Industrial and commercial enterprise management method and system based on Internet of Things

Abstract

The invention relates to an industrial and commercial enterprise management method and system based on the Internet of Things, and the method comprises the steps: obtaining production operation data and equipment asset data through Internet of Things equipment, and generating a structured data set according to the classification of preset service labels; based on the production operation data set, optimizing a production plan and productivity matching through a constrained programming algorithm, and generating a production scheduling scheme in combination with an equipment state; based on the equipment asset data set, utilizing a machine learning model to predict an equipment fault and calculate a maintenance period, and combining a maintenance standard to generate an equipment asset maintenance plan; and performing time conflict detection and resource allocation optimization on the production scheduling scheme and the equipment asset maintenance plan, and generating a comprehensive management scheme through a multi-target priority ranking algorithm. According to the method, by dynamically coordinating production resources and equipment maintenance tasks, the productivity utilization rate and the equipment reliability are improved, the non-planned shutdown loss is reduced, and collaborative optimization of enterprise operation efficiency and cost control is achieved.

Description

Technical Field

[0001] This invention belongs to the field of enterprise management, and in particular relates to a method and system for industrial and commercial enterprise management based on the Internet of Things. Background Technology

[0002] With the development of Industrial Internet of Things (IIoT) and intelligent manufacturing technologies, enterprises are gradually introducing sensor networks, edge computing devices, and cloud analytics platforms to build production management systems. By collecting equipment operation data in real time and combining it with algorithms to optimize production processes, the level of industrial automation is improved. In traditional technologies, enterprises typically adopt a separate management mechanism: the production scheduling relies on fixed scheduling rules based on historical experience (such as first-come, first-served, static priority allocation), and preset tasks are executed through a PLC control system; the equipment maintenance adopts a periodic inspection or reactive maintenance mode, relying on manual inspection records and fixed maintenance cycle tables, with maintenance work orders managed by an independent EAM (Enterprise Asset Management System). However, existing technologies have the following core flaws: Decision-making fragmentation: Production scheduling and equipment maintenance plans are formulated by independent systems, leading to frequent time conflicts (such as maintenance tasks occupying critical equipment time slots) and resource conflicts (such as manpower and spare parts being repeatedly used); Response lag: Traditional static scheduling cannot dynamically respond to sudden equipment failures (such as when sensors detect abnormal vibrations, the PLC system still requires manual intervention to adjust the production line); Resource waste: Regular maintenance can easily lead to over-maintenance (downtime even when equipment is healthy), while post-event maintenance leads to increased losses from unplanned downtime. Summary of the Invention

[0003] Therefore, it is necessary to provide an IoT-based business management method and system that can solve the above problems.

[0004] Firstly, this application provides a business management method based on the Internet of Things, including:

[0005] Production and operation data and equipment asset data are acquired through IoT devices and classified according to preset business tags to generate structured production and operation datasets and equipment asset datasets.

[0006] Based on the production operation dataset, production planning optimization and capacity matching analysis are performed through constrained programming algorithms, and production scheduling schemes are generated by combining IoT device status information.

[0007] Based on the equipment asset dataset, machine learning models are used to predict equipment failures and calculate maintenance cycles, and equipment asset maintenance plans are generated in combination with equipment asset maintenance standards.

[0008] Time conflict detection and resource allocation optimization are performed on production scheduling plans and equipment asset maintenance plans. A comprehensive management plan is generated through a multi-objective priority ranking algorithm. The comprehensive management plan is used to guide the allocation of enterprise production resources and the execution of equipment maintenance.

[0009] In one embodiment, production and operation data are acquired through IoT devices, including acquiring production equipment operating parameters through a sensor group deployed on the production site, acquiring material inventory data through a warehouse smart terminal, and acquiring order progress information through the order management system API interface;

[0010] The production scheduling scheme is generated by combining the status information of IoT devices. This includes dynamically allocating production tasks based on the real-time network status of the devices, triggering task migration to redundant devices for devices in a faulty state, setting the priority of production tasks based on the threshold of device operating parameters, optimizing the time window of production tasks through a genetic algorithm, and generating a production scheduling scheme with the minimum production cycle.

[0011] In one embodiment, a machine learning model is used to predict equipment failures, including extracting features from equipment runtime, energy consumption data and vibration signals through a convolutional neural network, training a failure prediction model in combination with historical failure records, and outputting the probability of equipment failure.

[0012] The system generates equipment asset maintenance plans based on equipment asset maintenance standards. This includes generating plans that specify maintenance time, maintenance type, and maintenance resource requirements, taking into account equipment failure probability and spare parts inventory data.

[0013] In one embodiment, the method further includes:

[0014] Based on real-time production and operation data and equipment asset status information collected by IoT devices, and through a preset production health monitoring model, abnormal status detection is performed, and an abnormal report including the abnormality level is generated.

[0015] Based on the anomaly level, the production scheduling scheme is adjusted through a constraint programming algorithm, and the equipment asset maintenance plan is adjusted using a multi-objective priority ranking algorithm according to the impact of the anomaly level on maintenance needs.

