Artificial inspection dynamic planning method and device based on Internet of Things platform, and medium

Abstract

The invention discloses a manual inspection dynamic planning method and device based on an Internet of Things platform and a medium, and relates to the technical field of the Internet of Things, and the method comprises the steps: carrying out the equipment quantization parameter calibration of equipment deployment data, so as to obtain an equipment importance degree score; performing multi-dimensional equipment anomaly threshold monitoring on the real-time operation parameters of the equipment to determine the number of times of equipment anomaly; based on the equipment importance degree score and the equipment abnormity frequency, obtaining a to-be-inspected object through equipment screening score analysis; performing inspection road section dynamic adjustment on the to-be-inspected object to determine an optimal path node sequence; according to the optimal path node sequence, performing planning constraint analysis on inspection scheduling to obtain a current inspection plan; and performing inspection planning analysis on the inspection parameters obtained by real-time monitoring to determine inspection planning update parameters. According to the method, the technical problem that the adaptation degree of industrial environment manual inspection planning making and the current industrial environment is insufficient is solved.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a method, device and medium for dynamic planning of manual inspection based on an Internet of Things platform. Background Art

[0002] Driven by the Industrial Internet of Things (IIoT) technology, traditional manual inspections are gradually transforming from paper records to digital management. The existing technical system is mainly based on two core frameworks: one is the fixed-cycle inspection mode based on the enterprise-level management system, which generates a standardized task list through preset work orders and shift plans combined with the equipment maintenance manual; the other is the use of static path planning strategies, which rely on manual experience or offline rule bases to generate inspection routes, and use QR codes, RFID and other technologies to achieve personnel sign-in and task verification.

[0003] In the existing technology, manual inspection planning in industrial environments is usually unable to meet the needs of personnel scheduling and real-time monitoring in complex environments. In industrial environments with multiple devices and multiple paths, the existing technology is also unable to meet the needs of real-time object screening of inspected devices and dynamic inspection planning. It is difficult to meet the needs of effective analysis of manual inspection planning in complex industrial environments with multiple devices. In addition to the low efficiency of inspection planning, the single data analysis will also lead to insufficient adaptability of inspection planning to the current industrial environment. Summary of the invention

[0004] The embodiments of the present application provide a method, device and medium for dynamic planning of manual inspection based on an Internet of Things platform, which solves the technical problem that the manual inspection planning in an industrial environment is not sufficiently compatible with the current industrial environment.

[0005] In a first aspect, an embodiment of the present application provides a method for dynamic planning of manual inspections based on an Internet of Things platform, characterized in that the method includes: obtaining equipment deployment data of an industrial environment, and calibrating equipment quantitative parameters of the equipment deployment data to obtain an equipment importance score; obtaining real-time operating parameters of the equipment, and performing multi-dimensional equipment abnormality threshold monitoring on the real-time operating parameters of the equipment to determine the number of equipment abnormalities; obtaining an object to be inspected through equipment screening score analysis based on the equipment importance score and the number of equipment abnormalities; dynamically adjusting the inspection section of the object to be inspected to determine the optimal path node sequence; obtaining the current inspection plan through planning constraint analysis of the inspection schedule based on the optimal path node sequence; monitoring the current inspection plan in real time, and performing inspection planning analysis on the inspection parameters obtained by real-time monitoring to determine the inspection plan update parameters.

[0006] In one implementation of the present application, the device deployment data is calibrated with device quantitative parameters to obtain a device importance score, specifically including: based on a preset importance level list, the device deployment data is configured with device importance to obtain device importance data; and the device importance data is calibrated with quantitative parameters to obtain a device importance score.

[0007] In one implementation of the present application, multi-dimensional device abnormality threshold monitoring is performed on the real-time operating parameters of the device to determine the number of device abnormalities, specifically including: classifying the real-time operating parameters of the device into abnormal states to obtain the type of device abnormal state; based on the type of device abnormal state, determining the number of device abnormalities through abnormal state monitoring.

[0008] In one implementation of the present application, based on the equipment importance score and the number of equipment anomalies, the equipment screening score analysis is performed to obtain the object to be inspected, specifically including: based on the equipment importance score and the number of equipment anomalies, the equipment screening score is evaluated by the equipment screening score to be inspected to obtain the equipment screening score; wherein the calculation formula for evaluating the screening score of the equipment to be inspected is:

[0009] in, Filter the score for the device, is the equipment asset price, is the equipment importance score, is the number of equipment abnormalities; the equipment screening scores are divided into groups to obtain a set of equipment arrays to be inspected; wherein, the division of the group range includes: sorting of screening scores, division of sub-data groups, and division of target data groups. The division formula of the sub-data group division is:

[0010] in, Filter the elements sorted by scores for the device, for Adjacent elements of; Based on the array set of devices to be inspected, the objects to be inspected are obtained by dynamically updating the preference requirements.

[0011] In one implementation of the present application, the inspection section of the inspection object is dynamically adjusted to determine the optimal path node sequence, specifically including: determining the equipment inspection node based on the inspection object, and performing inspection priority path analysis on the equipment inspection node through the Dijkstra algorithm to determine the inspection priority queue; performing edge weight analysis on the equipment inspection node of the inspection priority queue to obtain the node path edge weight; wherein the calculation formula of the g point and the h point in the equipment inspection node is:

[0012] in, is the path passing time, is the road condition index, The inspection personnel's path selection preference index; determine the inspection path vector according to the node path edge weight, and construct the graph structure of the inspection path vector to obtain the inspection path structure data; store the inspection path structure data as a graph structure dictionary, and perform predecessor node processing on the graph structure dictionary to determine the optimal path node sequence.

[0013] In one implementation of the present application, according to the optimal path node sequence, the current inspection plan is obtained by analyzing the planning constraints of the inspection schedule, specifically including: determining the key parameters of the inspection group according to the optimal path node sequence, and determining the shortest total inspection time by optimizing the total inspection time based on the key parameters of the inspection group; wherein the objective function of the total inspection time optimization is:

[0014] in, For the inspection team From the inspection point Arrival at the inspection point time, is the inspection point decision variable, and the value range of the decision variable is , No. The number of inspection points required by an inspection group, m is the number of types of problems to be inspected in the corresponding industrial scenario; based on the shortest total inspection time, the inspection scheduling time range constraint is used to obtain the current inspection plan; among which, the constraint conditions of the inspection scheduling time range constraint are:

[0015] in, , For the Inspection teams arrive at the inspection point , time, For the inspection team At the inspection point The length of inspection at the department.

