Production and processing digital monitoring management platform based on Internet of Things

Abstract

The invention discloses a production and processing digital monitoring management platform based on the Internet of Things, and belongs to the field of digital supervision. Comprising a personnel perception module, an operation monitoring module, an energy consumption perception module, a beat regulation and control module, an edge processing module, an analogue simulation module, a quality monitoring module, a traceability tracking module, a risk scheduling module, a block evidence storage module, an early warning response module and a management decision module. According to the method, accurate maintenance prediction and resource scheduling optimization are realized, the individual burden can be reduced, the overall operation efficiency and safety are improved, overload calculation and invalid energy consumption are effectively avoided, the system stability and flexible scheduling capability are improved, the failure position of equipment is early warned, the service life of the equipment is prolonged, and the non-planned downtime is reduced. The closed-loop operation of data driving-intelligent control-dynamic scheduling is realized, and the response speed and decision quality of the whole production system are improved.

Description

Technical Field

[0001] The present invention relates to the field of digital supervision, and in particular to a digital monitoring and management platform for production and processing based on the Internet of Things. Background Art

[0002] Driven by a new round of global scientific and technological revolution and industrial transformation, traditional manufacturing enterprises are undergoing a critical transition from "automation" to "intelligence." In particular, with the rapid integration and development of cutting-edge technologies such as the Internet of Things (IoT), artificial intelligence (AI), edge computing, 5G, and blockchain, the digitalization, networking, and intelligence of production and processing processes are continuously improving, reshaping the operational logic and value structure of the industrial system. However, common problems in traditional manufacturing systems include: delayed equipment operating status monitoring, reliance on manual experience for fault detection, and slow early warning responses; a disconnect between production pace and worker status, which can easily lead to overload, fatigue, and reduced efficiency; a lack of real-time, itemized management of energy consumption data, making it difficult to support refined energy efficiency optimization; and a lack of dynamic prediction capabilities based on physical realities, which hinders effective preventive maintenance and flexible scheduling.

[0003] The existing digital monitoring and management platform for production and processing cannot accurately predict maintenance and optimize resource scheduling, which increases individual burdens and reduces overall operational efficiency and safety. In addition, the system has poor stability and flexible scheduling capabilities, and cannot provide early warning of equipment failure locations, shortening equipment life. Unplanned downtime increases, and the response speed and decision-making quality of the overall production system are reduced. To this end, we propose a digital monitoring and management platform for production and processing based on the Internet of Things. Summary of the Invention

[0004] The purpose of the present invention is to solve the defects in the prior art and to propose a digital monitoring and management platform for production and processing based on the Internet of Things.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: An IoT-based digital production and processing monitoring and management platform, including a personnel sensing module, an operation monitoring module, an energy consumption sensing module, a rhythm control module, an edge processing module, a simulation module, a quality monitoring module, a traceability module, a risk scheduling module, a block evidence storage module, an early warning response module, and a management decision-making module; The personnel sensing module collects the physiological parameters of workers in real time and analyzes the working status of each worker; The operation monitoring module identifies the health status of the device in real time through the passive electromagnetic sensing array embedded in the device housing; The energy consumption sensing module is used to collect the environment and energy consumption data of the production workshop in real time, and to segment the energy consumption by process, equipment and shift; The beat control module identifies the physiological rhythm trend of the group according to the working status of the workers and the health status of the equipment, and dynamically adjusts the production line beat and equipment operating speed in real time; The edge processing module is used to manage the energy budget of the production workshop and allocate computing resources among nodes to optimize the power consumption of the equipment cluster; The simulation module is used to build a device simulation model and simulate the device wear process and the self-evolution of the device status in real time; The quality monitoring module is used to collect the quality parameters of each device in the processing process in real time, analyze the quality of the processed products, and generate a process quality report of the products; The traceability module is used to establish a quality data chain and a carbon emission data chain, and based on the established dual-chain structure, conduct real-time cross-chain verification; The risk scheduling module is used to collect threat intelligence from different sources, predict supply chain disruption risks, and reconfigure alternative supply paths and production plans; The block evidence module is used to encrypt and slice each quality parameter and upload it to the quality data chain for evidence storage; The early warning response module generates equipment pre-maintenance plans and operation and maintenance work orders based on equipment simulation data, quality fluctuation records, operator physiological status and energy consumption, and pushes early warning information in real time; The management decision module provides decision suggestions and visualizes the collected data and analysis results through the display screen and management platform.

