Safety protection monitoring system for rolling and connecting packaging unit

Abstract

The invention discloses a safety protection monitoring system for a rolling and connecting packaging unit, and relates to the field of rolling and connecting packaging units. The system comprises a server, a switch, a control module and a user terminal, the control module is arranged on a machine table device of the rolling and connecting packaging unit and used for collecting safety door opening and closing data of the machine table device, and the safety door opening and closing data comprises at least one of a safety door opening and closing state, a door opening and closing timestamp, door opening and closing duration, a door opening and closing frequency and a corresponding device identifier; the server is connected with the control module through the switch and is used for determining the equipment working state of the machine equipment according to the safety door opening and closing data; and the user terminal is connected with the server through the switch and is used for monitoring the safety door opening and closing data or the equipment working state. According to the invention, centralized management and remote monitoring of the rolling and connecting packaging unit can be realized, the monitoring efficiency is improved, and the abnormal condition of the safety door can be found in time.

Description

Technical Field

[0001] The present invention relates to the technical field of cigarette making and packing machines, and particularly to a safety protection monitoring system for a cigarette making and packing machine set. Background Art

[0002] A cigarette making and packing machine set is an automated device for cigarette production, integrating the functions of cigarette rolling, filter tipping and packing, and realizing the full-process automated production from rolling tobacco into cigarette rods to finished product packing.

[0003] Generally, safety doors are installed on the machine equipment of a cigarette making and packing machine set. The safety doors are usually used to isolate dangerous areas, protect the safety of operators, and ensure the operation of the equipment in a safe state. Monitoring the opening and closing states of the safety doors is crucial for ensuring the safety of industrial equipment operators, preventing accidental injuries and equipment damage, and meeting production safety standards.

[0004] In related technologies, the monitoring of the opening and closing states of safety doors mainly relies on physical contact sensors. These sensors are usually installed on the safety doors of the equipment, and detect the opening and closing states of the doors through mechanical contacts or limit switches. When the safety door is opened, the switch of the safety door will trigger a mechanical action, thereby changing the state of the circuit, usually used to cut off the power supply of the machine or emit an audible and visual alarm signal, so as to ensure that the machine equipment stops running when the safety door is opened and protect the safety of operators.

[0005] However, the monitoring scope of this safety door monitoring method is generally limited to the production site and requires on-site monitoring by management personnel. This results in low monitoring efficiency and a risk of not being able to detect abnormal situations of the safety doors in a timely manner. Summary of the Invention

[0006] Aiming at the above technical problems and defects, the purpose of the present invention is to provide a safety protection monitoring system for a cigarette making and packing machine set, which can achieve centralized management and remote monitoring, timely detect abnormal situations of safety doors, and improve the monitoring efficiency and the safety of equipment operation.

[0007] To achieve the above purpose, the present invention provides a safety protection monitoring system for a cigarette making and packing machine set, including a server, a switch, a control module and a user terminal; the control module is arranged on the machine equipment of the cigarette making and packing machine set and is used for collecting the safety door switch data of the machine equipment, and the safety door switch data includes at least one of the safety door switch state, the door switch timestamp, the door switch duration, the door switch frequency and the corresponding equipment identifier; the server is connected to the control module through the switch and is used for determining the equipment working state of the machine equipment according to the safety door switch data; the user terminal is connected to the server through the switch and is used for monitoring the safety door switch data or the equipment working state.

[0008] The present invention integrates a server, a switch, a control module, and a user terminal to achieve comprehensive monitoring and management of the opening and closing states of the safety doors of the machines. The control module collects the data of the opening and closing of the safety doors, the server determines the working state of the equipment based on these data, and the user terminal provides a remote monitoring function. This architecture not only breaks through the limitations of traditional monitoring methods, realizes centralized management and remote monitoring, but also improves the monitoring efficiency and the safety of equipment operation. The management personnel can grasp the equipment state in real time without on-site inspection, discover and handle abnormal situations in a timely manner, and reduce the safety risks caused by equipment failures or operation errors. At the same time, the system provides data support for equipment management, optimizes the production process, improves the production efficiency, and lays a solid foundation for the intelligent management of the cigarette making and packing unit.

[0009] In some embodiments, the system further includes an edge computing module. The edge computing module is respectively connected to the control module and the server, and is used for performing feature extraction processing on the safety door switch data to obtain door switch feature data, and uploading the door switch feature data to the server; the server is used for inputting the door switch feature data into a preset safety door switch recognition model to obtain a door switch behavior recognition result, and determining whether the working state of the equipment is normal according to the door switch behavior recognition result.

