Equipment maintenance management system and method based on Internet of Things cloud platform

Abstract

The present invention provides an equipment maintenance management system and method based on an Internet of Things cloud platform. The system includes a data acquisition module, an Internet of Things cloud platform module, and a decision-making module. The data acquisition module collects real-time data from equipment sites and uploads it to the Internet of Things cloud platform module. The Internet of Things cloud platform module stores and analyzes the real-time data, and uploads the analysis results to the decision-making module. The decision-making module optimizes the maintenance strategy for the equipment sites based on the decision results. The Internet of Things cloud platform module also performs predictive maintenance on the equipment sites. The equipment maintenance management system and method based on the Internet of Things cloud platform of the present invention, through predictive maintenance, reduces equipment failures and downtime, lowers maintenance costs, improves equipment operating efficiency, and achieves more intelligent operation and maintenance management.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment maintenance and management, and in particular to an equipment maintenance and management system and method based on an Internet of Things cloud platform. Background Art

[0002] In modern industrial and manufacturing environments, efficient equipment operation and maintenance management are key to ensuring production continuity and reducing operating costs. Traditional equipment maintenance management relies primarily on regular inspections and manual record-keeping, often employing a preventive maintenance strategy. While this approach can reduce the probability of failure to a certain extent, it has the following drawbacks:

[0003] 1. Data collection is not timely: Traditional maintenance management often relies on manual records and regular inspections, resulting in insufficient real-time information on equipment status.

[0004] 2. Lack of scientific basis for maintenance decisions: Maintenance decisions based on manual experience and scheduled maintenance can easily become arbitrary. The actual operating status and maintenance needs of the equipment are not assessed promptly and accurately, which can lead to excessive maintenance or a lack of necessary maintenance.

[0005] 3. High operating costs: Traditional methods are inefficient in resource allocation and maintenance arrangements, resulting in waste of human and material resources and affecting the overall efficiency of the enterprise.

[0006] 4. Information silos: Data across devices and systems often cannot be effectively integrated, leading to the formation of information silos. This lack of a global perspective makes it difficult for managers to optimize equipment maintenance strategies holistically and achieve collaborative management.

[0007] Therefore, a solution is urgently needed. Summary of the Invention

[0008] One of the purposes of the present invention is to provide an equipment maintenance and management system based on the Internet of Things cloud platform to solve the above-mentioned shortcomings.

[0009] An embodiment of the present invention provides an equipment maintenance and management system based on an Internet of Things cloud platform, comprising:

[0010] Data acquisition module, IoT cloud platform module and decision-making module;

[0011] The data acquisition module collects real-time data from the equipment site and uploads it to the IoT cloud platform module;

[0012] The IoT cloud platform module stores and analyzes real-time data and uploads the analysis results to the decision-making module;

[0013] The decision-making module optimizes the maintenance strategy of the equipment site based on the decision results;

[0014] Among them, the IoT cloud platform module also performs predictive maintenance on equipment on site.

[0015] Optionally, the data acquisition module specifically performs the following operations:

[0016] Obtain real-time data by communicating with equipment on site;

[0017] Use edge computing devices to process real-time data;

[0018] The processed data is uploaded to the IoT cloud platform module via wireless communication technology.

[0019] Optionally, the IoT cloud platform module specifically performs the following operations:

[0020] Use database to store real-time data;

[0021] Use big data technology and artificial intelligence (AI) technology to analyze data, generate real-time monitoring reports and predict faults.

[0022] Optionally, the decision module specifically performs the following operations:

[0023] Generate maintenance recommendations and decision support based on analysis results to optimize maintenance strategies.

[0024] Optionally, the IoT cloud platform module further specifically performs the following operations:

[0025] Based on historical data and industry standards, establish warning threshold ranges based on key equipment indicators;

[0026] When the device parameters in the real-time data exceed the corresponding warning threshold range, an early warning is triggered immediately;

[0027] When issuing an early warning, it will be issued through on-site alarm and mobile application push alarm.

[0028] Optionally, the IoT cloud platform module further specifically performs the following operations:

[0029] Based on pre-built fault prediction models and real-time data, equipment failure prediction is performed on-site.

[0030] The steps for pre-building the fault prediction model are as follows:

[0031] Preprocessing of large amounts of historical equipment failure data, including at least: outlier detection, missing value filling, normalization, data cleaning and conversion;

[0032] Based on the machine learning algorithm, the candidate fault prediction model is trained according to the pre-processed historical equipment failure data;

[0033] Based on the cross-validation method and the hyperparameter tuning method, the optimal candidate fault prediction model is verified and selected from the candidate fault prediction models as the fault prediction model.

[0034] Optionally, the IoT cloud platform module further specifically performs the following operations:

[0035] Define key performance indicators, including at least: equipment operating load, temperature, and vibration;

[0036] Based on key performance indicators, collect key performance parameters of equipment on site;

[0037] Dynamically adjust the monitoring strategy of the equipment site according to the equipment characteristics, operating conditions and external environmental changes at the equipment site; the monitoring strategy includes at least: collection frequency and monitoring parameters.

