Non-inductive inspection and path planning method and system based on Bluetooth tag

Abstract

The invention discloses a Bluetooth tag-based non-inductive routing inspection and path planning method and system, and the method comprises the steps: collecting historical routing inspection data to generate a routing inspection task, automatically connecting to a server through routing inspection equipment, and downloading the routing inspection task; when the inspection equipment enters the Bluetooth range of the electronic tag, connection is automatically established, and risk levels are divided according to the connection time of the inspection equipment and the electronic tag; the MCU of the electronic tag automatically records inspection data and uploads the inspection data to a server through WIFI, an ant colony optimization algorithm is used to optimize an inspection path, and risk assessment and historical inspection data are integrated to provide an inspection path. According to the method, the operation efficiency of a factory is improved through automatic non-inductive inspection and intelligent path planning; human errors and omission are reduced through an intelligent system, so that higher reliability and safety are ensured; the system reduces deployment and maintenance costs by utilizing existing low-cost techniques and intelligent algorithms.

Description

Technical Field

[0001] This invention belongs to the field of industrial automation and monitoring technology, and in particular relates to a method and system for contactless inspection and path planning based on Bluetooth tags. Background Technology

[0002] Achieving intelligent and automated factory operation has become a trend. Traditional factory inspections typically rely on manual labor, which is not only inefficient but also prone to errors. Existing automation solutions, on the other hand, often depend on complex sensor networks and central control systems, which are costly to maintain and lack flexibility.

[0003] In traditional industrial settings, routine equipment monitoring and maintenance often rely on manual inspections, which is not only inefficient but also prone to omissions and errors. Furthermore, traditional monitoring systems typically depend on wired connections, significantly limiting their flexibility and scalability.

[0004] To address these issues, several solutions based on wireless sensor networks (WSNs) have emerged in recent years. However, these solutions often have limitations, such as sensor energy constraints, network security issues, and high deployment and maintenance costs.

[0005] Furthermore, although existing technologies have begun to explore the use of ant colony optimization algorithms for path planning, they are usually limited to theoretical research or simple applications, without fully utilizing the algorithm's potential to solve complex problems in real industrial environments. Summary of the Invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by this invention is to address the issues of flexibility and scalability in traditional monitoring systems; traditional manual inspections are inefficient and prone to omissions and errors.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a Bluetooth tag-based non-contact inspection and path planning method, comprising: collecting historical inspection data to generate inspection tasks, and automatically connecting the inspection device to the server and downloading the inspection tasks;

[0009] When the inspection equipment enters the Bluetooth range of the electronic tag, a connection is automatically established, and the risk level is determined based on the connection time between the inspection equipment and the electronic tag.

[0010] The MCU of the electronic tag automatically records the inspection data and uploads it to the server via WIFI. The inspection path is optimized using the ant colony optimization algorithm, and a single inspection path is provided by integrating risk assessment and historical inspection data.

[0011] As a preferred embodiment of the Bluetooth tag-based contactless inspection and path planning method described in this invention, the step of generating the inspection task is as follows:

[0012] Real-time environmental data and status data of inspection equipment, as well as historical inspection data, are collected through Wi-Fi and Bluetooth tags to gather risk level data for each area;

[0013] Data preprocessing: Cleaning and integrating historical data and risk level data;

[0014] Model training: A prediction model is trained using a decision tree algorithm. The prediction model predicts future inspection tasks by using historical data and risk levels.

[0015] New inspection tasks are generated using the trained model. The generation of tasks will be based on historical data and risk levels to determine the frequency and priority of inspections.

[0016] Based on the location of the inspection personnel, the generated tasks are assigned to the corresponding inspection personnel.

[0017] As a preferred embodiment of the Bluetooth tag-based contactless inspection and path planning method described in this invention, the step of training a prediction model using a decision tree algorithm is as follows:

[0018] Data preparation and preprocessing: Extract features from historical inspection data, including historical connection time, regional risk level, connection stability, equipment response time and standard deviation, and standardize the features.

[0019] Feature selection and construction: Select the most informative features for training based on expert knowledge and historical data analysis; construct new features based on existing features to enhance the model's predictive ability;

[0020] Decision tree model training: The dataset is divided into training and test sets, and the CART decision tree algorithm is selected for training; the optimal hyperparameter combination is found using grid search; the decision tree model is trained using the optimized hyperparameters and the training set.

