A printing equipment state real-time monitoring system based on internet of things

Abstract

This invention relates to IoT monitoring, specifically to an IoT-based real-time monitoring system for printing equipment. The system includes: deploying temperature, pressure, vibration, and current sensors on the printing equipment to acquire real-time operating data; using visual sensors for print quality monitoring; forming a multi-source data acquisition system covering mechanical, electrical, and process aspects; constructing a low-latency communication channel using the MQTT protocol; ensuring transmission security through TLS encryption and dynamic token authentication; extracting time-domain, frequency-domain, and time-series features from the raw data; periodically feeding the on-site data back to the health assessment model and digital twin; and improving prediction accuracy through iterative model updates, forming a continuous optimization mechanism of monitoring-analysis-improvement. This invention solves the problems of incomplete data acquisition and inability to continuously optimize monitoring models in traditional printing equipment monitoring, making it difficult to achieve efficient and accurate monitoring and intelligent operation and maintenance.

Description

Technical Field

[0001] This invention pertains to Internet of Things (IoT) monitoring, specifically relating to a real-time monitoring system for the status of printing equipment based on the Internet of Things. Background Technology

[0002] In the printing industry, the stable operation of printing equipment is crucial for ensuring production efficiency and product quality. However, traditional methods of monitoring printing equipment have many limitations. On the one hand, traditional monitoring mainly relies on regular manual inspections and simple local instrument displays. Manual inspections are not only labor-intensive but also difficult to monitor in real time, failing to detect subtle anomalies during equipment operation. Intervention is often delayed until obvious malfunctions occur, leading to production interruptions and significant economic losses. Simple local instrument displays provide limited data, failing to comprehensively reflect the complex operating status of the equipment and providing insufficient basis for equipment maintenance and performance optimization. On the other hand, some existing monitoring systems have limited functionality and incomplete data collection, often limited to single data types, making it difficult to achieve comprehensive monitoring of mechanical, electrical, and process aspects of the equipment. Regarding data transmission, some systems use traditional communication methods, resulting in high latency, failing to meet real-time monitoring needs, and lacking sufficient data security, posing risks of data leakage and tampering. In equipment status assessment, there is a lack of accurate models and algorithms, making it difficult to adapt to different production conditions and resulting in inaccurate predictions. Furthermore, the lack of effective virtual mapping and remote collaboration means that the equipment's operating status cannot be intuitively presented, making remote maintenance difficult and reducing the efficiency of maintenance resource allocation.

[0003] Existing technologies suffer from shortcomings such as incomplete data collection, high transmission latency and poor security, inaccurate status assessment, lack of effective virtual mapping and remote collaboration methods, and lack of a continuous optimization mechanism, making it difficult to meet the needs of real-time, accurate, comprehensive monitoring and efficient operation and maintenance of printing equipment. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides an IoT-based real-time monitoring system for printing equipment status. This system solves the problems of incomplete data collection, insufficient real-time transmission and security, inaccurate status assessment, lack of remote collaboration and virtual simulation in operation and maintenance, and inability to continuously optimize monitoring models in traditional printing equipment monitoring systems, thus hindering efficient and accurate monitoring and intelligent operation and maintenance. To address the above objective, the present invention adopts the following technical solution: The aforementioned IoT-based real-time monitoring system for printing equipment includes: a data acquisition module, used to acquire real-time equipment operation data by deploying temperature, pressure, vibration, and current sensors on the printing equipment, and using visual sensors for print quality monitoring, forming a multi-source data acquisition system covering mechanical, electrical, and process aspects; a data transmission module, used to build a low-latency communication channel using the MQTT protocol, combined with 5G network slicing technology to ensure data real-time performance, preprocessing equipment data via an edge computing gateway before uploading it to the cloud, and ensuring transmission security through TLS encryption and dynamic token authentication to avoid data tampering risks; a health assessment module, used to extract time-domain, frequency-domain, and time-series features from raw data, inputting these features into an LSTM neural network to train an equipment health scoring model, dynamically adjusting thresholds to adapt to different production conditions, and obtaining accurate status prediction results; and a virtual mapping module, used to employ Unity... The 3D engine constructs a three-dimensional digital model of the equipment, driving the virtual body to dynamically change in real time with sensor data. It simulates fault scenarios and process adjustment effects through a digital twin, revealing equipment operating patterns. The remote collaboration module develops a web-based maintenance interface to remotely adjust equipment parameters, integrates AR technology to project maintenance steps onto the field, shares equipment status data with the supply chain module, and obtains spare parts inventory information through API interfaces, enabling intelligent allocation of maintenance resources and rapid fault response. The feedback optimization module analyzes equipment energy consumption data to obtain energy-saving optimization suggestions, establishes a quality traceability database by linking process parameters and printing defects, and regularly feeds field data back to the health assessment model and digital twin. Through iterative model updates, it improves prediction accuracy, forming a continuous optimization mechanism of monitoring-analysis-improvement.