[0038] Optionally, the IoT cloud platform module further specifically performs the following operations:

[0039] Based on the equipment failure prediction results of the fault prediction model, a predictive maintenance plan is generated and executed according to the importance of the equipment at the equipment site, maintenance time and resource availability.

[0040] Optionally, the IoT cloud platform module further specifically performs the following operations:

[0041] Use data analysis to predict component requirements for different equipment failure risks within the equipment site;

[0042] Based on the inventory management model, spare parts inventory is configured according to the component requirements of different equipment failure risks.

[0043] An embodiment of the present invention provides a device maintenance and management method based on an Internet of Things cloud platform, characterized by comprising:

[0044] Collect real-time data from the equipment site through the data acquisition module and upload it to the IoT cloud platform module;

[0045] The real-time data is stored and analyzed through the IoT cloud platform module, and the analysis results are uploaded to the decision-making module;

[0046] Optimize the maintenance strategy of the equipment site based on the decision-making results through the decision-making module;

[0047] Among them, predictive maintenance of equipment on site is also carried out through the Internet of Things cloud platform module.

[0048] The present invention has achieved the following beneficial effects:

[0049] 1. Through predictive maintenance, equipment failures and downtime can be reduced, maintenance costs can be lowered, equipment operating efficiency can be improved, and smarter operation and maintenance management can be achieved.

[0050] 2. Through data collection and analysis, real-time monitoring and management of equipment can be achieved, and potential faults can be discovered in a timely manner.

[0051] 3. Utilize the Internet of Things, big data, and artificial intelligence technologies to automate maintenance recommendations and decisions, reducing manual intervention.

[0052] 4. On-site data is collected automatically in real time, equipment is interconnected, and data is shared, providing reliable data support for big data decision-making, production management systems, etc., breaking down data silos.

[0053] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0054] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0056] Figure 1 Schematic diagram of an equipment maintenance and management system based on an Internet of Things cloud platform in an embodiment of the present invention;

[0057] Figure 2 Schematic diagram of an equipment maintenance and management method based on an Internet of Things cloud platform in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0059] The embodiment of the present invention provides an equipment maintenance and management system based on the Internet of Things cloud platform, such as Figure 1 Shown, including:

[0060] Data collection module 1, IoT cloud platform module 2, and decision-making module 3;

[0061] Data acquisition module 1 collects real-time data from the equipment site and uploads it to IoT cloud platform module 2;

[0062] The IoT cloud platform module 2 stores and analyzes the real-time data and uploads the analysis results to the decision module 3;

[0063] Decision module 3 optimizes the maintenance strategy of the equipment site based on the decision results;

[0064] Among them, the IoT cloud platform module 2 also performs predictive maintenance on equipment on site.

[0065] The working principle and beneficial effects of the above technical solution are:

[0066] The system's workflow includes:

[0067] Data collection: Sensors communicate with devices to continuously monitor device status, regularly collect and upload data to the IoT cloud platform.

[0068] Data storage and processing: The cloud platform receives and stores data, and performs real-time processing and historical data analysis.

[0069] Intelligent analysis and decision-making: Based on the analysis results, the decision-making module generates maintenance recommendations and sends alerts through the rule engine.

[0070] User feedback and actions: Maintenance personnel view device status, alarms, and maintenance recommendations through the user interface, perform corresponding actions, and record them.

[0071] Maintenance record management: All maintenance records and equipment status are stored for subsequent analysis and decision-making.

[0072] This application uses predictive maintenance to reduce equipment failures and downtime, lower maintenance costs, improve equipment operating efficiency, and achieve more intelligent operation and maintenance management.

[0073] Through data collection and analysis, real-time monitoring and management of equipment can be achieved, and potential faults can be discovered in a timely manner.

[0074] Automated maintenance recommendations and decisions reduce manual intervention.

[0075] On-site data is collected automatically in real time, equipment is interconnected, and data is shared, providing reliable data support for big data decision-making, production management systems, etc., breaking down data silos.

[0076] In one embodiment, the data acquisition module 1 specifically performs the following operations:

[0077] Obtain real-time data by communicating with equipment on site;

[0078] Use edge computing devices to process real-time data;

[0079] The processed data is uploaded to the IoT cloud platform module 2 via wireless communication technology.

[0080] The working principle and beneficial effects of the above technical solution are:

[0081] Get real-time data by communicating with devices;

[0082] Use edge computing devices (such as gateways) to process some data and reduce the burden on network transmission;

[0083] During communication, data is uploaded to the cloud platform through wireless communication technologies (such as Wi-Fi, LoRa, NB-IoT, etc.).

[0084] In one embodiment, the IoT cloud platform module 2 specifically performs the following operations:

[0085] Use database to store real-time data;

[0086] Use big data technology and artificial intelligence (AI) technology to analyze data, generate real-time monitoring reports and predict faults.

[0087] The working principle and beneficial effects of the above technical solution are:

[0088] Use a database (such as MongoDB, MySQL, etc.) to store device data and history.