[0021] Model validation and testing: Cross-validation is used to verify the stability and accuracy of the model; various performance metrics are used to evaluate the model's performance.

[0022] As a preferred embodiment of the Bluetooth tag-based contactless inspection and path planning method described in this invention, the risk level is determined based on the connection time between the inspection device and the electronic tag.

[0023] When the connection time T actual >Scheduled time T min If so, then further determine the connection stability:

[0024] When the connection stability is high, it is classified as a green risk level and monitoring continues.

[0025] When the connection stability is low, it is classified as a yellow risk level, and a warning signal is issued;

[0026] When the connection stability is low, it is classified as an orange risk level, and a signal is issued that an inspection is required.

[0027] When the connection time T actual ≤Reserved time T min If so, then further determine the connection stability:

[0028] When the connection stability is high, it is classified as an orange risk level, and a signal is issued that an inspection is required.

[0029] When the connection is unstable, it is classified as a red risk level, and an immediate check signal is issued.

[0030] When connection stability is low, it is classified as a red risk level, issuing an immediate inspection signal and initiating an emergency response procedure.

[0031] As a preferred embodiment of the Bluetooth tag-based seamless inspection and path planning method described in this invention, the connection stability is measured by comparing the variance of the actual connection time with the historical connection time, expressed as:

[0032]

[0033] Where, σ 2 (T actual,i Let be the variance of the actual time of the i-th connection. This is the average of the actual connection times.

[0034] When σ 2 (T actual,i ) < T 高 When T is high, the connection stability is considered high. 高 ≤σ 2 (T actual,i ) < T 低 When T is reached, the connection stability is determined to be medium. 低 ≤σ 2 (T actual,i When T is reached, the connection stability is considered low. 高 and T 低为 The two thresholds were determined based on historical data and actual needs.

[0035] As a preferred embodiment of the Bluetooth tag-based contactless inspection and path planning method described in this invention, wherein: the connection time Tactual The calculation formula is:

[0036]

[0037] Among them, T actual，i Let T be the actual connection time for the i-th connection. stay，j，i Let R be the dwell time in the j-th time period during the i-th inspection. k Let w represent the risk level of the k-th region. j Let v be the dwell time weight for the j-th inspection. k Let m be the risk level weight of the k-th region, m be the total number of historical inspections, and p be the total number of regions.

[0038] The predetermined time T min The calculation formula is:

[0039]

[0040] Among them, T avg,i Let W be the average connection time of the i-th inspection. i R represents the weight of the i-th inspection. resp,i S is the equipment response time for the i-th inspection. i Let λ1 be the standard deviation of the equipment response time during the i-th inspection, n be the total number of inspections, and λ1 and λ2 be adjustment factors.

[0041] The dwell time T stay The calculation formula is:

[0042]

[0043] Among them, D hist,j V represents the historical dwell time during the j-th inspection. j R represents the dwell time weight for the j-th inspection. risk,k Let Q be the risk level of the k-th region. k Let μ be the risk level weight of the k-th region, μ and ν be adjustment factors, m be the total number of historical inspections, and p be the total number of regions.

[0044] As a preferred embodiment of the Bluetooth tag-based contactless inspection and path planning method described in this invention, the step of optimizing the inspection path using an ant colony optimization algorithm is as follows:

[0045] The pheromone intensity is initialized based on historical inspection data and current risk level data. The initial pheromone intensity is derived from the formula:

[0046] τ ij (0)=τ0+α·R k

[0047] Where, τ ij (0) represents the pheromone intensity on path ij at time t=0, where τ0 is a positive constant used to initialize the pheromone, and R k Let k be the risk level of region k, and α be a parameter used to control the impact of the risk level.

[0048] Constructing the solution and solution space: Using historical data and the output of the decision tree model, all possible inspection paths and their respective risk levels are defined. The solution space is expressed by the formula:

[0049]

[0050] Where S is the solution space, P ij Let m be the path corresponding to the i-th inspection and the j-th time period, m be the total number of historical inspections, and p be the total number of regions.