[0005] Furthermore, the data acquisition module includes: a component data submodule, used to acquire real-time roller temperature and ink delivery pressure data by deploying temperature and pressure sensors on the mechanical parts of the equipment, extracting vibration characteristic signals of bearings and gears by installing vibration sensors on the transmission module, and acquiring equipment load change information by connecting a current sensor to the motor control circuit; and a real-time scanning submodule, used to use an industrial camera as a vision sensor to scan the surface of the printed material in real time, acquire quality data such as color deviation and registration error, and integrate three types of data—mechanical vibration, electrical parameters, and process quality—to obtain a multi-dimensional information flow covering the entire operating state of the equipment.

[0006] Furthermore, the data transmission module includes: a data allocation submodule, used to construct an efficient transmission channel between the printing equipment and the cloud using the MQTT lightweight communication protocol, and to allocate dedicated transmission resources for data through 5G network slicing technology to ensure millisecond-level latency requirements for real-time monitoring data of vibration and temperature; a data cleaning submodule, used to deploy an edge computing gateway on the device side to clean, compress, and extract features from the raw data, uploading only valid information to reduce bandwidth consumption; and a data encryption submodule, used to protect data integrity using the TLS 1.3 encryption protocol during transmission, and to verify device identity using a dynamic token authentication mechanism to obtain a secure, reliable, and low-latency cloud data stream.

[0007] Furthermore, the health assessment module includes: a data analysis submodule, used to perform in-depth analysis of the raw data of the printing equipment using signal processing technology, extracting frequency domain features through Fourier transform to capture periodic fault modes, extracting time domain features using the sliding window method to reflect transient changes in the equipment, and combining time series analysis to track the long-term evolution trend of parameters; a health scoring submodule, used to input multi-dimensional feature vectors into a bidirectional LSTM neural network, using long short-term memory to learn the degradation patterns of the equipment, and training to generate a health scoring model; and a result prediction submodule, used to dynamically adjust the model threshold according to the operating parameters of production batches and ambient temperature and humidity, continuously optimize the prediction sensitivity, and obtain accurate prediction results of equipment status covering the entire life cycle.

[0008] Furthermore, the virtual mapping module includes: a running state submodule, used to construct a three-dimensional digital model of the printing equipment using the Unity 3D engine, and to map real-time data from temperature and vibration sensors to corresponding parameters of the virtual body through a data interface, driving the model to dynamically present the actual operating state of the equipment; a recording and synchronization submodule, used to conduct fault injection tests using a digital twin, simulating abnormal scenarios such as bearing wear and motor overload, and synchronously recording the response characteristics of the virtual body; and a virtual adjustment submodule, used to virtually adjust process parameters, analyze the impact of changes in printing speed and ink viscosity on product quality, extract equipment state evolution patterns and process optimization strategies, and obtain a visualized decision-making basis to guide actual production.

[0009] Furthermore, the remote collaboration module includes: a precision projection submodule, used to develop a multi-terminal adapted operation and maintenance interface using a responsive web framework, to realize remote configuration and real-time monitoring of printing equipment parameters through a secure encrypted channel, to integrate an AR engine to overlay 3D maintenance guidance onto the equipment entity, and to precisely project operation steps into the field of vision of maintenance personnel through spatial positioning technology; a processing and push submodule, used to push equipment status data to the supply chain module after standardized processing, and to obtain information on spare parts inventory and supplier delivery dates through a RESTful API interface; and an intelligent scheduling submodule, used to generate maintenance plans based on equipment fault prediction results and spare parts availability data using an intelligent scheduling algorithm, thereby achieving cross-system collaborative dynamic allocation of maintenance resources and minute-level fault response capabilities.

