A method, device and equipment for automatic inspection of the undercarriage of a monorail vehicle
By acquiring the operating parameters of the monorail vehicle, inspection tasks are automatically generated and the skirt panels are automatically opened. Combined with path planning, intelligent inspection of the undercarriage of the monorail vehicle is realized, which solves the problem of low maintenance efficiency in the existing technology and improves inspection efficiency and detection accuracy.
Patent Information
- Application Number
- CN202611443280.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-09-16
- Publication Date
- 2026-11-17
AI Technical Summary
Existing technologies for undercarriage inspection of monorail vehicles are difficult to achieve automatic triggering, multi-system safety interlocking, and full-process automation, resulting in low maintenance efficiency.
By acquiring the operating parameters of multiple vehicles, inspection tasks are automatically generated based on a multi-dimensional evaluation model. After confirming that the environment is safe, the skirt panel is automatically opened. Based on the standby position of the inspection robot and the parking position of the vehicle, the path is automatically planned and the inspection robot is controlled to perform the inspection.
It enables intelligent generation and prioritization of inspection tasks, improves the scientific nature and accuracy of task allocation, reduces manual operation steps, improves inspection efficiency and detection accuracy, and ensures the safety and flexibility of inspection operations.
Smart Images

Figure CN123104747A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of rail transit vehicle inspection technology, and in particular to an automatic inspection method, device and equipment for the undercarriage of a monorail vehicle. Background Technology
[0002] As a base for train parking, inspection, and maintenance, the efficiency and quality of monorail vehicle depots directly affect operational safety. Monorail vehicles use a fully enclosed skirt design to cover the running gear inside the car body, and the vehicles straddle the track beams. Under-car maintenance requires opening the skirt and using ladders, making the operation quite difficult.
[0003] The relevant technologies mainly employ manual inspection methods, where inspectors use ladders to visually inspect the equipment under the vehicle and manually record the results. In addition, there are also automated inspection robot systems, which include inspection equipment, remote control equipment, and guidance equipment, to automatically scan and collect images of the underside of the vehicle along a preset path.
[0004] However, the existing methods for inspecting monorail vehicles under the vehicle are difficult to achieve automatic triggering of inspection operations, multi-system safety interlocking, and full-process automation, resulting in low maintenance efficiency. Summary of the Invention
[0005] This application provides an automatic inspection method, device, and equipment for the undercarriage of a monorail vehicle, which solves the technical problem of low maintenance efficiency in related technologies.
[0006] In a first aspect, embodiments of this application provide an automatic inspection method for the undercarriage of a monorail vehicle, the method comprising:
[0007] Obtain the operating parameters corresponding to multiple vehicles, and generate multiple inspection tasks arranged in sequence based on the operating parameters; multiple vehicles are parked in the monorail depot;
[0008] During the sequential execution of inspection tasks, if it is determined that the vehicle's environment meets the maintenance requirements, the side skirts of the vehicle corresponding to the current inspection task are opened.
[0009] The inspection robot's movement trajectory is obtained by path planning based on the standby position of the inspection robot and the parking position of the vehicle corresponding to the current inspection task.
[0010] The inspection robot is controlled to inspect the vehicle corresponding to the current inspection task according to the movement trajectory, and the inspection results of the vehicle corresponding to the current inspection task are obtained.
[0011] This application provides an automatic inspection method for the undercarriage of a monorail vehicle. By acquiring the operating parameters of multiple vehicles and automatically generating multiple sequentially arranged inspection tasks based on these parameters, it replaces the traditional method of task allocation relying on manual experience and paper records. This method achieves intelligent generation and prioritization of inspection tasks, improving the scientific nature and accuracy of task allocation. During the sequential execution of inspection tasks, the skirt panels are automatically opened after confirming that the vehicle's environment meets the maintenance requirements, reducing the manual operation of repeatedly opening and closing the skirt panels. Based on the standby position of the inspection robot and the parking position of the vehicle, the method automatically plans the path to obtain the movement trajectory and controls the inspection robot to perform inspections according to the movement trajectory. This enables the inspection robot to autonomously navigate and inspect the undercarriage components, improving inspection efficiency and detection accuracy.
[0012] Optionally, the operating parameters corresponding to multiple vehicles are obtained, and multiple sequentially arranged inspection tasks are generated based on the operating parameters, including:
[0013] For the operating factors of multiple operating dimensions included in the operating parameters, obtain the first evaluation score corresponding to each operating factor under each operating dimension;
[0014] For each operational dimension, the weighted sum of the first evaluation scores corresponding to multiple operational factors is used to obtain the second evaluation score corresponding to the operational dimension.
[0015] The second evaluation scores corresponding to multiple operational dimensions are weighted and summed to obtain the target evaluation score for each vehicle.
[0016] Based on the pre-defined mapping relationship between multiple score ranges and multiple priority levels, the priority order of the inspection tasks corresponding to each vehicle is determined.
[0017] Here, this application decomposes the operating parameters into multiple operating dimensions and operating factors under each dimension, obtains the first evaluation score corresponding to each operating factor, and obtains the second evaluation score corresponding to the operating dimension and the target evaluation score corresponding to the vehicle through a two-level weighted summation method. The process of evaluating the inspection priority is structured into a multi-level, multi-dimensional quantitative evaluation system. Compared with the traditional method of sorting inspection tasks based on manual experience, it can comprehensively evaluate information from multiple dimensions such as vehicle online operation plan, health status, maintenance cycle, and return-to-warehouse operation window, avoiding the one-sidedness of single-dimensional evaluation. At the same time, by pre-setting the mapping relationship between the score range and the priority level, the target evaluation score is mapped to a clear priority order, which improves the rationality and interpretability of the inspection task allocation.
[0018] Optionally, if multiple inspection robots exist, after controlling the side skirts of the vehicle corresponding to the current inspection task to open, the following steps are taken:
[0019] According to the priority order of multiple inspection tasks, the corresponding inspection tasks are assigned to multiple inspection robots in turn, so as to control multiple inspection robots to perform vehicle maintenance at the same time.
[0020] In this application, in a scenario with multiple inspection robots, the inspection tasks are assigned to the robots in order of priority, thereby enabling parallel operation scheduling of multiple inspection robots. Compared with the serial inspection method, this method can maximize the parallel utilization of multiple inspection devices in the depot while meeting power supply safety constraints and operational resource constraints, significantly shortening the overall inspection cycle of multiple trains and improving the depot's operation and maintenance efficiency and train turnaround rate.
[0021] Optionally, it also includes:
[0022] During the vehicle inspection process, if a new vehicle enters the monorail depot, the priority level of the newly entered vehicle is obtained.
[0023] If the priority level of a newly entered monorail vehicle depot is higher than that of at least one vehicle being inspected by an inspection robot, the inspection robot corresponding to the vehicle with the lowest priority level is controlled to stop executing the current inspection task. Based on the standby position of the inspection robot and the parking position of the newly entered monorail vehicle depot, path planning is performed to obtain the adjusted movement trajectory of the inspection robot.
[0024] The inspection robot is controlled to inspect newly arrived monorail depot vehicles according to the adjusted movement trajectory, and the inspection results of the newly arrived monorail depot vehicles are obtained.
[0025] Here, in this application, during the vehicle inspection process, the inspection robot can sense in real time whether a new vehicle has entered the depot and obtain the priority level of the new vehicle. When the priority level of the newly entered vehicle is higher than that of a vehicle being inspected, the system automatically triggers a priority preemption mechanism, controls the inspection robot with the lowest priority level to stop its current inspection task, releases inspection resources, replans the path based on the robot's standby position and the new vehicle's parking position to adjust its movement trajectory, and controls the robot to turn and execute the inspection task of the new vehicle. Compared with the related technologies where inspection tasks cannot be dynamically adjusted once assigned, this application realizes the dynamic reallocation of inspection resources, ensures that high-priority emergency tasks can be responded to in a timely manner, and improves the depot's response speed and scheduling flexibility to sudden inspection needs.
[0026] Optionally, a weighted sum is performed on the first evaluation scores corresponding to multiple operating factors to obtain a second evaluation score corresponding to the operating dimension, including:
[0027] Based on the occurrence time of historical operational failures corresponding to the operational factors, the attenuation coefficient corresponding to the operational factor is determined; the magnitude of the attenuation coefficient is negatively correlated with the duration of the occurrence time of historical operational failures corresponding to the operational factors.
[0028] The second evaluation score is obtained by weighted summing the products of the first evaluation score and the corresponding attenuation coefficient for each operating factor.
[0029] Here, when weighting and summing the first evaluation scores of the operating factors, this application introduces an attenuation coefficient based on the occurrence time of historical operating faults. By multiplying the first evaluation score by the corresponding attenuation coefficient and then performing a weighted summation, the impact of recently occurring faults on the inspection priority assessment is given a greater weight, while the impact of faults that occurred earlier and have not recurred for a long time is gradually weakened. Compared with the method of directly using historical statistical data as the assessment basis, the assessment results after introducing the attenuation coefficient can better reflect the timeliness characteristics of faults, making the allocation of inspection resources closer to the actual operation and maintenance needs of vehicles and improving the accuracy of inspection priority assessment.