[0010] Adopting the technical solution of the above embodiment, the edge computing module is introduced to perform feature extraction on the safety door switch data, obtain more representative door switch feature data and upload it to the server. The server uses these feature data to input into a preset safety door switch recognition model to judge whether the working state of the equipment is normal. This improvement significantly improves the intelligent level and monitoring accuracy of the system, reduces the data transmission volume and the computing burden on the server side, and improves the data processing efficiency and real-time performance. Through the door switch behavior recognition of the feature data, the system can more accurately judge the equipment state, discover abnormal behaviors in a timely manner, and provide a more reliable guarantee for the safe operation of the equipment.

[0011] In some embodiments, the safety bulletin board includes a screen wall and a decoder. The decoder is connected to the server. The decoder is used for decoding the working state of the equipment and converting it into playable image and video stream data, and transmitting the image and video stream data to the screen wall for playing.

[0012] Adopting the technical solution of the above embodiment, the safety bulletin board includes a screen wall and a decoder. The decoder decodes the working state of the equipment into image and video stream data and transmits it to the screen wall for playing. This improvement makes the display of the working state of the equipment more intuitive and visual, facilitating on-site operators and management personnel to view the operation of the equipment in real time without frequently checking the control panel or data reports. The intuitive display method improves the monitoring efficiency, facilitates the quick discovery of abnormal situations and timely measures, enhances the practicality of the system, and is especially suitable for the real-time monitoring requirements in complex industrial environments.

[0013] In some embodiments, the server is also used to store the safety door switch data in a database.

[0014] Adopting the technical solution of the above embodiment, the server stores the safety door switch data in the database, providing a solid foundation for the data management and analysis of the system. Through structured storage, the system can achieve long-term data preservation and efficient query, facilitating managers to retrieve historical data for analysis at any time, and understand the operation trends and state change rules of the equipment. Data storage provides rich data support for subsequent fault diagnosis, performance evaluation, and maintenance planning, helping to optimize the equipment management strategy and improve the reliability and operation efficiency of the equipment. At the same time, the centralized storage of data also facilitates the system expansion and integration with other management systems (such as MES, ERP), enhancing the overall function and value of the system.

[0015] In some embodiments, the system further includes a vision sensor for capturing an image of the safety door of the machine tool. The vision sensor is connected to the server through a switch, and the server is used to verify the safety door switch data based on the safety door image.

[0016] Adopting the technical solution of the above embodiment, a vision sensor is introduced to capture an image of the safety door of the machine tool, and the image data is transmitted to the server through a switch. The server verifies the safety door switch data based on the safety door image. This improvement significantly enhances the monitoring accuracy and reliability of the system. The image data provided by the vision sensor can intuitively reflect the actual state of the safety door, complementing the data collected by the control module and avoiding misjudgment caused by a single sensor failure or false alarm. Through image verification, the system can more accurately identify the opening and closing state of the safety door, timely detect abnormal situations, provide more comprehensive protection for the safe operation of the equipment, and effectively reduce safety risks.

[0017] In some embodiments, the server is also used to: determine the current state of the machine tool as the initial state of the state transition prediction; based on the initial state and a preset Markov model, iteratively perform state transition prediction processing to obtain a state distribution sequence of the machine tool at multiple future time steps; according to the state distribution sequence, determine the fault prediction probability that the machine tool transfers from the current state to the fault state.

[0018] Adopting the technical solution of the above embodiment, the failure probability of the machine tool equipment is predicted through the Markov model, providing forward-looking decision support for equipment maintenance. The server takes the current state of the equipment as the initial state, iteratively performs state transition prediction processing based on the preset Markov model, obtains the state distribution sequence of the equipment at multiple future time steps, and calculates the failure prediction probability. This improvement enables the system to give early warnings of equipment failures, providing sufficient time for maintenance personnel to perform preventive maintenance and avoiding production interruptions and equipment damage caused by sudden failures. By dynamically predicting changes in the equipment state, the system improves the safety and reliability of equipment operation, optimizes the allocation of maintenance resources, reduces maintenance costs, and enhances the scientific nature and efficiency of equipment management.

[0019] In some embodiments, the server is further configured to: determine the state space of the machine tool equipment, where the state space includes multiple operating states of the machine tool equipment, and the operating states include normal state, high-load state, failure state, and maintenance state; determine the number of state transitions between different operating states of the machine tool equipment according to the historical operation data of the machine tool equipment; construct a state transition probability matrix based on the number of state transitions; and construct a Markov model according to the state space, the state transition probability matrix, and the preset initial state distribution data.

