Communication machine room inspection system and method based on particle swarm optimization, terminal and storage medium
By using a communication equipment room inspection system based on particle swarm optimization, which combines lidar and wheel encoders to generate a two-dimensional grid map of the equipment room, and utilizes particle swarm optimization algorithm and dynamic window algorithm to plan the inspection path, the problem of the existing system's inability to dynamically adjust is solved, and efficient and accurate equipment room inspection and fault handling are achieved.
Patent Information
- Application Number
- CN202510852400.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-24
- Publication Date
- 2025-11-18
AI Technical Summary
Existing communication equipment room inspection systems cannot dynamically adjust inspection paths according to real-time changes in the equipment room environment, resulting in low inspection efficiency and a tendency to get lost or fall into a dead loop.
A communication equipment room inspection system based on particle swarm optimization is adopted. It combines lidar and wheel encoder to generate a two-dimensional grid map of the equipment room, uses particle swarm optimization algorithm and dynamic window algorithm to plan the inspection path, and is equipped with fault detection and environmental detection modules to achieve autonomous positioning and path adjustment.
It improves inspection efficiency, ensuring that inspection robots can complete tasks efficiently and accurately in complex environments, promptly detect faults and handle potential safety hazards, and avoid the problems of unreasonable paths and getting lost in traditional inspection methods.
Smart Images
Figure CN120975348A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of communication equipment management technology, specifically relating to a communication equipment room inspection system, method, terminal, and storage medium based on particle swarm optimization. Background Technology
[0002] In modern information society, communication equipment rooms, as the core hubs of communication networks, undertake critical tasks such as data transmission, processing, and storage. Their operational stability and security directly affect the efficiency and reliability of the entire communication network. However, with the rapid development of communication technology, the types and quantities of equipment within communication equipment rooms have increased dramatically, and the room environment has become increasingly complex. This presents unprecedented challenges to the daily inspection and maintenance of these rooms.
[0003] Traditional communication equipment room inspections primarily rely on manual labor. Inspectors need to periodically enter the room to check each piece of equipment. This method is not only inefficient but also prone to missed or false inspections when dealing with a large number of devices and complex environments. To address these challenges, existing automated inspection systems have emerged. However, these systems still have many shortcomings in practical applications. For example, many automated inspection systems lack intelligence in path planning, often using fixed inspection routes and failing to dynamically adjust the inspection path according to real-time changes in the equipment room environment. This results in low inspection efficiency and a tendency to get lost or enter dead loops in complex environments. Summary of the Invention
[0004] To address the shortcomings of existing data center inspection systems, which often employ fixed inspection routes and cannot dynamically adjust the inspection path according to real-time changes in the data center environment, resulting in low inspection efficiency and a tendency to get lost or fall into dead loops in complex environments, this invention provides a communication data center inspection system, method, terminal, and storage medium based on particle swarm optimization to solve the aforementioned technical problems.
[0005] In a first aspect, the present invention provides a communication equipment room inspection system based on particle swarm optimization, including an inspection terminal, a mobile terminal and a cloud server, wherein the inspection terminal and the mobile terminal are both connected to the cloud server. The inspection terminal includes an inspection robot, a fault detection module, an environmental monitoring module, a path planning module, a positioning and mapping module, and a microcontroller. The inspection robot is equipped with a lidar and a wheel encoder. The lidar is used to collect point cloud data of the computer room environment in real time. The inspection robot is electrically connected to the microcontroller. The localization and mapping module uses a pre-stored Gmapping algorithm to generate a two-dimensional grid map of the computer room based on the collected point cloud data of the computer room environment, and uses a built-in particle filter to fuse the odometer data of the wheel encoder to enable the inspection robot to locate autonomously. The path planning module has built-in particle swarm optimization algorithm and dynamic window algorithm, and is configured to generate a global inspection path based on the two-dimensional grid map of the computer room, and adjust the local path according to real-time obstacle information; The fault detection module is configured to detect the operating status and fault data of the equipment in the computer room and transmit the data to the microcontroller. The environmental monitoring module is used to detect the environmental parameters of the computer room and transmit them to the microcontroller; The mobile terminal is configured to receive inspection tasks input by inspection personnel and send them to the inspection terminal. The cloud server is used to store data such as data center map, equipment operating parameters and inspection history, and to optimize the parameters of the particle swarm optimization algorithm based on the obstacle location update data.