[0030] Optionally, determine that the vehicle's environment meets the maintenance requirements, including:
[0031] Obtain the environmental parameters of the environment in which the vehicle corresponding to the current inspection task is located; the environmental parameters should include at least the power outage status, the contact wire disconnection status, the grounding device closure status, the access control blockage status, and the video surveillance switching status;
[0032] When the power outage status indicates that the vehicle corresponding to the inspection task has been de-energized, the contact wire disconnection status indicates that the contact wire of the track corresponding to the inspection task has been disconnected, the grounding device closed status indicates that the grounding device of the track corresponding to the inspection task has been closed, the access control closed status indicates that the access control of the inspection task has been closed, and the video monitoring switching status indicates that the monitoring video of the location of the vehicle corresponding to the inspection task has been switched, it is determined that the environment of the vehicle meets the maintenance requirements.
[0033] Here, this application refines the safety confirmation of the vehicle's environment into five environmental parameters: power outage state, contact network disconnection state, grounding device closed state, access control blockage state, and video surveillance switching state. It requires that all five environmental parameters meet the corresponding safety conditions before the environment can be confirmed as meeting the maintenance requirements and the skirt panel can be controlled to open. Compared with related technologies where safety protection mainly relies on the robot's own sensors or manual item-by-item inspection, this application obtains environmental parameters through multi-system linkage and performs joint confirmation. It incorporates the safety status of the power supply system, access control system, and video surveillance system into a unified judgment condition, realizing the automation of multi-system collaborative safety verification before the skirt panel is opened, and improving the safety of inspection operations.
[0034] Secondly, embodiments of this application provide an automatic inspection device for the undercarriage of a monorail vehicle, comprising:
[0035] The inspection task generation module is used to obtain the operating parameters of multiple vehicles and generate multiple inspection tasks arranged in sequence based on the operating parameters; multiple vehicles are parked in the monorail depot.
[0036] The control module is used to control the opening of the side skirts of the vehicle corresponding to the current inspection task when the vehicle's environment meets the maintenance requirements during the sequential execution of inspection tasks.
[0037] The path planning module is used to plan the path based on the standby position of the inspection robot and the parking position of the vehicle corresponding to the current inspection task, so as to obtain the movement trajectory of the inspection robot.
[0038] The inspection execution module is used to control the inspection robot to inspect the vehicle corresponding to the current inspection task according to the movement trajectory, and obtain the inspection results of the vehicle corresponding to the current inspection task.
[0039] Optionally, the inspection task generation module is specifically used for:
[0040] For the operating factors of multiple operating dimensions included in the operating parameters, obtain the first evaluation score corresponding to each operating factor under each operating dimension;
[0041] For each operational dimension, the weighted sum of the first evaluation scores corresponding to multiple operational factors is used to obtain the second evaluation score corresponding to the operational dimension.
[0042] The second evaluation scores corresponding to multiple operational dimensions are weighted and summed to obtain the target evaluation score for each vehicle.
[0043] Based on the pre-defined mapping relationship between multiple score ranges and multiple priority levels, the priority order of the inspection tasks corresponding to each vehicle is determined.
[0044] Optionally, the inspection task generation module is also specifically used for:
[0045] If multiple inspection robots exist, after controlling the side skirts of the vehicle corresponding to the current inspection task to open, the following will be included:
[0046] According to the priority order of multiple inspection tasks, the corresponding inspection tasks are assigned to multiple inspection robots in turn, so as to control multiple inspection robots to perform vehicle maintenance at the same time.
[0047] Optionally, the inspection task generation module is also specifically used for:
[0048] During the vehicle inspection process, if a new vehicle enters the monorail depot, the priority level of the newly entered vehicle is obtained.
[0049] If the priority level of a newly entered monorail vehicle depot is higher than that of at least one vehicle being inspected by an inspection robot, the inspection robot corresponding to the vehicle with the lowest priority level is controlled to stop executing the current inspection task. Based on the standby position of the inspection robot and the parking position of the newly entered monorail vehicle depot, path planning is performed to obtain the adjusted movement trajectory of the inspection robot.
[0050] The inspection robot is controlled to inspect newly arrived monorail depot vehicles according to the adjusted movement trajectory, and the inspection results of the newly arrived monorail depot vehicles are obtained.
[0051] Optionally, the inspection task generation module is also specifically used for:
[0052] Based on the occurrence time of historical operational failures corresponding to the operational factors, the attenuation coefficient corresponding to the operational factor is determined; the magnitude of the attenuation coefficient is negatively correlated with the duration of the occurrence time of historical operational failures corresponding to the operational factors.
[0053] The second evaluation score is obtained by weighted summing the products of the first evaluation score and the corresponding attenuation coefficient for each operating factor.
[0054] Optionally, the control module is specifically used for:
[0055] Obtain the environmental parameters of the environment in which the vehicle corresponding to the current inspection task is located; the environmental parameters should include at least the power outage status, the contact wire disconnection status, the grounding device closure status, the access control blockage status, and the video surveillance switching status;
[0056] When the power outage status indicates that the vehicle corresponding to the inspection task has been de-energized, the contact wire disconnection status indicates that the contact wire of the track corresponding to the inspection task has been disconnected, the grounding device closed status indicates that the grounding device of the track corresponding to the inspection task has been closed, the access control closed status indicates that the access control of the inspection task has been closed, and the video monitoring switching status indicates that the monitoring video of the location of the vehicle corresponding to the inspection task has been switched, it is determined that the environment of the vehicle meets the maintenance requirements.
[0057] Thirdly, embodiments of this application provide an automatic inspection device for the undercarriage of a monorail vehicle, comprising:
[0058] At least one processor and memory;
[0059] The memory stores instructions that the computer executes;
[0060] At least one processor executes computer execution instructions stored in memory, causing at least one processor to perform the first aspect above and various possible methods for automatic inspection of the undercarriage of monorail vehicles involved in the first aspect.
[0061] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions. When a processor executes the computer-executable instructions, it implements the above-mentioned first aspect and various possible methods for automatic inspection of the undercarriage of monorail vehicles.
[0062] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the above-mentioned first aspect and various possible methods for automatic inspection of the undercarriage of monorail vehicles.
[0063] This application provides an automatic inspection method, device, and equipment for the undercarriage of a monorail vehicle. The method acquires multiple vehicle-specific operating parameters and automatically generates multiple sequentially arranged inspection tasks based on these parameters. This replaces the traditional task allocation method that relies on manual experience and paper records, achieving intelligent generation and prioritization of inspection tasks, thus improving the scientific nature and accuracy of task allocation. During the sequential execution of inspection tasks, the skirt panels are automatically opened after confirming that the vehicle's environment meets maintenance requirements, reducing the need for repeated manual opening and closing of the skirt panels. Based on the inspection robot's standby position and the vehicle's parking position, a path is automatically planned to obtain a movement trajectory. The inspection robot is then controlled to perform inspections according to this trajectory, enabling autonomous navigation and inspection of the undercarriage components, thus improving inspection efficiency and detection accuracy. Attached Figure Description
[0064] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0065] Figure 1 A schematic diagram of an automatic inspection system architecture for the undercarriage of a monorail vehicle is provided in this application embodiment;
[0066] Figure 2 A flowchart illustrating an automatic inspection method for the undercarriage of a monorail vehicle, provided in an embodiment of this application;
[0067] Figure 3 A flowchart illustrating a method for generating inspection tasks provided in an embodiment of this application;
[0068] Figure 4 A flowchart illustrating a method for determining whether a vehicle's environment meets maintenance requirements, provided in an embodiment of this application.
[0069] Figure 5 This application provides a schematic diagram of the state transition of an inspection operation process.
[0070] Figure 6A schematic diagram of the structure of an automatic inspection device for the undercarriage of a monorail vehicle provided in this application embodiment;
[0071] Figure 7 This is a schematic diagram of the structure of an automatic inspection device for the undercarriage of a monorail vehicle, provided in an embodiment of this application.
[0072] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0073] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application.
[0074] In related technologies, the systems focus solely on the automatic inspection function of the robot itself. The allocation of inspection tasks relies heavily on human experience and judgment, making it difficult to intelligently prioritize tasks based on multi-dimensional data such as vehicle health status, maintenance cycles, and operational plans. This leads to unreasonable allocation of inspection resources and untimely response to critical vehicles. Furthermore, these systems lack deep integration with the depot's power supply monitoring system, five-prevention system, train control system, and signaling system. Key aspects such as power outage grounding, skirt opening and closing, and safety protection still require manual operation and confirmation, increasing the possibility of omissions. Additionally, when new high-priority vehicles enter the depot, the systems cannot dynamically adjust ongoing inspection tasks, lacking a priority preemption and resource reallocation mechanism, making it difficult to meet the depot's rapid response to sudden inspection needs. In summary, these technologies are insufficient in intelligent generation of inspection tasks, multi-system safety collaboration, and dynamic scheduling, making it difficult to achieve fully automated closed-loop management of monorail vehicle undercarriage inspections.