[0020] Adopting the technical solution of the above embodiment, the construction process of the Markov model is provided, including determining the state space, counting the number of state transitions, constructing the state transition probability matrix, and finally constructing the Markov model. This improvement provides a solid theoretical basis for the failure prediction function of the system. By clarifying the state space of the equipment, the system can comprehensively cover all stages of equipment operation, ensuring the comprehensiveness of the prediction. Counting the number of state transitions based on historical operation data and constructing the state transition probability matrix enable the system to quantify the laws of equipment state changes and provide an accurate mathematical model for failure prediction. Finally, the Markov model constructed in combination with the initial state distribution data can dynamically simulate the changes in the equipment operation state, providing a scientific basis for failure prediction and maintenance decision-making.

[0021] In some embodiments, the server is further configured to: determine equipment maintenance suggestions according to the failure prediction probability, where the equipment maintenance suggestions include the early maintenance time, maintenance priority, and maintenance resource allocation.

[0022] Adopting the technical solution of the above embodiment further expands the functions of the system. The server generates equipment maintenance suggestions based on the failure prediction probability, including the early maintenance time, maintenance priority, and maintenance resource allocation. This improvement enables the system not only to predict failures but also to provide specific action guidelines for maintenance personnel. By planning the maintenance time in advance, the system can reduce equipment downtime and improve production efficiency. Determining the maintenance priority helps maintenance personnel reasonably arrange the work order, prioritize the processing of high-risk equipment, and ensure the continuity of the production process. At the same time, the suggestion of maintenance resource allocation optimizes the use efficiency of maintenance resources and avoids resource waste. Such maintenance suggestions based on failure prediction provide more scientific and efficient decision-making support for equipment management, significantly enhancing the reliability and operation efficiency of equipment, reducing maintenance costs, and strengthening the practicality and market competitiveness of the system.

[0023] In some embodiments, the server is further configured to: determine the equipment operation performance data of the machine tool equipment according to the safety door switch data, where the equipment operation performance data includes the operation time, downtime, and door switch operation frequency; based on the equipment operation performance data, determine the operation efficiency indicators of the machine tool equipment, where the operation efficiency indicators include the availability and performance efficiency, the availability is the ratio of the actual operation time of the machine tool equipment to the planned production time, and the performance efficiency is the ratio of the actual output of the equipment to the standard output; evaluate the operation efficiency of the machine tool equipment according to the operation efficiency indicators.

[0024] Adopting the technical solution of the above embodiment expands the functions of the system. The server not only collects the safety door switch data but also further calculates the equipment operation performance data, including the operation time, downtime, and door switch operation frequency. Based on these data, the server further determines the operation efficiency indicators of the equipment, such as the availability and performance efficiency. This improvement enables the system to comprehensively evaluate the operation efficiency of the equipment and provide richer data support for equipment management and optimization. By calculating the availability and performance efficiency, the system can help managers timely discover problems in equipment operation, optimize the production process, and improve the overall operation efficiency and production benefits of the equipment.

[0025] In some embodiments, the server is specifically further configured to substitute the operation efficiency indicators into the operation efficiency evaluation formula to calculate the operation efficiency of the machine tool equipment. The operation efficiency evaluation formula includes: where Q represents the operation efficiency, A represents the availability, B represents the performance efficiency, w A and w B are weight factors respectively, and k B represents the smoothing coefficient of the performance efficiency.

[0026] Adopting the technical solution of the above embodiment, the method for evaluating the operation efficiency is further refined. The server substitutes the operation efficiency indicators into a specific operation efficiency evaluation formula to calculate the comprehensive operation efficiency of the device. This formula comprehensively considers two key indicators, namely the availability rate and the performance efficiency, and flexibly adjusts the contributions of different indicators through weight factors and smoothing coefficients. This improvement makes the evaluation of operation efficiency more scientific and reasonable, and can more accurately reflect the actual operation status of the device. By introducing logarithmic functions and saturation functions, the formula can better simulate the law of efficiency change in actual production and avoid the influence of extreme values of a single indicator on the overall efficiency evaluation. This comprehensive evaluation method provides a more accurate decision-making basis for equipment management, helps managers optimize equipment configuration, improve production efficiency, ensure that the equipment operates in the best state, and thus enhances the overall competitiveness of the enterprise.

[0027] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: 1. By introducing a networked architecture of servers, switches, control modules, user terminals, and safety dashboards, this technical solution realizes the centralized management and remote monitoring of cigarette making and packing unit equipment. The control module collects safety door switch data and transmits it to the server. After the server processes the data, it real-time displays the equipment status through the user terminal and the safety dashboard. This architecture not only breaks through the limitations of traditional monitoring methods and avoids the inefficiency of manual on-site inspections, but also significantly improves the safety of equipment operation. Managers can view the equipment status at any time through the user terminal, discover and handle abnormal situations in a timely manner, reduce safety risks caused by equipment failures or operation errors, and at the same time provide data support for equipment management, optimize the production process, and improve production efficiency.