[0016] In one implementation of the present application, an inspection planning analysis is performed on the inspection parameters obtained from real-time monitoring to determine the inspection planning update parameters, specifically including: calculating the inspection time of the inspection parameters to obtain the inspection time of the inspection personnel's equipment; matching the inspection time of the inspection personnel's equipment with the processing time of the equipment exception processing type to determine the exception processing time of the equipment exception type; based on the exception processing time of the equipment exception type, the inspection planning update parameters are determined by updating the periodic exception processing planning parameters.

[0017] In one implementation of the present application, after performing an inspection planning analysis on the inspection parameters obtained through real-time monitoring to determine the inspection planning update parameters, the method also includes: updating the inspection planning update parameters to the current inspection plan, and performing real-time inspection monitoring on the updated current inspection plan to obtain the inspection time period; based on the inspection time period, obtaining the subsequent inspection path planning period update parameters through periodic inspection service time analysis; obtaining the inspection punch-in data, and performing an inspection completion status analysis on the inspection punch-in data to obtain the inspection completion rate; and determining the dynamic adjustment parameters of the personnel inspection work through the inspection completion status threshold judgment based on the inspection completion rate.

[0018] In the second aspect, the embodiment of the present application also provides a manual inspection dynamic planning device based on the Internet of Things platform, characterized in that the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that the at least one processor can: obtain equipment deployment data of the industrial environment, and calibrate the equipment quantitative parameters of the equipment deployment data to obtain the equipment importance score; obtain the real-time operation parameters of the equipment, and perform multi-dimensional equipment abnormality threshold monitoring on the real-time operation parameters of the equipment to determine the number of equipment abnormalities; based on the equipment importance score and the number of equipment abnormalities, obtain the object to be inspected through equipment screening score analysis; dynamically adjust the inspection section of the object to be inspected to determine the optimal path node sequence; according to the optimal path node sequence, obtain the current inspection plan through planning constraint analysis of the inspection schedule; monitor the current inspection plan in real time, and perform inspection planning analysis on the inspection parameters obtained by real-time monitoring to determine the inspection plan update parameters.

[0019] On the third aspect, the embodiment of the present application also provides a non-volatile computer storage medium for dynamic planning of manual inspections based on an Internet of Things platform, storing computer executable instructions, characterized in that the computer executable instructions are set to: obtain equipment deployment data of an industrial environment, and calibrate equipment quantitative parameters of the equipment deployment data to obtain an equipment importance score; obtain real-time operating parameters of the equipment, and perform multi-dimensional equipment abnormality threshold monitoring on the real-time operating parameters of the equipment to determine the number of equipment abnormalities; based on the equipment importance score and the number of equipment abnormalities, obtain the object to be inspected through equipment screening score analysis; dynamically adjust the inspection section of the object to be inspected to determine the optimal path node sequence; according to the optimal path node sequence, obtain the current inspection plan through planning constraint analysis of the inspection schedule; monitor the current inspection plan in real time, and perform inspection planning analysis on the inspection parameters obtained by real-time monitoring to determine the inspection plan update parameters.

[0020] The embodiments of the present application provide a method, device and medium for dynamic planning of manual inspection based on an Internet of Things platform. Through inspection object management, inspection path analysis, inspection planning, inspection execution judgment and personnel management, the technical problem of insufficient adaptability of manual inspection planning in an industrial environment to the current industrial environment is solved, the dynamic formulation of inspection planning is realized, the adaptability of manual inspection planning in complex industrial environments is improved, and the travel time of manual inspection paths in complex industrial environments is optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flow chart of a method for dynamic planning of manual inspection based on an Internet of Things platform provided in an embodiment of the present application; Figure 2 A structural diagram of a manual inspection dynamic planning system based on an Internet of Things platform provided in an embodiment of the present application; Figure 3 A schematic diagram of the internal structure of a manual inspection dynamic planning device based on an Internet of Things platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0023] The embodiments of the present application provide a method, device and medium for dynamic planning of manual inspection based on an Internet of Things platform. Through inspection object management, inspection path analysis, inspection planning, inspection execution judgment and personnel management, the technical problem of insufficient adaptability of manual inspection planning in an industrial environment to the current industrial environment is solved, the dynamic formulation of inspection planning is realized, the adaptability of manual inspection planning in complex industrial environments is improved, and the travel time of manual inspection paths in complex industrial environments is optimized.

[0024] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0025] Figure 1 A flow chart of a method for dynamic planning of manual inspection based on an Internet of Things platform is provided in an embodiment of the present application. Figure 1As shown, the embodiment of the present application provides a method for dynamic planning of manual inspection based on an Internet of Things platform, which specifically includes the following steps: Step 101: Acquire equipment deployment data of an industrial environment, and calibrate equipment quantitative parameters of the equipment deployment data to obtain equipment importance scores.

[0026] Exemplarily, the equipment deployment data is calibrated with equipment quantitative parameters to obtain equipment importance scores, and the importance of equipment inspections is intuitively represented by the quantitative scores.

[0027] Specifically, based on a preset importance level list, the device deployment data is configured with respect to the device importance level to obtain the device importance data; and the device importance data is calibrated with quantitative parameters to obtain the device importance level score.

[0028] In one embodiment, first, the operating data of various types of equipment in the industrial environment and the data returned by the handheld mobile terminal are collected in real time, including but not limited to the physical parameters of the equipment such as temperature, pressure, rotation speed, vibration frequency, the operating status of the equipment (such as power on, power off, fault, etc.), inspection results, personnel location, etc., to determine the equipment deployment data.

[0029] Through a variety of stable and reliable communication protocols (such as MQTT, HTTP, etc.), the collected data is transmitted to the IoT platform by wired or wireless communication. The IoT platform stores the data in the data storage module and waits for subsequent calls.

[0030] When creating a piece of equipment information in this submodule, the operator needs to open the equipment registration page and enter basic information such as equipment name, model, number, manufacturer, purchase date, etc. Select the importance of the equipment from the preset importance level list (such as high, medium, and low) to indicate the criticality of the equipment in industrial production. The importance level list is set in advance according to the actual needs of the user.

[0031] Each importance corresponds to a quantitative score. For example, the importance levels are artificially divided into [extremely high importance, high importance, medium importance, low importance, extremely low importance], and the corresponding quantitative scores are [5, 4, 3, 2, 1] to indicate the criticality of the equipment in industrial production.

[0032] IBM Maximo is an asset management software, in which the different importance levels in the importance column are set by the user through modular functions. The settings include how many importance levels there are, what the name of each level is, what color it is represented by, etc.

