Production monitoring method, system and equipment based on industrial internet of things, and medium

Abstract

The invention discloses a production monitoring method, system, equipment and medium based on industrial Internet of Things, relates to the technical field of industrial Internet of Things, is applied to an industrial Internet of Things system comprising a management platform, a sensing network platform and an object platform, and comprises the following steps: obtaining historical work data and historical maintenance data of production equipment; establishing a mapping relationship between the historical working data and the maintenance data information to obtain a historical data set; an equipment health model is established, and a historical data set is used for training; acquiring real-time working data of the production equipment and inputting the real-time working data into the trained health model to obtain an equipment health index; when the health index is smaller than a preset value, an alarm mechanism is triggered, and a production state report containing fault positioning and maintenance suggestions is generated. According to the invention, real-time monitoring and fault early warning of the industrial equipment can be realized, and the production efficiency and the equipment reliability are improved.

Description

Technical Field

[0001] This application relates to the field of industrial Internet of Things (IoT) technology, and in particular to a production monitoring method, system, device and medium based on industrial IoT. Background Technology

[0002] With the increasing level of industrial automation and informatization, production monitoring systems are playing an increasingly important role in production management. Traditional production monitoring systems typically rely on independent sensors and control equipment, making decisions based on manual data collection and analysis. This approach suffers from problems such as untimely data collection and inaccurate analysis, failing to effectively achieve real-time monitoring and optimization of the production process.

[0003] Therefore, using IoT technology to build a more intelligent, real-time, and accurate production monitoring system has become a development trend.

[0004] However, existing technologies still have some problems and shortcomings: First, most existing industrial IoT systems lack precise assessment mechanisms for equipment health status, making it impossible to accurately predict potential equipment failures; second, existing systems often suffer from insufficient timeliness in data acquisition and processing, making it difficult to achieve real-time monitoring of production equipment status; third, existing systems typically lack effective fusion and analysis of historical and real-time data, failing to fully utilize historical experience to guide current production; fourth, existing alarm mechanisms are mostly based on simple threshold judgments, lacking the ability to accurately locate the cause of failure and generate maintenance suggestions. These problems limit the application effectiveness of existing industrial IoT systems in production monitoring, making it difficult to meet the needs of modern manufacturing for refined management and predictive maintenance of production processes. Summary of the Invention

[0005] To address the aforementioned issues, this application provides a production monitoring method, system, device, and medium based on the Industrial Internet of Things (IIoT).

[0006] On the one hand, this application provides a production monitoring method based on the Industrial Internet of Things, which adopts the following technical solution: A production monitoring method based on the Industrial Internet of Things (IIoT) is applied to an IIoT system, which includes a management platform, a sensor network platform, and an object platform connected in sequence. The method is executed by the management platform and includes: Obtain historical operating data and historical maintenance data of production equipment; Based on the historical work data and the historical maintenance data, a mapping relationship between the historical work data and maintenance data information is established to obtain a historical dataset. Establish an equipment health model, and train the equipment health model based on the historical dataset to obtain the trained equipment health model; Acquire real-time operating data of production equipment, input the real-time operating data into the trained health model, and obtain the equipment health index; When the health index is lower than the preset value, an alarm mechanism is triggered, and a production status report containing fault location and maintenance suggestions is generated.

[0007] Optionally, acquiring real-time operating data of the production equipment includes: The real-time parameters of the production equipment operation are obtained, including temperature data, current data, and voltage data.

[0008] Optionally, the device health model satisfies the formula:

[0009] HI: Equipment Health Index; : The root mean square value of the voltage; Maximum voltage value; Ta: The actual temperature of the equipment; Reference temperature; ΔTc: Critical temperature difference; THD(I): Total Harmonic Distortion of Current; Rated current; α, β, γ: Weighting factors used to adjust the importance of each item in the overall health index.

[0010] Optional, of which,

[0011] v(t) is the voltage value at time t; T is the period of the signal. For a periodic signal, the period T is the time of a complete cycle.

[0012] It is the fundamental amplitude of the current; I2, I3, ..., I n It represents the amplitude of the 2nd, 3rd, ..., nth harmonics in the current; n is the highest order of the harmonic.

[0013] Optionally, establishing a device health model based on the real-time working data includes: The real-time working data is synchronously transmitted to edge computing nodes using a time-sensitive network for preprocessing, generating a fused data packet containing time-domain and frequency-domain features.

