and maintenance scheduling plan is generated, including task arrangement, equipment uptime, and personnel work allocation.

[0091] 4. Setting Algorithm Parameters: Depending on the specific problem, parameters of the multi-objective optimization algorithm can be set, such as population size, number of iterations, and probabilities of crossover and mutation. These parameters will affect the search and exploration capabilities of the optimization algorithm;

[0092] 5. Run a multi-objective optimization algorithm: Using the set algorithm and parameters, run a multi-objective optimization algorithm to search for the optimal solution. The algorithm will search the solution space for a series of non-dominated solutions (Pareto optimal solutions), that is, solutions that cannot improve one objective without improving other objectives;

[0093] 6. Analyze the optimization results: Analyze the results of multi-objective optimization to obtain a set of non-dominated solutions. These solution sets represent the optimal solutions under different optimization objective trade-offs. Depending on the specific situation, the optimal solution can be selected by adjusting the weights of the optimization objectives.

[0094] 7. Generate an Operation and Maintenance Schedule: Based on the analysis results, the optimal solution is transformed into an actual operation and maintenance schedule. By comprehensively considering the optimization objectives and constraints, an optimal operation and maintenance schedule is generated, including task arrangement, equipment uptime, and personnel work allocation.

[0095] Through the above steps, combined with the user-defined objective function and constraints, a multi-objective optimization algorithm is used to search for the optimal solution, thereby obtaining an operation and maintenance scheduling plan that satisfies multiple objectives. This optimized plan comprehensively considers the trade-offs between different objectives, meets the operation and maintenance needs and constraints of the area to be scheduled, and achieves more efficient and reliable operation and maintenance.

[0096] In specific embodiments, the 3D modeling-based operation and maintenance scheduling considers the actual geographical location data of wind turbines / solar photovoltaic systems as the basis for calculation. In addition to traditional two-dimensional planar distances, factors such as the actual geographical location altitude of the wind turbines / solar photovoltaic systems and the actual environment (mountains / sea / plains) are added as calculation factors for operation and maintenance scheduling. A multi-objective optimization algorithm-based operation and maintenance scheduling model is constructed to more accurately calculate the optimal total operation and maintenance cost, the most suitable operation and maintenance schedule for wind / solar equipment, and the operation and maintenance scheduling plan for maintenance personnel. The main influencing factors include altitude, location, and real-time weather.

[0097] Among them, the high-level factors of the operation and maintenance goals are:

[0098] Suppose a wind farm has three wind turbines, A, B, and C. The two-dimensional route distance between each turbine and the farm's workstation is 3 km. Turbine A is located on a mountaintop at a height of 300 meters, turbine B at a height of 100 meters, and turbine C on flat ground. In traditional operation and maintenance scheduling models, because the height data of the turbines is not included in the model calculation, the distance factors for these three turbines are the same, resulting in unreasonable operation and maintenance schedules and personnel arrangements. Clearly, the ease of reaching these three turbines from the workstation varies, and the time required will differ significantly. However, using a 3D model, the relative height of each turbine can be easily obtained and added to the operation and maintenance scheduling model's calculation factors, resulting in a more reasonable operation and maintenance schedule and personnel schedule.

[0099] Location factors of operation and maintenance targets:

[0100] Suppose a wind farm has three wind turbines, A, B, and C, and the two-dimensional path distance between each of the three wind turbines and the work station is 3km.

[0101] All three wind turbines are located on mountaintops 300 meters high, but the steepness of the three mountains varies, as does the windingness of the roads leading up to them. Traditional operation and maintenance models cannot accurately describe such data, but 3D models can. The operation and maintenance scheduling model can obtain data such as the steepness (angle of inclination to the plane) and windingness of the mountain routes at the location of each wind turbine, and use them as one of the calculation factors.

[0102] Real-time weather factors:

[0103] Different altitudes and environments will result in varying levels of difficulty in reaching a wind turbine, even under the same weather conditions. For example, in heavy rain, the increased difficulty of reaching a wind turbine on a mountain is several orders of magnitude greater than that of reaching one on flat ground. Therefore, the impact of weather on the difficulty level varies depending on the location, which can be determined through multiple calculations using 3D models and personnel movement trajectory data. However, this cannot be calculated using traditional 2D planar models.