[0010] Furthermore, the feedback optimization module includes: an energy-saving optimization submodule, used to analyze equipment energy consumption data using data mining algorithms, extract high-energy-consuming periods and abnormal fluctuation characteristics, and obtain targeted energy-saving optimization suggestions by comparing with industry benchmarks; a quality correlation submodule, used to correlate process parameters such as printing speed and ink viscosity with defect data such as color difference and registration error, and construct a traceability knowledge base containing equipment-process-quality correlation rules; and a learning update submodule, used to periodically input cleaned real-time data into the health assessment model and digital twin, update model parameters using an online learning mechanism, and continuously improve fault prediction accuracy and virtual simulation precision through iteration, forming a closed-loop optimization system covering the entire process from data collection, analysis and decision-making to process improvement.

[0011] Furthermore, the data cleaning submodule is used to deploy the edge computing gateway on the device side. Through the data preprocessing module, it performs outlier removal, redundant data filtering, and sliding window compression operations on the raw signals of temperature and vibration. It uses time-frequency analysis algorithms to extract feature parameters and combines business rules to filter out effective data that reflects the health status of the device.

[0012] Furthermore, the operating status submodule is used to construct a three-dimensional digital model of the printing equipment using the Unity 3D engine. The three-dimensional digital model includes mechanical structure, transmission components and electrical modules. Through the data interface, real-time data from temperature and vibration sensors are mapped to the corresponding parameters of the virtual body, driving the model to dynamically present the actual operating status of the equipment.

[0013] In the technical solution provided by this invention, the data acquisition module is used to acquire real-time equipment operation data by deploying temperature, pressure, vibration, and current sensors on the printing equipment, and to use visual sensors for printing quality monitoring, forming a multi-source data acquisition system covering mechanical, electrical, and process aspects; the data transmission module is used to build a low-latency communication channel using the MQTT protocol, combined with 5G network slicing technology to ensure data real-time performance, and to upload equipment data to the cloud after preprocessing via an edge computing gateway, ensuring transmission security through TLS encryption and dynamic token authentication to avoid the risk of data tampering; the health assessment module is used to extract time-domain, frequency-domain, and time-series features from the raw data, input the features into an LSTM neural network to train an equipment health rating model, dynamically adjust thresholds to adapt to different production conditions, and obtain accurate status prediction results; the virtual mapping module is used to use Unity A 3D engine constructs a three-dimensional digital model of the equipment, driving the virtual body to dynamically change in real time with sensor data. The digital twin simulates fault scenarios and process adjustment effects, revealing equipment operating patterns. A remote collaboration module develops a web-based maintenance interface for remote parameter adjustment, integrates AR technology to project maintenance steps onto the field, shares equipment status data with the supply chain module, and obtains spare parts inventory information via API, enabling intelligent allocation of maintenance resources and rapid fault response. A feedback optimization module analyzes equipment energy consumption data to obtain energy-saving optimization suggestions, establishes a quality traceability database by linking process parameters and printing defects, and periodically feeds field data back to the health assessment model and digital twin. Iterative model updates improve prediction accuracy, forming a continuous optimization mechanism of monitoring-analysis-improvement. This invention solves the problems of incomplete data collection, insufficient real-time transmission and security, inaccurate status assessment, lack of remote collaboration and virtual simulation in traditional printing equipment monitoring, and inability to continuously optimize monitoring models, hindering efficient and accurate monitoring and intelligent maintenance. Attached Figure Description

[0014] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention.

[0015] Figure 1 This is a schematic diagram of a first embodiment of a real-time monitoring system for the status of printing equipment based on the Internet of Things (IoT) according to an embodiment of the present invention.

[0016] Figure 2 This is a schematic diagram of a second embodiment of a real-time monitoring system for the status of printing equipment based on the Internet of Things (IoT) according to an embodiment of the present invention.

[0017] Figure 3 This is a schematic diagram of a third embodiment of a real-time monitoring system for the status of printing equipment based on the Internet of Things (IoT) according to an embodiment of the present invention.

[0018] Figure 4 This is a schematic diagram of the fourth embodiment of a real-time monitoring system for the status of printing equipment based on the Internet of Things in this invention.