[0016] In one embodiment, time conflict detection and resource allocation optimization are performed on the production scheduling scheme and equipment asset maintenance plan, including:

[0017] According to the function Detection time conflict, among which, T s T represents the execution time range of a single task in the production scheduling scheme. m Indicates the time range for executing equipment maintenance tasks;

[0018] According to formula Rs +R m ≤R cap Apply resource allocation constraints, where R cap R is the maximum amount of resources that can be provided. s R represents the amount of resources required for production scheduling tasks. m The amount of resources required for equipment maintenance tasks;

[0019] The formula Plan = arg max(w1·F) is used. t +w2·F r +w3·F p ) to optimize resource allocation, where F t F r and F p Let w1, w2, and w3 be the objective functions for time efficiency, resource utilization, and task priority, respectively, and w1, w2, and w3 be the weights corresponding to time efficiency, resource utilization, and task priority, respectively.

[0020] In one embodiment, the method further includes:

[0021] According to the formula Calculate the parameter fluctuation values ​​of real-time production and operation data, where d t These are real-time sampled values. This is the historical average.

[0022] Based on the fluctuation value, according to the formula The sampling frequency of IoT devices is dynamically adjusted, where f is the real-time sampling frequency. min Based on the sampling frequency, f max The maximum sampling frequency is defined as Fluct, where Fluct represents the parameter fluctuation value of real-time production and operation data. max This is the benchmark threshold for fluctuation range.

[0023] In one embodiment, the method further includes:

[0024] Generate a comprehensive management view, which is then integrated and presented through the following steps:

[0025] Based on a unified timeline, the task allocation of the production scheduling plan and the maintenance tasks of the equipment asset maintenance plan are displayed in layers within the same Gantt chart framework;

[0026] In the Gantt chart framework, the identifier of the IoT device is used as an index, and the corresponding device task column displays a visual identifier of the IoT device's failure probability and anomaly report level.

[0027] The time conflict detection results and resource allocation optimization results are dynamically synchronized to the resource occupancy status display area of ​​the Gantt chart framework.

[0028] Secondly, this application also provides an Internet of Things-based business management system, including:

[0029] The data acquisition and processing module is used to acquire production and operation data and equipment asset data through IoT devices, and classify and process them according to preset business tags to generate structured production and operation datasets and equipment asset datasets.

[0030] The production scheduling optimization module is used to optimize production plans and perform capacity matching analysis based on production operation datasets through constrained programming algorithms, and generate production scheduling solutions by combining IoT device status information.

[0031] The equipment maintenance management module is used to predict equipment failures and calculate maintenance cycles based on equipment asset datasets using machine learning models, and to generate equipment asset maintenance plans in conjunction with equipment asset maintenance standards.

[0032] The integrated management decision-making module is used to detect time conflicts and optimize resource allocation for production scheduling plans and equipment asset maintenance plans. It generates integrated management plans through a multi-objective priority ranking algorithm, which guides the allocation of enterprise production resources and the execution of equipment maintenance.

[0033] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described Internet of Things-based business management method.

[0034] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described Internet of Things-based business management method.

[0035] The aforementioned IoT-based industrial and commercial enterprise management method and system, computer equipment, and storage medium collect structured production operation and equipment asset data in real time through IoT devices. It dynamically optimizes production scheduling schemes using constrained programming algorithms and simultaneously generates predictive equipment asset maintenance plans by combining machine learning models. Time conflict detection and resource allocation optimization generate comprehensive management solutions, resolving the decision-making fragmentation problem in traditional management models and eliminating conflicts between production and maintenance tasks. By directly integrating equipment status information, it achieves real-time response scheduling for sudden failures, overcoming the lag in response to static scheduling. Relying on data-driven fault prediction, it accurately triggers maintenance tasks, reducing resource waste caused by unplanned downtime and over-maintenance. While ensuring equipment reliability, it improves overall capacity utilization and reduces operation and maintenance costs. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart of an IoT-based industrial and commercial enterprise management method according to the present invention.

[0038] Figure 2 This is a structural diagram of an Internet of Things-based industrial and commercial enterprise management system according to the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0040] This invention can be implemented in an industrial IoT cloud-edge collaborative architecture. It collects real-time equipment operation and production data through field sensors, preprocesses the data via an edge gateway, and then transmits it to an industrial server. The server dynamically optimizes the production scheduling scheme based on a constraint programming algorithm, while simultaneously using a machine learning model to predict equipment failures and generate maintenance plans. When a conflict between production tasks and maintenance windows is detected, or when a sudden equipment malfunction is detected, a multi-objective resource optimization algorithm is triggered to reallocate tasks. A comprehensive management plan is generated and synchronized to the workshop terminal for execution guidance. It supports flexible deployment and can achieve closed-loop management in the cloud, on local servers, or in hybrid environments.