[0006] Further improvements to this technical solution include a fault detection module comprising an audible and visual alarm, which is electrically connected to a microcontroller. The microcontroller is configured to trigger the audible and visual alarm based on fault data detected in the equipment in the computer room, and to control the inspection robot to move to the location of the corresponding faulty equipment for re-inspection.
[0007] Further improvements to this technical solution include an environmental detection module that includes a temperature sensor and a smoke sensor. When the microcontroller determines that the received ambient temperature is greater than a preset temperature threshold and the smoke concentration in the computer room is greater than a preset smoke concentration threshold, it triggers the path planning module to regenerate a detour path and sends an early warning message to the mobile terminal.
[0008] Further improvements to this technical solution include that the inspection tasks input by the mobile terminal include inspection modes, which include daily inspection mode, equipment maintenance inspection mode, and emergency inspection mode.
[0009] Further improvements to this technical solution include a voice control module in the inspection terminal. The voice control module is electrically connected to the microcontroller and is configured to receive voice commands and convert them into corresponding control signals to start or stop the inspection task.
[0010] Secondly, the present invention provides a communication equipment room inspection method based on particle swarm optimization, comprising: Step S1: Collect point cloud data of the computer room environment in real time using LiDAR, generate a two-dimensional grid map of the computer room based on the collected point cloud data using pre-stored Gmapping, and upload it to the cloud server. Step S2: Receive the inspection task input by the inspection personnel; Step S3: Based on the pre-stored particle swarm optimization algorithm, a global inspection path is generated according to the received inspection task and combined with the two-dimensional grid map of the computer room; including: Initialize the particle swarm, where each particle represents a path consisting of a sequence of coordinate points of the target inspection equipment; Establish a fitness function and iteratively update particle velocity and position to select the optimal path; Step S4: Adjust the path in real time using the pre-stored dynamic window algorithm to avoid dynamic obstacles; and upload the obstacle positions and environmental parameters to the cloud server to optimize the parameters of the particle swarm optimization algorithm. Step S5: After the inspection robot arrives at the target inspection task point according to the selected optimal path, it starts the fault detection module and the environmental detection module to detect the target inspection equipment, and transmits the detected operating status information of the computer room equipment and the computer room environmental parameters to the microcontroller for analysis.
[0011] Further improvements to this technical solution include the pre-stored particle swarm optimization algorithm, which includes: The formula for calculating the fitness function is: ; in, The fitness function; The path length from the inspection robot to the target inspection task point is measured by a wheel encoder; i represents particle i; j represents particle j. The vertical distance from the i-th candidate path to the j-th obstacle is collected in real time by lidar. The formula for iteratively updating particle velocity is: ; in, The updated particle velocity; The current particle velocity; Inertial weight; This represents the optimal position in the particle's history. The globally optimal position; The sum of individual learning factors controls the particle's trajectory toward its historical best. The weight of the movement; The group learning factor controls the particles to move towards the global optimum. The weight of the movement; , The result is a random number, ranging from [0, 1]. This represents the current particle position. The formula for iteratively updating the particle position is: ; in, This represents the updated particle position.
[0012] Further improvements to this technical solution include methods for selecting the optimal path, such as: Based on the updated particle velocity and position, the action cost corresponding to each candidate path is calculated using the following formula: ; in, The cost of the action the inspection robot is scheduled to perform in the next moment; The speed weight ranges from 0.8 to 1.0 and is dynamically adjusted based on the width of the data center corridor. As the heading deviation weight, , The number of obstacles, This represents the total number of devices in the computer room. This indicates the current heading of the inspection robot. The target course for the inspection robot; The candidate path with the lowest action cost is selected as the optimal path.
[0013] Thirdly, the present invention provides a terminal, comprising: Processor, memory, among which, This memory is used to store computer programs. The processor is used to retrieve and run the computer program from memory, causing the terminal to perform the terminal method described above.
[0014] Fourthly, the present invention provides a computer storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described in the above aspects.