[0075] To address the aforementioned issues, this application provides an automatic inspection method, apparatus, and device for the undercarriage of a monorail vehicle. By acquiring the operating parameters of multiple vehicles and automatically generating priority-ranked inspection tasks based on a multi-dimensional evaluation model, the device automatically controls the skirt panel to open after environmental safety confirmation. Based on the standby position of the inspection robot and the parking position of the vehicle, the device automatically plans the inspection path and controls the inspection robot to perform undercarriage inspection according to the planned path. This achieves integrated processing of intelligent generation and priority ranking of inspection tasks, multi-system collaborative safety confirmation, and autonomous navigation inspection by the robot, thus solving the technical problem of low inspection efficiency in related technologies.
[0076] Optional, Figure 1 This is a schematic diagram of an automatic undercarriage inspection system for monorail vehicles, provided as an embodiment of this application. This automatic undercarriage inspection system for monorail vehicles is a computer device. Figure 1 In the above architecture, at least one of data acquisition device 101, processing device 102 and display device 103 is included.
[0077] It is understood that the structure illustrated in the embodiments of this application does not constitute a specific limitation on the architecture of the automatic inspection system under the monorail vehicle. In other feasible embodiments of this application, the above architecture may include more or fewer components than illustrated, or combine some components, or split some components, or arrange different components, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown can be implemented in hardware, software, or a combination of both.
[0078] In the specific implementation process, the data acquisition device 101 may include an input / output interface or a communication interface, and the data acquisition device 101 can be connected to the processing device through the input / output interface or the communication interface.
[0079] The processing device 102 can automatically generate priority inspection tasks by acquiring the operating parameters of multiple vehicles and based on a multi-dimensional evaluation model. After confirming environmental safety, it can automatically control the skirt to open and automatically plan the inspection path based on the standby position of the inspection robot and the parking position of the vehicle. It can control the inspection robot to perform under-vehicle inspection according to the planned path, thus realizing the integrated processing of intelligent generation and priority arrangement of inspection tasks, multi-system collaborative safety confirmation, and robot autonomous navigation inspection.
[0080] The display device 103 can also be a touch screen or the screen of a terminal device, used to receive user commands while displaying the above-mentioned content, so as to realize interaction with the user.
[0081] It should be understood that the aforementioned processing device can be implemented by a processor reading instructions from memory and executing those instructions, or it can be implemented by a chip circuit.
[0082] Furthermore, the network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.
[0083] Figure 2This is a flowchart illustrating an automatic inspection method for the undercarriage of a monorail vehicle, provided as an embodiment of this application. The execution entity of this embodiment can be... Figure 1 The processor 102 in the code can be specifically executed based on the actual application scenario. For example... Figure 2 As shown, the method may include:
[0084] S201. Obtain the operating parameters corresponding to multiple vehicles, and generate multiple inspection tasks arranged in sequence based on the operating parameters.
[0085] In this embodiment, multiple vehicles are parked in a monorail depot. The monorail depot is a base for the parking, inspection, and maintenance of monorail trains. Vehicles parked on each track of the depot straddle or are suspended from the track beams. The vehicles in this embodiment are monorail vehicles, with modular skirts installed on both sides. The skirts employ a fully enclosed design to cover key components of the running gear (such as bogies, running wheels, guide wheels, air springs, electrical boxes, etc.) inside the vehicle body.
[0086] In this embodiment, the inspection task can refer to a key undercarriage component inspection task automatically generated by the intelligent control system based on multi-dimensional operating parameters for monorail vehicles parked in a monorail depot. Specifically, the inspection task may include the inspection of key undercarriage components such as bogies, running wheels, guide wheels, air springs, and electrical boxes. Each inspection task corresponds to a vehicle to be inspected, and its priority level is determined based on the vehicle's comprehensive evaluation score. Different task processing methods can be applied to different priority levels.
[0087] For example, the highest priority can generate an emergency repair task and trigger a manual maintenance plan; the high priority can generate a key inspection task and use a human-machine collaborative approach for manual review; the medium priority can generate a standard intelligent inspection task and only manually review the machine's inspection faults; the low priority will not generate an inspection task. This application does not limit the specific task processing method corresponding to each priority level.
[0088] It should be noted that "arranged in order" means that multiple inspection tasks are arranged in order of execution from high to low according to their corresponding priority levels, with higher priority inspection tasks being executed first.
[0089] Optionally, operating parameters can refer to multidimensional data used to evaluate vehicle inspection priorities. Operating parameters may include, but are not limited to, the following data: train operation plans (including next-day deployment plans and same-day return plans) pushed by the Automatic Train Supervision (ATS), vehicle maintenance cycles, historical fault data, and real-time vehicle status data and fault data actively pushed by the Train Control and Management System (TCMS). This application embodiment does not limit the specific data source and data type of the operating parameters. The specific evaluation method and priority generation process for operating parameters will be discussed in Embodiment Two. Figure 3 Please provide a detailed explanation.
[0090] S202. During the sequential execution of inspection tasks, if it is determined that the environment in which the vehicle is located meets the maintenance requirements, control the opening of the side skirts of the vehicle corresponding to the current inspection task.
[0091] In this embodiment, the vehicle's environment can refer to the comprehensive environmental conditions surrounding the vehicle's parking location, including power supply safety, area lockdown, and surveillance coverage. Meeting maintenance requirements means that all of the above environmental conditions satisfy the safety prerequisites for the inspection operation.
[0092] In one possible implementation, the safety verification process of the vehicle's environment can be driven by a finite state machine (FSM). The entire inspection operation process can be discretized into multiple hierarchical safety state nodes, including system idle state, task ready state, environmental safe state, skirt open state, inspection operation state, task completion state, and system recovery state. Transitions between any two adjacent states must satisfy multi-system joint Boolean logic gating conditions. For example, the transition from the environmental safe state to the skirt open state must simultaneously satisfy: feedback from the monorail vehicle that the pantograph has been lowered, feedback from the power supply system that the power outage and grounding have been completed, feedback from the access control system that the personnel entrance to the target track has been locked, feedback from the video surveillance system that the monitoring target has been switched, and feedback from the robot that the LiDAR scanning operation area is free of obstacles and personnel. This application embodiment does not limit the specific gating conditions between each state node.
[0093] It should be noted that in the task-ready state, the system acquires data such as vehicle positioning status, vehicle movement status, track closure status, and robot health status pushed by the signal system. It then performs inspection priority assessment and work order generation, and executes parallel scheduling, assigning the target robot to the target track entrance to stand by. Only after the work order is generated and the robot is in position and ready, and all conditions are jointly confirmed and passed, can the system transition to the environmentally safe state. If an operation malfunctions or times out, the system will revert to the system idle state and lock.
[0094] In one possible implementation, the safety operations performed in a safe environment may include the following steps: Step 1, pantograph lowering. The intelligent control system requests pantograph lowering from the signaling system. After verifying the conditions (vehicle positioning, vehicle zero speed, etc.), the signaling system issues a pantograph lowering command to the TCMS. The TCMS disconnects the load, executes the pantograph lowering, and reports the completion status. It should be noted that, depending on the specific conditions of the section, the intelligent control system may also directly request pantograph lowering from the TCMS after the safety assessment is passed. Step 2, overhead contact line power outage and grounding. The intelligent control system sends an overhead contact line power outage request to the Power Supervisory Control And Data Acquisition (PSCADA). After the five-prevention system logic verification is passed, PSCADA sequentially executes the circuit breaker tripping, disconnecting switch tripping, and grounding switch closing operations, and reports the status. Step 3, the linkage video monitoring system switches to the target track camera. Step 4, the access control system locks the entrance to the work area. Step 5, the robot's LiDAR scans the work area to confirm that there are no obstacles or personnel. The system must jointly confirm the completion and absence of faults after reporting the operation status. Only then can the process proceed to the skirt opening state. If an operation malfunctions or times out, the process will revert to the task ready state and lock. This application does not limit this aspect.
[0095] In this embodiment, environmental safety verification is not performed sequentially, but rather in parallel based on a multi-system joint Boolean logic gating mechanism. The intelligent control system synchronously retrieves real-time status signals from the power supply system, access control system, video surveillance system, and inspection robot via a standardized communication interface, and inputs all signals to the logic verification unit for Boolean operations. Only when the five signals—power outage, contact wire disconnection, grounding device closure, access control blockage, and video surveillance switching—simultaneously meet the preset safety triggering conditions (i.e., the logical AND operation result is true) will the logic verification unit output a high-level permission signal, driving the state machine to transition from the environmental safety state to the skirt control state. If any signal fails to meet the standard, communication is interrupted, or verification fails, the logic verification unit immediately outputs a blocking signal and locks the current operation process.
[0096] It should be noted that in a safe environment, the digital twin base module can also correct the coordinates of inspection points based on the real-time twin model and the actual stopping deviation of the train, complete the full path pre-play in the virtual environment, verify the accessibility and collision-free nature of the points, and generate the optimal inspection path to send to the robot; if the pre-play fails, it will automatically re-plan.
