Model layout method and building method of simulation training system for confined space operation
By improving the ant colony algorithm to automatically lay out confined space operation models in the Unity3D platform, and combining it with Maya software and other components, the problems of low efficiency and poor fidelity of existing training methods are solved, realizing efficient and immersive confined space operation training and reducing safety accidents.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU DIANZI UNIV
- Filing Date
- 2022-12-22
- Publication Date
- 2026-05-15
AI Technical Summary
Existing training methods for confined space operations are inefficient and have a high error rate in model layout. 3D virtual simulation training systems have poor fidelity and cannot effectively reduce safety accidents.
An improved ant colony algorithm was used to lay out the model of a confined space operation simulation training system in the Unity3D platform. 3D modeling was performed using Maya software, and bounding boxes were constructed using Collider and Rigidbody components. The improved ant colony algorithm was used to automatically lay out the equipment and character models. Animation was developed using LOD Group and TimeLine editors, and virtual character movement programs were written.
It enables efficient and immersive confined space operation simulation training, improves the realism and accuracy of training, and reduces the occurrence of safety accidents.
Smart Images

Figure CN115761150B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the technical field of training systems, and relates to a model layout method and construction method for a confined space operation simulation training system. Background Technology
[0002] Confined spaces refer to enclosed or semi-enclosed facilities and sites with restricted space and access. Confined spaces can be broadly categorized into three types: above-ground confined spaces, underground confined spaces, and enclosed (semi-enclosed) confined spaces. Above-ground confined spaces mainly include fermentation tanks, ruins, grain silos, and material storage silos; underground confined spaces mainly include underground pipelines, culverts, tunnels, pits, abandoned wells, cellars, and biogas digesters; enclosed (semi-enclosed) confined spaces mainly include ship holds, storage tanks, vehicle-mounted tankers, reaction towers (vessels), pressure vessels, and boilers. Confined space work involves specially trained personnel entering the confined spaces of a production enterprise to perform a series of operations. Confined space work is characterized by its limited space, inability to work for extended periods, and high risk of safety accidents.
[0003] Traditional training for confined space workers primarily relies on classroom theory, supplemented by hands-on practical training. Only a small number of training sessions utilize 3D virtual simulation systems. This combination of theoretical knowledge and hands-on practice suffers from low efficiency and poor effectiveness due to the significant differences between the simulated confined space and the real-world conditions, coupled with the demanding and complex nature of confined space work. Current 3D virtual simulation training systems, while available, suffer from limitations due to their immaturity. The models within the simulation are often manually laid out, resulting in high error rates and an inability to accurately reflect real-world scenarios. To address these issues, a confined space operation simulation training system addresses these shortcomings. This system offers a model layout method and system construction approach that overcomes the inefficiency of traditional methods while providing a highly realistic simulation. This allows trainees to become thoroughly familiar with confined space operations before undertaking real-world tasks, thus reducing the risk of accidents. Summary of the Invention
[0004] One objective of this invention is to address the shortcomings of current technologies by proposing a model layout method for a confined space operation simulation training system based on an improved ant colony algorithm.
[0005] The model layout method of the confined space operation simulation training system of the present invention includes the following steps:
[0006] Step 1: Based on the actual work site of the confined space operation, obtain the dimensions of the confined space work area, the dimensions of each piece of equipment in the area, and the external dimensions of the workers. Use Maya software to create a 3D model of the terrain, people, and equipment in the confined space operation, and export the model as an FBX file. The equipment includes walkie-talkies, buildings, valves, pipes, and wrenches.
[0007] Step 2: Import the FBX file of the model exported from Maya software into a new project in the Unity3D platform;
[0008] Step 3: Use the Collider component in the Unity3D platform to build bounding boxes for all models, and adjust the radius and orientation of all bounding boxes according to the size and orientation of the models in the Unity3D platform; all models include terrain models, character models, and equipment models; build capsule bounding boxes for character models, terrain bounding boxes for terrain models, and cuboid bounding boxes for equipment models.