[0041] In one embodiment, such as Figure 1 As shown, an IoT-based industrial and commercial enterprise management method is provided. This embodiment illustrates the method applied to a local server. It is understood that this method can also be applied to a cloud server, and further to a hybrid environment including both local and cloud servers, achieved through interaction between the local and cloud servers. In this embodiment, the method includes the following steps:

[0042] S01 acquires production and operation data and equipment asset data through IoT devices, and classifies them according to preset business tags to generate structured production and operation datasets and equipment asset datasets.

[0043] The process involves collecting production and operational data via IoT devices, including equipment operating parameters, material inventory data, and order progress information. It also involves collecting equipment asset data, including basic attributes (such as equipment model, manufacturer, and service life), real-time status (such as online / offline status and fault codes), and maintenance history (such as repair records and replacement part information). Based on enterprise business processes and management needs, multi-dimensional classification tags can be preset, such as: for production and operation dimensions: order type, product model, production process stage, and material category; for equipment asset dimensions: equipment type (such as processing equipment and refrigeration equipment), equipment level (production line - single machine - component), and maintenance level (routine maintenance and overhaul). The data collected by IoT devices is parsed, and automatically classified according to preset tag rules. For example, vibration data of a certain piece of equipment is classified under the "Equipment Status - Vibration Anomaly" tag, and progress data of a certain order is classified under the "Order Management - Delivery Time Warning" tag. Using a relational database or distributed data structure (such as Hive tables or JSON format), the classified data is mapped to standardized fields, generating structured production and operation datasets and equipment asset datasets.

[0044] S02, based on the production operation dataset, optimizes the production plan and analyzes the capacity matching through the constraint programming algorithm, and generates a production scheduling scheme by combining the status information of IoT devices.

[0045] The constraint-based programming can be constructed based on the following constraints: capacity constraints, setting the maximum production load of a single piece of equipment or production line based on parameters such as maximum equipment capacity and production line cycle time (e.g., a machining center's maximum daily processing capacity is 500 pieces); order constraints, establishing time window constraints for order execution based on order delivery dates, priorities, and product process routes (e.g., priority A orders must be completed within 48 hours); and material constraints: setting a threshold for available materials for production tasks based on material inventory data collected from intelligent warehouse terminals (e.g., suspending related production tasks when the inventory of a certain raw material is below 100kg). Optimization objectives can be set as follows: minimizing the production cycle by optimizing the start and end times of each production task through algorithms to shorten the overall order delivery cycle; maximizing equipment utilization by evenly distributing production tasks to avoid equipment idleness or overload (e.g., setting the equipment utilization target to ≥85%); and minimizing changeover costs by optimizing task sequencing based on product process similarity to reduce the number of equipment changeovers (e.g., reducing changeover costs by 20% when similar products are produced in concentrated batches).

[0046] S03, based on the equipment asset dataset, uses machine learning models to predict equipment failures and calculate maintenance cycles, and generates equipment asset maintenance plans in conjunction with equipment asset maintenance standards.

[0047] This involves using real-time parameters from equipment asset datasets, such as equipment runtime, energy consumption data (e.g., current, voltage), and vibration signals (e.g., acceleration, frequency spectrum), as well as historical failure times, failure types (e.g., bearing wear, motor overheating), and maintenance measures. Machine learning models (e.g., convolutional neural networks) are employed to extract deep features from the equipment runtime data (e.g., abnormal frequency components in vibration signals) through convolutional layers, reduce feature dimensionality through pooling layers, and output failure probability values ​​through fully connected layers. Weibull distribution parameters are estimated from historical lifespan data of similar equipment to calculate the remaining lifespan (e.g., a bearing model with an average lifespan of 5000 hours, already running for 4000 hours, predicts a remaining lifespan of 800 hours). The maintenance cycle is then calculated by combining failure probability, equipment runtime, cumulative energy consumption, and remaining lifespan. Finally, equipment asset maintenance standards are digitally decomposed, and a rule engine is used to link these standards with maintenance cycles to generate equipment asset maintenance plans.

[0048] S04 performs time conflict detection and resource allocation optimization on the production scheduling plan and equipment asset maintenance plan, and generates a comprehensive management plan through a multi-objective priority ranking algorithm. The comprehensive management plan is used to guide the enterprise's production resource allocation and equipment maintenance execution.

[0049] The system can detect time conflicts based on a preset time conflict detection algorithm. For example, if the production time of a machine tool overlaps with the lubrication and maintenance time of that machine tool, a conflict warning will be triggered. Resource allocation optimization is performed based on a resource constraint algorithm built upon human resources (matching engineers or workers with task requirements), spare parts resources (based on real-time inventory data to avoid task stagnation due to spare parts shortages), and equipment resources (the same equipment cannot be used for both production and maintenance simultaneously). A comprehensive management solution is generated by combining a multi-objective priority ranking algorithm with time efficiency, resource utilization, and task priority (using a non-dominated sorting genetic algorithm to generate a Pareto optimal solution set through selection, crossover, and mutation operations; combined with the company's preset priority rules, such as prioritizing high-priority order production tasks over non-critical equipment maintenance, the final solution is selected from the optimal solution set). The system uses equipment asset datasets to drive equipment fault prediction, maintenance cycle calculation, and maintenance plan generation, achieving full-process intelligentization.