[0051] Pheromone Update and Evaporation: After each iteration, the update and evaporation of pheromones along the path are expressed by the following formula:

[0052] τ ij (t+1)=(1-ρ)·τ ij (t)+Δτ ij (t)

[0053]

[0054] Where, τ ij (t+1) represents the pheromone intensity at time t+1, ρ represents the pheromone evaporation coefficient, and Δτ ij (t) represents the pheromone left by ant k on path ij at time t, and n is the number of ants;

[0055] Path selection and search: When choosing the next node, ants rely on pheromone strength and heuristic information. Path selection is derived from the formula:

[0056]

[0057] in, Let η be the probability that ant k chooses path ij at time t. ij α represents the heuristic information for path ij, β represents the parameters controlling the importance of pheromone and heuristic information, and allowed represents the set of nodes that the ant has not yet visited.

[0058] The loop iterates until the termination condition is met, which is the predetermined number of iterations.

[0059] To solve the above-mentioned technical problems, the present invention also provides the following technical solution: a Bluetooth tag-based contactless inspection and path planning system, comprising:

[0060] The data acquisition and preprocessing module is used to acquire inspection equipment status and environmental data via WiFi and Bluetooth tags;

[0061] The risk assessment module is used to dynamically classify risk levels by analyzing historical and real-time data, as well as based on the connection time and stability between the device and the electronic tag.

[0062] The decision tree training and prediction module is used to train decision tree models to predict future inspection tasks and generate new inspection tasks based on historical data and risk level data.

[0063] The task assignment module is used to assign newly generated inspection tasks based on the location of the inspection personnel.

[0064] Automatic connection and data logging module: used to automatically establish a connection and record data when the inspection equipment enters the Bluetooth range;

[0065] Path optimization and ant colony algorithm module: Used to optimize inspection paths using ant colony optimization algorithm, integrating risk assessment and historical inspection data to provide an optimal inspection path;

[0066] The server and data upload module are used to enable the MCU of the electronic tag to automatically record the inspection data and upload it to the server via WiFi;

[0067] The emergency response and early warning module is used to issue corresponding early warnings or initiate emergency response procedures at a determined risk level.

[0068] A computer device includes: a memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, it implements the steps of the method described in any one of the present invention.

[0069] A computer-readable storage medium having a computer program stored thereon, characterized in that: when the computer program is executed by a processor, it implements the steps of the method described in this invention.

[0070] The beneficial effects of this invention are as follows: The Bluetooth tag-based contactless inspection and path planning method provided by this invention improves the operating efficiency of the factory through automated contactless inspection and intelligent path planning; it reduces human error and omissions through intelligent systems, thereby ensuring higher reliability and safety; the system reduces deployment and maintenance costs by utilizing existing low-cost technologies and intelligent algorithms; and it is flexible and scalable: the new system is not only flexible but also easily expandable to meet the needs of constantly changing and upgrading factory environments. Attached Figure Description

[0071] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0072] Figure 1 The first embodiment of the present invention provides an overall flowchart of a Bluetooth tag-based non-contact inspection and path planning method. Detailed Implementation

[0073] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0074] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0075] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0076] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0077] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0078] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0079] Example 1

[0080] Reference Figure 1 As one embodiment of the present invention, a method for contactless inspection and path planning based on Bluetooth tags is provided, comprising:

[0081] S1: Collect historical inspection data to generate inspection tasks, and automatically connect to the server and download the inspection tasks through the inspection equipment.

[0082] Furthermore, the steps for generating inspection tasks are as follows:

[0083] Real-time environmental data and inspection equipment status data, as well as historical inspection data, including dwell time, connection time and stability, are collected using Wi-Fi and Bluetooth tags. Risk level data for each area is then gathered and determined through historical events and safety assessments.

[0084] Data preprocessing: Cleaning and integrating historical data and risk level data to ensure data quality and consistency.

[0085] Model training: A prediction model is trained using a decision tree algorithm. The prediction model uses historical data and risk levels to predict future inspection tasks.

[0086] New inspection tasks are generated using a trained model. The generation of tasks will be based on historical data and risk levels to determine the frequency and priority of inspections.

[0087] Based on the location of the inspection personnel, the generated tasks are assigned to the corresponding inspection personnel.

[0088] Furthermore, the specific steps for training a prediction model using the decision tree algorithm are as follows:

[0089] Data preparation and preprocessing: Extract the following features from historical inspection data: historical connection time, regional risk level, connection stability, equipment response time, and standard deviation.

[0090] To ensure that each feature has the same influence during training, the features are standardized.

[0091] Feature selection and construction: Select the most informative features for training based on expert knowledge and historical data analysis; construct new features based on existing features, such as feature interaction terms and multinomial features, to enhance the model's predictive ability.