[0009] Step 4: Use the Rigidbody component in the Unity3D platform to add gravity to the character model (which is a rigid body);
[0010] The process of constructing bounding boxes for all models and adding gravity to the character models prepares for the automatic layout of the models in step 5.
[0011] Step 5: In the Unity3D platform, use the improved ant colony algorithm to automatically lay out the equipment and character models in the confined space simulation scene, so that the equipment and character models can be automatically laid out into the terrain model (3D simulation scene). The specific steps are as follows:
[0012] 5-1 Determine the indicators that affect the automatic layout of the model, including: the size of the model, the number of identical models, the shape of the model, and the layout accuracy requirements of the model.
[0013] The dimensions of the model are obtained solely by calculating the dimensions of the model's bounding box.
[0014] 5-2 The weights of the indicators are calculated using the analytic hierarchy process.
[0015] 5-3 Substituting the weight values into the state transition probability formula of the traditional ant colony algorithm, we obtain the state transition probability of the improved ant colony algorithm.
[0016]
[0017] Where i represents coordinate i in the terrain model of the underground pipeline simulation scenario; j represents coordinate j in the terrain model of the underground pipeline simulation scenario; k represents ant k; allowedk Let τ be the coordinates that ant k can choose for the next step; ij (t) represents the flormon concentration values from coordinate i to coordinate j; η ij (t) represents the visibility value from coordinate i to coordinate j, which is inversely proportional to the path length from coordinate i to coordinate j; w ij (t) represents the weight value of path (i,j) at time t; α represents the weight value of flormon concentration; β represents the weight value of visibility; and λ represents the weight exponent of the weight value of path (i,j) at time t.
[0018] 5-4 State transition probabilities based on the improved ant colony algorithm Automatically lay out the models in the simulation scene.
[0019] Another objective of this invention is to propose a method for building a confined space operation simulation training system based on the Unity development platform.
[0020] The system construction method of the confined space operation simulation training system of the present invention includes the following steps:
[0021] Step 1: Based on the actual work site of the confined space operation, obtain the dimensions of the confined space work area, the dimensions of each piece of equipment in the area, and the external dimensions of the workers. Use Maya software to create a 3D model of the terrain, people, and equipment in the confined space operation, and export the model as an FBX file. The equipment includes walkie-talkies, buildings, valves, pipes, and wrenches.
[0022] Step 2: Import the FBX file of the model exported from Maya software into a new project in the Unity3D platform;
[0023] Step 3: Use the Collider component in the Unity3D platform to build bounding boxes for all models, and adjust the radius and orientation of all bounding boxes according to the size and orientation of the models in the Unity3D platform; all models include terrain models, character models, and equipment models; build capsule bounding boxes for character models, terrain bounding boxes for terrain models, and cuboid bounding boxes for equipment models.
[0024] Step 4: Use the Rigidbody component in the Unity3D platform to add gravity to the character model (which is a rigid body);
[0025] The process of constructing bounding boxes for all models and adding gravity to the character models prepares for the automatic layout of the models in step 5.
[0026] Step 5: In the Unity3D platform, use the improved ant colony algorithm to automatically lay out the equipment and character models in the confined space simulation scene, so that the equipment and character models can be automatically laid out into the terrain model (3D simulation scene). The specific steps are as follows:
[0027] 5-1 Determine the indicators that affect the automatic layout of the model, including: the size of the model, the number of identical models, the shape of the model, and the layout accuracy requirements of the model.
[0028] The dimensions of the model are obtained solely by calculating the dimensions of the model's bounding box.
[0029] 5-2 The weights of the indicators are calculated using the analytic hierarchy process.
[0030] 5-3 Substituting the weight values into the state transition probability formula of the traditional ant colony algorithm, we obtain the state transition probability of the improved ant colony algorithm.
[0031]
[0032] Where i represents coordinate i in the terrain model of the underground pipeline simulation scenario; j represents coordinate j in the terrain model of the underground pipeline simulation scenario; k represents ant k; allowed k Let τ be the coordinates that ant k can choose for the next step; ij (t) represents the flormon concentration values from coordinate i to coordinate j; η ij (t) represents the visibility value from coordinate i to coordinate j, which is inversely proportional to the path length from coordinate i to coordinate j; w ij (t) represents the weight value of path (i,j) at time t; α represents the weight value of flormon concentration; β represents the weight value of visibility; and λ represents the weight exponent of the weight value of path (i,j) at time t.