[0097] During the operation of the digital twin foundation module, a dynamic weight adjustment mechanism and a time series anomaly prediction module can also be introduced. For each security check item in the multi-system joint Boolean logic gating condition, the system dynamically allocates the logical weight ratio of each check item based on the response delay distribution of historical operation statistics. At the same time, by collecting historical time series data of instruction responses from each subsystem, an anomaly prediction model is established. When the predicted probability of the current operation timeout exceeds a preset threshold, a state rollback mechanism is triggered in advance to reduce process interruptions.
[0098] In one possible implementation, the opening process of the skirt doors can be as follows: the intelligent control system sends a skirt door opening request through the signaling system; after the signaling system performs a safety verification, it issues an opening command to the TCMS; after the TCMS verifies the status of the battery, skirt system, etc., and passes the verification, it controls the opening of all the skirt doors on the train. It should be noted that, depending on the specific conditions of the depot, the intelligent control system can also directly request the TCMS to open the skirt doors after a safety assessment is passed. After all skirt doors are fully opened and locked, a joint confirmation is made, and the system transitions to an inspection operation state; if an opening abnormality occurs, the system reverts to an environmental safety state and locks itself. This application embodiment does not limit this process.
[0099] Optionally, if multiple inspection robots exist, after controlling the side skirts of the vehicle corresponding to the current inspection task to open, the following steps are taken:
[0100] According to the priority order of multiple inspection tasks, the corresponding inspection tasks are assigned to multiple inspection robots in turn, so as to control multiple inspection robots to perform vehicle maintenance at the same time.
[0101] In this application, in a scenario with multiple inspection robots, the inspection tasks are assigned to the robots in order of priority, thereby enabling parallel operation scheduling of multiple inspection robots. Compared with the serial inspection method, this method can maximize the parallel utilization of multiple inspection devices in the depot while meeting power supply safety constraints and operational resource constraints, significantly shortening the overall inspection cycle of multiple trains and improving the depot's operation and maintenance efficiency and train turnaround rate.
[0102] It should be noted that during parallel scheduling, a three-dimensional resource constraint model of power supply area-track-robot can be established to maximize the parallel operation efficiency of multiple robots while meeting power supply safety constraints. The scheduling results can be displayed in real time in the form of a Gantt chart, supporting manual intervention and adjustment. This application embodiment does not limit this aspect.
[0103] Optionally, it also includes:
[0104] During the vehicle inspection process, if a new vehicle enters the monorail depot, the priority level of the newly entered vehicle is obtained.
[0105] If the priority level of a newly entered monorail vehicle depot is higher than that of at least one vehicle being inspected by an inspection robot, the inspection robot corresponding to the vehicle with the lowest priority level is controlled to stop executing the current inspection task. Based on the standby position of the inspection robot and the parking position of the newly entered monorail vehicle depot, path planning is performed to obtain the adjusted movement trajectory of the inspection robot.
[0106] The inspection robot is controlled to inspect newly arrived monorail depot vehicles according to the adjusted movement trajectory, and the inspection results of the newly arrived monorail depot vehicles are obtained.
[0107] Here, in this application, during the vehicle inspection process, the inspection robot can sense in real time whether a new vehicle has entered the depot and obtain the priority level of the new vehicle. When the priority level of the newly entered vehicle is higher than that of a vehicle being inspected, the system automatically triggers a priority preemption mechanism, controls the inspection robot with the lowest priority level to stop its current inspection task, releases inspection resources, replans the path based on the robot's standby position and the new vehicle's parking position to adjust its movement trajectory, and controls the robot to turn and execute the inspection task of the new vehicle. Compared with the related technologies where inspection tasks cannot be dynamically adjusted once assigned, this application realizes the dynamic reallocation of inspection resources, ensures that high-priority emergency tasks can be responded to in a timely manner, and improves the depot's response speed and scheduling flexibility to sudden inspection needs.
[0108] It should be noted that when a high-priority task arrives, the system automatically detects available resources; if no resources are available, the lowest-priority non-critical task is paused, resources are released and allocated to high-priority tasks, triggering a global resource reallocation and automatically rescheduling the execution time of the paused tasks. This application does not limit this aspect.
[0109] S203. Based on the standby position of the inspection robot and the parking position of the vehicle corresponding to the current inspection task, path planning is performed to obtain the movement trajectory of the inspection robot.
[0110] Optionally, the inspection robot can refer to an intelligent inspection device deployed in a monorail depot for automated data collection of key components under the monorail vehicle. The inspection robot may include, but is not limited to, a mobile platform, a multi-sensor fusion sensing system, a multi-axis robotic arm, an autonomous navigation system, and a safety protection system. The inspection robot communicates bidirectionally with the intelligent control system via the depot's wireless network, receives control commands from the intelligent control system, and reports its status. It can autonomously navigate to the target train to complete the data collection of the undercarriage components. This application does not limit this aspect.
[0111] Optionally, in the environmental perception stage of the inspection robot, in addition to lidar, the multi-sensor fusion perception system can also integrate infrared thermal imaging sensors and ultrasonic sensors to construct a multimodal environmental perception model. When the system detects a personnel intrusion signal, it calls a trajectory prediction algorithm based on deep learning to predict the movement path within a preset time period based on the personnel's current movement direction and speed characteristics, and then links the access control system to generate a dynamic blocking strategy.
[0112] Optionally, the standby position can refer to the initial position where the inspection robot is parked when not performing an inspection task, such as a charging dock or a designated standby area. The parking position refers to the track number and parking coordinates of the vehicle corresponding to the current inspection task within the monorail depot. This information can be pushed by the depot's signaling system or supplemented with high-precision location data by the depot's positioning system. The movement trajectory refers to the optimal path from the inspection robot's standby position to the designated work area under the target vehicle.
[0113] Optionally, before path planning is executed, the digital twin base module can call the augmented reality-assisted verification interface to visualize and overlay the virtual inspection path with the actual structure under the vehicle, allowing maintenance personnel to manually review and fine-tune the coordinates of abnormal points via touch devices. At the same time, the digital twin base module periodically calls the historical defect hotspot area analysis function to statistically analyze the distribution of high-frequency abnormal points in multiple inspection data, and dynamically increase the density of detection points in the corresponding areas accordingly, optimizing the robot's inspection energy consumption and coverage.
[0114] In one possible implementation, the path planning process can be based on digital twin technology. Before each task execution, the robot performs a virtual rehearsal in the digital twin environment, dynamically generating the optimal inspection path based on the actual parking deviation of the train (including parking alignment errors, etc.), and verifying the accessibility and collision-free nature of the inspection points. During the inspection, the twin model is updated in real time with robot perception data, achieving a two-way physical-digital mapping. After accumulating multiple inspection data, the twin model can automatically identify high-frequency abnormal areas and dynamically adjust the density of inspection points. This application does not limit this aspect.
[0115] It should be noted that the digital twin base module can integrate signal system location data, positioning system precise coordinates, historical parking deviation statistics, and robot real-time perception data to provide visualization and data support for path planning, task simulation, and status monitoring.
[0116] S204. Control the inspection robot to inspect the vehicle corresponding to the current inspection task according to the movement trajectory, and obtain the inspection result of the vehicle corresponding to the current inspection task.
[0117] Optionally, the inspection results may refer to the detection data obtained by the inspection robot after entering the underside of the vehicle along the planned path and collecting multi-sensor data on key components such as the vehicle's bogie, running wheels, guide wheels, air springs, and electrical boxes. This data includes image data, temperature data, and geometric dimension data. The inspection data is transmitted back to the edge computing gateway cluster in real time for preprocessing and lightweight defect handling. This application embodiment does not limit the specific data types included in the inspection results.
[0118] It should be noted that during the inspection operation, the state machine can monitor the status of the entire system, including the robot, power supply, and protection systems, in real time. If an anomaly occurs, it can immediately trigger a shutdown and return to a safe lock state. Furthermore, the safety management module can integrate a dynamic safety fence mechanism linking the robot and the five-prevention system: a 3D point cloud map of the work area is constructed in real time using the robot's LiDAR, dynamically defining the virtual safety fence boundary of the work area, forming a triple-linked protection system with the access control system and video surveillance system; when personnel are detected intruding into the virtual safety fence boundary, the PSCADA / five-prevention system is linked to maintain the power-off and grounded state of the work area and performs a graded safety response to the intrusion event. This application embodiment does not limit this aspect.
[0119] In one possible implementation, after the inspection is completed, the robot autonomously returns to the charging dock along the planned path; the edge computing gateway cluster verifies the inspection data, initially generates a defect classification result, and the intelligent control system generates a fault review work order. Then, the system enters a recovery state: the intelligent control system sends a skirt door closing command to the TCMS via the signal system, confirming that all doors are closed; the intelligent control system sends a contact rail power supply request to the PSCADA. The intelligent control system confirms that the inspection robot has left the work area and that all skirt doors are closed. After the power supply operation passes the logic verification by the five-prevention system, the PSCADA sequentially executes the grounding switch opening, isolating switch closing, and circuit breaker closing operations to restore contact rail power supply. A complete inspection report is generated, and all operation records, equipment status, inspection data, and videos are automatically archived, updating the train health record. The system returns to an idle state, waiting for the next task. This embodiment of the application does not limit this.