[0006] As a further solution of the present invention, the specific steps of the personnel perception module analyzing the working status of each worker are as follows: S1.1: Use uniformly distributed wearable devices to collect each worker's heart rate, skin temperature, epidermal conductivity, eye movement rate, and activity frequency in real time. These collected physiological parameters are then standardized to generate a comprehensive fatigue score for each worker. Based on this comprehensive fatigue score, each worker's current physiological load status is determined in real time. S1.2: Based on the human body's physiological rhythms, emotional rhythms, and intellectual rhythms, a corresponding three-cycle biorhythm model is established. The three-cycle biorhythm model is used to convert the rhythm data into time-domain signal superposition to obtain the rhythm synthesis intensity of each worker at different time points. S1.3: Based on the current physiological load status and rhythm synthesis intensity of each worker, obtain the comprehensive score of each worker's current status. If the worker's comprehensive status score is higher than the preset threshold, it is judged that the worker has entered the physiological trough, and the information of the worker in the physiological trough and the corresponding equipment number are recorded.

[0007] As a further solution of the present invention, the specific calculation formula for the comprehensive fatigue score in S1.1 is as follows: Where, Represents comprehensive fatigue score; HR represents current heart rate; Represents the historical average heart rate; represents the historical heart rate standard deviation; ST represents skin temperature; Represents the normal skin temperature baseline value; stands for temperature abnormality zone; EDA stands for real-time skin conductivity; represents the historical mean skin conductivity; represents the standard deviation of historical skin conductance; EF represents eye movement frequency; represents the normal peak of eye movement frequency; AF represents activity frequency; Represents the normal upper limit of activity frequency, which is derived from historical working condition records; as well as Respectively represent the weight coefficients of various physiological parameters, which are determined according to the type of work and job characteristics; The specific calculation formula of the three-cycle biorhythm model described in S1.2 is as follows: Where, Represents the rhythm synthesis intensity at the current time point; Represents the current time in days; represents the biological rhythm, which is 23 days; represents the emotional rhythm, which is 28 days; Represents the intellectual rhythm, which is 33 days.

[0008] As a further solution of the present invention, the specific steps of the operation monitoring module to identify the health status of the device in real time are as follows: P1.1: The passive electromagnetic sensing array embedded in the device housing detects the phase difference between the incident wave and the echo. Based on the detected phase difference, it calculates the local displacement of the reflection point. It then interpolates and spatially maps the data returned by the patch array to construct a local deformation heat map. P1.2: Use a feature denoising algorithm to remove noise interference from each device's signals. Then, construct a device state function based on the signal's mean drift, fluctuation rate, and periodic characteristic changes. Then, based on the local deformation heat map, use the device state function to calculate the health status of each device in real time. P1.3: If the health status of a device exceeds the preset warning threshold, the operation monitoring module will mark the device as sub-healthy and place the marked devices in the operation and maintenance observation list.

[0009] As a further solution of the present invention, the specific steps of the beat control module to dynamically adjust the production line beat and equipment operating speed in real time are as follows: S2.1: Collect the comprehensive status score of each worker at the current time point, count the number of workers in the current team, and then calculate the comprehensive status score of the group at the current time point based on the job information of different workers; S2.2: Based on the manufacturer's instructions and the current operating parameters of each group of devices, construct an adjustable rate window for each device. Simultaneously, calculate the load status of each device at the current time point. Based on the current group status comprehensive score and the load status of each device, establish the corresponding bio-mechanical coupling model; S2.3: Through the constructed bio-mechanical coupling model, the adjustment intensity of the worker status at the current time point on the production line tact is obtained in real time. The obtained adjustment intensity is used to dynamically adjust the current production line tact time. When the adjustment intensity is 0, it means no adjustment, and when the adjustment intensity is 1, the production line tact is reduced. S2.4: After the corresponding production line rhythm is adjusted, the actual operating speed of each group of equipment on the production line is automatically adjusted. Then, according to the preset update cycle, the comprehensive score of the worker group status, the equipment load status and the adjustment intensity are regularly recalculated, and the operating speed of each production line equipment is adjusted again based on the updated data.