[0015] The beneficial effects of this invention are as follows: This invention integrates particle swarm optimization (PSO) and dynamic window algorithms to achieve efficient planning and real-time dynamic adjustment of inspection paths. The PSO algorithm intelligently generates the globally optimal inspection path based on the 2D grid map of the computer room and the inspection task, while the dynamic window algorithm flexibly adjusts the local path based on real-time obstacle information, ensuring that the inspection robot completes its tasks efficiently and accurately in the complex and ever-changing computer room environment. This design significantly improves inspection efficiency and avoids the problems of unreasonable paths and getting lost in traditional inspection methods.
[0016] The inspection robot in this invention is equipped with a lidar and a wheel encoder. It uses the lidar to collect real-time point cloud data of the computer room environment, and combines this with a pre-stored Gmapping algorithm and particle filter to achieve precise positioning and autonomous navigation within the computer room. This technology not only improves positioning accuracy but also enables the inspection robot to autonomously plan its path in complex environments, effectively avoiding inspection failures or collisions caused by inaccurate positioning.
[0017] The fault detection module in this invention can monitor the operating status and fault data of the equipment in the computer room in real time and transmit the data to the microcontroller for analysis. Once a fault is detected, the microcontroller will trigger an audible and visual alarm to promptly notify the computer room staff and control the inspection robot to move to the location of the corresponding faulty equipment for re-inspection. This design ensures timely detection and handling of faults, effectively reducing the impact time of faults on the communication network.
[0018] The environmental detection module in this invention includes a temperature sensor and a smoke sensor, which can monitor environmental parameters in the computer room in real time and transmit the data to the microcontroller. When the microcontroller determines that the received ambient temperature is greater than a preset temperature threshold and the smoke concentration in the computer room is greater than a preset smoke concentration threshold, it will trigger the path planning module to regenerate a detour path and send an early warning message to the mobile terminal. This design helps to promptly detect and handle potential safety hazards, ensuring the safe operation of the computer room. Attached Figure Description
[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0020] Figure 1 This is a schematic block diagram of a system according to an embodiment of the present invention.
[0021] Figure 2 This is a schematic flowchart illustrating a method according to an embodiment of the present invention.
[0022] Figure 3 This is a schematic diagram of the structure of a terminal provided in an embodiment of the present invention.
[0023] 110 is the inspection terminal, 111 is the inspection robot, 112 is the fault detection module, 113 is the environmental detection module, 114 is the path planning module, 115 is the positioning and mapping module, 116 is the microcontroller, 120 is the mobile terminal, and 130 is the cloud server. Detailed Implementation
[0024] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the specific embodiments. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
[0026] like Figure 1 As shown, the present invention provides a communication equipment room inspection system based on particle swarm optimization, including an inspection terminal 110, a mobile terminal 120 and a cloud server 130, wherein the inspection terminal 110 and the mobile terminal 120 are both connected to the cloud server 130.
[0027] Specifically, the inspection terminal 110 includes an inspection robot 111, a fault detection module 112, an environmental detection module 113, a path planning module 114, a positioning and mapping module 115, and a microcontroller 116. The inspection robot 111, the fault detection module 112, the environmental detection module 113, the path planning module 114, and the positioning and mapping module 115 are all electrically connected to the microcontroller 116, and the microcontroller 116 is communicatively connected to the mobile terminal 120 and the cloud server 130.
[0028] The inspection robot 111 is equipped with a lidar, a wheel encoder, and a drive motor. The lidar is used to collect point cloud data of the computer room environment in real time. The inspection robot 111 is electrically connected to the microcontroller 116. The inspection robot 111 adopts a closed-loop control method. The wheel encoder provides real-time feedback on the robot's operating status, and the microcontroller 116 adjusts the output of the drive motor according to the feedback on the robot's operating status to ensure the smooth and accurate execution of the inspection task.
[0029] LiDAR (Light Detection and Ranging) emits laser beams and receives reflected light signals, enabling precise measurement of the distance and angle of surrounding objects to generate a two-dimensional grid map of the computer room. In this embodiment, the LiDAR is mounted on top of the inspection robot 111 to ensure comprehensive and seamless data collection of the computer room environment.
[0030] Wheel encoders are used to record the travel distance and direction of the inspection robot 111. By measuring the number of rotations and angles of the robot's wheels, the wheel encoders calculate the robot's travel distance (or odometer data) and directional changes, providing basic data for subsequent localization mapping and path planning.