[0104] Therefore, the difficulty model for personnel reaching wind turbines / photovoltaic equipment, etc., can be derived as follows:

[0105] min D=(∑ h∈H ∑ e∈E (sinA*α)∑ t∈T )*β

[0106] In the formula, D is the difficulty coefficient of reaching each device in the area to be maintained and scheduled; h is the set of relative heights of the target maintenance devices; e is the set of location factors, representing the parameter factors formed by the sum of comprehensive environmental factors of the device's location; A is the angle between the relative height of the target maintenance device and the plane; α is the conversion factor; t is the set of weather factors; and β is the final conversion factor.

[0107] The operation and maintenance scheduling model uses the difficulty of reaching equipment as one of the calculation factors, combined with the personnel situation in the area to be scheduled for operation and maintenance, basic operation and maintenance data, and operation and maintenance business patterns, to calculate the optimal operation and maintenance scheduling plan.

[0108] In a further embodiment, the operation and maintenance schedule generation step, based on the optimization results and various constraints, generates an actual operation and maintenance schedule, including the following steps:

[0109] Operation and maintenance task allocation: Based on optimization results and equipment status, different operation and maintenance tasks are assigned to corresponding maintenance personnel or operation and maintenance teams. This function needs to consider factors such as the priority of operation and maintenance tasks, skill requirements, and personnel availability;

[0110] Task scheduling and prioritization: Based on optimization goals, equipment status, and constraints, maintenance tasks are scheduled and prioritized appropriately. For example, tasks can be prioritized based on urgency, time limits, and dependencies between devices to meet overall maintenance strategies and requirements.

[0111] Time window management: Manages the time window for operation and maintenance tasks, i.e., the time period for task execution. This function ensures that tasks are completed within the appropriate time, avoiding conflicts and timeouts;

[0112] Equipment resource allocation: Based on equipment availability, constraints, and optimization goals, allocate equipment resources rationally. For example, this can involve optimizing equipment utilization and reducing downtime.

[0113] In a further embodiment, the visualization and real-time monitoring step presents the scheduling results in a visual manner and provides real-time monitoring and dynamic adjustment capabilities. Through visualization and real-time monitoring, users can intuitively understand the equipment's operating status and maintenance schedule, promptly identify problems and make adjustments, improving operational efficiency and management level. Simultaneously, data analysis and report generation functions provide users with crucial data support, aiding in decision-making and optimization efforts. Visualization and real-time monitoring typically includes the following steps:

[0114] 3D Modeling Demonstration: 3D modeling technology is used to visually display the operational status of equipment and sites to users. Users can observe information such as equipment operation, fault status, and personnel distribution through a graphical interface, gaining an intuitive understanding of the equipment's operating condition.

[0115] Visualized scheduling plan: The generated operation and maintenance schedule is presented to users in a visual manner. Users can view the operation and maintenance tasks for each device, the execution time and sequence of tasks, and the dependencies between tasks through a graphical interface, which facilitates understanding and review of the operation and maintenance schedule.

[0116] Real-time status monitoring: Monitors the execution status of equipment and maintenance tasks in real time. By comparing the data with the actual status of the equipment, it determines whether the equipment is operating normally and whether the tasks are being executed as planned. Simultaneously, it can also provide alerts and reminders to users about potential problems or risks based on real-time monitoring data.

[0117] Data analysis and report generation: By analyzing real-time monitoring data, various reports and analytical results can be generated to help users evaluate the effectiveness of their operation and maintenance scheduling plans and identify areas for improvement. For example, reports on equipment utilization, task completion time statistics, and failure frequency can be generated to provide decision support for users.

[0118] Example 3

[0119] This embodiment provides a system for intelligent operation and maintenance scheduling based on 3D modeling, such as... Figure 5 As shown, it includes:

[0120] The data acquisition module acquires real-time data of each device in the area to be maintained and scheduled.

[0121] A constraint module, which sets operation and maintenance requirements and constraints;

[0122] The scheduling generation module generates an operation and maintenance schedule plan based on the preset 3D model of the area to be scheduled for operation and maintenance, the real-time data of each device, the operation and maintenance requirements and constraints.

[0123] The same or similar labels correspond to the same or similar parts;

[0124] The terms used to describe positional relationships in the accompanying drawings are for illustrative purposes only and should not be construed as limiting this patent.