[0089] Use big data technologies (such as Apache Spark and Hadoop) and artificial intelligence (AI) technologies to analyze data, generate real-time monitoring reports, and predict faults.

[0090] In one embodiment, the decision module 3 specifically performs the following operations:

[0091] Generate maintenance recommendations and decision support based on analysis results to optimize maintenance strategies.

[0092] In one embodiment, the IoT cloud platform module 2 further specifically performs the following operations:

[0093] Based on historical data and industry standards, establish warning threshold ranges based on key equipment indicators;

[0094] When the device parameters in the real-time data exceed the corresponding warning threshold range, an early warning is triggered immediately;

[0095] When issuing an early warning, it will be issued through on-site alarm and mobile application push alarm.

[0096] The working principle and beneficial effects of the above technical solution are:

[0097] Establish early warning thresholds based on key equipment indicators (such as load, deflection, temperature, and vibration). By analyzing historical data and industry standards, appropriate thresholds are set. Once equipment parameters exceed these thresholds, the system triggers an immediate warning. Multiple notification methods are available, including on-site alarms and mobile app push notifications, ensuring maintenance personnel receive timely fault alerts.

[0098] In one embodiment, the IoT cloud platform module 2 further specifically performs the following operations:

[0099] Based on pre-built fault prediction models and real-time data, equipment failure prediction is performed on-site.

[0100] The steps for pre-building the fault prediction model are as follows:

[0101] Preprocessing of large amounts of historical equipment failure data, including at least: outlier detection, missing value filling, normalization, data cleaning and conversion;

[0102] Based on the machine learning algorithm, the candidate fault prediction model is trained according to the pre-processed historical equipment failure data;

[0103] Based on the cross-validation method and the hyperparameter tuning method, the optimal candidate fault prediction model is verified and selected from the candidate fault prediction models as the fault prediction model.

[0104] The working principle and beneficial effects of the above technical solution are:

[0105] The collected data is thoroughly pre-processed, including outlier detection, missing value filling, and normalization, to ensure data accuracy and consistency. In addition, data cleaning and transformation are implemented to eliminate noise and improve the efficiency of model training.

[0106] Fault prediction models are trained using a variety of machine learning algorithms (such as decision trees, random forests, support vector machines, and deep learning). Cross-validation and hyperparameter tuning techniques are used to compare the prediction results of different models and select the model with the best performance. The model's prediction accuracy is continuously tracked, and necessary model retraining and updates are performed.

[0107] In one embodiment, the IoT cloud platform module 2 further specifically performs the following operations:

[0108] Define key performance indicators, including at least: equipment operating load, temperature, and vibration;

[0109] Based on key performance indicators, collect key performance parameters of equipment on site;

[0110] Dynamically adjust the monitoring strategy of the equipment site according to the equipment characteristics, operating conditions and external environmental changes at the equipment site; the monitoring strategy includes at least: collection frequency and monitoring parameters.

[0111] The working principle and beneficial effects of the above technical solution are:

[0112] Define key performance indicators (KPIs), such as equipment load, temperature, and vibration, and collect data in real time. Dynamically adjust data collection frequency and monitoring parameters based on equipment characteristics, operating conditions, and external environmental changes. Automatically optimize monitoring strategies to maximize monitoring effectiveness and accuracy.

[0113] In one embodiment, the IoT cloud platform module 2 further specifically performs the following operations:

[0114] Based on the equipment failure prediction results of the fault prediction model, a predictive maintenance plan is generated and executed according to the importance of the equipment at the equipment site, maintenance time and resource availability.

[0115] The working principle and beneficial effects of the above technical solution are:

[0116] Data-driven dynamic maintenance planning: Based on the results of the failure prediction model, the maintenance plan is automatically generated and adjusted, taking into account the importance of the equipment, maintenance time, and resource availability, ensuring timely maintenance before equipment failure occurs.

[0117] In one embodiment, the IoT cloud platform module 2 further specifically performs the following operations:

[0118] Use data analysis to predict component requirements for different equipment failure risks within the equipment site;

[0119] Based on the inventory management model, spare parts inventory is configured according to the component requirements of different equipment failure risks.

[0120] The working principle and beneficial effects of the above technical solution are:

[0121] Leverage data analytics to predict demand for parts with high failure risk and rationally allocate spare parts inventory. By building inventory management models, dynamically adjust spare parts procurement and storage strategies to avoid equipment downtime due to spare parts shortages. Furthermore, predictive analytics can be used to optimize supply chain management and improve spare parts turnover efficiency.

[0122] Predictive maintenance can not only improve the operating efficiency of equipment, but also significantly reduce maintenance costs and downtime, and achieve more intelligent operation and maintenance management.