[0031] The localization and mapping module 115 uses a pre-stored Gmapping algorithm to generate a two-dimensional grid map of the computer room based on the collected point cloud data of the computer room environment. The Gmapping algorithm is a SLAM (Simultaneous Localization and Mapping) algorithm based on LiDAR, which can simultaneously realize robot localization and map building in unknown environments.
[0032] While generating a two-dimensional grid map of the computer room, the positioning and mapping module 115 also uses a built-in particle filter to fuse the odometer data of the wheel encoder to perform autonomous positioning of the inspection robot 111. The particle filter is a positioning algorithm based on Bayesian filtering theory. It achieves accurate estimation of the robot's position by continuously updating the state distribution of the particle swarm.
[0033] The path planning module 114 incorporates particle swarm optimization and dynamic window algorithms, and is configured to generate a global inspection path based on the two-dimensional grid map of the computer room, and adjust the local path based on real-time obstacle information.
[0034] In the inspection system, each particle represents a path consisting of a sequence of coordinate points of the target inspection equipment. The optimal path is selected by iteratively updating the particle's velocity and position.
[0035] The dynamic window algorithm is used to adjust the path in real time and avoid dynamic obstacles. By predicting the trajectory of the inspection robot 111 over a period of time and combining it with real-time obstacle information, the algorithm dynamically adjusts the robot's speed and direction to ensure the safe and efficient execution of the inspection task.
[0036] The fault detection module 112 is configured to detect the operating status and fault data of the equipment in the computer room and transmit the data to the microcontroller 116.
[0037] The fault detection module 112 includes various sensors, such as infrared sensors and current sensors, which can monitor the temperature, current, voltage and other parameters of the equipment in the computer room in real time. The microcontroller 116 will report any abnormality immediately based on the acquired equipment parameters.
[0038] The environmental detection module 113 detects environmental parameters in the computer room and transmits them to the microcontroller 116. The environmental detection module 113 includes a temperature sensor, a smoke sensor, and a humidity sensor. When the microcontroller 116 determines that the received ambient temperature is greater than a preset temperature threshold and the smoke concentration in the computer room is greater than a preset smoke concentration threshold, it triggers the path planning module 114 to regenerate a detour path and sends an early warning message to the mobile terminal 120, asking the user whether to activate the emergency response plan. The user can choose whether to allow automatic processing or manual confirmation on the APP. If manual confirmation is selected, the APP will send the corresponding control command to the inspection terminal 110 after the user clicks confirmation to continue the operation process. When the humidity sensor detects that the humidity in the computer room is greater than a preset humidity threshold, it immediately sends an alarm message to the mobile terminal 120. This design helps to promptly detect and handle potential safety hazards, ensuring the safe operation of the computer room.
[0039] As the interface for interaction between the inspection personnel and the inspection terminal 110, the main function of the mobile terminal 120 is to receive the inspection tasks input by the inspection personnel and send them to the inspection terminal 110. An inspection control APP (Application) is installed on the mobile terminal 120. This APP has a user-friendly interface. The inspection personnel can easily input inspection tasks, select inspection modes (such as daily inspection mode, equipment maintenance inspection mode, and emergency inspection mode) and view inspection results through the interface. The inspection control APP has the function of remotely sharing inspection control permissions. The user can share the inspection control permissions with other users, and the shared users can control the inspection tasks through the APP on their mobile terminals 120. When sharing inspection control permissions, the time range and operation permission range of the control can be set. The inspection control APP has an interface integrated with the computer room management system and can perform linkage control with other management devices in the computer room. For example, when the inspection terminal 110 detects abnormal temperature in the computer room, it automatically sends an instruction to the air conditioning control system to adjust the working state of the air conditioner.
[0040] The communication between the mobile terminal 120 and the inspection terminal 110 uses an encrypted communication protocol to ensure the security of data transmission. The encrypted communication protocol combines symmetric encryption and asymmetric encryption, encrypts the data before transmission, and decrypts it at the receiving end.