[0019] Figure 5 This is a schematic diagram of the fifth embodiment of a real-time monitoring system for the status of printing equipment based on the Internet of Things in this invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0021] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0022] A real-time monitoring system for the status of printing equipment based on the Internet of Things, such as Figure 1 As shown, it includes: like Figure 2 As shown, in this embodiment, the data acquisition module includes: a component data submodule, used to acquire real-time roller temperature and ink delivery pressure data by deploying temperature and pressure sensors on the mechanical parts of the equipment, extracting vibration characteristic signals of bearings and gears by installing vibration sensors on the transmission module, and acquiring equipment load change information by connecting a current sensor to the motor control circuit; and a real-time scanning submodule, used to use an industrial camera as a vision sensor to scan the surface of the printed material in real time, acquire quality data such as color deviation and registration error, and integrate three types of data—mechanical vibration, electrical parameters, and process quality—to obtain a multi-dimensional information flow covering the entire operating state of the equipment.

[0023] The component data submodule utilizes temperature, pressure, vibration, and current sensors to acquire parameters of the mechanical, transmission, and electrical systems in real time, providing fundamental data support for equipment health monitoring. The real-time scanning submodule uses industrial cameras to quickly identify printing defects, ensuring controllable process quality. The integration of these two modules forms a multi-dimensional information flow covering mechanical vibration, electrical characteristics, and process quality, effectively solving the data fragmentation problem in traditional monitoring methods and providing a high-precision, comprehensive data foundation for subsequent condition analysis, fault prediction, and process optimization.

[0024] like Figure 3As shown, in this embodiment, the data transmission module includes: a data allocation submodule, used to build an efficient transmission channel between the printing equipment and the cloud using the MQTT lightweight communication protocol, and to allocate dedicated transmission resources for the data through 5G network slicing technology to ensure the millisecond-level latency requirements of real-time monitoring data of vibration and temperature; a data cleaning submodule, used to deploy an edge computing gateway on the device side to clean, compress, and extract features from the raw data, and only upload valid information to reduce bandwidth consumption; and a data encryption submodule, used to protect data integrity using the TLS 1.3 encryption protocol during transmission, and to verify the device identity using a dynamic token authentication mechanism to obtain a secure, reliable, and low-latency cloud data stream.

[0025] The data transmission module significantly improves data transmission efficiency and security through multi-level optimization. The data distribution submodule utilizes the MQTT protocol and 5G slicing technology to ensure monitoring data reaches the cloud with millisecond-level latency, meeting real-time monitoring requirements. The data cleaning submodule processes raw data locally through edge computing, removing redundant information and extracting core features, significantly reducing bandwidth consumption and cloud storage pressure. The data encryption submodule employs TLS 1.3 and dynamic token dual authentication to build a security protection system covering the entire transmission process. These three components work synergistically to form an efficient, secure, and low-latency cloud data stream, providing reliable data support for remote equipment operation and maintenance and intelligent decision-making.

[0026] like Figure 4 As shown, in this embodiment, the health assessment module includes: a data analysis submodule, used to perform in-depth analysis of the raw data of the printing equipment using signal processing technology, extracting frequency domain features through Fourier transform to capture periodic fault modes, extracting time domain features using the sliding window method to reflect transient changes in the equipment, and combining time series analysis to track the long-term evolution trend of parameters; a health scoring submodule, used to input multi-dimensional feature vectors into a bidirectional LSTM neural network, using long short-term memory to learn the degradation law of the equipment, and training to generate a health scoring model; and a result prediction submodule, used to dynamically adjust the model threshold according to the operating parameters of production batch and ambient temperature and humidity, continuously optimize the prediction sensitivity, and obtain accurate prediction results of equipment status covering the entire life cycle.

[0027] The data analysis submodule comprehensively utilizes signal processing technology to mine data features from multiple dimensions, including the time domain, frequency domain, and time series, effectively capturing periodic faults and transient anomalies. The health scoring submodule uses a bidirectional LSTM neural network to deeply learn the degradation patterns of equipment and generate dynamic health scores, breaking through the limitations of traditional threshold judgment. The result prediction submodule combines operating parameters to adjust the model in real time, improving the predictive adaptability in complex environments.