[0125] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for intelligent operation and maintenance scheduling based on 3D modeling, characterized in that, Includes the following steps: Obtain real-time data for each device in the area to be scheduled for maintenance; Set up operation and maintenance requirements and constraints based on real-time needs; Based on the preset 3D model of the area to be maintained and scheduled, the real-time data of each device, maintenance requirements and constraints, an maintenance schedule plan is generated. Before generating the operation and maintenance schedule plan, the following steps are also included: Based on the 3D model of the area to be maintained and scheduled, the real-time data of each device, the maintenance requirements and constraints, a multi-objective optimization algorithm is selected from a preset multi-objective optimization algorithm library to generate the maintenance schedule plan. The preset multi-objective optimization algorithm library includes a variety of multi-objective optimization algorithms. The process of generating an operation and maintenance schedule plan based on the preset 3D model of the area to be operated and maintained, real-time data of each device, operation and maintenance requirements, and constraints includes: Based on the 3D model of the area to be maintained and scheduled, calculate the difficulty coefficient of reaching each device in the area to be maintained and scheduled. Based on the aforementioned difficulty coefficient, real-time data of each device, operation and maintenance requirements, and constraints, the selected multi-objective optimization algorithm is used to solve for the optimization result. The optimization results are then converted into an actual operation and maintenance scheduling plan to obtain the operation and maintenance scheduling plan.

2. The intelligent operation and maintenance scheduling method according to claim 1, characterized in that, The set operation and maintenance requirements and constraints shall include at least one of the following: 1) Set the priority of different operation and maintenance tasks; 2) Set restrictions for different devices in the area to be scheduled for maintenance; 3) Set optimization goals for the areas to be scheduled for maintenance; 4) Configure the allocation of human resources, including the number of personnel and skill requirements for different operation and maintenance tasks; 5) Set security requirements and standards for operation and maintenance tasks; 6) Set the weights for different optimization objectives.

3. The intelligent operation and maintenance scheduling method according to claim 1, characterized in that, The various multi-objective optimization algorithms include the NSGA-II algorithm, the SPEA2 algorithm, and the MOEA / D algorithm.

4. The intelligent operation and maintenance scheduling method based on 3D modeling according to claim 1, characterized in that, The preset 3D model of the area to be maintained and scheduled includes: Obtain three-dimensional data of the internal structure of the area to be maintained and scheduled and the distribution of equipment in the area to be maintained and scheduled. The three-dimensional data includes the actual three-dimensional coordinates of each equipment in the area to be maintained and scheduled and the real environment in which each equipment is located. The acquired 3D data is preprocessed, cleaned, and transformed to obtain preprocessed 3D data; The preprocessed 3D data is modeled to generate a 3D model of the area to be scheduled for maintenance.

5. The intelligent operation and maintenance scheduling method based on 3D modeling according to claim 1, characterized in that, The acquisition of real-time data for each device in the area to be scheduled for maintenance includes: Sensors are installed on each device in the area to be maintained and scheduled. The sensors acquire real-time parameters and indicators of each device, including temperature, humidity, pressure, current and voltage. Data cleaning is performed on the real-time parameters and indicators of each device. Information is extracted and processed from the cleaned real-time parameters and indicators to generate key parameters and indicators, which serve as real-time data for each device.

6. The intelligent operation and maintenance scheduling method based on 3D modeling according to claim 1, characterized in that, It also includes the following steps: The generated operation and maintenance schedule plan is visualized and provides real-time monitoring and dynamic adjustment functions.

7. A system for intelligent operation and maintenance scheduling based on 3D modeling, characterized in that, include: The data acquisition module acquires real-time data of each device in the area to be maintained and scheduled. The constraint module sets operation and maintenance requirements and constraint conditions according to real-time needs; The scheduling generation module generates an operation and maintenance schedule plan based on the preset 3D model of the area to be scheduled for operation and maintenance, the real-time data of each device, the operation and maintenance requirements and constraints. The scheduling generation module also selects a multi-objective optimization algorithm from a preset multi-objective optimization algorithm library to generate an operation and maintenance scheduling plan based on the 3D model of the area to be scheduled for maintenance, the real-time data of each device, the maintenance requirements and constraints. The preset multi-objective optimization algorithm library includes a variety of multi-objective optimization algorithms. The process of generating an operation and maintenance schedule plan based on the preset 3D model of the area to be operated and maintained, real-time data of each device, operation and maintenance requirements, and constraints includes: Based on the 3D model of the area to be maintained and scheduled, calculate the difficulty coefficient of reaching each device in the area to be maintained and scheduled. Based on the aforementioned difficulty coefficient, real-time data of each device, operation and maintenance requirements, and constraints, the selected multi-objective optimization algorithm is used to solve for the optimization result. The optimization results are then converted into an actual operation and maintenance scheduling plan to obtain the operation and maintenance scheduling plan.

Images