[0041] The cloud server 130 is used to store computer room map data, equipment operation parameters, and inspection history records, providing data support for data analysis and mining of the system. Analyze the collected inspection data, identify the fault modes of equipment, and generate diagnostic suggestions. At the same time, based on the updated data of the obstacle positions, optimize the parameters of the particle swarm optimization algorithm to improve the efficiency and accuracy of path planning. Manage the setting information and permission allocation of users to ensure the safe and stable operation of the system. The cloud server 130 has the functions of data backup and recovery, and regularly backs up the stored user setting information and inspection history data. When the data is lost or damaged, it can quickly recover the data to ensure the normal operation of the system.
[0042] In addition, the fault detection module 112 includes an audible and visual alarm. The audible and visual alarm is electrically connected to the microcontroller 116. The microcontroller 116 is configured to trigger the audible and visual alarm according to the fault data of the computer room equipment detected by the fault, and control the inspection robot 111 to move to the position of the corresponding faulty equipment for re-inspection.
[0043] The audible and visual alarm integrated in the fault detection module 112 of this invention is electrically connected to the microcontroller 116. This design ensures that when the inspection robot 111 detects a fault in the equipment in the computer room, it can immediately trigger the audible and visual alarm. The audible and visual alarm quickly attracts the attention of the staff in the computer room by emitting a high-decibel alarm sound and a conspicuous flashing signal, ensuring that the fault can be responded to and handled in a timely manner. This instant alarm mechanism effectively shortens the time from fault detection to response and reduces the impact of the fault on the normal operation of the communication network. After receiving the fault data from the fault detection module 112, the microcontroller 116 can not only trigger the audible and visual alarm, but also accurately calculate the location of the faulty equipment according to the preset program and algorithm, and control the inspection robot 111 to automatically move to the corresponding faulty equipment location for re-inspection. This function realizes accurate fault location and rapid re-inspection, avoiding the problems of inaccurate positioning or untimely re-inspection that may occur in manual inspection. After the inspection robot 111 reaches the location of the faulty equipment, it can use the fault detection module 112 again to perform detailed inspection of the equipment, ensuring the accuracy and completeness of the fault data and providing a reliable basis for subsequent fault repair.
[0044] In addition, the inspection terminal 110 also includes a voice control module, which is electrically connected to the microcontroller 116 and configured to receive voice commands and convert them into corresponding control signals to start or stop the inspection task.
[0045] The inspection terminal 110 of this invention integrates a voice control module and is electrically connected to the microcontroller 116. This design greatly improves operational convenience. Inspection personnel do not need to manually operate the control panel on the mobile terminal 120 or the inspection robot 111; they can quickly start or stop the inspection task simply by using voice commands. This operating method is particularly crucial in emergency situations. For example, when a sudden fault occurs in the computer room and the current inspection task needs to be stopped immediately for emergency handling, the inspection personnel can immediately issue a voice command to quickly interrupt the inspection process, effectively saving time and improving emergency response speed.
[0046] Figure 2 This is a schematic flowchart illustrating a communication equipment room inspection method based on particle swarm optimization provided by the present invention. Wherein, Figure 2 The executing entity can be a communication equipment room inspection system based on particle swarm optimization. Depending on different requirements, the order of steps in this flowchart can be changed, and some can be omitted. The method includes: Step S1: Collect point cloud data of the computer room environment in real time using LiDAR, generate a two-dimensional grid map of the computer room based on the collected point cloud data using pre-stored Gmapping, and upload it to the cloud server. Step S2: Receive the inspection task input by the inspection personnel; Step S3: Based on the pre-stored particle swarm optimization algorithm, a global inspection path is generated according to the received inspection task and combined with the two-dimensional grid map of the computer room; including: Initialize the particle swarm, where each particle represents a path consisting of a sequence of coordinate points of the target inspection equipment; Establish a fitness function and iteratively update particle velocity and position to select the optimal path; Step S4: Adjust the path in real time using the pre-stored dynamic window algorithm to avoid dynamic obstacles; and upload the obstacle positions and environmental parameters to the cloud server to optimize the parameters of the particle swarm optimization algorithm. Step S5: After the inspection robot arrives at the target inspection task point according to the selected optimal path, it starts the fault detection module and the environmental detection module to detect the target inspection equipment, and transmits the detected operating status information of the computer room equipment and the computer room environmental parameters to the microcontroller for analysis.