[0123] In one embodiment, the device maintenance and management system based on the Internet of Things cloud platform further includes:

[0124] Interactive module, used to interactively assist management personnel in on-site equipment maintenance management;

[0125] The interactive module interactively assists the management personnel in performing equipment maintenance management on the equipment site, specifically performing the following operations:

[0126] A1. Based on the real-time data stored in the IoT cloud platform module and the 3D map of the equipment site, a management interaction model is constructed;

[0127] In step A1, the 3D on-site map of the equipment site is a 3D model map of the equipment site, on which are 3D models corresponding to various equipment and infrastructure at the equipment site. First, the IoT cloud platform is used to collect and store real-time data on the equipment site, including the operating status of the equipment and environmental conditions. Based on the 3D on-site map, a management interaction model is constructed. Specifically, the real-time data can be displayed on the 3D on-site map, thereby constructing a management interaction model that dynamically displays the real-time data in real time, facilitating subsequent operations and management.

[0128] A2. Display the management interaction model to managers;

[0129] In step A2, the management interaction model will be displayed on the manager's display screen. The manager can intuitively see the 3D model of the equipment site and related real-time information, so as to clearly understand the site conditions and provide a basis for subsequent operations;

[0130] A3. Control the drone to enter the equipment site;

[0131] In step A3, after entering the equipment site, the drone can monitor the on-site situation in real time and obtain key audio and video information to assist in equipment maintenance work;

[0132] A4. Determine the target position and logical expectation of the drone based on interaction information between the manager and the management interaction model during a first period of time. The start time of the first period of time is the time when the manager and the management interaction model begin to interact, and the duration of the first period of time is a first threshold.

[0133] In step A4, the interaction information includes at least the type, time, and location of the operation performed by the administrator in the management interaction model. The interaction information reflects, to a certain extent, how the administrator intends to perform on-site equipment maintenance management. Based on this information, the position of the drone can be determined so that its flight footage can assist the administrator, i.e., the target position. Furthermore, the control of the drone can be determined based on this information to obtain the corresponding assistance, i.e., the logical expectation.

[0134] A5. Control the drone to enter the target position;

[0135] In step A5, the target position includes the flight position and the shooting attitude; controlling the UAV to enter the target position is to control the UAV to maintain the flight position and the shooting attitude;

[0136] A6. Display the drone's virtual control panel and real-time flight footage to management personnel;

[0137] In step A6, the drone's virtual control panel is a virtual operation interface for controlling the drone's flight photography. It displays multiple parameters for controlling the drone's flight photography, such as forward movement, descent, and shooting direction adjustment. The drone transmits real-time flight photography footage during flight photography.

[0138] A7. When the operational logic of the administrator's operation of the virtual operation panel during the second time period is inconsistent with the logical expectation, based on the logical expectation, restrictive guidance is provided to the administrator's operation of the virtual operation panel during a third time period; wherein the second time period is after the first time period, the start time of the second time period is the time when the administrator begins operating the virtual operation panel, and the duration of the second time period is a second threshold; the third time period is after the second time period and adjacent to the second time period, and the duration of the third time period is a third threshold; the third threshold is greater than the first threshold and greater than the second threshold;

[0139] In step A7, the administrator's operation of the virtual control panel generates an operation logic. The operation logic is the logic for the administrator to control the drone's flight and shooting of certain content by operating the virtual control panel in sequence. If the operation logic does not match the expected logic, it indicates that the administrator needs to make corrections, and the administrator's operation of the virtual control panel is constrained and guided.

[0140] A8. When the management personnel input the equipment maintenance management strategy, online equipment maintenance management is performed on the equipment site based on the equipment maintenance management strategy.

[0141] In step A8, when the management personnel decide how to carry out equipment maintenance management, they will input the equipment maintenance management strategy and carry out online equipment maintenance management on site based on the equipment maintenance management strategy.

[0142] The embodiments of the present invention achieve the following beneficial effects:

[0143] Through 3D maps and interactive management models, managers can quickly and intuitively understand the status of equipment on-site, eliminating the need to inspect each device individually, significantly saving time. The introduction of drones further improves the efficiency and accuracy of on-site inspections, photography, and data collection.

[0144] Using a virtual control panel and interactive model, managers can remotely control drones with simple and intuitive operation. The system provides intelligent guidance based on pre-set operating modes, reducing operational errors and improving operational accuracy and safety.

[0145] The system automatically collects on-site data and performs equipment maintenance according to pre-defined management strategies, effectively identifying potential failures in advance and preventing them from impacting production. Furthermore, drone-assisted inspections enable refined equipment management and monitoring.

[0146] Managers can perform maintenance tasks remotely. Combined with real-time feedback, drones and virtual operation panels significantly enhance the flexibility and controllability of on-site management. Even if equipment is located in hard-to-reach areas, managers can use drones to conduct inspections and collect data, significantly enhancing management flexibility.

[0147] The application of drones effectively avoids the need for personnel to enter dangerous or complex environments, reduces the risk of accidents, and improves the safety of equipment management.

[0148] Through intelligent constraints and guidance mechanisms, the system can identify and provide corrective suggestions in real time even if the operation is improper, ensuring that the drone operates as expected, thereby improving work quality and safety.