[0028] 2. By using the Markov model to dynamically predict the equipment status, the server calculates the state distribution sequence of multiple future time steps based on the current state and historical operation data of the equipment, and determines the fault prediction probability. Based on the fault prediction probability, the system can generate maintenance suggestions in advance, including the advance maintenance time, maintenance priority, and maintenance resource allocation. This intelligent fault prediction and maintenance management method not only improves the reliability and safety of equipment operation, but also optimizes the allocation of maintenance resources and reduces maintenance costs. By warning of equipment failures in advance, the system provides sufficient time for maintenance personnel to perform preventive maintenance, avoiding production interruptions caused by sudden failures, and significantly enhancing the scientific nature and efficiency of equipment management.

[0029] 3. The present invention not only monitors the opening and closing states of the safety doors, but also calculates the operation performance data of the device through the server, including the running time, downtime, and the frequency of door opening and closing operations. Based on these data, the system further determines the operation efficiency indicators of the device, such as the availability rate and performance efficiency, and calculates the comprehensive operation efficiency of the device through a specific operation efficiency evaluation formula. This comprehensive operation efficiency evaluation method provides a scientific basis for device management and optimization. Managers can understand the actual operation status of the device in real time, promptly discover problems in the device operation, optimize the production process, improve the overall operation efficiency of the device and production benefits. This comprehensive evaluation method not only improves the refined level of device management, but also provides strong support for the production decision-making of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts. In the drawings: Figure 1 is a schematic framework diagram of a safety protection monitoring system for a cigarette making and packing combination unit according to an embodiment of the present invention; Figure 2 is a schematic framework diagram of another safety protection monitoring system for a cigarette making and packing combination unit according to an embodiment of the present invention; Figure 3 is a schematic architecture diagram of a safety protection monitoring system for a cigarette making and packing combination unit according to an embodiment of the present invention; Figure 4 is a working flow chart of a safety protection monitoring system for a cigarette making and packing combination unit according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The terms used in the following embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention, the singular forms "a", "an", "above-mentioned", "the", and "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present invention refers to any or all possible combinations including one or more of the listed items.

[0032] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and should not be construed as implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more.

[0033] It should also be noted that, unless otherwise clearly specified and limited, in the embodiments of the present invention, terms such as "arranged" and "connected" should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two components; it can be a wired communication connection or a wireless communication connection. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The embodiments of the present invention will be specifically described below.

[0034] The embodiments of the present invention provide a safety protection monitoring system for a tipping and packaging machine unit (hereinafter referred to as the system or monitoring system), as Figure 1 shown, including a server 1, a switch 2, a control module 3, a user terminal 4, and a safety dashboard 5.

[0035] Among them, the switch 2 can include, but is not limited to, a layer-2 switch, a layer-3 switch, or other types of switches. In this embodiment, the switch 2 can specifically adopt a layer-3 switch. A layer-3 switch is a network device that integrates layer-2 switching functions and layer-3 routing functions. It can forward data packets quickly and perform routing forwarding according to IP addresses to achieve efficient communication and traffic optimization between different network segments.

[0036] Specifically, the OSI model, that is, the Open Systems Interconnection Model, is a conceptual framework for standardizing network communication processes. It divides network communication into seven different layers, namely the physical layer, the data link layer, the network layer, the transport layer, the session layer, the presentation layer, and the application layer from bottom to top. Each layer has specific functions and is responsible for different network communication tasks. Adjacent layers interact through interfaces, enabling interoperability between different systems. The OSI model provides a theoretical basis for the design of network devices and protocols and helps network engineers understand and build complex network systems.

[0037] The layer-3 switch in this embodiment can forward and process data packets at the third layer of the network (i.e., the network layer of the OSI model), that is, the layer-3 routing function, and determine the best transmission path of data packets according to IP addresses, thereby achieving efficient communication between different network segments.

[0038] The layer 2 switching function refers to the ability of a switch to perform packet switching at the second layer of the OSI model, i.e., the data link layer. A layer 2 switch determines how to forward packets between different devices within a local area network (LAN) by identifying the MAC address (a physical address used to uniquely identify network devices) in the packets. The main functions of a layer 2 switch are to isolate network collision domains, improve network efficiency and speed, and enable fast data frame forwarding, thereby enhancing the overall performance of the LAN.

[0039] The layer 3 switch in this embodiment optimizes network traffic by reducing network congestion and increasing data transmission speed, and is very suitable for use in the network environments of large enterprises or data centers.