[0120] This application provides an automatic inspection method for the undercarriage of a monorail vehicle. By acquiring the operating parameters of multiple vehicles and automatically generating multiple sequentially arranged inspection tasks based on these parameters, it replaces the traditional method of task allocation relying on manual experience and paper records. This method achieves intelligent generation and prioritization of inspection tasks, improving the scientific nature and accuracy of task allocation. During the sequential execution of inspection tasks, the skirt panels are automatically opened after confirming that the vehicle's environment meets the maintenance requirements, reducing the manual operation of repeatedly opening and closing the skirt panels. Based on the standby position of the inspection robot and the parking position of the vehicle, the method automatically plans the path to obtain the movement trajectory and controls the inspection robot to perform inspections according to the movement trajectory. This enables the inspection robot to autonomously navigate and inspect the undercarriage components, improving inspection efficiency and detection accuracy.
[0121] exist Figure 2 Based on the embodiments shown, the following, in conjunction with Figure 3 The method for obtaining the operating parameters of multiple vehicles and generating multiple sequentially arranged inspection tasks based on the operating parameters in the above-mentioned automatic inspection method for the undercarriage of monorail vehicles is explained in detail.
[0122] Figure 3 Please refer to the flowchart illustrating a method for generating inspection tasks provided in this application embodiment. Figure 3 ,include:
[0123] S301. For the operating factors of multiple operating dimensions included in the operating parameters, obtain the first evaluation score corresponding to each operating factor under each operating dimension.
[0124] In one possible implementation, the operational dimensions may include, but are not limited to: next-day online operation priority, vehicle health status priority, maintenance cycle compliance priority, and same-day return-to-warehouse operation window priority. This application's embodiments do not limit this.
[0125] For example, the next-day online operation priority can include multiple operational factors, such as the online route level score (first trip / peak route score is the highest), the next-day operating mileage intensity score, and the operational route / route importance score. The vehicle health status priority can include multiple operational factors, such as the TCMS real-time warning status score, the basic score of fault records within the statistical period, and the basic score of historical fault recurrence probability. The maintenance cycle compliance priority can include multiple operational factors, such as the remaining time of the maintenance cycle and the probability level of overdue maintenance. The same-day return-to-depot operation window priority can include multiple operational factors, such as the time of vehicle return to the depot, the available operation time at the depot, and the operation conditions of the parking space. This application embodiment does not limit the specific operational factors under each operational dimension.
[0126] It should be noted that the first evaluation score for each operating factor can range from [0, 100], and the specific score setting is determined based on the vehicle's operating conditions. This application does not limit this.
[0127] In one possible implementation, the calculation model for the comprehensive priority score of vehicle inspection (i.e., the target evaluation score) may include the following formula. This application does not limit this specific implementation.
[0128] The formula for calculating the overall priority score R for vehicle inspection is:
[0129]
[0130] Where R is the overall priority score for vehicle inspection, the higher the score, the higher the inspection priority; Let be the weight coefficient of the i-th running dimension, and the sum of the weight coefficients of all running dimensions is 1; This is the second evaluation score for the i-th operational dimension.
[0131] Second evaluation score for each operational dimension The calculation formula is:
[0132]
[0133] in, Let be the weight coefficient of the j-th running factor under the i-th running dimension, and the sum of the weight coefficients of all running factors is 1; The first evaluation score of the j-th operational factor under the i-th operational dimension; The correction coefficient is set for the j-th operating factor under the i-th operating dimension. Only the fault attenuation correction coefficient is set for operating factors involving historical faults.
[0134] S302. For each operational dimension, the first evaluation scores corresponding to multiple operational factors are weighted and summed to obtain the second evaluation score corresponding to the operational dimension.
[0135] Optionally, a weighted sum is performed on the first evaluation scores corresponding to multiple operating factors to obtain a second evaluation score corresponding to the operating dimension, including:
[0136] Based on the occurrence time of historical operational failures corresponding to the operational factors, the attenuation coefficient corresponding to the operational factor is determined; the magnitude of the attenuation coefficient is negatively correlated with the duration of the occurrence time of historical operational failures corresponding to the operational factors.
[0137] The second evaluation score is obtained by weighted summing the products of the first evaluation score and the corresponding attenuation coefficient for each operating factor.
[0138] Here, when weighting and summing the first evaluation scores of the operating factors, this application introduces an attenuation coefficient based on the occurrence time of historical operating faults. By multiplying the first evaluation score by the corresponding attenuation coefficient and then performing a weighted summation, the impact of recently occurring faults on the inspection priority assessment is given a greater weight, while the impact of faults that occurred earlier and have not recurred for a long time is gradually weakened. Compared with the method of directly using historical statistical data as the assessment basis, the assessment results after introducing the attenuation coefficient can better reflect the timeliness characteristics of faults, making the allocation of inspection resources closer to the actual operation and maintenance needs of vehicles and improving the accuracy of inspection priority assessment.
[0139] Specifically, the control system extracts the occurrence timestamps of the corresponding fault types for the target operating factors from the historical database and calculates the time difference between these timestamps and the current scoring calculation date. This time difference is then substituted into a preset exponential decay function to obtain the corresponding decay correction coefficient. This coefficient characterizes the degree to which the impact of the fault weakens over time. The control system multiplies this coefficient by the first evaluation score of each operating factor and substitutes the corrected score into the weighted summation formula to participate in the calculation of the second evaluation score.
[0140] In one possible implementation, the attenuation coefficient can adopt an exponential attenuation model, where the impact of the fault weakens nonlinearly over time.
[0141] For example, attenuation coefficient It can be represented as:
[0142]
[0143] in, λ is the historical fault attenuation coefficient, which is closer to 1 the more recent the fault occurred; λ is the attenuation rate factor, the specific value of which can be calibrated according to the line fault recurrence rate; t is the number of natural days from the day the fault occurred to the day of scoring.
[0144] It should be noted that, for the basic score of fault records within the statistical period under the vehicle health status priority dimension, the attenuation coefficient can be the arithmetic mean of the attenuation coefficients of all faults within the statistical period (the mean is taken for multi-fault scenarios); for the basic score of historical fault recurrence probability, the attenuation coefficient can be the attenuation coefficient corresponding to the latest fault among the recurring faults of the same type (only the attenuation value of the latest fault is taken, and old faults are not repeatedly added). This application embodiment does not limit this.
[0145] In one possible implementation, the sum of the weight coefficients of each operating factor is 1. The sum of the weight coefficients of each operating dimension is also 1. The weights and scores for each dimension are determined based on the vehicle's operating conditions. This application does not limit this aspect.
[0146] S303. The second evaluation scores corresponding to multiple operational dimensions are weighted and summed to obtain the target evaluation score for each vehicle.
[0147] In one possible implementation, the target evaluation score (i.e., the comprehensive priority score for vehicle inspection) can range from [0, 100], with higher scores indicating higher inspection priority.
[0148] For example, taking a scenario with four operational dimensions, the specific formula for calculating the target evaluation score R is as follows:
[0149]
[0150]
[0151]
[0152]
[0153]
[0154] in, This is the second evaluation score in the priority dimension of launching operations the following day. It is the second evaluation score in the vehicle health status priority dimension (including historical fault attenuation correction). This is the second evaluation score in the compliance priority dimension of the maintenance cycle. This is the second evaluation score in the priority dimension of the daily warehouse return operation window.
[0155] in, To achieve the required score for online route rating, The intensity score for the next day's running mileage. Score the importance of the operating routes / routes; The score is assigned to the real-time alert status of TCMS. This serves as the base score for fault records within the statistical period. The base score for the probability of historical failure recurrence; Score based on the remaining time of the inspection cycle. Score the likelihood of the repair process exceeding the deadline; Points are awarded based on the time the vehicle returns to the warehouse. Score based on available work hours during warehouse shutdown. Scoring is given based on the conditions for parking space operations.
[0156] in, The weighting coefficient for the next day's launch and operation priority dimension. The weighting coefficients for the vehicle health status priority dimension. This refers to the weighting coefficient for the compliance priority dimension of the maintenance cycle. This is the weighting coefficient for the priority dimension of the daily return-to-warehouse operation window, and the sum of the weighting coefficients for each operation dimension is 1.
[0157] in, , , These are the weighting coefficients for the following day's operational priority dimension: the score of the route level, the score of the mileage intensity, and the score of the importance of the operational route / routes. , , These are the weighting coefficients for the TCMS real-time warning status score, the basic score of fault records within the statistical period, and the basic score of historical fault recurrence probability under the vehicle health status priority dimension. , The weighting coefficients are the remaining time score of the maintenance cycle and the probability level score of maintenance overdue, respectively, under the maintenance cycle compliance priority dimension. , , These are the weighting coefficients for vehicle return time (early or late), available parking time, and parking space conditions, under the daily return operation window priority dimension. The sum of the weighting coefficients for each operation dimension is 1. The weighting coefficients for each dimension are determined based on vehicle operation conditions.
[0158] It should be noted that the specific operating dimensions and operating factors in the above formulas are only illustrative examples. In practice, the operating dimensions and operating factors can be increased or decreased according to the characteristics of the vehicle type and route. This application embodiment does not limit this.