[0033] Through the equipment asset importance configuration of IBM Maximo, the importance of equipment parameters is divided into [extremely high importance, high importance, medium importance, low importance, extremely low importance] to determine the equipment parameter importance sequence to characterize the importance ranking of the operating parameters of the same equipment.

[0034] Furthermore, the location information can be determined by manual input or by clicking on the map to locate it. Manual input refers to manually filling in the longitude and latitude coordinates of the device's location in the location information input box. This submodule also integrates professional map services (such as Baidu Maps and Amap API). You can click the "Map Location" button to pop up the map interface. By clicking on the actual location of the device on the map, the system automatically obtains and fills in the longitude and latitude information. Fill in the purchase price, depreciation information and other asset-related data of the equipment to provide a basis for asset accounting. After confirming that all the information is filled in correctly, click the "Submit" button and the system will save the equipment asset information to the database.

[0035] Finally, the asset price corresponding to the sth device, s∈S, of the S registered devices is set to , according to the preset importance degree quantification relationship, the corresponding importance degree score is set as .

[0036] Step 102: Acquire real-time operating parameters of the device, and perform multi-dimensional device abnormality threshold monitoring on the real-time operating parameters of the device to determine the number of device abnormalities.

[0037] For example, in order to obtain specific data on equipment abnormalities, multi-dimensional equipment abnormality threshold monitoring is performed on the real-time operating parameters of the equipment to determine the specific number of abnormalities of the industrial equipment, thereby satisfying the background data acquisition for abnormal analysis of each device in a complex industrial environment.

[0038] In one implementation of the present application, multi-dimensional device abnormality threshold monitoring is performed on the real-time operating parameters of the device to determine the number of device abnormalities, specifically including: classifying the real-time operating parameters of the device into abnormal states to obtain the type of device abnormal state; based on the type of device abnormal state, determining the number of device abnormalities through abnormal state monitoring.

[0039] In one embodiment, the device information is read from the database of the device asset management submodule to automatically generate a device information list, which can configure the measurement points of the data acquisition module for specific devices, set the abnormal type of the device and its judgment rules.

[0040] Then, the data collected and uploaded during the operation of the equipment is received in real time, such as temperature, pressure, flow, vibration and other parameters. According to the preset judgment rules, the collected data is analyzed to determine whether the equipment is abnormal and what kind of abnormality has occurred. In addition to the means of real-time monitoring, in order to avoid the abnormalities in some equipment not being detected, the abnormal events found during manual inspections will also be uploaded to the Internet of Things platform through handheld mobile terminals and stored in the data storage module.

[0041] Next, we divide the m types of abnormal conditions to be inspected in the corresponding specific industrial scenarios. For example, the three types of equipment abnormalities in the water supply scenario (m=3) and their corresponding judgment rules are as follows: The first is abnormal water quality: indicators such as pH value, turbidity, and microbial content in the water exceed the normal range. The judgment rule is threshold judgment. For example, when the pH value is lower than 6.5 or higher than 8.5, the turbidity is greater than 5NTU, and the microbial content exceeds the value specified by the national standard, it is judged that the water quality is abnormal. The second is mechanical failure: water pump impeller wear, valve sealing is not tight, pipe rupture, etc. The judgment rule is to monitor the vibration frequency and amplitude of the water pump through the vibration sensor. If it exceeds the normal threshold, it is judged that the water pump may have faults such as impeller wear; for valves, the pressure sensor is used to detect the pressure difference before and after the valve. If the pressure difference exceeds the normal range and the flow is abnormal, it is judged that the valve may not be sealed tightly; for pipelines, the flow sensor and pressure sensor are used to make a comprehensive judgment. If the flow suddenly decreases and the pressure changes abnormally, there may be a pipeline rupture. The third is electrical failure: motor overload, short circuit, aging of the distribution cabinet line, poor contact, etc. Judgment rules: Monitor the motor current through the current sensor. If the current exceeds a certain proportion of the rated current, the motor is judged to be overloaded. Use the insulation resistance tester to detect the insulation resistance of the distribution cabinet line. If the insulation resistance is lower than the specified value, it is judged that the line may be aged or have poor contact.

[0042] Finally, a counter is set for each device s and each abnormality type k. Whenever an abnormality is detected, the corresponding counter is incremented by 1. For the kth type of abnormality, , the abnormal count of the sth device is .

[0043] Step 103: Based on the equipment importance score and the number of equipment abnormalities, the equipment screening score is analyzed to obtain the object to be inspected.

[0044] For example, after determining the importance score of the equipment and the number of equipment anomalies, it is necessary to distinguish the priority of the equipment inspection for the actual equipment inspection needs, so as to determine which equipment is more in need of the arrangement of inspection tasks under the current circumstances, so as to improve the rationality and timeliness of the equipment inspection plan. Similarly, the present application can also meet the iterative update of the objects to be inspected for the periodic inspection tasks, so as to meet the timeliness of the inspection plan formulation in a complex industrial environment.

[0045] Specifically, based on the equipment importance score and the number of equipment anomalies, the equipment screening score analysis is performed to obtain the object to be inspected, including: based on the equipment importance score and the number of equipment anomalies, the equipment screening score is evaluated to obtain the equipment screening score; wherein the calculation formula for evaluating the screening score of the equipment to be inspected is:

[0046] in, Filter the score for the device, is the equipment asset price, is the equipment importance score, is the number of equipment abnormalities; the equipment screening scores are divided into groups to obtain a set of equipment arrays to be inspected; wherein, the division of the group range includes: sorting of screening scores, division of sub-data groups, and division of target data groups. The division formula of the sub-data group division is:

[0047] in, Filter the elements sorted by scores for the device, for Adjacent elements of; Based on the array set of devices to be inspected, the objects to be inspected are obtained by dynamically updating the preference requirements.

[0048] In one embodiment, the collected equipment asset prices are read from the data storage module. , importance score , anomaly count , set the screening score , through the equipment screening score analysis, the objects to be inspected are obtained, and the inspection equipment screening score evaluation is explained by the following formula: (1) in, Filter the score for the device, is the equipment asset price, is the equipment importance score, The number of device exceptions.

[0049] The principle of setting the screening score is to prioritize inspections of equipment that is high in asset value, important, and more prone to certain types of accidents.

[0050] It should be noted that the principle of setting the screening score is to prioritize equipment that is high in asset value, important, and more prone to certain types of accidents as objects of inspection. The setting of equipment value and the number of abnormal occurrences is also determined based on actual conditions.