[0040] The control module 3 is set on the machine equipment of the cigarette making and packing unit and is used to collect the safety door switch data of the machine equipment. Among them, the safety door switch data includes at least one of the safety door switch status, door switch timestamp, door switch duration, door switch frequency, and the corresponding device identifier.

[0041] The machine equipment is the main production equipment in the cigarette making and packing unit, such as cigarette making machines, tipping machines, packing machines, etc. These equipment jointly complete the entire technological process of cigarette production, packing, and finished product output.

[0042] The control module 3 collects the safety door switch data by connecting to sensors or switches on the equipment safety door. These sensors change their states when the safety door is opened or closed. After the control module 3 detects these state changes, it converts the corresponding switch signals into digital signals and transmits these digital signals to the server 1. The server 1 then processes and analyzes the digital signals to determine the operating state of the machine equipment, and uses the processed information for real-time monitoring, historical record query, statistical analysis, etc., so as to achieve comprehensive monitoring of the safe operation of the equipment.

[0043] Among them, the control module 3 includes but is not limited to a PLC (Programmable Logic Controller) module, a microcontroller (MCU), a programmable automation controller (PAC), and other control circuits.

[0044] In this embodiment, the control module 3 can specifically adopt a PLC module. The PLC module has high reliability and anti-interference ability, can operate stably in a complex industrial environment, ensure the accuracy of the collected data, and provide basic data support for the system's status monitoring and abnormal warning.

[0045] Server 1 is connected to the control module 3 through switch 2 and is used to determine the operating status of the machine equipment based on the safety door switch data.

[0046] In this embodiment, Server 1 is the core processing unit of the safety protection monitoring system for the cigarette making and packing unit, responsible for receiving, storing, and analyzing the safety door switch status data collected from the control module 3. Server 1 is connected to the control module 3 through switch 2, capable of processing a large amount of data in real time, and judging whether the operating status of the equipment is normal according to the preset algorithms and logics. Server 1 also supports the access requests of the user terminal 4, providing functions such as data query, statistical analysis, and early warning information push for the management personnel, and is a key component for the entire system to achieve centralized management and intelligent monitoring.

[0047] The user terminal 4 is connected to Server 1 through switch 2 and is used to monitor the safety door switch data or the operating status of the equipment.

[0048] Among them, the user terminal 4 is the interface for the system to interact with the management personnel. It is connected to Server 1 through the network, allowing users to access the door switch status and operating status information of the equipment anytime and anywhere. The user terminal 4 supports multiple devices such as computers, tablets, or mobile phones, providing an intuitive graphical interface for the management personnel to facilitate data query, statistical analysis, and viewing of early warning information. It also supports remote control functions such as remotely turning on or off the equipment, improving the management efficiency and flexibility, enabling the management personnel to respond in a timely manner to the changes in the equipment status and optimizing the production management. The system of the embodiment of the present invention introduces a networked architecture of Server 1, switch 2, control module 3, and user terminal 4, realizing the centralized management and remote monitoring of the safety door switch status of several pieces of equipment, effectively solving the problems of limited monitoring scope and low monitoring efficiency existing in the traditional monitoring methods. In this embodiment, the control module 3 collects key data such as the safety door switch status, timestamp, duration, frequency, and equipment identification, and uses the switch 2 to transmit the data to Server 1 for centralized processing and analysis, so as to determine the operating status of the machine equipment. This architecture not only breaks the limitations of traditional single-device monitoring but also realizes the remote monitoring function through the user terminal 4, enabling the management personnel to master the operation situation of the equipment in real time without being present at the scene, significantly improving the monitoring efficiency and management flexibility.

[0049] Through the combination of centralized management and remote monitoring, the system not only optimizes the equipment management process but also provides more comprehensive and efficient support for production safety management, reducing the risk of safety accidents caused by equipment failures or operation errors, while reducing the management cost and improving the production efficiency. This innovative monitoring system provides a strong guarantee for the safe operation of the cigarette making and packing unit, with significant technical effects and practical application values.

[0050] The working process of the safety protection monitoring system of the cigarette making and packing combination unit in this embodiment is as follows: First, the control module 3 deployed on the machine tool equipment collects the safety door switch status data in real time, including key information such as the door switch status, timestamp, duration, frequency, and equipment identification. These data are transmitted to the switch 2 through the industrial communication protocol, and the switch 2 is responsible for efficiently forwarding the data to the server 1.

[0051] After receiving the data, the server 1 analyzes the data using the preset algorithms and logic, determines whether the working state of the equipment is normal, and stores the analysis results in the database.