[0014] Optionally, the preprocessing of the parameters to obtain fused data containing time-domain and frequency-domain features includes: The real-time working data is sequentially processed by data cleaning, noise reduction, integration, and transformation.

[0015] Optionally, when the health index is less than a preset value, an alarm mechanism is triggered, and a production status report containing fault location and maintenance suggestions is generated, including: when the health index is lower than the preset value, the system will automatically detect and determine whether to trigger an alarm based on the triggering conditions; The triggering conditions include: The health index has dropped beyond the set threshold; Abnormal fluctuations in the actual temperature of the equipment; The system failed to return to normal within the scheduled testing period.

[0016] This application also provides a production monitoring system based on the Industrial Internet of Things, which adopts the following technical solution: A production monitoring system based on the Industrial Internet of Things (IIoT) includes a management platform, a sensor network platform, and an object platform that are sequentially connected in communication. The management platform includes: The information acquisition module is used to acquire historical operating data and historical maintenance data of production equipment; The data fusion module is used to establish a mapping relationship between historical working data and maintenance data information to obtain a historical dataset based on the historical working data and the historical maintenance data. The model training module is used to build a device health model, and to train the device health model based on the historical dataset to obtain the trained device health model. The health assessment module is used to acquire real-time operating data of production equipment, input the real-time operating data into the trained health model, and obtain the equipment health index. The alarm and reporting module is used to trigger an alarm mechanism and generate a production status report containing fault location and maintenance suggestions when the health index is less than a preset value.

[0017] This application also provides a computer device that adopts the following technical solution: A computer device, comprising one or more processors and memory; One or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the method.

[0018] This application also provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and execute the method.

[0019] In summary, this application includes at least one of the following beneficial technical effects: This health model is built based on parameters such as the root mean square value of voltage, temperature difference, and current harmonic distortion. Data is synchronously transmitted to edge computing nodes via a time-sensitive network for preprocessing. By employing IoT technology to construct a production monitoring system, real-time monitoring and health assessment of production equipment status are achieved, overcoming the problems of untimely data collection and inaccurate analysis in traditional monitoring systems. By establishing an equipment health model and training it using historical data, the system can accurately assess the health status of equipment and provide early warnings of potential faults. The system uses a time-sensitive network for data transmission, ensuring the real-time nature and synchronization of data. By setting multi-dimensional trigger conditions, the accuracy and reliability of the alarm mechanism are improved. The overall solution realizes intelligent monitoring and optimization of the production process, significantly improving production efficiency and equipment reliability.

[0020] By using data-driven, multi-parameter fusion, and scientific weighting methods, the complex physical state of equipment is transformed into an intuitive and quantifiable health index (HI). This not only greatly simplifies the complexity of equipment status monitoring, but more importantly, it provides powerful early fault warning capabilities and predictive maintenance decision support. The ultimate goal is to maximize equipment operational reliability, minimize maintenance costs, and optimize production efficiency. Attached Figure Description

[0021] Figure 1 This is a flowchart of a production monitoring method based on the Industrial Internet of Things (IIoT) according to an embodiment of this application; Figure 2 This is a structural block diagram of a production monitoring system based on the Industrial Internet of Things (IIoT) according to an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0023] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0024] In this invention, unless otherwise explicitly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection or an electrical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0025] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the meaning of "and / or" throughout the text includes three parallel solutions; for example, "A and / or B" includes solution A, solution B, or a solution where both A and B are satisfied simultaneously. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0026] Example 1 This application discloses a production monitoring method based on the Industrial Internet of Things (IIoT), applied to an IIoT system, with reference to... Figure 2 The industrial IoT system includes a management platform, a sensor network platform, and an object platform that are connected in sequence, and the method is executed by the management platform.

[0027] The Industrial Internet of Things (IIoT) generally refers to a technological system that continuously integrates various data acquisition and control sensors or controllers with sensing and monitoring capabilities, along with technologies such as mobile communication and intelligent analytics, into all aspects of the industrial production process. The goal of the IIoT is to significantly improve manufacturing efficiency, enhance product quality, reduce product costs and resource consumption, and ultimately elevate traditional industries to a new stage of intelligent manufacturing.

[0028] The management platform is a core component of industrial automation systems. It is responsible for receiving data from various sensors and devices, performing necessary calculations and logical judgments, and sending instructions to actuators to control system operation. In an Industrial Internet of Things (IIoT) environment, the management platform typically integrates advanced data processing capabilities and network communication functions, enabling it to exchange data efficiently with other systems.