[0092] Decision tree model training: The dataset is divided into training and test sets to ensure the model's generalization ability, and the CART decision tree algorithm is selected for training; grid search or random search is used to find the optimal combination of hyperparameters, such as the maximum depth of the tree and the minimum number of sample splits; the optimized hyperparameters and training set are used to train the decision tree model.

[0093] Model validation and testing: Cross-validation is used to verify the stability and accuracy of the model; various performance metrics, such as precision, recall and F1 score, are used to evaluate the model's performance.

[0094] S2: When the inspection equipment enters the Bluetooth range of the electronic tag, a connection is automatically established, and the risk level is determined based on the connection time between the inspection equipment and the electronic tag.

[0095] Furthermore, when the inspection device enters the range of the Wi-Fi Bluetooth tag, the tag not only sends its ID and location information, but also environmental data of the vicinity of the inspection device and status data of connected devices. Based on the additional data provided by the Wi-Fi Bluetooth tag, the predetermined time T is dynamically adjusted. min This makes it more targeted and flexible.

[0096] Furthermore, risk levels are categorized based on the connection time between the inspection equipment and the electronic tags:

[0097] When the connection time T actual >Scheduled time T min If so, then further determine the connection stability:

[0098] When the connection stability is high, it is classified as a green risk level and monitoring continues.

[0099] When the connection stability is low, it is classified as a yellow risk level, and a warning signal is issued.

[0100] When the connection stability is low, it is classified as an orange risk level, and a signal is issued that an inspection is required.

[0101] When the connection time T actual ≤Reserved time T min If so, then further determine the connection stability:

[0102] When the connection is highly stable, it is classified as an orange risk level, and a signal is issued indicating that an inspection is required.

[0103] When the connection is unstable, it is classified as a red risk level, and an immediate check signal is issued.

[0104] When connection stability is low, it is classified as a red risk level, issuing an immediate inspection signal and initiating an emergency response procedure.

[0105] Furthermore, connection stability is measured by comparing the variance of the actual connection time with the historical connection time, expressed as:

[0106]

[0107] Where, σ 2 (T actual,i Let be the variance of the actual time of the i-th connection. This is the average of the actual connection times.

[0108] When σ 2 (T actual,i ) < T 高 When T is high, the connection stability is considered high. 高 ≤σ 2 (T actual,i ) < T 低 When T is reached, the connection stability is determined to be medium. 低 ≤σ 2 (T actual,i When T is reached, the connection stability is considered low. 高 and T 低 These are two thresholds determined based on historical data and actual needs.

[0109] Furthermore, the connection time T actual The calculation formula is:

[0110]

[0111] Among them, T actual，i Let T be the actual connection time for the i-th connection. stay，j，i Let R be the dwell time in the j-th time period during the i-th inspection. k Let w represent the risk level of the k-th region. j Let v be the dwell time weight for the j-th inspection. k Let m be the risk level weight of the k-th region, m be the total number of historical inspections, and p be the total number of regions.

[0112] Scheduled time T min The calculation formula is:

[0113]

[0114] Among them, Tavg,i Let W be the average connection time of the i-th inspection. i R represents the weight of the i-th inspection. resp,i S is the equipment response time for the i-th inspection. i Let λ1 be the standard deviation of the equipment response time during the i-th inspection, n be the total number of inspections, and λ1 and λ2 be adjustment factors.

[0115] Duration T stay The calculation formula is:

[0116]

[0117] Among them, D hist,j V represents the historical dwell time during the j-th inspection. j R represents the dwell time weight for the j-th inspection. risk,k Let Q be the risk level of the k-th region. k Let μ be the risk level weight of the k-th region, μ and ν be adjustment factors, m be the total number of historical inspections, and p be the total number of regions.

[0118] S3: The MCU of the electronic tag automatically records the inspection data and uploads it to the server via WIFI. The ant colony optimization algorithm is used to optimize the inspection path and integrate risk assessment and historical inspection data to provide an inspection path.

[0119] Furthermore, the Ant Colony Optimization (ACO) algorithm is used to optimize the inspection path, integrating risk assessment and historical inspection data to provide an optimal inspection path. The detailed steps are as follows:

[0120] The pheromone intensity is initialized based on historical inspection data and current risk level data. The initialization of pheromone intensity can be given by the following formula:

[0121] τ ij (0)=τ0+α·R k

[0122] Where, τ ij (0) represents the pheromone intensity on path ij at time t=0, where τ0 is a positive constant used to initialize the pheromone, and R k Let k be the risk level of region k, and α be a parameter used to control the impact of the risk level.