[0047] This invention integrates particle swarm optimization (PSO) and dynamic window algorithms to achieve efficient planning and real-time dynamic adjustment of inspection paths. The PSO algorithm intelligently generates the globally optimal inspection path based on the 2D grid map of the computer room and the inspection task, while the dynamic window algorithm flexibly adjusts the local path based on real-time obstacle information, ensuring that the inspection robot completes its tasks efficiently and accurately in the complex and ever-changing computer room environment. This design significantly improves inspection efficiency and avoids the problems of unreasonable paths and getting lost in traditional inspection methods.
[0048] Specifically, the pre-stored particle swarm optimization algorithms include: The formula for calculating the fitness function is: ; in, The fitness function; The path length from the inspection robot to the target inspection task point is measured by a wheel encoder; i represents particle i; j represents particle j. The vertical distance from the i-th candidate path to the j-th obstacle is collected in real time by lidar. The formula for iteratively updating particle velocity is: ; in, The updated particle velocity; The current particle velocity; Inertial weight; This represents the optimal position in the particle's history. The globally optimal position; The sum of individual learning factors controls the particle's trajectory toward its historical best. The weight of the movement; The group learning factor controls the particles to move towards the global optimum. The weight of the movement; , The result is a random number, ranging from [0, 1]. This represents the current particle position. The formula for iteratively updating the particle position is: ; in, This represents the updated particle position.
[0049] The pre-stored particle swarm optimization algorithm in this invention achieves efficient path planning for inspection robots through a fitness function and an iterative update formula. The fitness function comprehensively considers both the path length from the inspection robot to the target inspection point and the perpendicular distance from the path to obstacles, ensuring that the generated path is both short and safe, avoiding collisions with obstacles. This fitness function design, which comprehensively considers multiple factors, makes the path planning results more accurate, effectively reducing the unnecessary movement of the inspection robot within the machine room and improving inspection efficiency.
[0050] Particle swarm optimization (PSO) achieves dynamic adjustment of particle swarm behavior by iteratively updating formulas for particle velocity and position. The introduction of inertia weights, individual learning factors, and swarm learning factors allows the algorithm to flexibly adjust the search direction and velocity of particles based on actual conditions. When the data center environment changes (such as the addition of obstacles or adjustments to equipment layout), the algorithm can quickly adapt and replan the optimal path, ensuring the smooth progress of inspection tasks. This dynamic adjustment capability enhances the algorithm's adaptability, enabling it to maintain efficient operation in complex and ever-changing data center environments.
[0051] In particle swarm optimization (PSO), the individual learning factor and the swarm learning factor control the weights of particle movement towards the historical best position and the global best position, respectively. This design allows the algorithm to focus on local optima (through the individual learning factor) while simultaneously exploring the global optimum (through the swarm learning factor) during the search process. In path planning, this combination of global and local search capabilities helps the algorithm quickly find the optimal path from the starting point to the target point, while avoiding getting trapped in local optima, thus improving the quality and efficiency of path planning.
[0052] Furthermore, methods for selecting the optimal path include: Based on the updated particle velocity and position, the action cost corresponding to each candidate path is calculated using the following formula: ; in, The cost of the action the inspection robot is scheduled to perform in the next moment; The speed weight ranges from 0.8 to 1.0 and is dynamically adjusted based on the width of the data center corridor. As the heading deviation weight, , The number of obstacles, This represents the total number of devices in the computer room. This indicates the current heading of the inspection robot. The target course for the inspection robot; The candidate path with the lowest action cost is selected as the optimal path.
[0053] This invention calculates the action cost for each candidate path based on updated particle velocity and position, enabling precise quantification of the potential overhead of different paths during execution. The action cost comprehensively considers velocity and heading deviation factors, visually reflecting the performance of each path in terms of efficiency and safety in numerical form. This allows the system to clearly compare the merits of different candidate paths, quickly and accurately selecting the candidate path with the lowest action cost as the optimal path, avoiding blind trial and inefficient selection, and significantly improving the efficiency of path planning.
[0054] The speed weight is dynamically adjusted based on the width of the computer room aisles (ranging from 0.8 to 1.0), allowing the algorithm to flexibly adapt to computer room environments of varying sizes. In computer rooms with wider aisles, appropriately increasing the speed weight helps the inspection robot complete tasks more quickly, improving inspection efficiency. Conversely, in computer rooms with narrow aisles or numerous obstacles, decreasing the speed weight prompts the robot to plan its path more cautiously, avoiding the risk of collisions due to excessive speed. This dynamic adjustment mechanism enhances the algorithm's adaptability to complex computer room environments, ensuring that inspection tasks can be executed efficiently and safely under various conditions.