[0029] The object platform includes a cluster of production equipment deployed in the workshop, which integrates heterogeneous sensing units, including a combination of RFID tags, triaxial MEMS accelerometers, fiber optic temperature sensors, and Rogowski coil current transformers.

[0030] The sensor network platform, consisting of a data transmission network constructed by TSN switches, connects edge computing nodes to the object platform. The edge computing nodes are configured to perform preprocessing tasks such as vibration signal RMS value calculation, temperature threshold comparison, and current harmonic FFT analysis.

[0031] Reference Figure 1 A production monitoring method based on the Industrial Internet of Things (IIoT) specifically includes the following steps: S1. Obtain historical operating data and historical maintenance data of production equipment; In this embodiment, the management platform obtains historical operating data and historical maintenance data of the production equipment from the object platform through a sensor network platform. Historical operating data includes various parameters recorded during equipment operation, such as temperature, voltage, current, vibration, and noise. Historical maintenance data includes equipment maintenance records, fault types, fault causes, maintenance plans, and maintenance results. This data is typically stored in the database of the industrial IoT system, and the management platform can directly access and retrieve this data through a data interface.

[0032] S2. Based on historical work data and historical maintenance data, establish a mapping relationship between historical work data and maintenance data information to obtain historical datasets; The management platform performs correlation analysis on acquired historical operational and maintenance data to establish a mapping relationship between the two. Specifically, the platform first aligns the historical operational and maintenance data over time to ensure precise matching between the two types of data in the temporal dimension. Then, the platform analyzes the operational data characteristics prior to equipment failure to identify abnormal parameter patterns that may have led to the failure. In this way, the platform establishes a correlation between equipment operating status and failure type, forming a comprehensive historical dataset containing information such as operating parameters, failure type, and maintenance plans.

[0033] S3. Establish an equipment health model, train the equipment health model based on historical datasets, and obtain the trained equipment health model. The management platform builds an equipment health model based on historical datasets. This model uses mathematical formulas to express the equipment health status, comprehensively considering key parameters such as voltage, temperature, and current. The mathematical expression of the model is:

[0034] Wherein, HI represents the equipment health index; RMS(v) represents the root mean square value of voltage; Vmax represents the maximum voltage value; Ta represents the actual temperature of the equipment; Tb represents the reference temperature; ΔTc represents the critical temperature difference, which is the temperature threshold for safe operation or optimal working condition; THD(I) represents the total harmonic distortion of current, which is a measure of waveform distortion; Ir represents the rated current, which is the maximum current that the equipment is designed to withstand; α, β, and γ are weighting factors used to adjust the importance of each item in the overall health index.

[0035] In this embodiment, the optimal values ​​of the weighting factors were determined through analysis of historical data: α=0.4, β=0.35, and γ=0.25. These weighting values ​​reflect the relative importance of voltage, temperature, and current to the health status of the equipment.

[0036] This system integrates complex, multi-dimensional physical signals (voltage, temperature, current) into a single, quantifiable Health Index (HI). It eliminates the tediousness of manually monitoring multiple parameters individually, providing a clear and intuitive standard for measuring the overall health of equipment. Managers can quickly assess equipment status using a single numerical value.

[0037] In this formula, the root mean square value (RMS) of the voltage (V) is calculated as follows:

[0038] Where v(t) is the voltage value at time t; T is the period of the signal. For a periodic signal, the period T is the time of a complete cycle.

[0039] The formula for calculating the total harmonic distortion (THD) of current is:

[0040] in, These are the fundamental amplitudes of the current; I2, I3, ..., I n It represents the amplitude of the 2nd, 3rd, ..., nth harmonics in the current; n is the highest order of the harmonics. In this embodiment, n is taken as 10, that is, the 10th harmonic is taken into account.

[0041] The management platform uses historical datasets to train the device health model, optimizing the values ​​of model parameters α, β, and γ through machine learning algorithms to ensure the model accurately reflects the device's health status. During training, the management platform divides the historical dataset into training and validation sets. The training set is used to adjust model parameters, and the validation set is used to evaluate model performance, ensuring the model has good generalization ability.