[0123] Constructing the solution and solution space: Using historical data and the output of the decision tree model, we define all possible inspection paths and their respective risk levels. The solution space can be represented by the following formula:

[0124]

[0125] Where S is the solution space, Pij Let m be the path corresponding to the i-th inspection and the j-th time period, m be the total number of historical inspections, and p be the total number of regions.

[0126] Pheromone Update and Evaporation: After each iteration, the pheromones on the path are updated and evaporated. The update and evaporation of pheromones can be represented by the following formula:

[0127] τ ij (t+1)=(1-ρ)·τ ij (t)+Δτ ij (t)

[0128]

[0129] Where, τ ij (t+1) represents the pheromone intensity at time t+1, ρ is the pheromone evaporation coefficient, and Δτ ij (t) represents the pheromone left by ant k on path ij at time t, and n is the number of ants.

[0130] Path selection and search: Ants rely on pheromone strength and heuristics (such as current risk level and historical data) when choosing the next node. Path selection can be given by the following formula:

[0131]

[0132] in, Let η be the probability that ant k chooses path ij at time t. ij Let be the heuristic information for path ij, α and β be the parameters that control the importance of pheromones and heuristic information, and allowed be the set of nodes that the ant has not yet visited.

[0133] The process iterates until a predetermined number of iterations is met. By combining risk assessment and historical data, pheromones and heuristic information are dynamically adjusted. The ACO algorithm is used to find the optimal inspection path while ensuring the safety and efficiency of the system.

[0134] This embodiment also provides a Bluetooth tag-based contactless inspection and path planning system, including:

[0135] The data acquisition and preprocessing module is used to acquire the status and environmental data of the inspection equipment via WiFi and Bluetooth tags.

[0136] The risk assessment module is used to dynamically classify risk levels by analyzing historical and real-time data, as well as based on the connection time and stability between the device and the electronic tag.

[0137] The decision tree training and prediction module is used to train decision tree models to predict future inspection tasks and generate new inspection tasks based on historical data and risk level data.

[0138] The task assignment module is used to assign newly generated inspection tasks based on the location of the inspection personnel.

[0139] Automatic connection and data logging module: used to automatically establish a connection and record data when the inspection equipment enters the Bluetooth range.

[0140] Path Optimization and Ant Colony Algorithm Module: This module uses the ant colony optimization algorithm to optimize inspection paths and integrates risk assessment and historical inspection data to provide an optimal inspection path.

[0141] The server and data upload module are used to enable the MCU of the electronic tag to automatically record inspection data and upload it to the server via WiFi.

[0142] The emergency response and early warning module is used to issue corresponding early warnings and initiate emergency response procedures under a determined risk level.

[0143] This embodiment also provides a computing device, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement a Bluetooth tag-based non-contact inspection and path planning method as proposed in the above embodiment.

[0144] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a Bluetooth tag-based non-contact inspection and path planning method as proposed in the above embodiment.

[0145] The storage medium proposed in this embodiment belongs to the same inventive concept as the Bluetooth tag-based non-contact inspection and path planning method proposed in the above embodiment. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0146] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory, magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory, magnetic variable memory, ferroelectric memory, phase change memory, graphene memory, etc. Volatile memory can include random access memory or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory or dynamic random access memory, etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include blockchain-based distributed databases, etc., and are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited thereto.

[0147] Example 2

[0148] The following is an embodiment of the present invention, which provides a method for contactless inspection and path planning based on Bluetooth tags. In order to verify the beneficial effects of the present invention, a simulation experiment is conducted for scientific demonstration.

[0149] Experimental objective: To verify the effectiveness and performance of our technical solution based on Bluetooth tags, ant colony optimization algorithm, contactless inspection, and path planning system.

[0150] Experimental scenario: Simulate a large factory environment containing 50 different areas, each equipped with various types of sensors to monitor environmental parameters such as temperature, humidity, and vibration in real time.

[0151] Inspection Implementation: Over the next two months, the Bluetooth tag-based contactless inspection and path planning system of this invention will be used to conduct inspections, ensuring that each area is inspected at least 5 times.