[0033] 5-4 State transition probabilities based on the improved ant colony algorithm Automatically lay out the models in the simulation scene.
[0034] Step 6: Use the LOD Group component in the Unity3D platform to set the rendering mode of the simulation scene.
[0035] Step 7: Develop animations for the confined space work simulation training system using the TimeLine editor in the Unity3D platform to complete the development of the confined space work training and assessment procedures. The TimeLine editor includes tracks such as camera track, motion track, audio track, subtitle track, and lighting control track.
[0036] The use of the TimeLine editor for animation development is a conventional existing technique, so it will not be explained in detail.
[0037] Step 8: Write a program in the Visual Studio development platform to control the movement of the virtual character in the simulation scene. The virtual character can move forward, backward, left, right, jump, and crouch.
[0038] The beneficial effects of this invention are:
[0039] This invention uses an improved ant colony algorithm to automatically lay out equipment and human models within a confined space simulation training system. Furthermore, it constructs the system using a system building method. This not only overcomes the low efficiency of traditional training methods but also creates a highly realistic and immersive simulation training system. This allows students to become fully familiar with the operational procedures for confined space work before going to the field, thereby reducing the occurrence of work-related safety accidents. Attached Figure Description
[0040] Figure 1 This is a simplified diagram of the model layout method of the present invention.
[0041] Figure 2 This is a simplified diagram of the system setup method of the present invention. Detailed Implementation
[0042] The present invention will be further analyzed below with reference to specific embodiments.
[0043] Underground pipeline operations are a type of confined space operation. The following example demonstrates how to automatically lay out the model within a confined space operation simulation training system and build such a system.
[0044] Model layout methods for confined space operation simulation training systems, such as Figure 1 Includes the following steps:
[0045] Step 1: Based on the actual work site of underground pipeline confined space operations, obtain the dimensions of the underground pipeline confined space work site, the dimensions of each piece of equipment in the site, and the external dimensions of the workers. Use Maya software to create a 3D model of the terrain, people, walkie-talkies, buildings, valves, pipes, wrenches, etc. in the underground pipeline confined space operation, and export the model as an fbx file.
[0046] Step 2: Create a new project in the Unity3D platform and import the FBX file of the model exported from Maya software into the new project in the Unity3D platform.
[0047] Step 3: In the Unity3D platform, use the Collider component to build bounding boxes for all models, including terrain models, character models, valve models, etc. Specifically, build capsule bounding boxes for character models, terrain bounding boxes for underground pipeline operation terrain, and cuboid bounding boxes for equipment such as buildings, valves, pipes, and wrenches. Adjust the radius and orientation of all bounding boxes according to the size and orientation of the models in the Unity3D platform.
[0048] In the Unity3D platform, model bounding boxes include Box Collider, Sphere Collider, Capsule Collider, and Terrain Collider. The Terrain Collider is a dedicated bounding box for terrain models and can only be used with them. For models other than terrain, the choice of bounding box is based on which shape the model's approximates. Generally, capsule colliders are used for character models, while box colliders are used for walkie-talkie models, building models, etc.
[0049] Step 4: Use the Rigidbody component in the Unity3D platform to add gravity to the character model (which is a rigid body).
[0050] Step 5: In the Unity3D platform, use the improved ant colony algorithm to automatically lay out the equipment and character models in the underground pipeline simulation scene, so that the equipment and character models can be automatically laid out into the terrain model (3D simulation scene). The specific steps are as follows:
[0051] 5-1 Determine the indicators that affect the automatic layout of the model, including: the size of the model, the number of identical models, the shape of the model, and the layout accuracy requirements of the model.
[0052] 5-2 The weights of the indicators are calculated using the analytic hierarchy process.