[0050] The aforementioned IoT-based industrial and commercial enterprise management method acquires production operation data and equipment asset data through IoT devices and classifies them into structured datasets. It then uses constrained programming algorithms to optimize production plans and capacity matching to generate production scheduling schemes, and leverages machine learning models to predict equipment failures and calculate maintenance cycles to generate equipment asset maintenance plans. Finally, it performs time conflict detection and resource allocation optimization on the production scheduling scheme and equipment asset maintenance plan to generate a comprehensive management scheme, achieving dynamic coordination between production resources and equipment maintenance tasks. In this process, the collaborative management of production scheduling and equipment maintenance is integrated into the same system, avoiding time and resource conflicts caused by production scheduling schemes and equipment maintenance plans being formulated in separate systems under traditional separate management mechanisms, thus solving the problem of fragmented decision-making. Real-time generation of production scheduling schemes through IoT device status information enables dynamic response to sudden equipment failures, overcoming the lag in response of traditional static scheduling. Fault prediction driven by equipment asset datasets accurately triggers maintenance tasks, changing the situation of over-maintenance caused by periodic inspections and the expansion of unplanned downtime losses due to post-event repairs, reducing resource waste, improving capacity utilization and equipment reliability, reducing unplanned downtime losses, and achieving synergistic optimization of enterprise operational efficiency and cost control.

[0051] In one embodiment, production operation data is obtained through IoT devices, including S11, obtaining production equipment operating parameters through a sensor group deployed on the production site, obtaining material inventory data through a warehouse smart terminal, and obtaining order progress information through the order management system API interface;

[0052] The production scheduling scheme is generated by combining the status information of IoT devices, including S12, which dynamically allocates production tasks according to the real-time network status of the devices, triggers the migration of tasks to redundant devices for devices in a faulty state, sets the priority of production tasks based on the threshold of device operating parameters, optimizes the time window of production tasks through genetic algorithms, and generates a production scheduling scheme with the minimum production cycle.

[0053] Specifically, IoT sensor devices deployed on-site can be used to collect real-time operating parameters of production equipment (such as speed, temperature, vibration frequency, etc.), and warehouse smart terminals can be used to dynamically acquire material inventory data (including the stock and flow information of raw materials, semi-finished products, and finished products). Order progress information (including order status, delivery date, production process requirements, etc.) can be synchronously acquired through the API interface of the order management system, realizing real-time acquisition and fusion of multi-source data. When generating production scheduling plans based on IoT device status information, production tasks are dynamically allocated according to the real-time network status of the equipment (online / offline, equipment operation status) to achieve task matching with equipment capacity. When a fault is detected in the equipment, a task migration mechanism is triggered to transfer the tasks undertaken by the faulty equipment to redundant equipment. Production task priorities are set based on equipment operating parameter thresholds (such as the load limit and energy consumption threshold of key equipment) to ensure that high-priority tasks are executed first. The time window of production tasks can be optimized through genetic algorithms, and the optimal task order can be solved iteratively by crossover, mutation and other operations to generate a production scheduling plan with the minimum production cycle, realizing the synergistic optimization of capacity utilization and time efficiency.

[0054] In one embodiment, a machine learning model is used to predict equipment failures, including S21, extracting features from equipment runtime, energy consumption data and vibration signals through a convolutional neural network, training a failure prediction model by combining historical failure records, and outputting the probability of equipment failure.

[0055] The equipment asset maintenance plan is generated by combining the equipment asset maintenance standards, including S22, which generates an equipment asset maintenance plan that includes maintenance time, maintenance type and maintenance resource requirements based on the equipment asset maintenance standards and the equipment failure probability and spare parts inventory data.

[0056] For example, the equipment failure prediction step using a machine learning model can utilize the convolutional layers of a convolutional neural network to process equipment runtime, energy consumption data, and vibration signals, extracting features. These features are then used to train the model in conjunction with historical failure records, resulting in a failure prediction model. Based on this model, the probability of equipment failure is output according to newly acquired production and operation data and equipment asset data. When generating an equipment asset maintenance plan based on equipment asset maintenance standards, a maintenance plan including maintenance time, maintenance type, and maintenance resource requirements can be generated, taking into account the equipment asset maintenance standards, equipment failure probability, and spare parts inventory data. Specifically, the maintenance time is determined considering the equipment failure probability; maintenance is triggered when the failure probability reaches a certain threshold. The maintenance type is determined based on the equipment failure situation and maintenance standards. Maintenance resource requirements are planned based on the maintenance type and spare parts inventory data.

[0057] In one embodiment, the method further includes:

[0058] S31, based on real-time production operation data and equipment asset status information collected by IoT devices, and through a preset production health monitoring model, detects abnormal states and generates an anomaly report including the anomaly level.