[0010] As a further solution of the present invention, the specific calculation formula for the comprehensive status score in S2.1 is as follows: Where, Represents time The comprehensive status score of the group; N represents the number of workers in the current team; represents the job weight of the mth worker; represents the comprehensive status score of the mth worker; The specific calculation formula for the equipment load status described in S2.2 is as follows: Where, Represents time Equipment load status; Represents time The actual load of the equipment in group d; Represents the rated load capacity of group d equipment; The bio-mechanical coupling model described in S2.2 is specifically expressed as follows: Where, Representative time The coupling adjustment factor, that is, the adjustment intensity of the worker status on the production line beat; represents the synergistic sensitivity coefficient.

[0011] As a further solution of the present invention, the specific steps of the edge processing module to optimize the power consumption of the device cluster are as follows: S3.1: Collect information about each production line device and simulate the energy metabolism process of each device based on the current energy balance of each device group, input energy conversion rate, ambient energy received during the time period, unit energy consumption coefficient of the task, and the number of activations in the current cycle; S3.2: Based on the number of task types and load status of each device, the energy metabolism process simulation results of the corresponding device are used to obtain a real-time estimate of the energy demand of each device at the next point in time. Based on the current energy status of each device and the predicted energy demand, the corresponding energy budget upper limit is allocated to each group of devices. S3.3: Monitor each group of devices in real time and encode the continuous monitoring data into a pulse stream. When the value changes beyond a preset threshold, a pulse activation signal is generated and the actual power consumption of each device generated by the pulse activation signal is calculated. S3.4: If the actual power consumption of the device is higher than the current energy budget upper limit of the device, the built-in smart contract is used to apply for support from neighboring device nodes. If there is a neighboring device node that meets the conditions, the task migration mechanism is triggered through the smart contract to migrate the current device task to the neighboring device node for execution, record the resource scheduling status, and adjust the energy credit and resource quota of each device.

[0012] As a further solution of the present invention, the specific manifestation of the simulation of the energy metabolism process of each device in S3.1 is as follows: Where, Representative time The energy balance of the equipment; Representative time The energy balance of the equipment; represents the input energy conversion rate; Representative time Environmental energy received internally; Represents the unit energy consumption coefficient of the task; Representative point time The number of activations of the device.

[0013] As a further solution of the present invention, the specific steps of the simulation module for simulating the equipment wear process and the self-evolution of the equipment state in real time are as follows: S4.1: Use multi-field coupling simulation to perform physical field modeling of each device group at the microscale. Then, divide the device materials into discrete units based on the design specifications provided by the manufacturer and actual test results. S4.2: Assign a set of corresponding state variables, namely, wear levels, to each cell. The wear levels in each cell are updated in real time according to a preset update cycle. Based on the updated wear levels in each cell, the wear propagation behavior of each device at the material microscopic level is simulated. S4.3: Based on the material properties of the cell, calculate the wear impact of each neighboring cell on the central cell, and record the wear level and wear impact of each cell in each time period. When the cell wear level exceeds the preset failure state value, it indicates that the device location corresponding to the cell has lost its function; S4.4: Record the cell information of the grid device where the function is lost, and mark it as a potential fault area. At the same time, based on the cell location information and the wear and tear at different time periods, output the corresponding spatial coordinates and evolution path.

[0014] As a further solution of the present invention, the specific formula for the physical field modeling described in S4.1 is as follows: Where, Any point on the device In time The comprehensive field energy function; Represents any point in time on the device Thermal field distribution; Any point on the device In time The electromagnetic field strength; Any point of equipment In time stress field; as well as Represent the normalized weight factors of each physical field.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention collects the status of the worker group in real time and calculates a comprehensive score. It combines the job distribution and equipment operation parameters to establish a rate adjustment window for each device and obtains the beat adjustment strength according to the load status. After the beat is adjusted, the rate of each device is updated synchronously. Then the system simulates the energy metabolism process of the equipment, evaluates future energy demand, and allocates the energy budget according to the conversion rate and activation frequency. When the power consumption of the equipment exceeds the budget, it uses the smart contract to apply for support from neighboring nodes, triggers task migration and adjusts the energy credit. At the same time, based on multi-physics field simulation, the cellular automation method is used to simulate the evolution of equipment material wear, track the cell wear level and diffusion path, mark potential fault areas, and realize accurate maintenance prediction and resource scheduling optimization. It can reduce individual burdens, improve overall work efficiency and safety, effectively avoid overload calculation and invalid energy consumption, improve system stability and flexible scheduling capabilities, and warn of equipment failure locations in advance, extend equipment life, reduce unplanned downtime, and realize the closed-loop operation of "data-driven-intelligent control-dynamic scheduling", thereby improving the response speed and decision-making quality of the overall production system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0017] Figure 1 This is a system block diagram of a production and processing digital monitoring and management platform based on the Internet of Things proposed by the present invention. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] Reference Figure 1 A digital monitoring and management platform for production and processing based on the Internet of Things, including personnel perception module, operation monitoring module, energy consumption perception module, rhythm control module, edge processing module, simulation module, quality monitoring module, traceability module, risk scheduling module, block evidence module, early warning response module and management decision-making module.