[0149] In one embodiment, based on the interaction information between the manager and the management interaction model during the first period, determining the target position and logical expectation of the drone includes:

[0150] A401. Representing the interaction information in a management interaction model as an interaction time-space distribution to obtain an interaction time-space distribution;

[0151] In step A401, when performing the interaction spatiotemporal distribution representation, the operations performed by the administrator on the management interaction model in the interaction information are represented according to the operation location, and the operation type, operation time, and the spatiotemporal relationship and spatial location relationship between each operation are marked. The multiple represented contents are combined to form the interaction spatiotemporal distribution;

[0152] A402. Perform fuzzy feature extraction on the interactive spatiotemporal distribution to obtain a fuzzy feature set;

[0153] In step A402, the fuzzy feature set includes multiple fuzzy features, including: the operation type performed most times by the manager in the interaction spatiotemporal distribution, the operation object performed most times continuously by the manager, etc.;

[0154] A403, determining a target refined feature extraction rule from a refined feature extraction rule library; wherein the standard fuzzy feature set of the target refined feature extraction rule matches the fuzzy feature set;

[0155] In step A403, the fuzzy feature set preliminarily reflects the equipment maintenance and management intention of the manager. Based on this, it can be determined how the manager's deeper equipment maintenance and management intention will be reflected, that is, the target refined feature extraction rule is determined. For example, if the fuzzy feature in the fuzzy feature set is that the operation type performed most times by the manager in the interactive spatiotemporal distribution is the zoom viewing operation, and the operation object operated most times continuously by the manager is the machine tool working motor, it means that the manager may want to perform in-depth equipment maintenance and management on the machine tool working motor. Then, the target refined feature extraction rule is to extract all data related to the machine tool working motor in the interactive spatiotemporal distribution. There are different refined feature extraction rules in the refined feature extraction rule library. Different refined feature extraction rules are preset with corresponding standard fuzzy feature sets. When the standard fuzzy feature set matches the fuzzy feature set, the corresponding refined feature extraction rule can be adopted.

[0156] A404. Based on the target refined feature extraction rule, refine the feature extraction of the interactive spatiotemporal distribution to obtain a refined feature set;

[0157] In step A404, based on the target refined feature extraction rule, corresponding refined features can be extracted from the interactive spatiotemporal distribution to obtain a refined feature set;

[0158] A405. Determine target determination knowledge corresponding to the refined feature set from the determination knowledge base; wherein the standard refined feature set of the target determination knowledge and the refined feature set match each other;

[0159] In step A405, after the refined feature set is determined, it can be used to determine how to determine the appropriate position of the drone and how to control the drone so that the management personnel can be assisted. In other words, target determination knowledge is determined. The knowledge base contains different determination knowledge, and each determination knowledge has a preset standard refined feature set. When the standard refined feature set matches the refined feature set, the corresponding determination knowledge can be adopted.

[0160] A406. Analyze target determination knowledge and determine the effective target distribution and division rules and target expectation formulation rules;

[0161] In step A406, the target determination includes a target effective distribution division rule, which indicates how to divide the effective distribution of the range that the drone needs to shoot from the interactive spatiotemporal distribution. For example, if the refined features in the refined feature set are the operating parameters related to the machine tool working motor, then the target effective distribution division rule is to divide the relevant operation types and operation times of the machine tool working motor from the interactive spatiotemporal distribution, and to divide other operations performed before and after operating the machine tool working motor, etc., as the effective distribution; the target expectation formulation rule indicates how to formulate logical expectations based on the shooting range circle. For example, if the refined features in the refined feature set are the operating parameters related to the machine tool working motor, then the target expectation formulation rule is to control the drone to shoot each parameter in descending order of importance of the operating parameters;

[0162] A407, based on the target effective distribution partitioning rule, divide the effective distribution from the interactive spatiotemporal distribution;

[0163] A408. Based on the effective distribution, determine a shooting range circle in the management interaction model; wherein the shooting range circle is a minimum enclosing sphere that minimum encloses the effective distribution;

[0164] A409: Determine the drone model's position based on the shooting range circle; wherein, when the drone enters the drone model's position, it can clearly capture all of the shooting range circles simultaneously or can sequentially and clearly capture all of the shooting range circles by changing the shooting angle no more than a preset number of times;

[0165] In step A409, clear shooting means that the straight-line distance between the drone's camera and the feature to be shot does not exceed a certain value, for example, 2 meters; the preset number of times may be 3; and changing the shooting angle within the preset number of times to be able to clearly shoot all shooting range circles in sequence means that the drone can clearly shoot all shooting range circles in sequence by switching the shooting angle within the preset number of times;

[0166] A410. Determine the actual position corresponding to the drone model position at the equipment site and use it as the target position.

[0167] In step A410, after the drone model position is determined, it will correspond to a real position at the equipment site, which will be used as the target position;

[0168] A411. Establish rules based on target expectations and formulate logical expectations based on the shooting range circle.

[0169] In step A411, finally, rules are formulated based on target expectations, and logical expectations are formulated according to the shooting range circle.

[0170] The embodiments of the present invention achieve the following beneficial effects:

[0171] By capturing and analyzing managers' interaction information (such as operation type, operation time, and operation object), we can gain a deeper understanding of their equipment maintenance and management intentions. Existing technologies typically rely on preset rules or fixed patterns, but this solution dynamically captures managers' actual needs and behaviors through real-time analysis of interaction information, enabling more intelligent prediction of their maintenance intentions. This precise intention mining significantly improves the system's response speed and accuracy, optimizing the management decision-making process.