[0051] Furthermore, in an actual industrial environment, equipment with low value and prone to abnormalities will have a low importance index and be called low-quality consumable parts. They will not be used in key production links and production lines, and inspections are of little significance. Preventive maintenance strategies are often adopted, with regular replacement and scrapping.

[0052] Equipment that needs inspection and maintenance is often relatively important and critical equipment with high equipment value. Take the water pump commonly used in the water treatment field as an example. The economic value of a 1900kw water pump is usually more than 200,000 yuan. Assuming that it has 4 failures in a short period of time, the product of the two is also 800,000 yuan*times. Similarly, equipment of the same importance as the pump, even if it fails once, is generally worth more than 800,000 yuan, but the proportion of the above equipment is also very small, and it is often because it is very critical equipment that will not fail.

[0053] In this case, low-priced devices with many failures will still be selected for inspection first, avoiding the problem that in the prior art, low-priced devices with many abnormalities will not be inspected because of their low prices and low screening scores, and abnormal failures cannot be truly eliminated. An array of device screening scores , according to which The values ​​are rearranged from large to small into an array ,in , .

[0054] Divide the array according to the principle of data mutation , and form a sub-array. The specific process is as follows: Calculate the value of two adjacent elements in array B and The difference is explained by the following formula: , (2) in, Filter the elements sorted by scores for the device, for Adjacent elements of There are S-1 differences in total, which together form a new set .

[0055] According to the user's desire to classify the objects to be inspected into several categories, assuming there are W categories, then pick out the largest W-1 numbers in set b, record the subscripts of these numbers, and sort them in descending order according to the subscripts. , , , According to these subscripts, it can be divided into new W groups of arrays, which are , , , According to the needs of users, one or several sets are selected as the objects of inspection, and the devices corresponding to the elements in these sets are found, thus completing the selection of the devices to be inspected.

[0056] Finally, the objects to be inspected are divided into three categories: [worthy of inspection, inspectable, not worthy of inspection], i.e., W=3. In the case of 30 devices in total, i.e., S=30, select the two elements with the largest numbers in set b and set them as and ,Right now , .

[0057] Therefore, according to and The subscripts 15 and 20 divide the B array into three arrays , , .

[0058] The above three arrays correspond to "worth inspection", "can be inspected" and "not worth inspection" respectively. Assume that the user only wants to select the "worth inspection" array as the object to be inspected. The corresponding 15 devices are the selected objects to be inspected.

[0059] The one-dimensional array is divided according to the mutations, and the two with the largest differences are selected to divide the data into three groups, which are respectively set as very important, generally important, and relatively unimportant.

[0060] It should be noted that the objects to be inspected are not static. They can change according to user preferences and the update of data such as the device list and inspection task completion rate in the IoT platform. The principle of data mutation refers to the sudden and significant change of data values ​​at a certain point in time or in a certain area in the data sequence, and this change does not conform to the original trend or pattern of the data. The objects to be inspected are divided into three categories: [worthy of inspection, inspectable, and not worthy of inspection], that is, W=3. The value of W can be adjusted according to actual conditions, and can be divided into 2 categories, 4 categories or even more. It can be set by the user based on actual needs.

[0061] For the two elements b15 and b20 with the largest numbers, it indicates that the difference b15 between the 16th value and the 15th value, and the difference between the 20th and 21st elements are too large, and mutations have occurred between these two pairs of data. According to the principle of data mutation, the first 15 data are considered to be a stable trend data group, the 15th to 20th data are the second stable trend data group, and the 21st to 30th data are the third stable trend data group. Therefore, according to the size of the equipment screening score, the three categories of worth inspection, inspectable, and not worth inspection divided by users in W are determined in turn.

[0062] Similarly, "worthy of inspection", "possible to inspect" and "not worth inspecting" are only relative inspection suggestions, which can be adjusted and named according to the value of W. At the same time, the analysis of the objects to be inspected based on data mutation has a more sensitive detection capability for abnormal change data and is more suitable for complex industrial scenarios.

[0063] Finally, we can get the data set of inspection points for each inspection group. is the number of inspection points required by the kth inspection group (excluding the starting point).

[0064] Step 104: Dynamically adjust the inspection section of the inspection object to determine the optimal path node sequence.

[0065] For example, since there are a large number of inspection objects and the manual inspection path for each inspection object (equipment) is not unique, it is necessary to analyze the optimal path for manual inspection so that inspection personnel can reach the inspection object as quickly as possible and perform the inspection task in the current industrial system environment.

[0066] Specifically, the inspection section of the inspection object is dynamically adjusted to determine the optimal path node sequence, including: determining the equipment inspection node based on the inspection object, and performing inspection priority path analysis on the equipment inspection node through the Dijkstra algorithm to determine the inspection priority queue; performing edge weight analysis on the equipment inspection node of the inspection priority queue to obtain the node path edge weight; wherein, the calculation formula for the edge weight analysis from the equipment inspection node g to the node h is:

[0067] in, is the path passing time, is the road condition index, A preference index is selected for the inspection personnel's path; the inspection path vector is determined according to the node path edge weight, and the inspection path vector is graph-structured to obtain the inspection path structure data; the inspection path structure data is stored as a graph structure dictionary, and the graph structure dictionary is processed by predecessor nodes to determine the optimal path node sequence.

[0068] In one embodiment, first, obtain high-definition images. Use a drone to take aerial photos of industrial scenes at a suitable height and angle to ensure that high-resolution, clear, complete and well-lit images are obtained; when using remote sensing images, it is necessary to obtain regional images in industrial environments that meet accuracy requirements. Use image editing or processing software (such as Photoshop, ENVI, etc.) to preprocess the acquired images, including removing noise, adjusting brightness and contrast, and performing geometric corrections to improve image quality and provide a good foundation for subsequent analysis. Use professional geographic information system (GIS) software (such as ArcGIS) to import the processed images. Through the vectorization tool of GIS software, the path features in the image can be extracted by spectral, texture, and shape-based methods, and the path can be converted into vector data.

[0069] The path is vectorized, and the extracted road pixels are converted to a specific value (such as 1) and non-road pixels are converted to another value (such as 0) through binarization to simplify subsequent processing; the binarized image is thinned, and the road pixel width is reduced to one pixel width using a morphological thinning algorithm (such as the Zhang-Suen algorithm) while maintaining road connectivity to obtain the road centerline; finally, through vectorization software or algorithms, a tracking-based method is used to track the centerline pixel by pixel from the road endpoint, record the node coordinates and convert them into a vector format (such as Shapefile or GeoJSON) to accurately represent the location, length, shape and other information of the road. Finally, using the path vector data generated in the GIS software, combined with the actual needs of the factory and factors such as logistics, personnel flow, and whether it is passable, the Dijkstra algorithm is used to calculate the shortest path between any two locations to be inspected and store it as a path dataset.