[0159] It should be noted that the decay coefficient is applied to the base score of fault records within the statistical period under the vehicle health status priority dimension. It can be expressed as the arithmetic mean of the attenuation coefficients of all faults within the statistical period (the mean is taken in multi-fault scenarios); for the basic score of the probability of historical fault recurrence, its attenuation coefficient It can be expressed as the attenuation coefficient corresponding to the latest recurring fault among similar recurring faults (only the attenuation value of the latest fault is taken, and old faults are not repeatedly added). The embodiments of this application do not limit this.
[0160] It should be noted that the weights and scores for each dimension are determined based on the vehicle's operating conditions, and mandatory constraints can be set. For example, if the maintenance cycle compliance priority score is zero, the priority score cannot be lower than level B; if the vehicle health status priority score is zero, the priority score cannot be lower than level S. This application does not impose such limitations.
[0161] S304. Determine the priority order of the inspection tasks corresponding to each vehicle according to the pre-set mapping relationship between multiple score ranges and multiple priority levels.
[0162] In one possible implementation, priority scoring can be used to set S-level (highest priority), A-level (highest priority), B-level (medium priority), and C-level (lowest priority). For example, S-level can be the highest score range, A-level the higher score range, B-level the medium score range, and C-level the lower score range; the specific scores can be adjusted according to the application. This application does not limit this approach.
[0163] For example, different priorities can correspond to different task processing methods: Level S generates emergency repair tasks and prohibits intelligent inspections, triggering manual maintenance plans; Level A generates key inspection tasks, adopting human-machine collaboration, with manual key checks; Level B generates standard intelligent inspection tasks, with manual checks only on machine inspection faults; Level C does not generate inspection tasks. This application embodiment does not limit this.
[0164] It should be noted that the scoring model can employ a self-learning optimization mechanism, periodically adjusting the weight coefficients of each dimension and the historical fault weight factors using a gradient descent algorithm based on historical inspection results and actual fault data, thereby continuously improving the accuracy of the scoring model. This application does not limit this aspect.
[0165] Optionally, in the vehicle inspection priority quantitative scoring model, different decay rate factors are preset for different types of historical operational faults to distinguish the urgency of different faults to operational safety. During the scoring calculation process, the system calls the external environmental factor assessment module in real time. When the environmental parameters indicate abnormal weather such as rain or snow or line congestion, the weight coefficient of the corresponding running component health status dimension is automatically increased to adapt the inspection plan to the actual operating conditions.
[0166] Optionally, the operating parameters corresponding to multiple vehicles are obtained, and multiple sequentially arranged inspection tasks are generated based on the operating parameters, including:
[0167] For the operating factors of multiple operating dimensions included in the operating parameters, obtain the first evaluation score corresponding to each operating factor under each operating dimension;
[0168] For each operational dimension, the weighted sum of the first evaluation scores corresponding to multiple operational factors is used to obtain the second evaluation score corresponding to the operational dimension.
[0169] The second evaluation scores corresponding to multiple operational dimensions are weighted and summed to obtain the target evaluation score for each vehicle.
[0170] Based on the pre-defined mapping relationship between multiple score ranges and multiple priority levels, the priority order of the inspection tasks corresponding to each vehicle is determined.
[0171] Here, this application decomposes the operating parameters into multiple operating dimensions and operating factors under each dimension, obtains the first evaluation score corresponding to each operating factor, and obtains the second evaluation score corresponding to the operating dimension and the target evaluation score corresponding to the vehicle through a two-level weighted summation method. The process of evaluating the inspection priority is structured into a multi-level, multi-dimensional quantitative evaluation system. Compared with the traditional method of sorting inspection tasks based on manual experience, it can comprehensively evaluate information from multiple dimensions such as vehicle online operation plan, health status, maintenance cycle, and return-to-warehouse operation window, avoiding the one-sidedness of single-dimensional evaluation. At the same time, by pre-setting the mapping relationship between the score range and the priority level, the target evaluation score is mapped to a clear priority order, which improves the rationality and interpretability of the inspection task allocation.
[0172] Based on any of the above embodiments, the following, in conjunction with Figure 4 The method for determining that the environment in which the vehicle is located meets the maintenance requirements in the above-mentioned automatic inspection method for the undercarriage of monorail vehicles is explained in detail.
[0173] Figure 4 This is a flowchart illustrating a method for determining whether a vehicle's environment meets maintenance requirements, as provided in an embodiment of this application. Please refer to... Figure 4 ,include:
[0174] S401. Obtain the environmental parameters of the environment in which the vehicle corresponding to the current inspection task is located.
[0175] Optionally, the environmental parameters include at least the power outage status, the contact network disconnection status, the grounding device closure status, the access control blockage status, and the video surveillance switching status.
[0176] In one possible implementation, obtaining environmental parameters may involve the coordinated operation of multiple existing business systems within the vehicle depot. For example:
[0177] The power outage state is obtained by the vehicle performing a pantograph lowering operation. The intelligent control system requests pantograph lowering from the signal system. After verifying the conditions (vehicle positioning, vehicle zero speed, etc.), the signal system issues a pantograph lowering command to the TCMS. The TCMS disconnects the load, executes the pantograph lowering, and reports the completion status. This application embodiment does not limit this.
[0178] The contact wire disconnection status is obtained by PSCADA executing a circuit breaker tripping operation. The intelligent control system sends a contact rail power outage request to PSCADA. After the logic verification by the five-prevention system is passed, PSCADA executes the circuit breaker tripping operation and feeds back the status. This application embodiment does not limit this.
[0179] The grounding device closing status is fed back by PSCADA after the grounding switch closing operation is completed.
[0180] The access control status can be obtained through the depot's access control system. The access control system communicates two-way with the intelligent control system, which can automatically lock personnel entrances in the inspection area and prevent unauthorized personnel from entering.
[0181] The video surveillance status can be obtained through the depot's video surveillance system. The video surveillance system communicates bidirectionally with the intelligent control system and can automatically switch to the inspection area cameras to monitor and record inspection videos in real time.
[0182] It should be noted that the above methods for obtaining environmental parameters are merely illustrative examples. In practice, environmental parameters can also be obtained through other systems or sensors, and this application does not limit this.
[0183] S402. Determine that the vehicle's environment meets the maintenance requirements.
[0184] When the power outage status indicates that the vehicle corresponding to the inspection task has been de-energized, the contact wire disconnection status indicates that the contact wire of the track corresponding to the inspection task has been disconnected, the grounding device closed status indicates that the grounding device of the track corresponding to the inspection task has been closed, the access control closed status indicates that the access control of the inspection task has been closed, and the video monitoring switching status indicates that the monitoring video of the location of the vehicle corresponding to the inspection task has been switched, it is determined that the environment of the vehicle meets the maintenance requirements.
[0185] In one possible implementation, the state machine can record information such as the time of each state transition, triggering conditions, participating systems, and confirmation results in real time, and use a hash chain storage structure to form an immutable operation sequence log chain for later review.
[0186] Optionally, in the data storage and transmission stage, the hash chain storage structure can be upgraded to a blockchain multi-node consensus mechanism. Log data is synchronized and cross-verified through intelligent control system nodes across vehicle depots, improving the credibility of operation records. In the data processing of the edge computing gateway cluster, a data encryption module is integrated, and the national cryptographic SM4 algorithm is used to encrypt sensitive image data and status data in the inspection process in real time to prevent data from being stolen during transmission and storage.
[0187] Optionally, determine that the vehicle's environment meets the maintenance requirements, including:
[0188] Obtain the environmental parameters of the environment in which the vehicle corresponding to the current inspection task is located; the environmental parameters should include at least the power outage status, the contact wire disconnection status, the grounding device closure status, the access control blockage status, and the video surveillance switching status;
[0189] When the power outage status indicates that the vehicle corresponding to the inspection task has been de-energized, the contact wire disconnection status indicates that the contact wire of the track corresponding to the inspection task has been disconnected, the grounding device closed status indicates that the grounding device of the track corresponding to the inspection task has been closed, the access control closed status indicates that the access control of the inspection task has been closed, and the video monitoring switching status indicates that the monitoring video of the location of the vehicle corresponding to the inspection task has been switched, it is determined that the environment of the vehicle meets the maintenance requirements.
[0190] Here, this application refines the safety confirmation of the vehicle's environment into five environmental parameters: power outage state, contact network disconnection state, grounding device closed state, access control blockage state, and video surveillance switching state. It requires that all five environmental parameters meet the corresponding safety conditions before the environment can be confirmed as meeting the maintenance requirements and the skirt panel can be controlled to open. Compared with related technologies where safety protection mainly relies on the robot's own sensors or manual item-by-item inspection, this application obtains environmental parameters through multi-system linkage and performs joint confirmation. It incorporates the safety status of the power supply system, access control system, and video surveillance system into a unified judgment condition, realizing the automation of multi-system collaborative safety verification before the skirt panel is opened, and improving the safety of inspection operations.
[0191] Figure 5 This is a schematic diagram of the state transition of an inspection operation process provided in an embodiment of this application. Figure 5 The transition relationships between various safety states and the anomaly rollback paths in the entire inspection process driven by a finite state machine are demonstrated.