[0042] This application transforms the complex physical state of equipment into an intuitive and quantifiable Health Index (HI) through data-driven, multi-parameter fusion, and scientific weighting. This not only greatly simplifies the complexity of equipment condition monitoring but, more importantly, provides powerful early fault warning capabilities and predictive maintenance decision support. The ultimate goal is to maximize equipment operational reliability, minimize maintenance costs, and optimize production efficiency. Furthermore, the model integrates key indicators reflecting equipment performance degradation. Subtle changes in indicators such as voltage stability, abnormal thermal conditions, and current quality deterioration (which may not yet reach independent alarm thresholds) are captured by the model and reflected in the trend of HI value changes, providing earlier and more sensitive fault warning signals than single-parameter threshold alarms.

[0043] S4. Obtain real-time operating data of production equipment, input the real-time operating data into the trained health model, and obtain the equipment health index. The management platform acquires real-time operating data from production equipment, including parameters such as temperature, current, and voltage, through a sensor network platform. This data is collected by various sensors installed on the equipment and transmitted to the management platform via the Industrial Internet of Things (IIoT).

[0044] The management platform uses Time-Sensitive Networking (TSN) to synchronously transmit real-time working data to edge computing nodes for preprocessing, generating fused data packets containing both time-domain and frequency-domain features. During preprocessing, the management platform sequentially performs data cleaning, denoising, integration, and transformation on the real-time working data. Data cleaning primarily removes outliers and missing values; denoising reduces random noise in the data through filtering algorithms; integration combines data from different sources into a unified data structure; and transformation converts the raw data into a more suitable form for analysis, such as performing Fourier transforms to extract frequency-domain features.

[0045] Specifically, data cleaning uses the 3σ principle to identify and process outliers, and linear interpolation is used to fill in missing values; denoising uses wavelet transform denoising algorithm to effectively preserve signal features while removing high-frequency noise; data integration uses timestamp alignment to ensure time consistency of data from different sensors; and transformation processing uses Fast Fourier Transform (FFT) to extract frequency domain features while preserving time domain features, forming a time-frequency domain fusion data packet.

[0046] The management platform inputs preprocessed real-time operational data into the trained device health model to calculate the device's health index. The health index is a value between 0 and 1; the closer the value is to 1, the better the device's health, and the closer the value is to 0, the worse the device's health.

[0047] In one embodiment, temperature data is acquired via thermocouples or infrared temperature sensors, with a measurement range of -50°C to 500°C and an accuracy of ±0.5°C; current data is acquired via Hall effect current sensors, with a measurement range of 0 to 100A and an accuracy of ±0.1A; and voltage data is acquired via voltage sensors, with a measurement range of 0 to 1000V and an accuracy of ±0.5V. These sensors acquire data at a frequency of 10 times per second to ensure that rapid changes in the device's state can be captured.

[0048] S5. When the health index is lower than the preset value, an alarm mechanism is triggered, and a production status report containing fault location and maintenance suggestions is generated.

[0049] Optionally, when the health index is less than a preset value, an alarm mechanism is triggered, and a production status report containing fault location and maintenance suggestions is generated, including: When the health index is lower than the preset value, the system will automatically detect it and determine whether to trigger an alarm based on the triggering conditions. The triggering conditions include: The health index has dropped beyond the set threshold; Abnormal fluctuations in the actual temperature of the equipment; The system failed to return to normal within the scheduled testing period.

[0050] The management platform continuously monitors the health index of the equipment. When the health index falls below a preset value, the system will automatically detect it and determine whether to trigger an alarm based on the triggering conditions. Triggering conditions include: the health index dropping beyond a set threshold; abnormal fluctuations in the actual temperature of the equipment; and the system failing to return to a normal state within a predetermined detection cycle.

[0051] In this embodiment, the preset health index threshold is 0.75. When the health index is below 0.75, the system starts to monitor the device status; when the health index is below 0.6, the system triggers a level 1 warning; when the health index is below 0.4, the system triggers a level 2 warning and suggests arranging maintenance; when the health index is below 0.2, the system triggers an emergency alarm and suggests immediately shutting down the device for maintenance.

[0052] The criteria for determining if the health index drops below the set threshold are: the health index drops by more than 0.15 within 10 consecutive minutes; the criteria for determining if the actual equipment temperature fluctuates abnormally are: the temperature rises by more than 20°C within 5 minutes or exceeds 85% of the upper limit of the normal operating temperature of the equipment; the criteria for determining if the system fails to return to normal status within the predetermined detection cycle are: the health index remains below 0.6 for 30 consecutive minutes and shows no upward trend.