[0172] Traditional drone positioning is typically static, based on preset parameters. This solution, however, dynamically calculates the optimal drone positioning through real-time, interactive spatiotemporal distribution analysis, enabling the drone to capture footage at the most appropriate angle and position. This approach ensures precise coverage of the target area, reduces blind spots, and clearly captures all the details necessary for equipment maintenance.

[0173] The shooting range is determined based on effective target distribution rules, ensuring that the drone can capture all target areas with minimal adjustments to the shooting angle. This reduces the need to frequently adjust the shooting angle, improves shooting efficiency, reduces operational complexity, and minimizes the risk of equipment failure.

[0174] By analyzing this interactive information, key maintenance targets (such as machine tool motors) and their associated parameters are identified. This information is then used for in-depth analysis to generate detailed features relevant to equipment maintenance. This precise equipment identification and feature extraction helps managers quickly identify potential equipment issues or impending failures, enabling proactive maintenance and improving equipment reliability and reducing downtime.

[0175] By identifying detailed features and target-specific knowledge, we can provide managers with more targeted decision support. For example, based on real-time feedback on equipment operating status, we can recommend equipment components that require priority inspection. This type of decision support can reduce managers' workload, improve decision-making efficiency, and avoid judgment bias caused by human factors.

[0176] By using target-refined feature extraction rules and identifying knowledge bases, different maintenance requirements are effectively mapped to optimal solutions within the knowledge base. This approach, powered by machine learning and a rule engine, provides continuously optimized maintenance management strategies, unlike traditional methods that rely solely on fixed empirical rules. This provides more robust decision support for drones in complex equipment maintenance tasks.

[0177] Based on logical expectations, during the third period, managers are given constrained guidance on operating the virtual operation panel, including:

[0178] A701. Serialize the logical expectation to obtain a sub-logical sequence;

[0179] In step A701, when performing serialization representation, multiple sub-logics in the logical expectation are sorted according to the logical sequence;

[0180] A702. When the operation sub-logic of the administrator's operation of the virtual operation panel in the i-th sub-period within the third time period matches the j-th sub-logic in the sub-logic sequence, if i+j is less than or equal to N and the absolute value of the difference between i and j is greater than the absolute value threshold, a first operation constraint rule is generated based on the other sub-logics within the first number preset after the j-th sub-logic in the sub-logic sequence. Based on the first operation constraint rule, corresponding operation constraints are imposed on the administrator's operation of the virtual operation panel in the sub-period within the second number preset after the i-th sub-period within the third time period.

[0181] In step A702, the third time period is evenly divided into N sub-periods, where N is the total number of sub-logics in the sub-logic sequence. The absolute value threshold may be 4. If i+j is less than or equal to N and the absolute value of the difference between i and j is greater than the absolute value threshold, it indicates that one or both of the sub-periods and the sub-logics that are matched are relatively early. However, the sub-periods and sub-logics that are matched reflect that the manager's decision-making rhythm is inconsistent with the time trend. Therefore, it is necessary to quickly guide the manager based on the subsequent sub-logics to improve their decision-making rhythm. Therefore, based on the other sub-logics within a preset first number after the j-th sub-logic in the sub-logic sequence, a first operation constraint rule is generated. Based on the first operation constraint rule, the first number may be 3. The first operation constraint rule restricts the manager from performing operations unrelated to the other sub-logics within a preset first number after the j-th sub-logic in the sub-logic sequence. However, continuous guidance of the manager is not possible. Therefore, based on the first operation constraint rule, corresponding operation constraints are imposed on the manager's operation of the virtual operation panel within the sub-period within a preset second number after the i-th sub-period in the third time period. The second number may be 2.

[0182] A703. If i+j is greater than N and the absolute value of the difference between i and j is greater than the absolute value threshold, a second operation constraint rule is generated based on other sub-logics within a preset third number before and after the j-th sub-logic in the sub-logic sequence, and based on the second operation constraint rule, corresponding operation constraints are imposed on the administrator's operation of the virtual operation panel in all sub-periods after the i-th sub-period within the third time period.

[0183] If i+j is greater than N and the absolute value of the difference between i and j is greater than the absolute value threshold, it means that one or both of the sub-period and the sub-logic are at the end. However, the sub-period and the sub-logic reflect that the management decision-making rhythm of the manager is inconsistent with the time trend, and it is necessary to pay attention to the current management decision, that is, to make focused management decisions. Based on the other sub-logics within the third number preset before and after the j-th sub-logic in the sub-logic sequence, a second operation constraint rule is generated. The second operation constraint rule is to constrain the manager from performing operations unrelated to other sub-logics within the third number preset before and after the j-th sub-logic in the sub-logic sequence; the third number can be 4; and based on the second operation constraint rule, in all sub-periods after the i-th sub-period in the third time period, the manager's operation of the virtual operation panel is subject to corresponding operation constraints to achieve continuous constraint guidance.