[0052] Meanwhile, the server 1 is connected to the user terminal 4 through the switch 2, providing functions such as data query, statistical analysis, and early warning information push for the management personnel. In addition, the server 1 also transmits the equipment status information to the safety bulletin board 5 set around the machine tool equipment in real time, providing immediate feedback for the on-site operators through an intuitive display method.

[0053] The entire working process realizes the full-chain intelligent monitoring from data collection, transmission, processing to display, ensuring the safety of equipment operation and the efficiency of management.

[0054] In some embodiments, as Figure 2 shown, the system further includes a safety bulletin board 5, which is set in the central control room and used to display the working state of the equipment. Specifically, the safety bulletin board 5 is set in the central control room, connected to the server 1 through the switch 2, and used to display the working state of the equipment and the door switch status information of the safety door in real time. The safety bulletin board 5 provides immediate feedback on the equipment operation for the staff in the central control room through intuitive graphics, text, or color changes, facilitating the quick discovery of abnormal situations and taking measures. The safety bulletin board 5 can intuitively understand the operation status of the entire production line, timely discover and handle equipment abnormalities, and ensure the safety and stability of the production process. The safety bulletin board 5 usually adopts a large screen display for easy viewing from a distance and improving the monitoring efficiency.

[0055] In some embodiments, the system further includes an edge computing module 6, which is respectively connected to the control module 3 and the server 1, used to extract and process the features of the safety door switch data to obtain the door switch feature data, and upload the door switch feature data to the server 1; the server 1 is used to input the door switch feature data into the preset safety door switch recognition model to obtain the door switch behavior recognition result, and determine whether the working state of the equipment is normal according to the door switch behavior recognition result.

[0056] In this embodiment, the edge computing module 6 is a computing unit deployed at the network edge, which is used to perform real-time processing and analysis on device data close to the data source, extract key features and make preliminary decisions, so as to reduce the data transmission volume, reduce latency, and improve the response speed and efficiency of the system.

[0057] Specifically, in the safety protection monitoring system of the cigarette making and packing machine set, the edge computing module 6, as a key component of the system, is deployed between the control module 3 and the server 1. The edge computing module 6 receives the original safety door switch data collected by the control module 3, performs feature extraction processing on these data through the built-in algorithm, extracts representative door switch feature data, such as key indicators like switch frequency, duration, switch interval, etc., and uploads these feature data to the server 1 through the switch 2.

[0058] After receiving the door switch feature data, the server 1 inputs it into a preset safety door switch recognition model. This model is based on machine learning or deep learning algorithms and can identify and classify the door switch behavior to determine whether the switch behavior of the device conforms to the normal operation mode. According to the door switch behavior recognition result output by the safety door switch recognition model, the server 1 further determines whether the working state of the device is normal and triggers an early warning mechanism when detecting abnormal behavior to notify the management personnel for timely handling.

[0059] This process not only improves the data processing efficiency, reduces the computing burden on the server 1 side, but also enhances the system's real-time monitoring and abnormal detection capabilities for the device status.

[0060] In this embodiment, the process of the edge computing module 6 performing feature extraction processing on the safety door switch data is as follows: First, the module receives the original door switch data collected from the control module 3, and these data include information such as the open or closed state of the door, switch timestamp, switch duration, and switch frequency. Subsequently, the edge computing module 6 preprocesses these data, such as removing noise data, filling in missing values, and aligning the timestamps.

[0061] Then, indicators that can reflect the core features of the data are extracted from the preprocessed data, such as calculating statistical features like mean, variance, frequency, duration, etc., or extracting the main components of the data through dimensionality reduction techniques. These extracted features are organized into a numerical vector, that is, a feature vector, which can retain the key information of the original data in a concise form, while removing redundancy and irrelevant information, so as to provide efficient and accurate input for subsequent data analysis, model training, or decision support. These feature vectors can effectively reflect the patterns and rules of the door switch behavior, thus forming the door switch feature data.

[0062] Finally, the edge computing module 6 uploads the extracted door switch feature data to the server 1, providing the basic input for subsequent device status analysis and anomaly detection. This process not only reduces the amount of data transmission but also decreases the computational burden on the server 1 side, improving the overall efficiency and real-time performance of the system.

[0063] In this embodiment, the training process of the security door switch recognition model is based on machine learning or deep learning algorithms, and the specific steps are as follows: 1. Data collection and annotation: First, a large amount of door switch status data, including samples of normal operations and abnormal operations, is collected from the control module 3 of the cigarette making and packaging machine set as training sample data. After being processed by the edge computing module 6, key features such as switch frequency, switch duration, and switch interval are extracted from these data. Subsequently, these data are annotated, with normal operations marked as "normal state" and abnormal operations (such as frequent switching, switching at abnormal times, etc.) marked as "abnormal state", forming the annotated data set required for training.