[0053] When the triggering conditions are met, the management platform will activate the alarm mechanism, notifying relevant personnel through audible and visual alarms, SMS notifications, email alerts, and other means. Simultaneously, the management platform will analyze possible causes of the fault based on the equipment's real-time operating data and historical fault data, locate the fault position, and generate a production status report containing fault location and maintenance recommendations.

[0054] The report includes: basic equipment information (equipment ID, model, location, etc.); time and severity of failure; type and possible causes of failure; location of failure; recommended maintenance plan; estimated maintenance time and cost; and suggested measures to prevent similar failures. This information helps maintenance personnel respond quickly and resolve problems, reducing equipment downtime and improving production efficiency.

[0055] Example 2 Reference Figure 2 A production monitoring system based on the Industrial Internet of Things (IIoT) includes a management platform, a sensor network platform, and an object platform that are sequentially connected in communication. The management platform includes: The information acquisition module is used to acquire historical operating data and historical maintenance data of production equipment; The information acquisition module obtains historical operating and maintenance data of the production equipment from the object platform through the sensor network platform. Historical operating data includes various parameters recorded during equipment operation, such as temperature, voltage, current, vibration, and noise. Historical maintenance data includes equipment maintenance records, fault types, fault causes, maintenance plans, and maintenance results. This data is typically stored in the database of the industrial IoT system, and the information acquisition module can directly access and retrieve this data through a data interface.

[0056] The data fusion module is used to establish a mapping relationship between historical work data and maintenance data to obtain historical datasets based on historical work data and historical maintenance data. The data fusion module performs correlation analysis on the acquired historical operating data and historical maintenance data to establish a mapping relationship between the two. Specifically, the data fusion module first aligns the historical operating data and historical maintenance data in terms of time, ensuring that the two types of data can be accurately matched in the time dimension. Then, the data fusion module analyzes the characteristics of the operating data before the equipment failure occurred, identifying abnormal parameter patterns that may have led to the failure. In this way, the data fusion module establishes a correlation between the equipment's operating status and the failure type, forming a comprehensive historical dataset containing information such as operating parameters, failure type, and maintenance plan.

[0057] The model training module is used to build a device health model. It trains the device health model based on historical datasets to obtain the trained device health model. The model training module builds a device health model based on historical datasets. This model uses mathematical formulas to express the device health status, comprehensively considering key parameters such as voltage, temperature, and current.

[0058] The health assessment module is used to acquire real-time operating data of production equipment, input the real-time operating data into the trained health model, and obtain the equipment health index. The health assessment module acquires real-time operating data from production equipment via a sensor network platform, including parameters such as temperature, current, and voltage. This data is collected by various sensors installed on the equipment and transmitted to the management platform via the Industrial Internet of Things (IIoT).

[0059] The health assessment module uses Time-Sensitive Networking (TSN) to synchronously transmit real-time working data to edge computing nodes for preprocessing, generating fused data packets containing both time-domain and frequency-domain features. During preprocessing, the health assessment module sequentially performs data cleaning, denoising, integration, and transformation on the real-time working data. Data cleaning primarily removes outliers and missing values; denoising reduces random noise in the data through filtering algorithms; integration combines data from different sources into a unified data structure; and transformation converts the raw data into a more suitable form for analysis, such as performing Fourier transforms to extract frequency-domain features.

[0060] The health assessment module inputs preprocessed real-time working data into the trained device health model to calculate the device's health index. The health index is a value between 0 and 1; the closer the value is to 1, the better the device's health status, and the closer the value is to 0, the worse the device's health status.

[0061] The alarm and reporting module is used to trigger an alarm mechanism and generate a production status report containing fault location and maintenance suggestions when the health index is lower than the preset value.

[0062] The alarm and reporting module continuously monitors the equipment's health index. When the health index falls below a preset value, the system automatically detects it and determines whether to trigger an alarm based on the triggering conditions. Triggering conditions include: the health index dropping beyond a set threshold; abnormal fluctuations in the actual equipment temperature; and the system failing to return to normal within a predetermined detection cycle.

[0063] When the triggering conditions are met, the alarm and reporting module will activate the alarm mechanism, notifying relevant personnel through audible and visual alarms, SMS notifications, email alerts, etc. Simultaneously, the alarm and reporting module will analyze possible causes of the fault based on the equipment's real-time operating data and historical fault data, locate the fault location, and generate a production status report containing fault location and maintenance suggestions.