[0184] The embodiments of the present invention achieve the following beneficial effects:

[0185] By providing real-time constraints and guidance on managers' operations, the solution can effectively adjust the manager's decision-making rhythm, bringing their actions more in line with established logical expectations. In particular, when there's a mismatch between a manager's operations and the predetermined sequence, guidance can be used to adjust their operational progress, avoiding overly hasty or delayed decisions. Existing management decision-making systems often lack in-depth guidance on operational timing. Most systems provide static prompts or suggestions, failing to make real-time, dynamic adjustments based on discrepancies between a manager's current operational status and the logical sequence. This technical solution, however, enables more precise control of the decision-making rhythm through dynamic adjustments to the guidance mechanism.

[0186] The third period is divided into N sub-periods, and refined guidance is provided based on the operational logic of each sub-period. This guidance mechanism ensures that managers can focus on the most important decision points at different times, thus avoiding operational fragmentation or over-centralization.

[0187] When managers' actions don't align with the predefined sub-logical sequence, dynamically generated operational constraints can promptly correct deviations. This mechanism helps strengthen the accuracy and consistency of decisions and prevents deviations from objectives caused by overly arbitrary operations or decisions.

[0188] By presetting sub-logical intervals with different values, the solution can maintain a continuous constraint on managers' operations. In particular, in cases where decisions deviate, the solution not only provides timely corrections but also ensures that managers remain on the right path through continuous guidance.

[0189] By precisely combining logical sequences with time periods and providing real-time operational constraints, this solution enables managers to more accurately follow predetermined decision-making paths, avoiding missing critical decision-making opportunities or making incorrect decisions, thereby improving the quality of overall management decisions.

[0190] The embodiment of the present invention provides a device maintenance management method based on the Internet of Things cloud platform, such as Figure 2 Shown, including:

[0191] S1. Collect real-time data from the equipment site through the data acquisition module and upload it to the Internet of Things cloud platform module;

[0192] S2. The real-time data is stored and analyzed through the IoT cloud platform module, and the analysis results are uploaded to the decision-making module;

[0193] S3. Optimize the maintenance strategy of the equipment site based on the decision results through the decision module;

[0194] Among them, predictive maintenance of equipment on site is also carried out through the Internet of Things cloud platform module.

[0195] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An equipment maintenance and management system based on the Internet of Things cloud platform, characterized in that: include: Data acquisition module, IoT cloud platform module and decision-making module; The data acquisition module collects real-time data from the equipment site and uploads it to the IoT cloud platform module; The IoT cloud platform module stores and analyzes real-time data and uploads the analysis results to the decision-making module; The decision-making module optimizes the maintenance strategy of the equipment site based on the decision results; Among them, the IoT cloud platform module also performs predictive maintenance on equipment sites; Also includes: Interaction module for: Based on the real-time data stored in the IoT cloud platform module, a management interaction model is constructed according to the on-site 3D map of the equipment site; Represent the interaction information in the management interaction model in terms of interaction time and space distribution to obtain the interaction time and space distribution; Perform fuzzy feature extraction on the interactive spatiotemporal distribution to obtain a fuzzy feature set; Determining a target refined feature extraction rule from a refined feature extraction rule library; wherein the standard fuzzy feature set of the target refined feature extraction rule and the fuzzy feature set match each other; Based on the target refined feature extraction rules, the interactive spatiotemporal distribution is refined to obtain a refined feature set; Determining target determination knowledge corresponding to the refined feature set from a determination knowledge base; wherein the standard refined feature set of the target determination knowledge and the refined feature set match each other; Analyze target determination knowledge and determine the effective target distribution division rules and target expectation formulation rules; Based on the target effective distribution partitioning rule, the effective distribution is divided from the interactive spatiotemporal distribution; Based on the effective distribution, a shooting range circle is determined in the management interaction model; wherein the shooting range circle is the minimum enclosing sphere that minimum encloses the effective distribution; The drone model position is determined based on the shooting range circle; wherein, when the drone enters the drone model position, it can clearly capture all the shooting range circles at the same time or can sequentially and clearly capture all the shooting range circles by changing the shooting angle no more than a preset number of times; Determine the actual position of the drone model from the equipment site and use it as the target position; Formulate rules based on target expectations and formulate logical expectations based on shooting range circles; Control the drone to enter the target position; Display the drone's virtual control panel and real-time flight footage to managers; When the operation logic of the administrator's operation of the virtual operation panel in the second period does not conform to the logical expectation, based on the logical expectation, the administrator's operation of the virtual operation panel is guided in a constrained manner in the third period; When the management personnel input the equipment maintenance management strategy, online equipment maintenance management is performed on the equipment site based on the equipment maintenance management strategy.

2. The equipment maintenance and management system based on the Internet of Things cloud platform according to claim 1, characterized in that: The data acquisition module specifically performs the following operations: Obtain real-time data by communicating with equipment on site; Use edge computing devices to process real-time data; The processed data is uploaded to the IoT cloud platform module via wireless communication technology.