[0028] like Figure 5As shown, in this embodiment, the virtual mapping module includes: a running state submodule, used to construct a three-dimensional digital model of the printing equipment using the Unity3D engine, and to map real-time sensor data of temperature and vibration to the corresponding parameters of the virtual body through a data interface, driving the model to dynamically present the actual operating state of the equipment; a recording and synchronization submodule, used to conduct fault injection tests using a digital twin, simulating abnormal scenarios such as bearing wear and motor overload, and synchronously recording the response characteristics of the virtual body; and a virtual adjustment submodule, used to virtually adjust process parameters, analyze the impact of changes in printing speed and ink viscosity on product quality, extract equipment state evolution patterns and process optimization strategies, and obtain a visual decision-making basis to guide actual production.

[0029] The operational status submodule uses Unity 3D to build a high-fidelity 3D model and map sensor data in real time, making the equipment status visual and improving the intuitiveness of monitoring; the recording and synchronization submodule simulates various abnormal scenarios and records response characteristics through fault injection testing, providing data support for fault tracing and contingency plan formulation; the virtual adjustment submodule is based on parameter virtual optimization, quantitatively analyzes the impact of process changes on quality, extracts optimization strategies and generates visual solutions.

[0030] In this embodiment, the remote collaboration module includes: a precision projection submodule, which uses a responsive web framework to develop a multi-terminal adapted operation and maintenance interface, enables remote configuration and real-time monitoring of printing equipment parameters through a secure encrypted channel, integrates an AR engine to overlay 3D maintenance guidance onto the equipment entity, and precisely projects operation steps into the field of vision of maintenance personnel through spatial positioning technology; a processing and push submodule, which pushes standardized equipment status data to the supply chain module, and obtains spare parts inventory and supplier delivery information through a RESTful API interface; and an intelligent scheduling submodule, which uses an intelligent scheduling algorithm to generate maintenance plans based on equipment fault prediction results and spare parts availability data, thereby achieving cross-system collaborative dynamic allocation of maintenance resources and minute-level fault response capabilities.

[0031] The Precision Projection submodule utilizes responsive Web and AR technologies to enable remote parameter configuration, real-time monitoring, and 3D maintenance guidance projection, allowing maintenance personnel to quickly locate faults and obtain operational guidance, significantly reducing on-site handling time. The Processing Push submodule breaks down information barriers between equipment status and the supply chain through standardized data interaction, ensuring real-time sharing of spare parts inventory and delivery data. The Intelligent Scheduling submodule combines fault prediction and spare parts resources to dynamically generate the optimal maintenance plan, achieving efficient cross-system resource allocation.

[0032] In this embodiment, the feedback optimization module includes: an energy-saving optimization submodule, used to analyze equipment energy consumption data using data mining algorithms, extract high-energy-consuming periods and abnormal fluctuation characteristics, and obtain targeted energy-saving optimization suggestions by comparing with industry benchmarks; a quality correlation submodule, used to correlate process parameters such as printing speed and ink viscosity with defect data such as color difference and registration error, and construct a traceability knowledge base containing equipment-process-quality correlation rules; and a learning update submodule, used to periodically input cleaned real-time data into the health assessment model and digital twin, update model parameters using an online learning mechanism, and continuously improve fault prediction accuracy and virtual simulation precision through continuous iteration, forming a closed-loop optimization system covering the entire process from data collection, analysis and decision-making to process improvement.

[0033] The energy-saving optimization submodule deeply mines energy consumption data, accurately identifies high-energy-consuming links, and provides optimization strategies to effectively reduce production costs. The quality correlation submodule builds a knowledge base linking equipment, processes, and quality, enabling defect tracing and dynamic optimization of process parameters to improve product consistency. The learning and updating submodule uses on-site data to feed back into the model and utilizes an online learning mechanism to continuously optimize the accuracy of health assessments and digital twins, forming a closed-loop optimization of "data collection - analysis and decision-making - process improvement".

[0034] In this embodiment, the data cleaning submodule is used to deploy the edge computing gateway on the device side. Through the data preprocessing module, it performs outlier removal, redundant data filtering, and sliding window compression operations on the raw signals of temperature and vibration. It uses time-frequency analysis algorithms to extract feature parameters and combines business rules to filter out effective data that reflects the health status of the device.