[0192] Below, in conjunction with Figure 5 The process of transitioning between various safety states is explained in detail.
[0193] like Figure 5 As shown, the entire inspection process is discretized into seven progressively higher safety states, namely: S0 system idle state, S1 task ready state, S2 environmental safe state, S3 skirt open state, S4 robot operating state, S5 task completed state, and S6 system restored state. Each safety state transitions forward sequentially according to a preset order. If any state becomes abnormal, it automatically reverts to the previous safety state and locks the workflow. This application does not limit the method of dividing the safety states; different vehicle depots can add or remove state nodes according to the actual workflow.
[0194] The S0 system is in an idle state, with no inspection tasks and all subsystems in standby mode.
[0195] In one possible implementation, when the system is in the S0 system idle state, if it receives train entry information pushed by the signal system, it triggers a state transition to the S1 task ready state; if it determines that there is no inspection work order after receiving the train entry information, the system remains in the S0 system idle state. This application embodiment does not limit this.
[0196] S1 is the task-ready state, which includes the acquisition and confirmation of data such as vehicle positioning status, vehicle movement status, track closure status, and robot health status.
[0197] In one possible implementation, when the system is in the S1 task-ready state, it acquires data such as vehicle positioning status, vehicle movement status, track closure status, and robot health status pushed by the signal system. It then performs inspection priority assessment and work order generation, and executes parallel scheduling, assigning the target robot to the target track entrance to wait. After the target robot passes its self-check, it proceeds to the target track entrance to wait and reports readiness. Once the work order is generated and the robot is in position, and all conditions are jointly confirmed, the system transitions to the S2 environment-safe state. If an abnormality occurs while in the S1 task-ready state, the system reverts to the S0 system-idle state and locks the workflow. This application's embodiments do not limit this aspect.
[0198] S2 environmental safety state includes the execution and confirmation of safety operations such as power outage five-prevention verification, contact network disconnection, grounding device closure, access control blockade, and video surveillance target switching.
[0199] In one possible implementation, when the system is in the S2 safe state, the intelligent control system, in coordination with multiple related subsystems such as the power supply system, access control system, video surveillance system, and inspection robot, sequentially performs safety operations including lowering the pantograph, disconnecting and grounding the overhead contact line, switching the video surveillance to the target track camera, locking the entrance to the work area via the access control system, and scanning the work area with the robot's LiDAR to confirm the absence of obstacles and personnel. After the vehicle and the coordinated systems are all in a safe state, each system reports back the work status, jointly confirming completion and no faults, and then transitions to the S3 skirt panel opening state. If an abnormality occurs while in the S2 safe state, the system reverts to the S1 task-ready state and locks the work process. This application embodiment does not limit this.
[0200] S3 Skirt Opening State includes the execution and confirmation of opening and locking operations of the skirt doors on monorail vehicles.
[0201] In one possible implementation, when the system is in the S3 skirt opening state, the intelligent control system sends a skirt door opening command to the TCMS via the signal system. After the TCMS verifies the status of the battery, skirt system, etc., it controls the opening of all the train's skirt doors. It should be noted that, depending on the specific conditions of the depot, the intelligent control system can also directly request the TCMS to open the skirt doors after a safety assessment is passed. If the skirt doors open normally (i.e., all skirt doors are fully opened and locked), and after joint confirmation that there are no errors, the system transitions to the S4 robot operation state. If an abnormality occurs while in the S3 skirt opening state, the system reverts to the S2 environmental safety state and locks the operation process. This application embodiment does not limit this.
[0202] The S4 robot's operational state includes the inspection robot performing inspection tasks according to a preset path and uploading inspection data.
[0203] In one possible implementation, when the system is in the S4 robot operation state, the inspection robot enters the undercarriage along the planned path and performs multi-sensor data collection on key components such as the bogie, running wheels, guide wheels, air springs, and electrical boxes. The data is transmitted back to the edge computing gateway cluster in real time. During the inspection operation, the state machine monitors the status of the entire system, including the robot, power supply, and protection systems, in real time. Upon completion of the inspection operation, i.e., data collection at all inspection points is complete, the robot returns to the track entrance, and after joint confirmation, transitions to the S5 task completion state. If an abnormality occurs while in the S4 robot operation state, the system immediately triggers a shutdown and reverts to the S3 skirt opening state, locking the operation process. This application embodiment does not limit the specific components to be inspected.
[0204] The S5 task completion status includes feedback that the inspection robot has returned to its original position and that the detection data has been uploaded.
[0205] In one possible implementation, when the system is in the S5 task completion state, the robot autonomously returns to the charging dock according to the planned path; the edge computing gateway cluster completes the inspection data verification, initially generates defect classification results, and the intelligent management and control system generates a fault review work order. After the robot returns to its position and the data is uploaded, it is jointly confirmed and transferred to the S6 system recovery state. If an abnormality occurs while in the S5 task completion state, the system reverts to the previously confirmed safe state and locks the operation process. This application embodiment does not limit this.
[0206] The S6 system recovery state includes the execution and confirmation of recovery operations such as closing the skirt door, passing the five-proof power-on verification, disconnecting the grounding device, and closing the contact wire.
[0207] In one possible implementation, when the system is in the S6 system recovery state, the intelligent control system sends a skirt door closing command to the TCMS via the signal system to confirm that all doors are closed. The intelligent control system sends a contact rail power supply request to the PSCADA. After confirming that the inspection robot has left the work area and that all skirt doors are closed, and after the power supply operation has passed the logic verification by the five-prevention system, the PSCADA sequentially executes the grounding switch opening, isolating switch closing, and circuit breaker closing operations to restore contact rail power supply. After the skirt doors are closed and the collaborative system has recovered, a complete inspection report is generated, all operation records, equipment status, inspection data, and videos are automatically archived, the train health record is updated, and the system returns to the S0 system idle state, waiting for the next task. This application embodiment does not limit this.
[0208] It should be noted that the transition process between the above-mentioned security states is based on verification using multi-system joint Boolean logic gating conditions. If any subsystem reports a timeout, state anomaly, or instruction error, the current state transition is immediately terminated, and the system automatically rolls back to the previously confirmed security state, locking the entire workflow until the anomaly is resolved and authorization is granted. The state machine records the time, triggering conditions, participating systems, and confirmation results of each state transition in real time, and uses a hash chain storage structure to form an immutable operation sequence log chain for later review. This application does not limit this aspect.
[0209] It should be noted that, Figure 5 The transition relationships between various safety states are merely illustrative. The state nodes of the finite state machine can be added or removed according to the operational processes of different vehicle depots. For example, the video access control linkage can be split into independent state nodes, and the Boolean logic gating conditions between various safety states can be flexibly configured according to the security level. This application does not limit this aspect.
[0210] Figure 6 This is a schematic diagram of an automatic undercarriage inspection device for a monorail vehicle, provided as an embodiment of this application. Please refer to... Figure 6 The automatic undercarriage inspection device 600 for monorail vehicles includes an inspection task generation module 601, a control module 602, a path planning module 603, and an inspection execution module 604, wherein:
[0211] The inspection task generation module 601 is used to obtain the operating parameters of multiple vehicles and generate multiple inspection tasks arranged in sequence based on the operating parameters; multiple vehicles are parked in the monorail vehicle depot.
[0212] The control module 602 is used to control the opening of the side skirts of the vehicle corresponding to the current inspection task when the environment of the vehicle meets the maintenance requirements during the sequential execution of inspection tasks.
[0213] The path planning module 603 is used to perform path planning based on the standby position of the inspection robot and the parking position of the vehicle corresponding to the current inspection task, so as to obtain the movement trajectory of the inspection robot.
[0214] The inspection execution module 604 is used to control the inspection robot to inspect the vehicle corresponding to the current inspection task according to the movement trajectory, and obtain the inspection result of the vehicle corresponding to the current inspection task.
[0215] Optionally, the inspection task generation module 601 is specifically used for:
[0216] For the operating factors of multiple operating dimensions included in the operating parameters, obtain the first evaluation score corresponding to each operating factor under each operating dimension;
[0217] For each operational dimension, the weighted sum of the first evaluation scores corresponding to multiple operational factors is used to obtain the second evaluation score corresponding to the operational dimension.
[0218] The second evaluation scores corresponding to multiple operational dimensions are weighted and summed to obtain the target evaluation score for each vehicle.
[0219] Based on the pre-defined mapping relationship between multiple score ranges and multiple priority levels, the priority order of the inspection tasks corresponding to each vehicle is determined.
[0220] Optionally, the inspection task generation module 601 is also specifically used for:
[0221] If multiple inspection robots exist, after controlling the side skirts of the vehicle corresponding to the current inspection task to open, the following will be included:
[0222] According to the priority order of multiple inspection tasks, the corresponding inspection tasks are assigned to multiple inspection robots in turn, so as to control multiple inspection robots to perform vehicle maintenance at the same time.
[0223] Optionally, the inspection task generation module 601 is also specifically used for:
[0224] During the vehicle inspection process, if a new vehicle enters the monorail depot, the priority level of the newly entered vehicle is obtained.