3. The equipment maintenance and management system based on the Internet of Things cloud platform according to claim 1, characterized in that: The IoT cloud platform module specifically performs the following operations: Use database to store real-time data; Use big data technology and artificial intelligence (AI) technology to analyze data, generate real-time monitoring reports and predict faults.

4. The equipment maintenance and management system based on the Internet of Things cloud platform according to claim 1, characterized in that: The decision module specifically performs the following operations: Generate maintenance recommendations and decision support based on analysis results to optimize maintenance strategies.

5. The equipment maintenance and management system based on the Internet of Things cloud platform according to claim 1, characterized in that: The IoT cloud platform module also specifically performs the following operations: Based on historical data and industry standards, establish warning threshold ranges based on key equipment indicators; When the device parameters in the real-time data exceed the corresponding warning threshold range, an early warning is triggered immediately; When issuing an early warning, it will be issued through on-site alarm and mobile application push alarm.

6. The equipment maintenance and management system based on the Internet of Things cloud platform according to claim 1, characterized in that: The IoT cloud platform module also specifically performs the following operations: Based on pre-built fault prediction models and real-time data, equipment failure prediction is performed on-site. The steps for pre-building the fault prediction model are as follows: Preprocessing of large amounts of historical equipment failure data, including at least: outlier detection, missing value filling, normalization, data cleaning and conversion; Based on the machine learning algorithm, the candidate fault prediction model is trained according to the pre-processed historical equipment failure data; Based on the cross-validation method and the hyperparameter tuning method, the optimal candidate fault prediction model is verified and selected from the candidate fault prediction models as the fault prediction model.

7. The equipment maintenance and management system based on the Internet of Things cloud platform according to claim 1, characterized in that: The IoT cloud platform module also specifically performs the following operations: Define key performance indicators, including at least: equipment operating load, temperature, and vibration; Based on key performance indicators, collect key performance parameters of equipment on site; Dynamically adjust the monitoring strategy of the equipment site according to the equipment characteristics, operating conditions and external environmental changes at the equipment site; the monitoring strategy includes at least: collection frequency and monitoring parameters.

8. The equipment maintenance and management system based on the Internet of Things cloud platform according to claim 6, characterized in that: The IoT cloud platform module also specifically performs the following operations: Based on the equipment failure prediction results of the fault prediction model, a predictive maintenance plan is generated and executed according to the importance of the equipment at the equipment site, maintenance time and resource availability.

9. The equipment maintenance and management system based on the Internet of Things cloud platform according to claim 6, characterized in that: The IoT cloud platform module also specifically performs the following operations: Use data analysis to predict component requirements for different equipment failure risks within the equipment site; Based on the inventory management model, spare parts inventory is configured according to the component requirements of different equipment failure risks.

10. A device maintenance and management method based on the Internet of Things cloud platform, characterized in that: include: Collect real-time data from the equipment site through the data acquisition module and upload it to the IoT cloud platform module; The real-time data is stored and analyzed through the IoT cloud platform module, and the analysis results are uploaded to the decision-making module; Optimize the maintenance strategy of the equipment site based on the decision-making results through the decision-making module; Among them, predictive maintenance of equipment on site is also carried out through the IoT cloud platform module; Based on the real-time data stored in the IoT cloud platform module, a management interaction model is constructed according to the on-site 3D map of the equipment site; Represent the interaction information in the management interaction model in terms of interaction time and space distribution to obtain the interaction time and space distribution; Perform fuzzy feature extraction on the interactive spatiotemporal distribution to obtain a fuzzy feature set; Determining a target refined feature extraction rule from a refined feature extraction rule library; wherein the standard fuzzy feature set of the target refined feature extraction rule and the fuzzy feature set match each other; Based on the target refined feature extraction rules, the interactive spatiotemporal distribution is refined to obtain a refined feature set; Determining target determination knowledge corresponding to the refined feature set from a determination knowledge base; wherein the standard refined feature set of the target determination knowledge and the refined feature set match each other; Analyze target determination knowledge and determine the effective target distribution division rules and target expectation formulation rules; Based on the target effective distribution partitioning rule, the effective distribution is divided from the interactive spatiotemporal distribution; Based on the effective distribution, a shooting range circle is determined in the management interaction model; wherein the shooting range circle is the minimum enclosing sphere that minimum encloses the effective distribution; The drone model position is determined based on the shooting range circle; wherein, when the drone enters the drone model position, it can clearly capture all the shooting range circles at the same time or can sequentially and clearly capture all the shooting range circles by changing the shooting angle no more than a preset number of times; Determine the actual position of the drone model from the equipment site and use it as the target position; Formulate rules based on target expectations and formulate logical expectations based on shooting range circles; Control the drone to enter the target position; Display the drone's virtual control panel and real-time flight footage to managers; When the operation logic of the administrator's operation of the virtual operation panel in the second period does not conform to the logical expectation, based on the logical expectation, the administrator's operation of the virtual operation panel is guided in a constrained manner in the third period; When the management personnel input the equipment maintenance management strategy, online equipment maintenance management is performed on the equipment site based on the equipment maintenance management strategy.

Images