[0055] The introduction of heading deviation weights (reflected in the formula as a calculation related to the number of obstacles and the total number of devices in the machine room) allows the algorithm to fully consider the deviation between the inspection robot's current heading and the target heading when planning the path. Through this deviation calculation, the algorithm can plan paths more rationally, reducing unnecessary turns and adjustments, enabling the inspection robot to reach the target location more directly and efficiently. This not only helps shorten inspection time but also reduces energy consumption and equipment wear caused by frequent turns, improving the overall efficiency of the inspection task.
[0056] The formula for calculating action costs incorporates both speed and heading deviation weights. This means that when selecting the optimal path, the algorithm considers not only path length and speed but also safety and rationality. By avoiding excessive proximity to obstacles and minimizing unnecessary heading adjustments, the algorithm can generate safe and efficient inspection paths. This path planning method, which comprehensively considers multiple factors, helps reduce risks during inspections and improves the quality and efficiency of inspection tasks.
[0057] The motion cost-based screening method enables the inspection system to automatically select and optimize routes without human intervention. The system can dynamically adjust speed and heading deviation weights based on real-time collected data from the computer room environment and inspection task requirements to generate the optimal inspection route. This autonomy not only reduces the workload of inspection personnel but also improves the response speed and execution efficiency of inspection tasks.
[0058] Figure 3 This is a schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the communication equipment room inspection method based on particle swarm optimization provided in the embodiment of the present invention.
[0059] The terminal 300 may include a processor 310, a memory 320, and a communication module 330. These components communicate via one or more buses. Those skilled in the art will understand that the server structure shown in the figure does not constitute a limitation of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0060] The memory 320 can be used to store the execution instructions of the processor 310. The memory 320 can be implemented by any type of volatile or non-volatile memory terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 is able to perform some or all of the steps in the above method embodiments.
[0061] The processor 310 serves as the control center of the storage terminal, connecting various parts of the electronic terminal via various interfaces and lines. It executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 310 may consist only of a central processing unit (CPU). In this embodiment of the invention, the CPU may have a single processing core or include multiple processing cores.
[0062] The communication module 330 is used to establish a communication channel, enabling the storage terminal to communicate with other terminals. It receives user data sent by other terminals or sends user data to other terminals.
[0063] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps provided in the embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.
[0064] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, mobile hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or other media capable of storing program code. It includes several instructions to cause a computer terminal (which may be a personal computer, server, or a second terminal, network terminal, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.
[0065] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the terminal embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.
[0066] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or modules may be electrical, mechanical, or other forms.
[0067] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0068] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.
[0069] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.
Claims
1. A communication equipment room inspection system based on particle swarm optimization, characterized in that, It includes inspection terminals, mobile terminals, and cloud servers, with both inspection terminals and mobile terminals communicating with the cloud server. The inspection terminal includes an inspection robot, a fault detection module, an environmental monitoring module, a path planning module, a positioning and mapping module, and a microcontroller. The inspection robot is equipped with a lidar and a wheel encoder. The lidar is used to collect point cloud data of the computer room environment in real time. The inspection robot is electrically connected to the microcontroller. The localization and mapping module uses a pre-stored Gmapping algorithm to generate a two-dimensional grid map of the computer room based on the collected point cloud data of the computer room environment, and uses a built-in particle filter to fuse the odometer data of the wheel encoder to enable the inspection robot to locate autonomously. The path planning module has built-in particle swarm optimization algorithm and dynamic window algorithm, and is configured to generate a global inspection path based on the two-dimensional grid map of the computer room, and adjust the local path according to real-time obstacle information; The fault detection module is configured to detect the operating status and fault data of the equipment in the computer room and transmit the data to the microcontroller. The environmental monitoring module is used to detect the environmental parameters of the computer room and transmit them to the microcontroller; The mobile terminal is configured to receive inspection tasks input by inspection personnel and send them to the inspection terminal. The cloud server is used to store data such as data center map, equipment operating parameters and inspection history, and to optimize the parameters of the particle swarm optimization algorithm based on the obstacle location update data.