[0064] 2. Feature engineering: The collected raw data is preprocessed and feature extracted to improve the training effect of the model. The preprocessing steps include data cleaning (removing noise and outliers), normalization (scaling the data to a unified range), etc. Feature extraction extracts feature vectors related to door switch behavior through statistical analysis or mathematical transformation, such as: Switch frequency: The number of switches per unit time.

[0065] Switch duration: The duration of each switch.

[0066] Switch interval time: The interval time between two switches.

[0067] Switch timestamp: The specific time point when the switch occurs.

[0068] These feature vectors will be used as the input data for the model.

[0069] 3. Select a suitable algorithm: According to the complexity of the problem and the characteristics of the data, a suitable machine learning or deep learning algorithm is selected. Common algorithms include: Supervised learning algorithms: such as support vector machine (SVM), decision tree, random forest, etc., which are suitable for classification problems.

[0070] Deep learning algorithms: such as convolutional neural network (CNN) or recurrent neural network (RNN), which are suitable for processing time series data.

[0071] Anomaly detection algorithms: such as Isolation Forest and Autoencoder, are used to detect abnormal behavior patterns.

[0072] 4. Model training: The labeled dataset is divided into a training set and a validation set. The selected algorithm is trained using the training set, and the performance of the model is optimized by adjusting the model's parameters (such as learning rate, number of layers, number of neurons, etc.). During the training process, the model learns the characteristic patterns of normal and abnormal behaviors in the data, so as to be able to distinguish the door switch behaviors in different states.

[0073] 5. Model validation and optimization: The trained model is validated using the validation set, and metrics such as the accuracy, recall rate, and F1 score of the model are evaluated. According to the validation results, the model is adjusted and optimized, for example: Adjust hyperparameters (such as learning rate, regularization coefficient, etc.) to improve the generalization ability of the model.

[0074] Use cross-validation methods to reduce overfitting or underfitting problems.

[0075] Prune or compress the model to improve the running efficiency of the model.

[0076] 6. Model deployment: The verified and optimized security door switch recognition model is deployed to Server 1. During actual operation, Server 1 receives the door switch feature data uploaded by the edge computing module 6, inputs it into the model, quickly outputs the recognition result (normal or abnormal) of the door switch behavior, and determines whether the working state of the device is normal according to the result.

[0077] 7. Continuous learning and update: In order to adapt to changes in the device operating state and new abnormal patterns, the model needs to have the ability of continuous learning. The system can regularly collect new data, retrain the model, or adopt online learning methods to update the model parameters in real time to maintain the accuracy and adaptability of the model.

[0078] Through the above training process, the security door switch recognition model can learn the characteristic patterns of normal and abnormal door switch behaviors, so as to quickly and accurately identify the device state in practical applications and provide strong support for security management.

[0079] In some embodiments, the security dashboard 5 includes a screen wall 51 and a decoder 52. The decoder 52 is connected to the server 1. The decoder 52 is used to decode the device working state and convert it into playable image and video stream data, and transmit the image and video stream data to the screen wall 51 for playback.

[0080] Among them, the screen wall 51 is a large display system composed of multiple display screens, which is used to centrally display the device operation status, monitoring data or other important information, facilitating the intuitive viewing and management by the staff in the central control room.

[0081] The decoder 52 is an electronic device used to convert the encoded data signal (such as device status data) into a playable image or video stream, so as to present intuitive visual information on the display device.

[0082] In this embodiment, the server 1 transmits the device working status data to the decoder 52 through the switch 2. The decoder 52 decodes these data and converts them into playable image or video stream data. Subsequently, the decoder 52 transmits the converted image and video stream data to the screen wall 51, and the screen wall 51 displays the real-time working status of the device in an intuitive visual form, including information such as door switch status and device operation conditions.

[0083] This visual display method facilitates the on-site operators and managers to understand the device operation conditions in real time, discover anomalies in a timely manner and take measures, thereby improving the safety of device operation and management efficiency.

[0084] In some embodiments, the server 1 is also used to store the security door switch data in the database.

[0085] Specifically, the server 1 receives the security door switch status data collected from the control module 3, including key information such as switch timestamps, durations, frequencies, etc. After preliminary processing, these data are organized into a structured format and stored in the database according to the preset database schema, such as MySQL or other relational databases.

[0086] In this way, the system can achieve long-term preservation of the security door switch data, facilitating subsequent historical queries, statistical analysis and backtracking of device status. This data storage mechanism provides a solid data foundation for the intelligent management and decision-making of the system, and also provides strong support for device maintenance and fault troubleshooting.