[0020] The personnel sensing module collects workers' physiological parameters in real time and analyzes the working status of each worker.

[0021] Specifically, the heart rate, skin temperature, epidermal conductivity, eye movement frequency and activity frequency of each worker are collected in real time through uniformly distributed wearable devices. The collected physiological parameters are then standardized to generate a comprehensive fatigue score for the corresponding worker. The current physiological load status of each worker is judged in real time based on the obtained comprehensive fatigue score. According to the physiological rhythm, emotional rhythm and intellectual rhythm of the human body, a corresponding three-cycle biorhythm model is established. The rhythm data are converted into time domain signal superposition through the three-cycle biorhythm model to obtain the rhythm synthesis intensity of each worker at different time points. Based on the current physiological load status and rhythm synthesis intensity of each worker, the comprehensive score of the current state of each worker is obtained. If the comprehensive score of the worker's state is higher than the preset threshold, it is judged that the worker has entered a physiological trough, and the information of the worker in the physiological trough and the corresponding equipment number are recorded.

[0022] It should be further explained that the specific calculation formula for the comprehensive fatigue score is as follows: Where, Represents comprehensive fatigue score; HR represents current heart rate; Represents the historical average heart rate; represents the historical heart rate standard deviation; ST represents skin temperature; Represents the normal skin temperature baseline value; stands for temperature abnormality zone; EDA stands for real-time skin conductivity; represents the historical mean skin conductivity; represents the standard deviation of historical skin conductance; EF represents eye movement frequency; represents the normal peak of eye movement frequency; AF represents activity frequency; Represents the normal upper limit of activity frequency, which is derived from historical working condition records; as well as Respectively represent the weight coefficients of various physiological parameters, which are determined according to the type of work and job characteristics; The specific calculation formula of the three-cycle biological rhythm model is as follows: Where, Represents the rhythm synthesis intensity at the current time point; Represents the current time in days; represents the biological rhythm, which is 23 days; represents the emotional rhythm, which is 28 days; Represents the intellectual rhythm, which is 33 days.

[0023] The operation monitoring module uses the passive electromagnetic sensing array embedded in the device casing to identify the health status of the device in real time.

[0024] In addition, it should be further explained that the passive electromagnetic sensing array embedded in the device shell detects the phase difference between the incident wave and the echo, and calculates the local displacement of the reflection point based on the detected phase difference. The data returned by the patch array is then interpolated and spatially mapped to construct a local deformation heat map. The feature denoising algorithm is used to remove noise interference in the signals of each device body. Based on the signal mean drift, fluctuation rate and periodic characteristic changes, the device state function is constructed. Based on the local deformation heat map, the health status of each device is calculated in real time through the device state function. If the health status of the device exceeds the preset warning threshold, the operation monitoring module marks the device as sub-healthy and puts the marked devices into the operation and maintenance observation list.

[0025] The energy consumption perception module is used to collect environmental and energy consumption data from the production workshop in real time, and to segment energy consumption by process, equipment, and shift; the rhythm control module identifies the physiological rhythm trends of the group based on the working status of workers and the health status of equipment, and dynamically adjusts the production line rhythm and equipment operating rate in real time.

[0026] Specifically, the comprehensive status score of each worker at the current time point is collected, and the number of workers in the current team is counted. Then, based on the job information of different workers, the comprehensive status score of the group at the current time point is calculated. According to the manufacturer's instructions and the current operating parameters of each group of equipment, the adjustable rate window of each device is constructed, and the load status of each device at the current time point is calculated. Based on the current comprehensive status score of the group and the load status of each device, a corresponding bio-mechanical coupling model is established. Through the constructed bio-mechanical coupling model, the regulation intensity of the worker status at the current time point on the production line beat is obtained in real time, and the obtained regulation intensity is used to dynamically adjust the current production line beat time. When the regulation intensity is 0, it means no adjustment. When the regulation intensity is 1, the production line beat is reduced. After the corresponding production line beat is adjusted, the actual operating rate of each group of equipment in the production line is automatically adjusted. Then, according to the preset update cycle, the comprehensive status score of the worker group, the equipment load status and the regulation intensity are recalculated regularly, and the operating rate of each production line equipment is adjusted again based on the updated data.