[0152] Data analysis: Using data analysis tools to process and analyze collected data to evaluate system performance.

[0153] Experimental results:

[0154] Inspection time: The average inspection time is 3.5 hours, which shows the efficiency of the system. This is due to the combination of ant colony optimization algorithm and non-intrusive inspection technology, which realizes fast and automatic inspection path planning and problem identification.

[0155] Problem identification: 260 problems were identified, covering 18 different categories, demonstrating the efficiency and accuracy of the solution in capturing and identifying problems.

[0156] Problem resolution time: The average problem resolution time is 45 minutes, reflecting the system's rapid response mechanism and problem-solving capabilities.

[0157] Simulation experiments verified the effectiveness and efficiency of the technical solution of this invention in actual operation. Compared with historical data of traditional solutions, this invention not only significantly reduces inspection time but also accurately identifies more types of problems, while reducing problem-solving time.

[0158] The system of this invention realizes an efficient and intelligent factory monitoring and maintenance solution through intelligent path planning and non-contact detection technology, which greatly improves operational efficiency. This shows that our invention can not only improve the existing factory operating efficiency, but also greatly improve the safety and reliability of the factory through a fast and accurate problem identification and resolution mechanism.

[0159] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for contactless inspection and path planning based on Bluetooth tags, characterized in that, include: Historical inspection data is collected to generate inspection tasks, and the inspection equipment automatically connects to the server and downloads the inspection tasks. When the inspection equipment enters the Bluetooth range of the electronic tag, a connection is automatically established, and the risk level is determined based on the connection time between the inspection equipment and the electronic tag. The MCU of the electronic tag automatically records the inspection data and uploads it to the server via WIFI. The inspection path is optimized using the ant colony optimization algorithm, and a single inspection path is provided by integrating risk assessment and historical inspection data.

2. The Bluetooth tag-based contactless inspection and path planning method as described in claim 1, characterized in that: The steps for generating the inspection task are as follows: Real-time environmental data and status data of inspection equipment, as well as historical inspection data, are collected through Wi-Fi and Bluetooth tags to gather risk level data for each area; Data preprocessing: Cleaning and integrating historical data and risk level data; Model training: A prediction model is trained using a decision tree algorithm. The prediction model predicts future inspection tasks by using historical data and risk levels. New inspection tasks are generated using the trained model. The generation of tasks will be based on historical data and risk levels to determine the frequency and priority of inspections. Based on the location of the inspection personnel, the generated tasks are assigned to the corresponding inspection personnel.

3. The Bluetooth tag-based contactless inspection and path planning method as described in claim 2, characterized in that: The steps to train a prediction model using the decision tree algorithm are as follows: Data preparation and preprocessing: Extract features from historical inspection data, including historical connection time, regional risk level, connection stability, equipment response time and standard deviation, and standardize the features. Feature selection and construction: Select the most informative features for training based on expert knowledge and historical data analysis; construct new features based on existing features to enhance the model's predictive ability; Decision tree model training: The dataset is divided into training and test sets, and the CART decision tree algorithm is selected for training; the optimal hyperparameter combination is found using grid search; the decision tree model is trained using the optimized hyperparameters and the training set. Model validation and testing: Cross-validation is used to verify the stability and accuracy of the model; various performance metrics are used to evaluate the model's performance.

4. The Bluetooth tag-based contactless inspection and path planning method as described in claim 3, characterized in that: Risk levels are determined based on the connection time between the inspection equipment and the electronic tags. When the connection time T actual >Scheduled time T min Then, further determine the connection stability: When the connection stability is high, it is classified as a green risk level and monitoring continues. When the connection stability is low, it is classified as a yellow risk level, and a warning signal is issued; When the connection stability is low, it is classified as an orange risk level, and a signal is issued that an inspection is required. When the connection time T actual ≤Reserved time T min Then, further determine the connection stability: When the connection stability is high, it is classified as an orange risk level, and a signal is issued that an inspection is required. When the connection is unstable, it is classified as a red risk level, and an immediate check signal is issued. When connection stability is low, it is classified as a red risk level, issuing an immediate inspection signal and initiating an emergency response procedure.

