Intelligent health management system for die cutting and hot stamping equipment based on digital twinning

Abstract

The invention discloses an intelligent health management system and method for die cutting and hot stamping equipment based on digital twinning, and belongs to the technical field of intelligent operation and maintenance of high-end equipment. The system comprises a field layer, an edge computing unit, a cloud platform and a health regulation and control unit. The field layer comprises a die cutting and hot stamping equipment body, a multi-source sensing network and an equipment control system; the edge calculation unit is responsible for data acquisition and edge processing; the cloud platform deploys a digital twinning and prediction analysis unit; and the health regulation and control unit generates a regulation and control instruction according to the prediction result. According to the invention, by constructing a closed-loop system architecture of perception-analysis-regulation, intelligent management and autonomous regulation of the health state of the die cutting and hot stamping equipment are realized, and the technical problems of incomplete monitoring, inaccurate prediction and non-closed-loop regulation in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance technology for high-end equipment, and in particular to an intelligent health management system and method for die-cutting and hot stamping equipment based on digital twins. Background Technology

[0002] Die-cutting and hot stamping equipment is a core process equipment in the high-end packaging and printing field. Its core transmission components are under high-speed and heavy-load conditions for a long time, and the accumulation of damage leads to frequent sudden failures. Due to the lack of effective condition monitoring and fault early warning methods, the average fault repair time is as long as 48 hours or more, and the direct economic loss caused by a single unplanned downtime can reach 200,000 to 500,000 yuan.

[0003] Existing technologies for equipment health management solutions have significant shortcomings: most equipment uses single-parameter threshold alarms and lacks the ability to fuse multi-source information; fault diagnosis models have weak generalization ability under conditions of scarce samples and variable operating conditions; existing systems lack a deep closed loop with equipment control systems, and the operation and maintenance mode is still mainly based on passive response.

[0004] Although digital twin technology has been gradually applied in the industrial field, existing digital twin-based solutions mostly focus on status monitoring and visualization, and still have significant shortcomings in terms of system architecture innovation, predictive analysis accuracy, and control loop integrity. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide an intelligent health management system and method for die-cutting and hot stamping equipment with innovative architecture, capable of realizing closed-loop management of the entire process from state perception to autonomous control.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] A digital twin-based intelligent health management system for die-cutting and hot stamping equipment, characterized in that it includes:

[0008] The field layer includes the die-cutting and hot stamping equipment body, a multi-source sensor network for collecting equipment operating status data, and an equipment control system responsible for controlling equipment operation; the edge computing unit is connected to the multi-source sensor network of the field layer and includes a data acquisition and edge processing module; the cloud platform is connected to the edge computing unit and includes a digital twin and predictive analysis unit; the health control unit is connected to both the cloud platform and the equipment control system of the field layer and includes a control decision module; wherein, the multi-source sensor network, the edge computing unit, the cloud platform, and the health control unit are connected in sequence to form a closed-loop system from status perception to health control.

[0009] Preferably, the multi-source sensor network includes vibration sensors and temperature sensors deployed on the spindle system, worm gear pair, and elbow mechanism of the die-cutting and hot stamping equipment.

[0010] Preferably, the digital twin and predictive analysis unit performs health status assessment and remaining lifespan prediction by integrating the physical mechanism model and operational data of the equipment.

[0011] Preferably, the health regulation unit uses a model-predictive control strategy to generate regulation commands.

[0012] A smart health management method for die-cutting and hot stamping equipment, characterized by comprising the following steps:

[0013] Operational status data is collected through a multi-source sensor network deployed at the equipment site;

[0014] The collected data is preprocessed and feature fused using edge computing units;

[0015] The processed data is sent to the cloud platform to drive the digital twin to synchronize its state with the physical entity;

[0016] By integrating physical mechanisms and data-driven analysis through digital twin and predictive analytics units, health prediction results are generated.

[0017] The health regulation unit generates optimized control commands based on health prediction results.

[0018] The control commands are sent to the equipment control system to adjust the equipment operating parameters.

[0019] The equipment operates under new parameters, and its state changes are collected by the sensor network, forming a closed-loop feedback loop. Control commands are then issued.

[0020] Preferably, the multi-source sensing and edge computing unit includes a network of vibration sensors and temperature sensors deployed on the equipment spindle system, worm gear pair, and elbow mechanism.

[0021] Preferably, the digital twin and predictive analysis unit performs remaining life prediction by integrating the physical mechanism model and operational data of the equipment.

[0022] Preferably, the health regulation unit generates the regulation command using a model-predictive control strategy.

[0023] A smart health management method for die-cutting and hot stamping equipment, characterized by comprising the following steps:

[0024] The system collects and processes equipment operation status data through multi-source sensing and edge computing units deployed at the equipment site.

[0025] The processed data is sent to the digital twin and predictive analytics unit deployed in the cloud, and the digital twin is updated based on the received data and the health prediction results are output.

[0026] The health control unit, which connects the edge computing unit and the equipment control system, outputs control commands to the equipment control system based on the health prediction results.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] In terms of architectural innovation, a four-layer system architecture of "field layer - edge computing unit - cloud platform - health control unit" is proposed. Through functional decoupling and collaborative work, resource optimization and efficient operation and maintenance are achieved.

[0029] In terms of analytical precision, the analysis method that integrates physical mechanisms and data-driven approaches overcomes the limitations of single models under complex working conditions, significantly improving the accuracy of health status assessment and remaining life prediction.