[0027] It should be further explained that the specific calculation formula for the comprehensive status score is as follows: Where, Represents time The comprehensive status score of the group; N represents the number of workers in the current team; represents the job weight of the mth worker; represents the comprehensive status score of the mth worker; The specific calculation formula for the equipment load status is as follows: Where, Represents time Equipment load status; Represents time The actual load of the equipment in group d; Represents the rated load capacity of group d equipment; The specific expression of the bio-mechanical coupling model is as follows: Where, Representative time The coupling adjustment factor, that is, the adjustment intensity of the worker status on the production line beat; represents the synergistic sensitivity coefficient.

[0028] The edge processing module is used to manage the energy budget of the production workshop and allocate computing resources among nodes to optimize the power consumption of the equipment cluster.

[0029] Specifically, the system collects information about each production line's equipment and simulates the energy metabolism process of each device based on the current energy balance of each device group, the input energy conversion rate, the ambient energy received during the time period, the unit energy consumption coefficient of the task, and the number of activations in the current cycle. Based on the number of task types and load status of each device, the system uses the corresponding device energy metabolism simulation results to obtain a real-time estimate of the energy demand of each device at the next point in time. Based on the current energy status of each device and the predicted energy demand, the system allocates a corresponding energy budget upper limit to each device group. The system monitors each device group in real time and encodes the continuous monitoring data into a pulse stream. When the value change exceeds a preset threshold, a pulse activation signal is generated and the actual power consumption of each device generating a pulse activation signal is calculated. If the actual power consumption of a device exceeds the current energy budget upper limit, the system requests support from neighboring device nodes through the built-in smart contract. If a neighboring device node meets the conditions, the smart contract triggers the task migration mechanism to migrate the current device task to the neighboring device node for execution. The system also records the resource scheduling status and adjusts the energy credit and resource quota of each device.

[0030] It should be further explained that the specific forms of simulating the energy metabolism process of each device are as follows: Where, Representative time The energy balance of the equipment; Representative time The energy balance of the equipment; represents the input energy conversion rate; Representative time Environmental energy received internally; Represents the unit energy consumption coefficient of the task; Representative point time The number of activations of the device.

[0031] The simulation module is used to build a device simulation model and simulate the device wear process and the self-evolution of the device status in real time.

[0032] Specifically, multi-field coupling simulation is used to perform physical field modeling on each group of equipment at the micro scale. Then, according to the design instructions provided by the manufacturer and the actual test results, the equipment materials are divided into discrete cells, and a set of corresponding state variables, namely wear levels, are assigned to each cell. At the same time, the wear level in each cell is updated in real time according to the preset update cycle. According to the real-time updated wear level of each cell, the wear extension and propagation behavior of each device at the micro level of the material is simulated. According to the material properties of the cell, the wear impact of each neighboring cell on the central cell is calculated, and the wear level and wear impact of each unit in each time period are recorded. When the cell wear level is higher than the preset failure state value, it means that the function of the device position corresponding to the cell is lost. The cell information of the device position with lost function is recorded and marked as a potential fault area. At the same time, based on the cell position information and the wear impact in different time periods, the corresponding spatial coordinates and evolution path are output.

[0033] It should be further explained that the specific formula for physical field modeling is as follows: Where, Any point on the device In time The comprehensive field energy function; Represents any point in time on the device Thermal field distribution; Any point on the device In time The electromagnetic field strength; Any point of equipment In time stress field; as well as Represent the normalized weight factors of each physical field.

[0034] The quality monitoring module is used to collect the quality parameters of each device during the processing in real time, analyze the quality of the processed products, and generate a process quality report for the products; the traceability module is used to establish a quality data chain and a carbon emission data chain, and based on the established dual-chain structure, perform real-time cross-chain verification; the risk scheduling module is used to collect threat intelligence from different sources, predict the risk of chain breaks, and reconfigure alternative supply paths and production plans; the block evidence module is used to encrypt and slice each quality parameter and upload it to the quality data chain for evidence.