[0070] Dynamic adjustment of inspection sections requires dynamic allocation of edge weights through the Dijkstra algorithm, which is used to calculate the shortest path from a source node to all other nodes in a weighted graph. This algorithm is used to calculate the path with the least cost from a source node to all other nodes in a weighted graph. There are N points on the weighted graph, and the connecting line represents that there is a path between the two points. The number on each edge represents the cost of going from one point to another, including the distance of the journey and the time it takes for the pregnancy test personnel to pass.

[0071] It should be noted that there are great differences between nodes and between inspection points. One inspection point may contain multiple nodes.

[0072] The goal of establishing the graph structure is to obtain the path with the shortest travel time between two inspection points, taking into full account the actual needs of the factory and the logistics and personnel flow conditions. The actual factors such as whether it is passable, the busyness of logistics, and the density of personnel flow are quantified as the weight of the edge between two adjacent nodes on the path, as follows: The edge weight analysis of the device inspection node of the inspection priority queue is performed to obtain the node path edge weight; wherein, the edge weight analysis from the device inspection node g to the node h is explained by the following formula: (3) in, is the path passing time, is the road condition index, Inspection personnel’s route selection preference index.

[0073] Furthermore, the inspection personnel's path selection preference index It is obtained based on the inspection records in the IoT platform. By counting the number of times the inspectors walk through each edge over a period of time and standardizing these data, the probability of them passing through each edge can be calculated by dividing the number of times they walk through a certain edge by the total number of times they walk through all edges between two nodes. This probability is the inspectors' path selection preference index. In the initial case, because there is no historical inspection data accumulation, the inspection personnel path selection preference index of all edges between two nodes is are set equal.

[0074] Furthermore, the road condition index Affected by whether passage is allowed and the flow of logistics and people, the value range is For a convenient and unobstructed path, It can be set to 1; for routes with slow traffic due to busy logistics, increase this value accordingly. , for example, set it to 5; for paths that are not allowed to pass, Set to infinity or a very large number such as 10000.

[0075] Furthermore, through time is the time it takes for the inspector to pass between two nodes. Initially, assume that the travel speed of each path on the map is the same, and the weight of each feasible path is the value of the path length divided by the walking speed, that is, the total travel time However, as the IoT platform accumulates data, the actual travel time of each path is updated based on historical data.

[0076] It should be noted that the design of the preference index fully considers the actual environment. In a park, the road conditions and travel time of different routes vary. Some roads may cause certain safety hazards to passers-by due to construction, and inspection personnel will choose to bypass dangerous areas.

[0077] By reflecting the preference index with the number of times the route is passed, the inspectors' consideration of actual conditions is incorporated, which greatly avoids some unfavorable factors on the inspection route for the inspectors, truly considers the needs and safety of the inspectors, and the number of times passed within a certain time range can represent the inspectors' action preferences within that period of time. The preference index is not simply affected by the inspectors' subjective feelings, but also by environmental changes such as construction and road conditions, thus avoiding the singularity of subjective judgment.

[0078] Furthermore, in the implementation of the Dijkstra algorithm, in addition to recording the distance of the shortest path, the node sequence of the path also needs to be recorded. By introducing a `previous` dictionary in the algorithm, it is used to record the predecessor node of each node in the shortest path. After the algorithm ends, starting from the target node, by backtracking the predecessor node, a complete shortest path node sequence is gradually generated. The calculated shortest path information is converted into a geospatial data format for storage.

[0079] Any two inspection locations in an industrial environment , The shortest feasible path between can be abstracted into an edge. The set of these edges is It should be noted that as the IoT platform accumulates data and updates the weights between nodes in real time, that is, the shortest path data set A is constantly updated.

[0080] Step 105: According to the optimal path node sequence, the current inspection plan is obtained by analyzing the planning constraints of the inspection schedule.

[0081] Exemplarily, the present application solves the path planning of each inspection group within the planned time range, the arrangement of the inspection sequence of each inspection point, and the inspection group allocation plan for each inspection point through planning constraint analysis of the inspection schedule.

[0082] It should be noted that if the planning constraint analysis specifies a planned path for one day, the relevant parameters (such as the shift schedule, the set of points to be inspected, etc.) are obtained or calculated based on the time range of one day.

[0083] Specifically, according to the optimal path node sequence, the current inspection plan is obtained by analyzing the planning constraints of the inspection schedule, which specifically includes: determining the key parameters of the inspection group according to the optimal path node sequence, and determining the shortest total inspection time by optimizing the total inspection time based on the key parameters of the inspection group; wherein the objective function of the total inspection time optimization is:

[0084] in, For the inspection team From the inspection point Arrival at the inspection point time, is the inspection point decision variable, and the value range of the decision variable is , No. The number of inspection points required for each inspection group; based on the shortest total inspection time, the current inspection plan is obtained through the inspection scheduling time range constraint; among which, the constraints of the inspection scheduling time range constraint are:

[0085] in, , For the Inspection teams arrive at the inspection point , time, For the inspection team At the inspection point The length of inspection at the department.

[0086] In one embodiment, the following parameters are determined by acquiring key parameters of dynamic inspection: m is the total number of inspection personnel groups and abnormal situation classifications, ; is the number of inspection points required by the kth inspection group (excluding the starting point); The earliest starting time of the inspection task at inspection point i in the inspection group k schedule, which is generally the working time of the kth group of personnel; The latest end time of inspection point i in the inspection group k schedule, which is generally the end time of the kth group personnel; It is the time for inspection group k to arrive at inspection point j from inspection point i. This parameter will be updated by the inspection execution judgment module as the IoT platform runs; is the inspection time of inspection group k at inspection point i. This parameter can be set to 0 when there is no relevant data. However, as the inspection records in the IoT platform accumulate, the inspection execution judgment module will perform calculations and parameter updates.

[0087] First, according to the optimal path node sequence, the key parameters of the inspection group are determined, and based on the key parameters of the inspection group, the shortest total inspection time is determined by optimizing the total inspection time. Among them, the objective function of total inspection time optimization is: (4) in, For the inspection team From the inspection point Arrival at the inspection point time, is the inspection point decision variable.

[0088] For the constraints of the objective function, the first constraint is constrained by the value of the decision variable, and the value range of the decision variable is

[0089] in, No. The number of inspection points required for each inspection group.