[0059] S32 adjusts the production scheduling scheme based on the anomaly level using a constraint programming algorithm, and adjusts the equipment asset maintenance plan using a multi-objective priority ranking algorithm based on the impact of the anomaly level on maintenance needs.

[0060] For example, based on real-time production and operation data (such as equipment operating parameters, material inventory data, and order progress information) and equipment asset status information (such as equipment network status and fault codes) collected by IoT devices, abnormal status detection is performed through a preset production health monitoring model. This model constructs benchmark thresholds (such as equipment temperature thresholds and vibration amplitude thresholds) based on historical normal operation data. It compares real-time data with benchmark thresholds to identify abnormal data points that exceed the threshold range. Combined with parameters such as the frequency of abnormal occurrence and the scope of impact, it generates an abnormal report containing anomaly levels (such as low, medium, and high levels divided using a preset level mapping mechanism) to quantify the severity of anomalies in the production system. Based on the anomaly levels, a two-dimensional dynamic adjustment is implemented: For the production scheduler, a constraint programming algorithm can be used to reconstruct the time window, priority, and resource allocation of production tasks according to the anomaly level. For example, when the anomaly level is high, non-critical tasks are automatically suspended, and resources are prioritized for allocation to affected production lines. Capacity compensation is achieved by adjusting task order and equipment load. For the equipment asset maintenance plan, the priority of maintenance tasks is recalculated using a multi-objective priority ranking algorithm based on the degree of impact of the anomaly level on maintenance needs (such as the higher the anomaly level, the greater the increase in equipment failure probability). For example, for equipment with an anomaly level of medium, the maintenance window is triggered in advance, and the maintenance type is dynamically adjusted based on spare parts inventory data (such as upgrading from routine maintenance to component replacement), and the maintenance resource requirements are updated simultaneously (such as increasing the number of maintenance personnel).

[0061] In one embodiment, time conflict detection and resource allocation optimization are performed on the production scheduling scheme and equipment asset maintenance plan, including:

[0062] S41, according to the function Detection time conflict, among which, T s T represents the execution time range of a single task in the production scheduling scheme. m Indicates the time range for executing equipment maintenance tasks;

[0063] S42, according to formula R s +R m ≤R cap Apply resource allocation constraints, where R cap R is the maximum amount of resources that can be provided.s R represents the amount of resources required for production scheduling tasks. m The amount of resources required for equipment maintenance tasks;

[0064] S43, using the formula Plan = arg max(w1·F t +w2·F r +w3·F p ) to optimize resource allocation, where F t F r and F p Let w1, w2, and w3 be the objective functions for time efficiency, resource utilization, and task priority, respectively, and w1, w2, and w3 be the weights corresponding to time efficiency, resource utilization, and task priority, respectively.

[0065] Specifically, the time conflict detection function Conflict(T) is used. s T m Determine the time overlap between production scheduling tasks and equipment maintenance tasks: when the execution time range T of a single task in the production scheduling plan is... s The execution time range T of equipment maintenance tasks m If an intersection exists, the function returns 1, triggering a conflict warning; if there is no intersection, it returns 0, indicating no conflict. This is based on the resource allocation constraint formula R. s +R m ≤R cap Implement total resource control: among which R s R m and R cap This can include manpower hours, equipment hours, and spare parts quantity; expressed by the formula Plan = arg max(w1·F t +w2·F r +w3·F p Construct a comprehensive optimization objective, F t For a time efficiency objective function (such as minimizing production cycle time or maintenance window delay), F r For the objective function of resource utilization (such as maximizing equipment / labor utilization), F p The objective function is the task priority (such as the weight coefficient of high priority orders or critical equipment maintenance). The weight parameters w1, w2 and w3 of each objective function can be dynamically adjusted according to the actual needs of the enterprise (such as increasing the weight of w1 when the order is urgent). By solving for the maximum value of the objective function, the optimal resource allocation scheme that takes into account time efficiency, resource utilization and task priority is generated, so as to realize the coordinated scheduling of production and maintenance tasks.

[0066] In one embodiment, the method further includes:

[0067] S51, according to formula Calculate the parameter fluctuation values ​​of real-time production and operation data, where d t For real-time sampled values, This is the historical average.

[0068] S52, based on fluctuation values, according to the formula The sampling frequency of IoT devices is dynamically adjusted, where f is the real-time sampling frequency. min Based on the sampling frequency, f max The maximum sampling frequency is defined as Fluct, where Fluct represents the parameter fluctuation value of real-time production and operation data. max This is the benchmark threshold for fluctuation range.

[0069] For example, the formula In the middle, the real-time sampled value d t This refers to the historical average of production and operation data (such as equipment operating parameters and material inventory data) collected in real time by IoT devices. This data is obtained based on statistical analysis of similar data within a preset time window (e.g., the past 24 hours); the fluctuation of production and operation data is quantified by calculating the absolute deviation rate between real-time sampled values ​​and historical averages, and the magnitude of data deviation from normal conditions is represented as a percentage; based on the calculated Fluct, the formula is used... The sampling frequency is dynamically adjusted, where the real-time sampling frequency f is updated in real time according to the fluctuation value, and the base sampling frequency f... min Set as the minimum sampling rate and maximum sampling frequency f during normal system operation. max The maximum sampling rate of the system is limited under abnormal conditions. As Fluct increases, the sampling frequency f increases towards f. max Approaching, using high-frequency data acquisition to capture anomaly details; as Fluct decreases, f regresses to f min This reduces data transmission and storage overhead.