2. The communication equipment room inspection system based on particle swarm optimization according to claim 1, characterized in that, The fault detection module includes an audible and visual alarm, which is electrically connected to a microcontroller. The microcontroller is configured to trigger the audible and visual alarm based on the fault data detected in the equipment in the computer room, and to control the inspection robot to move to the location of the corresponding faulty equipment for re-inspection.
3. The communication equipment room inspection system based on particle swarm optimization according to claim 1, characterized in that, The environmental detection module includes a temperature sensor and a smoke sensor. When the microcontroller determines that the received ambient temperature is greater than a preset temperature threshold and the smoke concentration in the computer room is greater than a preset smoke concentration threshold, it triggers the path planning module to regenerate the detour path and send an early warning message to the mobile terminal.
4. The communication equipment room inspection system based on particle swarm optimization according to claim 1, characterized in that, The inspection tasks input by the mobile terminal include inspection modes, which include daily inspection mode, equipment maintenance inspection mode, and emergency inspection mode.
5. The communication equipment room inspection system based on particle swarm optimization according to claim 1, characterized in that, The inspection terminal also includes a voice control module, which is electrically connected to the microcontroller and configured to receive voice commands and convert them into corresponding control signals to start or stop the inspection task.
6. A communication equipment room inspection method based on particle swarm optimization, characterized in that, include: Step S1: Collect point cloud data of the computer room environment in real time using LiDAR, generate a two-dimensional grid map of the computer room based on the collected point cloud data using pre-stored Gmapping, and upload it to the cloud server. Step S2: Receive the inspection task input by the inspection personnel; Step S3: Based on the pre-stored particle swarm optimization algorithm, a global inspection path is generated according to the received inspection task and combined with the two-dimensional grid map of the computer room; including: Initialize the particle swarm, where each particle represents a path consisting of a sequence of coordinate points of the target inspection equipment; Establish a fitness function and iteratively update particle velocity and position to select the optimal path; Step S4: Adjust the path in real time using the pre-stored dynamic window algorithm to avoid dynamic obstacles; and upload the obstacle positions and environmental parameters to the cloud server to optimize the parameters of the particle swarm optimization algorithm. Step S5: After the inspection robot arrives at the target inspection task point according to the selected optimal path, it starts the fault detection module and the environmental detection module to detect the target inspection equipment, and transmits the detected operating status information of the computer room equipment and the computer room environmental parameters to the microcontroller for analysis.
7. The communication equipment room inspection method based on particle swarm optimization according to claim 6, characterized in that, The pre-stored particle swarm optimization algorithms include: The formula for calculating the fitness function is: ； in, The fitness function; The path length from the inspection robot to the target inspection task point is measured by a wheel encoder; i represents particle i; j represents particle j. The vertical distance from the i-th candidate path to the j-th obstacle is collected in real time by lidar. The formula for iteratively updating particle velocity is: ； in, The updated particle velocity; The current particle velocity; Inertial weights; This represents the optimal position in the particle's history. The globally optimal position; The sum of individual learning factors controls the particle's trajectory toward its historical best. The weight of the movement; The group learning factor controls the particles to move towards the global optimum. The weight of the movement; , The result is a random number, ranging from [0, 1]. This represents the current particle position. The formula for iteratively updating the particle position is: ； in, This represents the updated particle position.
8. The communication equipment room inspection method based on particle swarm optimization according to claim 7, characterized in that, Methods for selecting the optimal path include: Based on the updated particle velocity and position, the action cost corresponding to each candidate path is calculated using the following formula: ； in, The cost of the action the inspection robot is scheduled to perform in the next moment; The speed weight ranges from 0.8 to 1.0 and is dynamically adjusted based on the width of the data center corridor. As the heading deviation weight, , The number of obstacles, This represents the total number of devices in the computer room. This indicates the current heading of the inspection robot. The target course for the inspection robot; The candidate path with the lowest action cost is selected as the optimal path.
9. A terminal, characterized in that, include: processor; Memory used to store the processor's execution instructions; The processor is configured to perform the method according to any one of claims 6-8.
10. A computer-readable storage medium storing a computer program, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 6-8.