5. The Bluetooth tag-based contactless inspection and path planning method as described in claim 4, characterized in that: The stability of the connection is measured by comparing the variance of the actual connection time with the historical connection time, expressed as: Where, σ 2 (T actual,i Let be the variance of the actual time of the i-th connection. This is the average of the actual connection times. When σ 2 (T actual,i ) < T 高 When T is high, the connection stability is considered high. 高 ≤σ 2 (T actual,i ) < T 低 When T is reached, the connection stability is determined to be medium. 低 ≤σ 2 (T actual,i When T is reached, the connection stability is considered low. 高 and T 低为 The two thresholds were determined based on historical data and actual needs.

6. The Bluetooth tag-based contactless inspection and path planning method as described in claim 5, characterized in that: The connection time T actual The calculation formula is: Among them, T actual，i Let T be the actual connection time for the i-th connection. stay，j，i Let R be the dwell time in the j-th time period during the i-th inspection. k Let w represent the risk level of the k-th region. j Let v be the dwell time weight for the j-th inspection. k Let m be the risk level weight of the k-th region, m be the total number of historical inspections, and p be the total number of regions. The predetermined time T min The calculation formula is: Among them, T avg,i W represents the average connection time of the i-th inspection. i R represents the weight of the i-th inspection. resp,i S is the equipment response time for the i-th inspection. i Let λ1 be the standard deviation of the equipment response time during the i-th inspection, n be the total number of inspections, and λ1 and λ2 be adjustment factors. The dwell time T stay The calculation formula is: Among them, D hist,j V represents the historical dwell time during the j-th inspection. j R represents the dwell time weight for the j-th inspection. risk,k Let Q be the risk level of the k-th region. k Let μ be the risk level weight of the k-th region, μ and ν be adjustment factors, m be the total number of historical inspections, and p be the total number of regions.

7. The Bluetooth tag-based contactless inspection and path planning method as described in claim 6, characterized in that: The steps for optimizing the inspection path using the ant colony optimization algorithm are as follows: The pheromone intensity is initialized based on historical inspection data and current risk level data. The initial pheromone intensity is derived from the formula: t ij (0)=τ0+α·R k Where, τ ij (0) represents the pheromone intensity on path ij at time t=0, where τ0 is a positive constant used to initialize the pheromone, and R k Let k be the risk level of region k, and α be a parameter used to control the impact of the risk level. Constructing the solution and solution space: Using historical data and the output of the decision tree model, all possible inspection paths and their respective risk levels are defined. The solution space is expressed by the formula: Where S is the solution space, P ij Let m be the path corresponding to the i-th inspection and the j-th time period, m be the total number of historical inspections, and p be the total number of regions. Pheromone Update and Evaporation: After each iteration, the update and evaporation of pheromones along the path are expressed by the following formula: t ij (t+1)=(1-ρ)·τ ij (t)+Δτ ij (t) Where, τ ij (t+1) represents the pheromone intensity at time t+1, ρ represents the pheromone evaporation coefficient, and Δτ ij (t) represents the pheromone left by ant k on path ij at time t, and n is the number of ants; Path selection and search: When choosing the next node, ants rely on pheromone strength and heuristic information. Path selection is derived from the formula: in, Let η be the probability that ant k chooses path ij at time t. ij α represents the heuristic information for path ij, β represents the parameters controlling the importance of pheromone and heuristic information, and allowed represents the set of nodes that the ant has not yet visited. The loop iterates until the termination condition is met, which is the predetermined number of iterations.

8. A system for implementing the Bluetooth tag-based contactless inspection and path planning method as described in any one of claims 1 to 7, characterized in that, include: The data acquisition and preprocessing module is used to acquire inspection equipment status and environmental data via WiFi and Bluetooth tags; The risk assessment module is used to dynamically classify risk levels by analyzing historical and real-time data, as well as based on the connection time and stability between the device and the electronic tag. The decision tree training and prediction module is used to train decision tree models to predict future inspection tasks and generate new inspection tasks based on historical data and risk level data. The task assignment module is used to assign newly generated inspection tasks based on the location of the inspection personnel. Automatic connection and data logging module: used to automatically establish a connection and record data when the inspection equipment enters the Bluetooth range; Path optimization and ant colony algorithm module: Used to optimize inspection paths using ant colony optimization algorithm, integrating risk assessment and historical inspection data to provide an optimal inspection path; The server and data upload module are used to enable the MCU of the electronic tag to automatically record the inspection data and upload it to the server via WiFi; The emergency response and early warning module is used to issue corresponding early warnings and initiate emergency response procedures under a determined risk level.

9. A computer device, comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images