[0030] In terms of closed-loop intelligence, a complete intelligent operation and maintenance closed loop from state perception to autonomous control has been constructed, transforming the operation and maintenance mode from passive response to proactive early warning and autonomous decision-making, which significantly improves equipment reliability. Attached Figure Description

[0031] Figure 1 This is a schematic diagram of the overall architecture of the system of the present invention.

[0032] Figure 2 This is a flowchart of the process of the method of the present invention. Detailed Implementation

[0033] A preferred embodiment of the present invention will be described in detail below with reference to the accompanying drawings.

[0034] See system architecture implementation Figure 1 The implementation of this system consists of four main parts:

[0035] On-site layer: This part is deployed on-site at the die-cutting and hot stamping equipment site, including the equipment body, a multi-source sensor network deployed on key mechanical components (such as the spindle system, worm gear pair, and toggle mechanism), and the equipment control system. The sensor network is responsible for collecting real-time equipment operating status data, and the equipment control system is responsible for receiving control commands and driving the actuators.

[0036] Edge computing unit: This unit connects to the multi-source sensor network in the field layer and includes data acquisition and edge processing modules. This module is responsible for real-time preprocessing, feature extraction, and fusion of the raw data acquired by the sensor network.

[0037] Cloud Platform: This platform connects to the edge computing unit and includes a digital twin and predictive analytics unit. This unit receives processed data from the edge computing unit, updates the state of the digital twin, and outputs equipment health prediction results based on an analysis method that integrates physical mechanisms and operational data.

[0038] Health Control Unit: This unit connects to both the cloud platform and the field-level equipment control system, and includes a control decision module. This module receives prediction results from the cloud platform, generates optimized control commands based on preset control strategies, and drives the actuators to move through the equipment control system.

[0039] See workflow Figure 2 The workflow of the method of the present invention includes the following steps:

[0040] S1: Collect operational status data such as vibration and temperature through a multi-source sensor network deployed at the equipment site;

[0041] S2: The collected data is preprocessed and feature fused through the edge computing unit;

[0042] S3: Send the processed feature data to the cloud platform;

[0043] S4: The cloud platform updates the state of the digital twin based on the received data;

[0044] S5: Through digital twin and predictive analytics units, physical mechanisms and data-driven analysis are integrated to generate health prediction results;

[0045] S6: Health prediction results are sent to the health regulation unit;

[0046] S7: The health regulation unit generates optimized control instructions based on the prediction results and through preset regulation strategies;

[0047] S8: Control commands drive the actuators to move through the equipment control system, enabling autonomous adjustment of equipment operating parameters;

[0048] S9: The equipment operates under new parameters, and its state changes are collected by the sensor network to form a closed-loop feedback.

[0049] Example Effects

[0050] Practical application in die-cutting and hot stamping equipment shows that this system can achieve an early diagnosis accuracy of ≥95% for critical component failures, a remaining life prediction error of no more than 15%, and a 50% reduction in unplanned equipment downtime, effectively verifying the practicality and advancement of this invention.

Claims

1. A smart health management system for die-cutting and hot stamping equipment based on digital twins, characterized in that, include: The field layer includes the die-cutting and hot stamping equipment body, a multi-source sensor network for collecting equipment operation status data, and an equipment control system responsible for controlling the operation of the equipment. The edge computing unit is connected to the multi-source sensor network of the field layer and includes a data acquisition and edge processing module. The cloud platform, connected to the edge computing unit, includes a digital twin and predictive analysis unit; the health control unit, connected to both the cloud platform and the field-level equipment control system, includes a control decision module; wherein the multi-source sensor network, edge computing unit, cloud platform, and health control unit are connected in sequence to form a closed-loop system from state perception to health control.

2. The system according to claim 1, characterized in that, The multi-source sensor network includes vibration sensors and temperature sensors deployed on the spindle system, worm gear pair, and elbow mechanism of the die-cutting and hot stamping equipment.

3. The system according to claim 1, characterized in that, The digital twin and predictive analysis unit performs health status assessment and remaining life prediction by integrating the physical mechanism model and operational data of the equipment. The method according to claim 7, wherein the health prediction result includes a prediction of the remaining service life of key equipment components.

4. The system according to claim 1, characterized in that, The health regulation unit uses a model-predictive control strategy to generate regulation commands.

5. The system according to claim 1, characterized in that, The system forms a closed loop from state perception to health regulation.

6. A method for intelligent health management of die-cutting and hot stamping equipment, characterized in that, Includes the following steps: Operational status data is collected through a multi-source sensor network deployed at the equipment site; The collected data is preprocessed and feature fused using edge computing units; The processed data is sent to the cloud platform to drive the digital twin to synchronize its state with the physical entity; By integrating physical mechanisms and data-driven analysis through digital twin and predictive analytics units, health prediction results are generated. The health regulation unit generates optimized control commands based on health prediction results. The control commands are sent to the equipment control system to adjust the equipment operating parameters. The equipment operates under new parameters, and its state changes are collected by the sensor network, forming a closed-loop feedback.

7. The method according to claim 6, characterized in that, The health prediction results include an assessment of the remaining service life of key equipment components.

8. The method according to claim 6, characterized in that, The fusion of physical mechanism and data-driven analysis includes performing physical mechanism reasoning and data-driven analysis in parallel, and making a fusion decision based on the outputs of both.

Images