[0070] In one embodiment, the method further includes:

[0071] S61, Generate a comprehensive management view, which is then integrated and presented through the following steps:

[0072] S61.1, based on a unified timeline, displays the task allocation of the production scheduling scheme and the maintenance tasks of the equipment asset maintenance plan in a layered overlay within the same Gantt chart framework;

[0073] S61.2 In the Gantt chart framework, the identifier of the IoT device is used as an index, and the corresponding device task column displays a visual identifier of the IoT device's failure probability and anomaly report level.

[0074] S61.3 dynamically synchronizes the time conflict detection results and resource allocation optimization results to the resource occupancy status display area of ​​the Gantt chart framework.

[0075] For example, based on a unified timeline, the task allocation of the production scheduling plan and the maintenance tasks of the equipment asset maintenance plan are displayed in a layered overlay within the same Gantt chart framework. This can include: using the timeline as a horizontal reference (e.g., divided by hour, day, or week), and setting up production task layers and maintenance task layers vertically; in the production task layer, each task is represented by a rectangle, including the task name, start time, end time, and information about the production line / equipment to which it belongs; in the maintenance task layer, maintenance tasks are distinguished by rectangles of different colors (e.g., blue for routine maintenance and red for fault repair), and the maintenance type and estimated time are displayed synchronously; through the layered overlay mechanism, the time overlap relationship between production and maintenance tasks is presented intuitively, providing a visual basis for time conflict detection; in the Gantt chart framework, the identifier of the IoT device (e.g., device number, MAC address) is used as an index to display the fault probability and anomaly report level in the corresponding device task column. The visualization indicators may include: a fault probability progress bar (e.g., 0-100%) on the left side of each device column, displaying the current fault probability value in real time; an anomaly level indicator light on the right side (e.g., green for normal, yellow for warning, red for emergency), corresponding to the anomaly report level generated in step S31; clicking the visualization indicator will pop up a details window, displaying detailed device operating parameters, historical fault records, and maintenance suggestions; dynamically synchronizing the time conflict detection results and resource allocation optimization results to the resource occupancy status display area of ​​the Gantt chart framework, which may include: highlighting conflicting tasks (e.g., overlapping time periods of production and maintenance tasks) with the time borders or shadows of the time conflict detection results, and explaining the conflict type (time conflict / resource conflict) in the legend; the resource occupancy status display area uses a heatmap or bar chart to display the occupancy rate and remaining quantity of various resources (manpower, equipment, spare parts) in real time, where: R s With R m Different colored stripes are used to distinguish them; when R s +R m >R cap When the resource deficit exceeds the limit, a red warning is displayed, and the resource gap value is shown simultaneously. Through a visualization integration solution, abstract data such as time conflicts and resource allocation are transformed into graphical information, reducing the decision-making cost for managers. Production and maintenance tasks are presented in the same view, which makes it easy for cross-departmental teams to quickly locate conflict points and optimize collaboration processes. Key indicators such as equipment health status and resource occupancy are visualized in real time, supporting rapid identification and response to abnormal states.

[0076] The aforementioned IoT-based industrial and commercial enterprise management method collects production operation and equipment asset data in real time through IoT devices and generates structured datasets. It utilizes constrained programming algorithms to optimize production scheduling schemes, machine learning models to predict equipment failures and generate maintenance plans, and time conflict detection and resource allocation optimization to generate comprehensive management schemes. This achieves dynamic coordination between production resources and equipment maintenance tasks, resolving the decision-making fragmentation caused by production scheduling and equipment maintenance being independent systems under traditional separate management mechanisms, and eliminating time and resource conflicts. By generating scheduling schemes and task migration mechanisms in real time through equipment status information, it dynamically responds to sudden equipment failures, overcoming the response lag of static scheduling. Data-driven fault prediction accurately triggers maintenance tasks, avoiding over-maintenance from periodic inspections and unplanned downtime losses from post-event repairs, reducing resource waste, improving capacity utilization and equipment reliability, and achieving synergistic optimization of enterprise operational efficiency and cost control. Furthermore, through anomaly detection and dynamic adjustment, adaptive sampling mechanisms, and comprehensive management view technology, it further enhances the real-time response capability to production anomalies and the flexibility of resource scheduling, improves data collection efficiency and decision visualization, and optimizes cross-departmental collaboration processes.

[0077] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0078] Based on the same inventive concept, this application also provides an IoT-based business management system for implementing the aforementioned IoT-based business management method. The solution provided by this system is similar to the implementation described in the above method. Therefore, the specific limitations of one or more IoT-based business management system embodiments provided below can be found in the limitations of the IoT-based business management method described above, and will not be repeated here.