[0090] Then, the status of each inspection team is either not dispatched or triggered. If the status is dispatched, the inspection team must start from the origin and return to the origin. This origin is different from the waiting inspection point, which refers to the daily work or standby location of the inspection team.

[0091] Therefore, based on the status of the inspection group, the second constraint can be obtained, which is explained by the following formula: (5) Furthermore, the third constraint is used to ensure that the inspection points assigned to each inspection group k should be visited and visited once, which is explained by the following formula: (6) Furthermore, the fourth constraint is used to ensure the size relationship between the service start times of the adjacent nodes being inspected, where M is a large positive number used in the Big-M method in linear programming to implement the conditional constraint. It is recommended that it be a value not less than +1. The current inspection plan is obtained by constraining the inspection schedule time range; the constraint condition of the inspection schedule time range constraint (the fourth constraint condition) is: (7) in, , For the Inspection teams arrive at the inspection point , time, For the inspection team At the inspection point The length of inspection at the department.

[0092] Furthermore, the fifth constraint is used to ensure that the time to reach a patrol point is within the range allowed by the shift schedule, which is explained by the following formula.

[0093] (8) It should be noted that vehicle routing problems with time windows (VRPTW) refer to a certain number of customers, each of whom has different quantities of goods demanded. A distribution center provides goods to customers, and a fleet is responsible for delivering the goods and organizing appropriate driving routes. The goal is to meet customer needs and achieve goals such as shortest distance, lowest cost, and least time under certain constraints.

[0094] The constraint condition proposed in this application is a variant of the VRPTW model, and the first constraint condition is constrained by the value of the decision variable.

[0095] The first constraint is constrained by the value of the decision variable; The second constraint and the third constraint are used to ensure that the inspection points assigned to each inspection group k should be visited and visited once; The fourth constraint condition is used to ensure the size relationship of the service start time of the adjacent nodes being inspected; The fifth constraint is used to ensure that the time to reach a patrol point is within the range allowed by the schedule; Based on the above constraints, the inspection group allocation plan for each inspection point can be met, which avoids subjective analysis and obtains constraints through VRPTW model improvement, thereby improving the real-time and rationality of inspection planning.

[0096] Through the construction of the above-mentioned constraints and objective functions, this application realizes the path planning of each inspection group within the planned time range, the arrangement of the inspection order of each inspection point to be inspected, and the reasonable configuration of the inspection group allocation plan for each inspection point to be inspected, further improving the real-time and rationality of the inspection plan.

[0097] Step 106: Monitor the current inspection plan in real time, and perform inspection plan analysis on the inspection parameters obtained by real-time monitoring to determine the inspection plan update parameters.

[0098] For example, for personnel positioning, the location of personnel can be grasped in real time, so that managers can monitor in real time whether the inspection personnel are working according to the scheduled inspection plan and time nodes. By optimizing the inspection route, the actual walking route and stay time of the inspection personnel can be understood, and the existing inspection route can be evaluated whether it is reasonable. According to the analysis results, the inspection route can be optimized and adjusted to reduce unnecessary trips and improve inspection efficiency.

[0099] Specifically, an inspection planning analysis is performed on the inspection parameters obtained from real-time monitoring to determine the inspection planning update parameters, including: calculating the inspection time of the inspection parameters to obtain the equipment inspection time of the inspection personnel; matching the equipment inspection time of the inspection personnel with the processing time of the equipment exception processing type to determine the exception processing time of the equipment exception type; based on the exception processing time of the equipment exception type, the inspection planning update parameters are determined by updating the periodic exception processing planning parameters.

[0100] In one embodiment, each device to be inspected is installed with an RFID tag, which stores basic information of the device, including detailed information such as device model, number, and specifications, providing necessary device identification and basic data support for the inspection process.

[0101] First, when the inspectors arrive at each inspection point (device to be inspected), they can choose to scan the QR code posted near the device, or use the NFC function of the handheld mobile terminal and the RFID of the device to trigger and complete the point inspection and clocking in operation. At the moment of successful scanning, the mobile terminal obtains the basic information of the device and records the scanning time at the same time. This time point is used as the starting time for the inspection personnel to start inspecting the equipment.

[0102] Then, the data of inspection personnel punching in and equipment inspection completion is uploaded to the IoT platform, which calculates , we can accurately obtain the inspection time of the inspection personnel at the device this time, average the inspection time recorded in the parameter update cycle, and record it as the service time for type k abnormality at point i .

[0103] Furthermore, the parameter update cycle is set to one month. In January, three inspections were carried out on the ventilator, the equipment to be inspected, for motor abnormality types. The inspection time was 1 hour, 2 hours, and 3 hours respectively. The average inspection time was 2 hours, which is recorded as the service time for abnormality type k at point i. The updated parameters will be used in the inspection route planning in February.

[0104] Furthermore, after performing inspection planning analysis on the inspection parameters obtained by real-time monitoring to determine the inspection planning update parameters, the method also includes: updating the inspection planning update parameters to the current inspection plan, and performing real-time inspection monitoring on the updated current inspection plan to obtain the inspection time period; based on the inspection time period, obtaining the subsequent inspection path planning period update parameters through periodic inspection service time analysis; obtaining inspection punch-in data, and performing inspection completion status analysis on the inspection punch-in data to obtain the inspection completion rate; and determining the dynamic adjustment parameters of personnel inspection work based on the inspection completion rate through inspection completion status threshold judgment.

[0105] In one embodiment, the IoT platform counts the number of inspection points that each inspection group has completed punching in in real time based on the received punch-in information. The inspection completion rate formula is used to calculate the inspection completion rate of each inspection group. The inspection completion rate formula is explained by the following formula: (9) in, is the number of inspection points required by the kth inspection group (excluding the starting point). This inspection completion rate not only allows management personnel to know the inspection situation, but can also be used to adjust the arrangement of the inspection process. When it is less than 1, the parameters can be dynamically adjusted as follows based on the value of the inspection completion rate: when , we should first consider adjusting the user preferences in the inspection object screening module to reduce the number of objects to be inspected, that is, to reduce .

[0106] when , we should first consider increasing the number of personnel in the inspection group. The upper limit is taken as 0.9 here, but in actual situations it can be solved by the following method. Assuming that there are peo inspection personnel in the kth inspection group, the upper limit is .

[0107] when , the working hours of workers should be appropriately increased in the inspection personnel management module, that is, and The new working hours and the old working hours should satisfy the following relationship: .

[0108] Figure 2 A structural diagram of a manual inspection dynamic planning system based on an Internet of Things platform provided in an embodiment of the present application.