[0035] The data cleaning submodule significantly improves data quality and transmission efficiency through the synergistic application of edge computing and intelligent algorithms. By deploying the gateway on the device side, it preprocesses raw signals such as temperature and vibration locally. Noise interference is eliminated through outlier removal and redundancy filtering, sliding window compression reduces data volume, and time-frequency analysis algorithms accurately extract characteristic parameters reflecting the device's health status. Finally, it filters valid data based on business rules.

[0036] In this embodiment, the running status submodule is used to construct a three-dimensional digital model of the printing equipment using the Unity 3D engine. The three-dimensional digital model includes mechanical structure, transmission components and electrical modules. Through the data interface, real-time data from temperature and vibration sensors are mapped to the corresponding parameters of the virtual body, driving the model to dynamically present the actual running status of the equipment.

[0037] The operational status submodule utilizes a 3D digital model of the printing equipment built with the Unity 3D engine to accurately reproduce details such as the mechanical structure, transmission components, and electrical modules, achieving a virtual mapping of the equipment's physical form. Through a data interface, real-time data from sensors such as temperature and vibration are dynamically bound to the virtual body parameters, allowing the model to change synchronously with the actual operating status and intuitively presenting key information such as the distribution of hot zones and abnormal vibrations during equipment operation.

[0038] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time status monitoring system for printing equipment based on the Internet of Things, characterized in that, The IoT-based real-time status monitoring system for printing equipment includes: The data acquisition module is used to acquire real-time equipment operation data by deploying temperature, pressure, vibration and current sensors on the printing equipment, and to use visual sensors for printing quality monitoring, forming a multi-source data acquisition system covering mechanical, electrical and process aspects. The data transmission module is used to build a low-latency communication channel using the MQTT protocol, combined with 5G network slicing technology to ensure data real-time performance, and uploads device data to the cloud after preprocessing by the edge computing gateway. It ensures transmission security through TLS encryption and dynamic token authentication to avoid the risk of data tampering. The health assessment module is used to extract time-domain, frequency-domain, and time-series features from raw data, input the features into an LSTM neural network to train the equipment health rating model, dynamically adjust the threshold to adapt to different production conditions, and obtain accurate status prediction results. The virtual mapping module is used to build a 3D digital model of the equipment using the Unity 3D engine, drive the virtual body to change dynamically in real time with sensor data, simulate fault scenarios and process adjustment effects through digital twins, and obtain the operating rules of the equipment. The remote collaboration module is used to develop a web-based operation and maintenance interface to remotely adjust equipment parameters, integrate AR technology to project maintenance steps to the site, share equipment status data with the supply chain module, and obtain spare parts inventory information through API interface to achieve intelligent allocation of maintenance resources and rapid fault response. The feedback optimization module is used to analyze equipment energy consumption data to obtain energy-saving optimization suggestions, link process parameters with printing defects to establish a quality traceability database, and regularly feed field data back to the health assessment model and digital twin. Through model iteration and updates, the prediction accuracy is improved, forming a continuous optimization mechanism of monitoring-analysis-improvement.

2. The real-time monitoring system for the status of printing equipment based on the Internet of Things according to claim 1, characterized in that, The data acquisition module includes: The component data submodule is used to acquire real-time data on roller temperature and ink delivery pressure by deploying temperature and pressure sensors in the mechanical parts of the equipment, to extract vibration characteristic signals of bearings and gears by installing vibration sensors in the transmission module, and to acquire equipment load change information by connecting current sensors in the motor control circuit. The real-time scanning submodule uses an industrial camera as a vision sensor to scan the surface of printed materials in real time, acquire quality data such as color deviation and registration error, and integrate three types of data: mechanical vibration, electrical parameters and process quality, to obtain a multi-dimensional information flow covering the entire operating status of the equipment.

3. The real-time status monitoring system for printing equipment based on the Internet of Things according to claim 1, characterized in that, The data transmission module includes: The data allocation submodule is used to build an efficient transmission channel between the printing equipment and the cloud using the MQTT lightweight communication protocol. It allocates dedicated transmission resources for data through 5G network slicing technology to ensure the millisecond-level latency requirements of real-time monitoring data of vibration and temperature. The data cleaning submodule is used to deploy the edge computing gateway on the device side to clean, compress and extract features from the raw data, and only upload valid information to reduce bandwidth consumption. The data encryption submodule is used to protect data integrity during transmission using the TLS 1.3 encryption protocol and to verify device identity using a dynamic token authentication mechanism, resulting in a secure, reliable, and low-latency cloud data stream.