[0053] The Analytic Hierarchy Process (AHP) is a commonly used method for determining the weights of each indicator in a problem by using a positive reciprocal matrix.
[0054] 5-3 Substituting the weight values into the state transition probability formula of the traditional ant colony algorithm
[0055]
[0056] In this process, the state transition probability formula of the improved ant colony algorithm is obtained.
[0057]
[0058] Where i represents coordinate i in the terrain model of the underground pipeline simulation scenario; j represents coordinate j in the terrain model of the underground pipeline simulation scenario; k represents ant k; allowed k Let τ be the coordinates that ant k can choose for the next step; ij (t) represents the flormon concentration values from coordinate i to coordinate j; η ij (t) represents the visibility value from coordinate i to coordinate j, which is inversely proportional to the path length from coordinate i to coordinate j; w ij (t) represents the weight value of path (i,j) at time t; α represents the weight value of flormon concentration; β represents the weight value of visibility; and λ represents the weight exponent of the weight value of path (i,j) at time t.
[0059] Ant Colony Optimization (ACO) is a heuristic algorithm developed by simulating the foraging behavior of ants. ACO calculates state transition probabilities based on pheromone concentration and visibility, and determines the final optimal path solution through rules governing perception range, environmental information, foraging, movement, obstacle avoidance, and pheromone emission. ACO is commonly used for path planning or automatic layout problems. However, ACO is heavily influenced by the weights of pheromone concentration and visibility, which can lead to overly rapid convergence or relying solely on visibility for decision-making, resulting in an incorrect global solution. To address these shortcomings, improvements are typically made to ACO based on specific problem scenarios.
[0060] 5-4 Automatic layout of models in underground pipeline simulation scenarios based on the state transition probabilistic formula of the improved ant colony algorithm.
[0061] A method for building a confined space operation simulation training system based on the above model layout method, such as... Figure 2 Includes the following steps:
[0062] Step 1: Based on the actual work site of underground pipeline confined space operations, obtain the dimensions of the underground pipeline confined space work site, the dimensions of each piece of equipment in the site, and the external dimensions of the workers. Use Maya software to create a 3D model of the terrain, people, walkie-talkies, buildings, valves, pipes, wrenches, etc. in the underground pipeline confined space operation, and export the model as an fbx file.
[0063] Step 2: Create a new project in the Unity3D platform and import the FBX file of the model exported from Maya software into the new project in the Unity3D platform.
[0064] Step 3: In the Unity3D platform, use the Collider component to build bounding boxes for all models, including terrain models, character models, valve models, etc. Specifically, build capsule bounding boxes for character models, terrain bounding boxes for terrain, and cuboid bounding boxes for equipment such as buildings, valves, pipes, and wrenches. Adjust the radius and orientation of all bounding boxes according to the size and orientation of the models in the Unity3D platform.
[0065] Step 4: Use the Rigidbody component in the Unity3D platform to add gravity to the character model (which is a rigid body).
[0066] Step 5: Use the improved ant colony algorithm in the Unity3D platform to automatically lay out the equipment models and character models in the underground pipeline simulation scene, so that the equipment models and character models can be automatically laid out into the terrain model (3D simulation scene).
[0067] Step 6: Use the LOD Group component in the Unity3D platform to set the rendering mode of the simulation scene.
[0068] Step 7: Develop animations for the confined space operation simulation training system using the TimeLine editor in the Unity3D platform, to complete the development of training and assessment procedures for underground pipeline operations. The TimeLine editor includes tracks such as camera track, motion track, audio track, subtitle track, and lighting control track.
[0069] Step 8: Write a C# program in the Visual Studio development platform to control the movement of the virtual character in the simulation scene. The virtual character can move forward, backward, left, right, jump, and crouch.
[0070] After the system is built using the confined space operation simulation training system construction method of this invention, trainees can use the system for training and assessment through human-computer interaction. The main implementation process of human-computer interaction includes the following steps:
[0071] Step 1: The confined space operation simulation training system prompts trainees to operate the equipment.
[0072] Step 2: Students use the mouse to control the virtual character in the system scene to walk next to the device model.