[0109] In one embodiment, a manual inspection dynamic planning system structure based on the Internet of Things platform is composed of the following modules: Information collection module: The data collection module includes all sensors and instruments deployed on instruments in the industrial environment, handheld mobile terminals of inspection personnel, etc. It can also collect and pre-process data.

[0110] Internet of Things Platform: The Internet of Things Platform is the main body of the system, which is used to control the cooperation between various modules. It has the functions of equipment connection, management and monitoring, including equipment asset management submodule, equipment status monitoring submodule and visual operation interface submodule, and can also exchange data with data acquisition module, inspection object management module, personnel management module, personnel positioning module, inspection execution judgment module and data storage information.

[0111] Equipment asset management submodule: It is aimed at industrial environments and aims to manage existing equipment comprehensively and efficiently. By registering the importance of the equipment, its location (latitude and longitude positioning and support map click confirmation), asset price and other information, it realizes the digital management of equipment assets and provides accurate equipment information query, analysis and decision support for industrial enterprises.

[0112] Equipment status monitoring submodule: This module is designed to monitor the status of equipment in industrial environments in real time. By reading the equipment information registered in the equipment asset management submodule, the equipment is classified according to the abnormal type, which is convenient for subsequent allocation to different inspection groups. Combined with the data uploaded by the data acquisition module, a variety of judgment rules are used to achieve real-time monitoring, and the number of abnormalities of different equipment is counted, providing strong support for equipment management and maintenance.

[0113] Visual operation interface submodule: It is the key entry point for users to interact with the IoT system and the medium for users to operate the IoT platform and collaborate with various modules. It is convenient for users to view information such as device status, data reports, and analysis results. It supports users to create personalized visual dashboards through simple operations such as dragging and dropping and configuration to meet the needs of different users. It greatly improves the usability and management efficiency of the IoT system.

[0114] Inspection object management module: read the collected equipment asset prices , importance score , exception count ,According to the calculated device screening score, user preference and inspection completion rate, the objects to be inspected are screened out through the inspection object screening algorithm.

[0115] Personnel management module: This module can assign employees to inspection teams of different types of inspection tasks according to their job responsibilities, and generate reasonable shift plans based on factors such as employees' working hours and vacation plans.

[0116] Path management module: First, it is possible to use professional geographic information system (GIS) software (such as ArcGIS) to make all paths in the industrial environment into vector data based on geographic information images. Then, based on this vector data, the preference index , Road Condition Index and passing time ,Based on the Dijkstra algorithm, a shortest path data set between any two objects to be inspected is generated, and the data set is updated regularly.

[0117] Dynamic path planning module: responsible for formulating inspection routes and selecting the most commonly used inspection routes Inspection planning module: built-in mathematical model, through the parameter values ​​passed in from other modules, can eventually solve the path planning of each inspection group within the planned time range, the arrangement of the inspection sequence of each inspection point, and the inspection group allocation plan for each inspection point.

[0118] Inspection execution judgment module: responsible for personnel positioning and real-time monitoring of the completion of inspection tasks Personnel positioning module: Based on the collected personnel positioning records, which should contain node identification, personnel identification, timestamp and location information at each time point, calculate and update the preference index and passing time The results are stored in the data storage module and called by the path management module. The inspection completion rate can also be calculated based on the inspection personnel opening and inspection completion report results. And according to the inspection completion rate value, the parameters , , and etc. for dynamic adjustment.

[0119] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a manual inspection dynamic planning device based on the Internet of Things platform, and its structure is as follows Figure 3 shown.

[0120] Figure 3 The internal structure diagram of a manual inspection dynamic planning device based on the Internet of Things platform provided in the embodiment of the present application is as follows. Figure 3 As shown, the device includes: at least one processor 301; and, a memory 302 communicatively connected to at least one processor; The memory 302 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 301 to enable at least one processor 301 to: Acquire the equipment deployment data of the industrial environment, and calibrate the equipment quantitative parameters of the equipment deployment data to obtain the equipment importance score; acquire the real-time operation parameters of the equipment, and perform multi-dimensional equipment abnormality threshold monitoring on the real-time operation parameters of the equipment to determine the number of equipment abnormalities; based on the equipment importance score and the number of equipment abnormalities, obtain the objects to be inspected through equipment screening score analysis; dynamically adjust the inspection sections of the objects to be inspected to determine the optimal path node sequence; according to the optimal path node sequence, obtain the current inspection plan through planning constraint analysis of the inspection schedule; monitor the current inspection plan in real time, and perform inspection planning analysis on the inspection parameters obtained from real-time monitoring to determine the inspection plan update parameters.

[0121] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for dynamic planning of manual inspection based on an Internet of Things platform stores computer executable instructions, and the computer executable instructions are set as follows: Acquire the equipment deployment data of the industrial environment, and calibrate the equipment quantitative parameters of the equipment deployment data to obtain the equipment importance score; acquire the real-time operation parameters of the equipment, and perform multi-dimensional equipment abnormality threshold monitoring on the real-time operation parameters of the equipment to determine the number of equipment abnormalities; based on the equipment importance score and the number of equipment abnormalities, obtain the objects to be inspected through equipment screening score analysis; dynamically adjust the inspection sections of the objects to be inspected to determine the optimal path node sequence; according to the optimal path node sequence, obtain the current inspection plan through planning constraint analysis of the inspection schedule; monitor the current inspection plan in real time, and perform inspection planning analysis on the inspection parameters obtained from real-time monitoring to determine the inspection plan update parameters.

[0122] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0123] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0124] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0125] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0128] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0129] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0130] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0131] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0132] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A dynamic planning method for manual inspection based on the Internet of Things platform, characterized in that: The method comprises: Acquire equipment deployment data of an industrial environment, and calibrate equipment quantitative parameters of the equipment deployment data to obtain equipment importance scores; Acquire real-time operating parameters of the equipment, and perform multi-dimensional equipment abnormality threshold monitoring on the real-time operating parameters of the equipment to determine the number of equipment abnormalities; Based on the importance score of the equipment and the number of abnormalities of the equipment, the object to be inspected is obtained through equipment screening score analysis; Dynamically adjust the inspection section of the object to be inspected to determine the optimal path node sequence; According to the optimal path node sequence, the current inspection plan is obtained by analyzing the planning constraints of the inspection schedule; The current inspection plan is monitored in real time, and inspection planning analysis is performed on the inspection parameters obtained by the real-time monitoring to determine the inspection planning update parameters.