[0225] If the priority level of a newly entered monorail vehicle depot is higher than that of at least one vehicle being inspected by an inspection robot, the inspection robot corresponding to the vehicle with the lowest priority level is controlled to stop executing the current inspection task. Based on the standby position of the inspection robot and the parking position of the newly entered monorail vehicle depot, path planning is performed to obtain the adjusted movement trajectory of the inspection robot.
[0226] The inspection robot is controlled to inspect newly arrived monorail depot vehicles according to the adjusted movement trajectory, and the inspection results of the newly arrived monorail depot vehicles are obtained.
[0227] Optionally, the inspection task generation module 601 is also specifically used for:
[0228] Based on the occurrence time of historical operational failures corresponding to the operational factors, the attenuation coefficient corresponding to the operational factor is determined; the magnitude of the attenuation coefficient is negatively correlated with the duration of the occurrence time of historical operational failures corresponding to the operational factors.
[0229] The second evaluation score is obtained by weighted summing the products of the first evaluation score and the corresponding attenuation coefficient for each operating factor.
[0230] Optionally, the control module 602 is specifically used for:
[0231] Obtain the environmental parameters of the environment in which the vehicle corresponding to the current inspection task is located; the environmental parameters should include at least the power outage status, the contact wire disconnection status, the grounding device closure status, the access control blockage status, and the video surveillance switching status;
[0232] When the power outage status indicates that the vehicle corresponding to the inspection task has been de-energized, the contact wire disconnection status indicates that the contact wire of the track corresponding to the inspection task has been disconnected, the grounding device closed status indicates that the grounding device of the track corresponding to the inspection task has been closed, the access control closed status indicates that the access control of the inspection task has been closed, and the video monitoring switching status indicates that the monitoring video of the location of the vehicle corresponding to the inspection task has been switched, it is determined that the environment of the vehicle meets the maintenance requirements.
[0233] This embodiment provides an automatic inspection device for the undercarriage of a monorail vehicle, which can execute the method provided in the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.
[0234] Figure 7 This is a schematic diagram of an automatic undercarriage inspection device for a monorail vehicle, provided as an embodiment of this application. Please refer to... Figure 7 The diagram illustrates a structural schematic of an automatic inspection device 700 for the undercarriage of a monorail vehicle suitable for implementing this embodiment. The automatic inspection device 700 for the undercarriage of a monorail vehicle may include, but is not limited to, mobile terminals such as mobile phones, laptops, and tablet computers (Portable Android Devices, PADs), as well as fixed terminals such as digital TVs and desktop computers. Figure 7 The illustrated automatic inspection device 700 for the undercarriage of a monorail vehicle is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0235] like Figure 7 As shown, the automatic inspection device 700 for the undercarriage of a monorail vehicle may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the automatic inspection device 700. The processing unit 701, the ROM 702, and the RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.
[0236] Typically, the following devices can be connected to the I / O interface 705: input devices 706 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 707 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 708 including, for example, magnetic tape, hard disk, etc.; and communication devices 709. The communication device 709 allows the monorail vehicle undercarriage automatic inspection equipment 700 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An automated inspection system 700 for the undercarriage of a monorail vehicle is shown, but it should be understood that implementation of or possession of all the shown devices is not required. More or fewer devices may be implemented alternatively.
[0237] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 709, or installed from storage device 708, or installed from read-only memory 702. When the computer program is executed by processing device 701, it performs the functions defined in the methods of embodiments of this application.
[0238] It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.
[0239] The aforementioned computer-readable medium may be included in the aforementioned automatic inspection equipment for the undercarriage of the monorail vehicle; or it may exist independently and not be installed in the automatic inspection equipment for the undercarriage of the monorail vehicle.
[0240] The aforementioned computer-readable medium carries one or more programs, which, when executed by the automatic inspection equipment under the monorail vehicle, cause the automatic inspection equipment under the monorail vehicle to perform the method shown in the above embodiments.
[0241] This application provides a computer-readable storage medium storing computer-executable instructions. When a processor executes the computer-executable instructions, it implements various methods that may be involved in the above embodiments.
[0242] This application provides a computer program product, including a computer program that, when executed by a processor, implements various methods that may be involved in the above embodiments.
[0243] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0244] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0245] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.
[0246] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0247] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".
[0248] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.
[0249] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.
Claims
1. A method for automatic inspection of the undercarriage of a monorail vehicle, characterized in that, The method includes: The system acquires the operating parameters corresponding to multiple vehicles and generates multiple sequentially arranged inspection tasks based on the operating parameters; the multiple vehicles are parked in a monorail depot. During the sequential execution of the inspection tasks, if it is determined that the environment in which the vehicle is located meets the maintenance requirements, the side skirts of the vehicle corresponding to the current inspection task are opened. The movement trajectory of the inspection robot is obtained by path planning based on the standby position of the inspection robot and the parking position of the vehicle corresponding to the current inspection task. The inspection robot is controlled to inspect the vehicle corresponding to the current inspection task according to the movement trajectory, and the inspection result of the vehicle corresponding to the current inspection task is obtained.
2. The method according to claim 1, characterized in that, The step of acquiring operating parameters corresponding to multiple vehicles and generating multiple sequentially arranged inspection tasks based on the operating parameters includes: For the operating factors of the multiple operating dimensions included in the operating parameters, the first evaluation score corresponding to each operating factor under each operating dimension is obtained respectively; For each of the aforementioned operational dimensions, the first evaluation scores corresponding to multiple operational factors are weighted and summed to obtain the second evaluation score corresponding to the operational dimension. The second evaluation scores corresponding to multiple operational dimensions are weighted and summed to obtain the target evaluation score for each vehicle. The priority order of the inspection tasks corresponding to each vehicle is determined according to the pre-set mapping relationship between multiple score ranges and multiple priority levels.
3. The method according to claim 2, characterized in that, If there are multiple inspection robots, after controlling the side skirts of the vehicle corresponding to the current inspection task to open, the process includes: According to the priority order of the multiple inspection tasks, the corresponding inspection tasks are assigned to the multiple inspection robots in turn, so as to control the multiple inspection robots to perform vehicle maintenance at the same time.
4. The method according to claim 2 or 3, characterized in that, Also includes: During the vehicle inspection process, if a new vehicle enters the monorail depot, the priority level of the newly entered vehicle is obtained. If the priority level of a newly entered vehicle into the monorail depot is higher than that of at least one vehicle being inspected by the inspection robot, the inspection robot corresponding to the vehicle with the lowest priority level is controlled to stop executing the current inspection task, and path planning is performed based on the standby position of the inspection robot and the parking position of the newly entered vehicle into the monorail depot to obtain the adjusted movement trajectory of the inspection robot. The inspection robot is controlled to inspect newly entered vehicles in the monorail depot according to the adjusted movement trajectory, and the inspection results of the newly entered vehicles in the monorail depot are obtained.
5. The method according to claim 2, characterized in that, The step of weighted summing of the first evaluation scores corresponding to multiple operating factors to obtain the second evaluation score corresponding to the operating dimension includes: Based on the occurrence time of historical operational failures corresponding to the operational factors, the attenuation coefficient corresponding to the operational factor is determined; the magnitude of the attenuation coefficient is positively correlated with the duration of the occurrence time of historical operational failures corresponding to the operational factors. The second evaluation score is obtained by weighted summing the products of the first evaluation score and the corresponding attenuation coefficient for each of the aforementioned operating factors.
6. The method according to claim 1, characterized in that, Determining that the environment in which the vehicle is located meets the maintenance requirements includes: Obtain the environmental parameters of the environment in which the vehicle corresponding to the current inspection task is located; the environmental parameters include at least the power outage status, the contact wire disconnection status, the grounding device closure status, the access control blockage status, and the video surveillance switching status; When the power outage state indicates that the vehicle corresponding to the inspection task has been de-energized, the contact wire disconnection state indicates that the contact wire of the track corresponding to the inspection task has been disconnected, the grounding device closure state indicates that the grounding device of the track corresponding to the inspection task has been closed, the access control blockage state indicates that the access control of the inspection task has been blocked, and the video monitoring switching state indicates that the monitoring video has been switched to the location of the vehicle corresponding to the inspection task, it is determined that the environment of the vehicle meets the maintenance requirements.
7. An automatic inspection device for the undercarriage of a monorail vehicle, characterized in that, include: The inspection task generation module is used to obtain the operating parameters of multiple vehicles and generate multiple inspection tasks arranged in sequence based on the operating parameters. Multiple of the aforementioned vehicles are parked in the monorail depot; The control module is used to control the opening of the side skirts of the vehicle corresponding to the current inspection task when it is determined that the environment of the vehicle meets the maintenance requirements during the sequential execution of the inspection tasks. The path planning module is used to perform path planning based on the standby position of the inspection robot and the parking position of the vehicle corresponding to the current inspection task, so as to obtain the movement trajectory of the inspection robot. The inspection execution module is used to control the inspection robot to inspect the vehicle corresponding to the current inspection task according to the movement trajectory, and to obtain the inspection result of the vehicle corresponding to the current inspection task.
8. An automatic inspection device for the undercarriage of a monorail vehicle, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.
10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.