[0064] The report includes: basic equipment information (equipment ID, model, location, etc.); time and severity of failure; type and possible causes of failure; location of failure; recommended maintenance plan; estimated maintenance time and cost; and suggested measures to prevent similar failures. This information helps maintenance personnel respond quickly and resolve problems, reducing equipment downtime and improving production efficiency.

[0065] Example 3 This application also discloses a computer device, including one or more processors and a memory; One or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the methods described above.

[0066] Example 4 This application also discloses a computer-readable storage medium storing a computer program that can be loaded by a processor and execute the method.

[0067] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0068] In the above embodiments of this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0069] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0070] The units described as separate components may or may not be physically separate. 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0071] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0072] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a non-volatile storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0073] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A production monitoring method based on the Industrial Internet of Things, characterized in that, Applied to an industrial Internet of Things (IIoT) system, the IIoT system includes a management platform, a sensor network platform, and an object platform that are sequentially connected in communication. The method is executed by the management platform and includes: Obtain historical operating data and historical maintenance data of production equipment; Based on the historical work data and the historical maintenance data, a mapping relationship between the historical work data and maintenance data information is established to obtain a historical dataset. Establish an equipment health model, and train the equipment health model based on the historical dataset to obtain the trained equipment health model; Acquire real-time operating data of production equipment, input the real-time operating data into the trained health model, and obtain the equipment health index; When the health index is lower than the preset value, an alarm mechanism is triggered, and a production status report containing fault location and maintenance suggestions is generated.

2. The production monitoring method according to claim 1, characterized in that, The acquisition of real-time operating data of the production equipment includes: The real-time parameters of the production equipment operation are obtained, including temperature data, current data, and voltage data.

3. The production monitoring method according to claim 2, characterized in that, The equipment health model satisfies the following formula: HI: Equipment Health Index; : The root mean square value of the voltage; Maximum voltage value; Ta: The actual temperature of the equipment; Reference temperature; ΔTc: Critical temperature difference; THD(I): Total Harmonic Distortion of Current; Rated current; α, β, γ: Weighting factors used to adjust the importance of each item in the overall health index.

4. The production monitoring method according to claim 3, characterized in that, in, v(t) is the voltage value at time t; T is the period of the signal. For a periodic signal, the period T is the time of a complete cycle. It is the fundamental amplitude of the current; I2, I3, ..., I n It represents the amplitude of the 2nd, 3rd, ..., nth harmonics in the current; n is the highest order of the harmonic.

5. The production monitoring method according to claim 1, characterized in that, The step of training the device health model based on the historical dataset to obtain the trained device health model includes: The real-time working data is synchronously transmitted to edge computing nodes using a time-sensitive network for preprocessing, generating a fused data packet containing time-domain and frequency-domain features.

6. The production monitoring method according to claim 5, characterized in that, Before establishing the mapping relationship between historical working data and maintenance data based on the historical working data and the historical maintenance data to obtain the historical dataset, The real-time working data is sequentially processed by data cleaning, noise reduction, integration, and transformation.

7. The production monitoring method according to claim 1, characterized in that, When the health index is lower than a preset value, an alarm mechanism is triggered, and a production status report containing fault location and maintenance suggestions is generated, including: When the health index is lower than the preset value, the system will automatically detect it and determine whether to trigger an alarm based on the triggering conditions. The triggering conditions include: The health index has dropped beyond the set threshold; Abnormal fluctuations in the actual temperature of the equipment; The system failed to return to normal within the scheduled testing period.

8. A production monitoring system based on the Industrial Internet of Things, characterized in that, The system includes a management platform, a sensor network platform, and an object platform that are connected in sequence. The management platform includes: The information acquisition module is used to acquire historical operating data and historical maintenance data of production equipment; The data fusion module is used to establish a mapping relationship between historical working data and maintenance data information to obtain a historical dataset based on the historical working data and the historical maintenance data. The model training module is used to build a device health model, and to train the device health model based on the historical dataset to obtain the trained device health model. The health assessment module is used to acquire real-time operating data of production equipment, input the real-time operating data into the trained health model, and obtain the equipment health index. The alarm and reporting module is used to trigger an alarm mechanism and generate a production status report containing fault location and maintenance suggestions when the health index is less than a preset value.

9. A computer device, characterized in that, Includes one or more processors and memory; One or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and execute the method of any one of claims 1-7.

Images