2. According to claim 1, a method for dynamic planning of manual inspection based on the Internet of Things platform is characterized in that: The device deployment data is calibrated with device quantitative parameters to obtain a device importance score, specifically including: Based on a preset importance level list, configuring the device deployment data according to the device importance level to obtain device importance data; The equipment importance data is quantified and calibrated with parameters to obtain the equipment importance degree score.

3. According to claim 2, a method for dynamic planning of manual inspection based on the Internet of Things platform is characterized in that: Perform multi-dimensional device abnormality threshold monitoring on the real-time operating parameters of the device to determine the number of device abnormalities, specifically including: Classifying the abnormal state of the real-time operating parameters of the device to obtain the abnormal state type of the device; Based on the abnormal state type of the device, the number of abnormalities of the device is determined through abnormal state monitoring.

4. According to claim 3, a method for dynamic planning of manual inspection based on the Internet of Things platform is characterized in that: Based on the importance score of the equipment and the number of abnormalities of the equipment, the objects to be inspected are obtained through equipment screening score analysis, including: Based on the equipment importance score and the number of equipment anomalies, the equipment screening score is evaluated through the equipment screening score to be inspected, where the calculation formula for the equipment screening score to be inspected is: in, Filter the score for the device, is the equipment asset price, is the equipment importance score, is the number of device abnormalities; The device screening scores are divided into a score group range to obtain a set of device arrays to be inspected; wherein the score group range division includes: screening score sorting, sub-data group division, and target data group division, and the division formula of the sub-data group division is: in, Filter the elements sorted by scores for the device, for The adjacent elements of Based on the array set of devices to be inspected, the objects to be inspected are obtained by dynamically updating the preference requirements.

5. According to claim 1, a method for dynamic planning of manual inspection based on the Internet of Things platform is characterized in that: Dynamically adjusting the inspection section of the object to be inspected to determine the optimal path node sequence specifically includes: Based on the object to be inspected, determine the device inspection node, and perform inspection priority path analysis on the device inspection node through the Dijkstra algorithm to determine the inspection priority queue; The edge weight analysis of the device inspection node is performed on the inspection priority queue to obtain the node path edge weight; wherein the calculation formula for the edge weight analysis of the g point and the h point in the device inspection node is: in, is the path passing time, is the road condition index, It is the route selection preference index for patrol personnel; Determine an inspection path vector according to the node path edge weights, and construct a graph structure for the inspection path vector to obtain inspection path structure data; The inspection path structure data is stored as a graph structure dictionary, and the graph structure dictionary is processed by a predecessor node to determine the optimal path node sequence.

6. According to claim 1, a method for dynamic planning of manual inspection based on the Internet of Things platform is characterized in that: According to the optimal path node sequence, the current inspection plan is obtained by analyzing the planning constraints of the inspection schedule, which specifically includes: According to the optimal path node sequence, the key parameters of the inspection group are determined, and based on the key parameters of the inspection group, the shortest total inspection time is determined by optimizing the total inspection time; wherein the objective function of the total inspection time optimization is: in, For the inspection team From the inspection point Arrival at the inspection point time, is the inspection point decision variable, and the value range of the decision variable is , No. The number of inspection points required by each inspection group, m is the number of types of problems to be inspected in the corresponding industrial scenario; Based on the shortest total inspection time, the current inspection plan is obtained by constraining the inspection scheduling time range; wherein the constraint condition of the inspection scheduling time range constraint is: in, , For the Inspection teams arrive at the inspection point , time, For the inspection team At the inspection point The length of inspection at the department.

7. According to claim 1, a method for dynamic planning of manual inspection based on the Internet of Things platform is characterized in that: Performing inspection planning analysis on the inspection parameters obtained by the real-time monitoring to determine the inspection planning update parameters, specifically including: Calculating the inspection time of the inspection parameters to obtain the inspection time of the equipment by the inspection personnel; Matching the equipment inspection time of the inspection personnel with the processing time of the equipment abnormality processing type to determine the abnormality processing time of the equipment abnormality type; Based on the exception handling time of the device exception type, the inspection plan update parameters are determined by updating the periodic exception handling plan parameters.

8. According to claim 1, a method for dynamic planning of manual inspection based on the Internet of Things platform is characterized in that: After performing inspection planning analysis on the inspection parameters obtained by the real-time monitoring to determine the inspection planning update parameters, the method further includes: The inspection plan update parameters are updated to the current inspection plan, and the updated current inspection plan is subjected to real-time inspection monitoring to obtain an inspection time period; Based on the inspection time period, the subsequent inspection path planning period update parameters are obtained through periodic inspection service time analysis; Obtaining inspection punch-in data, and performing inspection completion status analysis on the inspection punch-in data to obtain an inspection completion rate; According to the inspection completion rate, the dynamic adjustment parameters of the personnel inspection work are determined by judging the inspection completion status threshold.

9. A manual inspection dynamic planning device based on the Internet of Things platform, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Acquire equipment deployment data of an industrial environment, and calibrate equipment quantitative parameters of the equipment deployment data to obtain equipment importance scores; Acquire real-time operating parameters of the equipment, and perform multi-dimensional equipment abnormality threshold monitoring on the real-time operating parameters of the equipment to determine the number of equipment abnormalities; Based on the importance score of the equipment and the number of abnormalities of the equipment, the object to be inspected is obtained through equipment screening score analysis; Dynamically adjust the inspection section of the object to be inspected to determine the optimal path node sequence; According to the optimal path node sequence, the current inspection plan is obtained by analyzing the planning constraints of the inspection schedule; The current inspection plan is monitored in real time, and inspection planning analysis is performed on the inspection parameters obtained by the real-time monitoring to determine the inspection planning update parameters.

10. A non-volatile computer storage medium for dynamic planning of manual inspection based on an Internet of Things platform, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Acquire equipment deployment data of an industrial environment, and calibrate equipment quantitative parameters of the equipment deployment data to obtain equipment importance scores; Acquire real-time operating parameters of the equipment, and perform multi-dimensional equipment abnormality threshold monitoring on the real-time operating parameters of the equipment to determine the number of equipment abnormalities; Based on the importance score of the equipment and the number of abnormalities of the equipment, the object to be inspected is obtained through equipment screening score analysis; Dynamically adjust the inspection section of the object to be inspected to determine the optimal path node sequence; According to the optimal path node sequence, the current inspection plan is obtained by analyzing the planning constraints of the inspection schedule; The current inspection plan is monitored in real time, and inspection planning analysis is performed on the inspection parameters obtained by the real-time monitoring to determine the inspection planning update parameters.

Images