[0035] The early warning response module generates equipment pre-maintenance plans and operation and maintenance work orders based on equipment simulation data, quality fluctuation records, operator physiological status and energy consumption, and pushes early warning information in real time; the management decision module provides decision-making recommendations and visualizes the collected data and analysis results through display screens and management platforms.

Claims

1. A digital monitoring and management platform for production and processing based on the Internet of Things, characterized by: It includes personnel perception module, operation monitoring module, energy consumption perception module, rhythm control module, edge processing module, simulation module, quality monitoring module, traceability module, risk scheduling module, block evidence storage module, early warning response module and management decision module; The personnel sensing module collects the physiological parameters of workers in real time and analyzes the working status of each worker; The operation monitoring module identifies the health status of the device in real time through the passive electromagnetic sensing array embedded in the device housing; The energy consumption sensing module is used to collect the environment and energy consumption data of the production workshop in real time, and to segment the energy consumption by process, equipment and shift; The beat control module identifies the physiological rhythm trend of the group according to the working status of the workers and the health status of the equipment, and dynamically adjusts the production line beat and equipment operating speed in real time; The edge processing module is used to manage the energy budget of the production workshop and allocate computing resources among nodes to optimize the power consumption of the equipment cluster; The simulation module is used to build a device simulation model and simulate the device wear process and device state self-evolution in real time; The quality monitoring module is used to collect the quality parameters of each device in the processing process in real time, analyze the quality of the processed products, and generate a process quality report of the products; The traceability module is used to establish a quality data chain and a carbon emission data chain, and based on the established dual-chain structure, conduct real-time cross-chain verification; The risk scheduling module is used to collect threat intelligence from different sources, predict supply chain disruption risks, and reconfigure alternative supply paths and production plans; The block evidence module is used to encrypt and slice each quality parameter and upload it to the quality data chain for evidence storage; The early warning response module generates equipment pre-maintenance plans and operation and maintenance work orders based on equipment simulation data, quality fluctuation records, operator physiological status and energy consumption, and pushes early warning information in real time; The management decision module provides decision suggestions and visualizes the collected data and analysis results through the display screen and management platform.

2. The digital monitoring and management platform for production and processing based on the Internet of Things according to claim 1 is characterized in that: The specific steps of the personnel perception module to analyze the working status of each worker are as follows: S1.1: Use uniformly distributed wearable devices to collect each worker's heart rate, skin temperature, epidermal conductivity, eye movement rate, and activity frequency in real time. These collected physiological parameters are then standardized to generate a comprehensive fatigue score for each worker. Based on this comprehensive fatigue score, each worker's current physiological load status is determined in real time. S1.2: Based on the human body's physiological rhythms, emotional rhythms, and intellectual rhythms, a corresponding three-cycle biorhythm model is established. The three-cycle biorhythm model is used to convert the rhythm data into time-domain signal superposition to obtain the rhythm synthesis intensity of each worker at different time points. S1.3: Based on the current physiological load status and rhythm synthesis intensity of each worker, obtain the comprehensive score of each worker's current status. If the worker's comprehensive status score is higher than the preset threshold, it is judged that the worker has entered the physiological trough, and the information of the worker in the physiological trough and the corresponding equipment number are recorded.

3. The digital monitoring and management platform for production and processing based on the Internet of Things according to claim 2 is characterized in that: The specific calculation formula for the comprehensive fatigue score mentioned in S1.1 is as follows: Where, represents the comprehensive fatigue score; HR stands for current heart rate; Represents the historical average heart rate; represents the historical heart rate standard deviation; ST represents skin temperature; Represents the normal skin temperature baseline value; stands for temperature abnormality zone; EDA stands for real-time skin conductivity; represents the historical mean skin conductivity; represents the standard deviation of historical skin conductance; EF represents eye movement frequency; represents the normal peak of eye movement frequency; AF represents activity frequency; Represents the normal upper limit of activity frequency, which is derived from historical working condition records; as well as Respectively represent the weight coefficients of various physiological parameters, which are determined according to the type of work and job characteristics; The specific calculation formula of the three-cycle biorhythm model described in S1.2 is as follows: Where, Represents the rhythm synthesis intensity at the current time point; Represents the current time in days; represents the biological rhythm, which is 23 days; represents the emotional rhythm, which is 28 days; Represents the intellectual rhythm, which is 33 days.