[0079] In one exemplary embodiment, such as Figure 2 As shown, an Internet of Things (IoT)-based business management system is provided, including:

[0080] The data acquisition and processing module 101 is used to acquire production and operation data and equipment asset data through IoT devices, and classify and process them according to preset business tags to generate structured production and operation datasets and equipment asset datasets.

[0081] The production scheduling optimization module 102 is used to optimize production plans and perform capacity matching analysis based on production operation datasets through constrained programming algorithms, and generate production scheduling schemes by combining IoT device status information.

[0082] Equipment maintenance management module 103 is used to predict equipment failures and calculate maintenance cycles based on equipment asset datasets using machine learning models, and generate equipment asset maintenance plans in conjunction with equipment asset maintenance standards.

[0083] The integrated management decision module 104 is used to detect time conflicts and optimize resource allocation for production scheduling plans and equipment asset maintenance plans. It generates integrated management plans through a multi-objective priority ranking algorithm, which guides the allocation of enterprise production resources and the execution of equipment maintenance.

[0084] In one embodiment, the data acquisition and processing module 101 is also used to acquire production equipment operating parameters through a sensor group deployed on the production site, acquire material inventory data through a warehouse smart terminal, and acquire order progress information through the order management system API interface;

[0085] The production scheduling optimization module 102 is also used to dynamically allocate production tasks according to the real-time network status of the equipment, trigger task migration to redundant equipment for equipment in a faulty state, set the priority of production tasks based on the equipment operating parameter threshold, optimize the time window of production tasks through genetic algorithm, and generate a production scheduling scheme with the minimum production cycle.

[0086] In one embodiment, the equipment maintenance management module 103 is further configured to:

[0087] Features are extracted from equipment runtime, energy consumption data and vibration signals using convolutional neural networks. A fault prediction model is trained by combining historical fault records and the equipment fault probability is output.

[0088] The system generates equipment asset maintenance plans based on equipment asset maintenance standards. This includes generating plans that specify maintenance time, maintenance type, and maintenance resource requirements, taking into account equipment failure probability and spare parts inventory data.

[0089] In one embodiment, the system further includes a production anomaly detection module, used for:

[0090] Based on real-time production and operation data and equipment asset status information collected by IoT devices, and through a preset production health monitoring model, abnormal status detection is performed, and an abnormal report including the abnormality level is generated.

[0091] Based on the anomaly level, the production scheduling scheme is adjusted through a constraint programming algorithm, and the equipment asset maintenance plan is adjusted using a multi-objective priority ranking algorithm according to the impact of the anomaly level on maintenance needs.

[0092] In one embodiment, the integrated management decision module 104 is further configured to:

[0093] According to the function Detection time conflict, among which, T s T represents the execution time range of a single task in the production scheduling scheme. m Indicates the time range for executing equipment maintenance tasks;

[0094] According to formula R s +R m ≤R cap Apply resource allocation constraints, where R cap R is the maximum amount of resources that can be provided. s R represents the amount of resources required for production scheduling tasks. m The amount of resources required for equipment maintenance tasks;

[0095] The formula Plan = arg max(w1·F) is used. t +w2·F r +w3·F p ) to optimize resource allocation, where F t F r and F p Let w1, w2, and w3 be the objective functions for time efficiency, resource utilization, and task priority, respectively, and w1, w2, and w3 be the weights corresponding to time efficiency, resource utilization, and task priority, respectively.

[0096] In one embodiment, the data acquisition and processing module 101 is further configured to:

[0097] According to the formula Calculate the parameter fluctuation values ​​of real-time production and operation data, where d t These are real-time sampled values. This is the historical average.

[0098] Based on the fluctuation value, according to the formula The sampling frequency of IoT devices is dynamically adjusted, where f is the real-time sampling frequency. min Based on the sampling frequency, f max The maximum sampling frequency is defined as Fluct, where Fluct represents the parameter fluctuation value of real-time production and operation data.max This is the benchmark threshold for fluctuation range.

[0099] In one embodiment, a visualization module is also included for:

[0100] Generate a comprehensive management view, which is then integrated and presented through the following steps:

[0101] Based on a unified timeline, the task allocation of the production scheduling scheme and the maintenance tasks of the asset maintenance plan are displayed in layers within the same Gantt chart framework;

[0102] In the Gantt chart framework, the identifier of the IoT device is used as an index, and the corresponding device task column displays a visual identifier of the IoT device's failure probability and anomaly report level.

[0103] The time conflict detection results and resource allocation optimization results are dynamically synchronized to the resource occupancy status display area of ​​the Gantt chart framework.

[0104] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the Internet of Things-based business management method as described above.