4. The real-time status monitoring system for printing equipment based on the Internet of Things according to claim 1, characterized in that, The health assessment module includes: The data analysis submodule is used to perform in-depth analysis of the raw data of the printing equipment using signal processing technology. It extracts frequency domain features through Fourier transform to capture periodic fault modes, extracts time domain features using the sliding window method to reflect transient changes in the equipment, and combines time series analysis to track the long-term evolution trend of parameters. The health scoring submodule is used to input multi-dimensional feature vectors into a bidirectional LSTM neural network, utilize long short-term memory to learn the device degradation patterns, and train to generate a health scoring model. The results prediction submodule is used to dynamically adjust the model threshold based on the production batch and environmental temperature and humidity parameters, continuously optimize the prediction sensitivity, and obtain accurate prediction results of equipment status covering the entire life cycle.

5. The real-time status monitoring system for printing equipment based on the Internet of Things according to claim 1, characterized in that, The virtual mapping module includes: The runtime status submodule is used to build a 3D digital model of the printing equipment using the Unity 3D engine. Through the data interface, it maps real-time data from temperature and vibration sensors to the corresponding parameters of the virtual body, driving the model to dynamically present the actual running status of the equipment. The recording and synchronization submodule is used to conduct fault injection tests using digital twins, simulating abnormal scenarios such as bearing wear and motor overload, and synchronously recording the response characteristics of the virtual entity. The virtual adjustment submodule is used to analyze the impact of changes in printing speed and ink viscosity on product quality through virtual adjustment of process parameters, extract equipment state evolution patterns and process optimization strategies, and obtain a visualized decision-making basis to guide actual production.

6. The real-time status monitoring system for printing equipment based on the Internet of Things according to claim 1, characterized in that, The remote collaboration module includes: The Precision Projection submodule is used to develop a multi-terminal adapted operation and maintenance interface using a responsive web framework. It enables remote configuration and real-time monitoring of printing equipment parameters through a secure encrypted channel, integrates an AR engine to overlay 3D maintenance guidance onto the equipment entity, and precisely projects operation steps into the field of vision of maintenance personnel through spatial positioning technology. The push processing submodule is used to push standardized equipment status data to the supply chain module and obtain information on spare parts inventory and supplier delivery dates through a RESTful API interface. The intelligent scheduling submodule is used to generate maintenance plans based on equipment failure prediction results and spare parts availability data, using intelligent scheduling algorithms to achieve dynamic allocation of maintenance resources across systems and minute-level fault response capabilities.

7. The real-time monitoring system for the status of printing equipment based on the Internet of Things according to claim 1, characterized in that, The feedback optimization module includes: The energy-saving optimization submodule is used to analyze equipment energy consumption data using data mining algorithms, extract high energy consumption periods and abnormal fluctuation characteristics, and obtain targeted energy-saving optimization suggestions by comparing with industry benchmarks. The quality correlation submodule is used to correlate process parameters such as printing speed and ink viscosity with defect data such as color difference and registration error, and to build a traceability knowledge base containing equipment-process-quality correlation rules. The learning and updating submodule is used to periodically input cleaned real-time field data into the health assessment model and digital twin, and use an online learning mechanism to update model parameters. Through continuous iteration, the accuracy of fault prediction and the precision of virtual simulation are improved, forming a closed-loop optimization system covering the entire process from data collection, analysis and decision-making to process improvement.

8. A real-time monitoring system for the status of printing equipment based on the Internet of Things according to claim 3, characterized in that, The data cleaning submodule is used to deploy the edge computing gateway on the device side. Through the data preprocessing module, it performs outlier removal, redundant data filtering, and sliding window compression operations on the raw signals of temperature and vibration. It uses time-frequency analysis algorithms to extract feature parameters and combines business rules to filter out effective data that reflects the health status of the device.

9. A real-time monitoring system for the status of printing equipment based on the Internet of Things according to claim 5, characterized in that, The running status submodule is used to build a three-dimensional digital model of the printing equipment using the Unity 3D engine. The three-dimensional digital model includes mechanical structure, transmission components and electrical modules. Through the data interface, real-time data from temperature and vibration sensors are mapped to the corresponding parameters of the virtual body, driving the model to dynamically present the actual running status of the equipment.

Images