4. The digital monitoring and management platform for production and processing based on the Internet of Things according to claim 2 is characterized in that: The specific steps of the beat control module to dynamically adjust the production line beat and equipment operating speed in real time are as follows: S2.1: Collect the comprehensive status score of each worker at the current time point, count the number of workers in the current team, and then calculate the comprehensive status score of the group at the current time point based on the job information of different workers; S2.2: Based on the manufacturer's instructions and the current operating parameters of each group of devices, construct an adjustable rate window for each device. Simultaneously, calculate the load status of each device at the current time point. Based on the current group status comprehensive score and the load status of each device, establish the corresponding bio-mechanical coupling model; S2.3: Through the constructed bio-mechanical coupling model, the adjustment intensity of the worker status at the current time point on the production line tact is obtained in real time. The obtained adjustment intensity is used to dynamically adjust the current production line tact time. When the adjustment intensity is 0, it means no adjustment, and when the adjustment intensity is 1, the production line tact is reduced. S2.4: After the corresponding production line rhythm is adjusted, the actual operating speed of each group of equipment on the production line is automatically adjusted. Then, according to the preset update cycle, the comprehensive score of the worker group status, the equipment load status and the adjustment intensity are regularly recalculated, and the operating speed of each production line equipment is adjusted again based on the updated data.

5. The digital monitoring and management platform for production and processing based on the Internet of Things according to claim 1 is characterized in that: The specific steps of the edge processing module to optimize the power consumption of the device cluster are as follows: S3.1: Collect information about each production line device and simulate the energy metabolism process of each device based on the current energy balance of each device group, input energy conversion rate, ambient energy received during the time period, unit energy consumption coefficient of the task, and the number of activations in the current cycle; S3.2: Based on the number of task types and load status of each device, the energy metabolism process simulation results of the corresponding device are used to obtain a real-time estimate of the energy demand of each device at the next point in time. Based on the current energy status of each device and the predicted energy demand, the corresponding energy budget upper limit is allocated to each group of devices. S3.3: Monitor each group of devices in real time and encode the continuous monitoring data into a pulse stream. When the value changes beyond a preset threshold, a pulse activation signal is generated and the actual power consumption of each device generated by the pulse activation signal is calculated. S3.4: If the actual power consumption of the device is higher than the current energy budget upper limit of the device, the built-in smart contract is used to apply for support from neighboring device nodes. If there is a neighboring device node that meets the conditions, the task migration mechanism is triggered through the smart contract to migrate the current device task to the neighboring device node for execution, record the resource scheduling status, and adjust the energy credit and resource quota of each device.

6. The digital monitoring and management platform for production and processing based on the Internet of Things according to claim 5 is characterized in that: The specific forms of simulating the energy metabolism process of each device described in S3.1 are as follows: Where, Representative time The energy balance of the equipment; Representative time The energy balance of the equipment; represents the input energy conversion rate; Representative time Environmental energy received internally; Represents the unit energy consumption coefficient of the task; Representative point time The number of activations of the device.

7. The digital monitoring and management platform for production and processing based on the Internet of Things according to claim 1 is characterized in that: The simulation module simulates the equipment wear process in real time, and the specific steps of the equipment state self-evolution are as follows: S4.1: Use multi-field coupling simulation to perform physical field modeling of each device group at the microscale. Then, divide the device materials into discrete units based on the design specifications provided by the manufacturer and actual test results. S4.2: Assign a set of corresponding state variables, namely, wear levels, to each cell. The wear levels in each cell are updated in real time according to a preset update cycle. Based on the updated wear levels in each cell, the wear propagation behavior of each device at the material microscopic level is simulated. S4.3: Based on the material properties of the cell, calculate the wear impact of each neighboring cell on the central cell, and record the wear level and wear impact of each cell in each time period. When the cell wear level exceeds the preset failure state value, it indicates that the device location corresponding to the cell has lost its function; S4.4: Record the cell information of the grid device where the function is lost, and mark it as a potential fault area. At the same time, based on the cell location information and the wear and tear at different time periods, output the corresponding spatial coordinates and evolution path.

8. The digital monitoring and management platform for production and processing based on the Internet of Things according to claim 7 is characterized in that: The specific formula for physical field modeling described in S4.1 is as follows: Where, Any point on the device In time The comprehensive field energy function; Represents any point in time on the device Thermal field distribution; Any point on the device In time The electromagnetic field strength; Any point of equipment In time stress field; as well as Represent the normalized weight factors of each physical field.

Images