[0073] Step 3: Students control the virtual character in the system scene by clicking on the device model to operate it using the mouse.
[0074] Step 4: The confined space operation simulation training system determines whether the virtual character has correctly operated the equipment model by judging whether the bounding box of the virtual character collides with the bounding box of the operated equipment model. If a collision occurs, the system determines that the virtual character has correctly operated the equipment model and prompts "Operation Correct"; otherwise, the system determines that the virtual character has not correctly operated the equipment model and prompts "Operation Error".
Claims
1. A model layout method for a confined space operation simulation training system, characterized in that... Includes the following steps: Step 1: Based on the actual work site of the confined space operation, obtain the dimensions of the confined space work site, the dimensions of each piece of equipment in the site, and the external dimensions of the workers. Use Maya software to create a 3D model of the terrain, people, and equipment in the confined space operation, and export the model as an fbx file. Step 2: Import the FBX file of the model exported from Maya software into a new project in the Unity3D platform; Step 3: Use the Collider component in the Unity3D platform to build bounding boxes for all models, and adjust the radius and orientation of all bounding boxes according to the size and orientation of the models in the Unity3D platform; all models include terrain models, character models, and equipment models; Step 4: Use the Rigidbody component in the Unity3D platform to add gravity to the character model; Step 5: In the Unity3D platform, use the improved ant colony algorithm to automatically lay out the equipment and character models in the confined space simulation scene, so that the equipment and character models can be automatically laid out into the terrain model. The specific steps are as follows: 5-1 Determine the indicators that affect the automatic layout of the model, including: the size of the model, the number of identical models, the shape of the model, and the layout accuracy requirements of the model; 5-2 Use the Analytic Hierarchy Process (AHP) to calculate the weights of the indicators; 5-3 Substituting the weight values into the state transition probability formula of the traditional ant colony algorithm, we obtain the state transition probability of the improved ant colony algorithm. ; Equation (1) Where i represents coordinate i in the terrain model of the underground pipeline simulation scenario; j represents coordinate j in the terrain model of the underground pipeline simulation scenario; k represents ant k; Let K be the coordinates that ant k can choose for the next step; The flormon concentration values are from coordinate i to coordinate j; The visibility value from coordinate i to coordinate j is inversely proportional to the path length from coordinate i to coordinate j. Let be the weight of path (i, j) at time t; The weighting value for pheromone concentration; This is the weighted value for visibility. The weight exponent is the weight value of path (i, j) at time t; The flormon concentration is from coordinate i to coordinate s; The visibility value from coordinate i to coordinate s is inversely proportional to the path length from coordinate i to coordinate s; Let be the weight of path (i, s) at time t; 5-4 State transition probabilities based on the improved ant colony algorithm Automatically lay out the models in the simulation scene.
2. The method according to claim 1, characterized in that... In step 1, the equipment includes walkie-talkies, buildings, valves, pipes, and wrenches.
3. The method according to claim 1, characterized in that... In step 3, a capsule bounding box is constructed for the character model, a terrain bounding box is constructed for the terrain model, and a cuboid bounding box is constructed for the equipment model.
4. The method according to claim 1, characterized in that... In step 5-1, the size of the model is obtained by calculating the size of the model's bounding box.
5. A method for building a confined space operation simulation training system, characterized in that... The method includes the following steps: Step 1: Using the model layout method described in any one of claims 1-4, the equipment model and the character model can be automatically laid out into the terrain model; Step 2: Use the LOD Group component in the Unity3D platform to set the rendering mode of the simulation scene; Step 3: Use the TimeLine editor in the Unity3D platform to develop animations for the confined space operation simulation training system, in order to complete the development of the confined space operation training procedures and assessment procedures; Step 4: Write a program in the Visual Studio development platform to control the movement of the virtual character in the simulation scene.
6. The method according to claim 5, characterized in that... In step 3, the tracks in the TimeLine editor include: camera track, motion track, audio track, caption track, and lighting control track.
7. The method according to claim 5, characterized in that... In step 4, the virtual character can move in the following ways: forward, backward, left, right, jump, and crouch.