[0105] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0106] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0107] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A business management method based on the Internet of Things, characterized in that, The method includes: Production and operation data and equipment asset data are acquired through IoT devices and classified according to preset business tags to generate structured production and operation datasets and equipment asset datasets. Based on the aforementioned production and operation dataset, production planning optimization and capacity matching analysis are performed using a constraint programming algorithm, and a production scheduling scheme is generated by combining IoT device status information. Based on the equipment asset dataset, a machine learning model is used to predict equipment failures and calculate maintenance cycles, and an equipment asset maintenance plan is generated by combining the equipment asset maintenance standards. The production scheduling scheme and equipment asset maintenance plan are subjected to time conflict detection and resource allocation optimization. A comprehensive management scheme is generated through a multi-objective priority ranking algorithm. The comprehensive management scheme is used to guide the enterprise's production resource allocation and equipment maintenance execution.

2. The method according to claim 1, characterized in that, The acquisition of production and operation data through IoT devices includes acquiring production equipment operating parameters through sensor groups deployed on the production site, acquiring material inventory data through intelligent warehouse terminals, and acquiring order progress information through the order management system API interface; The production scheduling scheme generated by combining IoT device status information includes dynamically allocating production tasks based on the real-time network status of the devices, triggering task migration to redundant devices for devices in a faulty state, setting production task priorities based on device operating parameter thresholds, optimizing the production task time window through a genetic algorithm, and generating the production scheduling scheme with the minimum production cycle.

3. The method according to claim 1, characterized in that, The method of using machine learning models for equipment fault prediction includes extracting features from equipment runtime, energy consumption data, and vibration signals through convolutional neural networks, training a fault prediction model in combination with historical fault records, and outputting the probability of equipment fault. The process of generating an equipment asset maintenance plan by combining the equipment asset maintenance standards includes generating an equipment asset maintenance plan that includes maintenance time, maintenance type, and maintenance resource requirements based on the equipment asset maintenance standards, combined with the equipment failure probability data and spare parts inventory data.

4. The method according to claim 3, characterized in that, The method further includes: Based on real-time production and operation data and equipment asset status information collected by IoT devices, and through a preset production health monitoring model, abnormal status detection is performed, and an abnormal report including the abnormality level is generated. Based on the anomaly level, the production scheduling scheme is adjusted using the constraint programming algorithm, and the equipment asset maintenance plan is adjusted using the multi-objective priority ranking algorithm according to the impact of the anomaly level on maintenance requirements.

5. The method according to claim 1, characterized in that, The process of detecting time conflicts and optimizing resource allocation between the production scheduling scheme and the equipment asset maintenance plan includes: According to the function Detection time conflict, among which, T s T represents the execution time range of a single task in the production scheduling scheme. m Indicates the time range for executing equipment maintenance tasks; According to formula R s +R m ≤R cap Apply resource allocation constraints, where R cap R is the maximum amount of resources that can be provided. s R represents the amount of resources required for production scheduling tasks. m The amount of resources required for equipment maintenance tasks; The formula Plan = argmax(w1·F) is used. t +w2·F r +w3·F p ) to optimize resource allocation, where F t F r and F p Let w1, w2, and w3 be the objective functions for time efficiency, resource utilization, and task priority, respectively, and w1, w2, and w3 be the weights corresponding to time efficiency, resource utilization, and task priority, respectively.

6. The method according to claim 1, characterized in that, The method further includes: According to the formula Calculate the parameter fluctuation values ​​of real-time production and operation data, where d t These are real-time sampled values. This is the historical average. Based on the fluctuation value, according to the formula The sampling frequency of the IoT device is dynamically adjusted, where f is the real-time sampling frequency. min Based on the sampling frequency, f max The maximum sampling frequency is defined as Fluct, where Fluct represents the parameter fluctuation value of real-time production and operation data. max This is the benchmark threshold for fluctuation range.

7. The method according to claim 1, characterized in that, The method further includes: Generate a comprehensive management view, which is presented through the following steps: Based on a unified timeline, the task allocation of the production scheduling scheme and the maintenance tasks of the equipment asset maintenance plan are displayed in layers within the same Gantt chart framework; In the Gantt chart framework, the identifier of the IoT device serves as an index, and a visual identifier of the IoT device's failure probability and anomaly report level is displayed in the corresponding device task column. The time conflict detection results and resource allocation optimization results are dynamically synchronized to the resource occupancy status display area of ​​the Gantt chart framework.

8. An industrial and commercial enterprise management system based on the Internet of Things, characterized in that, The system includes: The data acquisition and processing module is used to acquire production and operation data and equipment asset data through IoT devices, and classify and process them according to preset business tags to generate structured production and operation datasets and equipment asset datasets. The production scheduling optimization module is used to optimize production plans and perform capacity matching analysis based on the production operation dataset using a constraint programming algorithm, and generate production scheduling schemes by combining IoT device status information. The equipment maintenance management module is used to predict equipment failures and calculate maintenance cycles using machine learning models based on the equipment asset dataset, and generate equipment asset maintenance plans in conjunction with equipment asset maintenance standards. The integrated management decision module is used to detect time conflicts and optimize resource allocation for the production scheduling plan and equipment asset maintenance plan. It generates an integrated management plan through a multi-objective priority ranking algorithm, which guides the enterprise's production resource allocation and equipment maintenance execution.

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

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

Images