[0087] In some embodiments, the system further includes a visual sensor 7 for taking images of the security doors of the machine equipment. The visual sensor 7 is connected to the server 1 through the switch 2, and the server 1 is used to verify the security door switch data according to the security door images.

[0088] Among them, for example, the visual sensor 7 can adopt an industrial-grade high-definition camera, which has the characteristics of high resolution, low latency and strong anti-interference ability, and can capture clear images of the security doors in real time, providing accurate visual data for the system to support the verification and monitoring of the door switch status.

[0089] In the safety protection monitoring system of the cigarette making and packing unit, the vision sensor 7 is integrated into the system architecture as an important auxiliary device. The vision sensor 7 is installed near the machine equipment and is used to capture images of the safety door in real time, and capture the opening and closing state of the door and its appearance details. These image data are transmitted to the server 1 through the switch 2, and the server 1 uses image recognition technology to analyze and process the safety door images, so as to verify the safety door switch data collected by the control module 3. For example, when the control module 3 reports that the safety door is in the closed state, the server 1 can further confirm whether the door is indeed completely closed and whether there are any abnormal situations (such as the door is not fully closed or there are foreign objects blocking) by analyzing the images captured by the vision sensor 7.

[0090] This dual verification mechanism not only improves the accuracy of the safety door state monitoring, but also enhances the reliability and security of the system, effectively preventing potential safety hazards caused by sensor failures or false alarms.

[0091] In some embodiments, the server 1 is also used to implement and execute the following steps: (1) Determine the current state of the machine equipment as the initial state of the state transition prediction.

[0092] Specifically, the server 1 first comprehensively judges the current operating state of the machine equipment according to the collected safety door switch data and the vision sensor 7 image information. This current operating state is defined as the initial state of the state transition prediction and is the starting point of the subsequent prediction model. The accurate determination of the initial state is crucial because it directly affects the accuracy of the subsequent state transition prediction. For example, if the current safety door is in the normal closed state and there is no abnormal alarm, the server 1 marks this state as "normal operation" as the initial state, providing a basis for the subsequent state transition prediction.

[0093] (2) Based on the initial state and the preset Markov model, iteratively execute the state transition prediction process to obtain the state distribution sequence of the machine equipment at multiple future time steps.

[0094] Among them, the Markov model is a mathematical model based on state transition probabilities. In this embodiment, the Markov model is used to predict the state changes of the cigarette making and packing unit equipment at future time steps. By analyzing the current state of the equipment and the preset transition probability matrix, the possibility of the equipment transferring from the current state to other states (including the failure state) is calculated, so as to realize the dynamic prediction of the equipment operation trend and the fault warning.

[0095] Specifically, the server 1 utilizes a preset Markov model and starts from the initial state to iteratively execute state transition prediction processing. The Markov model describes the possibility of the device transitioning between different states through a pre-calculated state transition probability matrix. At each time step (a time step refers to dividing time into discrete interval units in time series analysis or state prediction to describe the process of the system state changing over time), the server 1 calculates the probabilities of the various states that the device may enter at the next time step based on the current state and the transition probability matrix, and records these probabilities.

[0096] Through multiple iterations, the server 1 can generate a state distribution sequence of the machine tool equipment at multiple future time steps. The state distribution sequence not only shows the possible states of the device at each time step but also provides the probability distribution of each state, providing a quantitative description of the future operation trend of the device.

[0097] (3) Determine the fault prediction probability of the machine tool equipment transitioning from the current state to the fault state according to the state distribution sequence.

[0098] Specifically, based on the generated state distribution sequence, the server 1 further analyzes the probability of the device transitioning from the current state to the fault state. In the state distribution sequence, the fault state is specially marked, and the server 1 calculates the probabilities of the device entering the fault state at various future time steps through statistical analysis. This fault prediction probability provides an important basis for equipment maintenance and safety management. For example, if the fault prediction probability significantly increases at a certain time step, the management can take preventive maintenance measures in advance to avoid production interruptions or safety accidents caused by equipment failures. In this way, the system can not only monitor the device state in real time but also give early warnings of potential faults, significantly improving the safety and reliability of the device operation.

[0099] In some embodiments, the server 1 is also used to implement and execute the following steps: (11) Determine the state space of the machine tool equipment, where the state space includes multiple operating states of the machine tool equipment.

[0100] Among them, the operating states include the normal operating state (the device operates stably according to the predetermined parameters), the high-load state (the device operates beyond the normal load but has not failed), the fault state (the device has an abnormality and cannot work properly), and the maintenance state (the device is in the stage of maintenance or repair).

[0101] First, it is necessary to clarify the state space of the machine tool equipment, that is, the set of all possible operating states of the device. The state space includes multiple specific states, such as the normal operating state, the high-load state, the fault state, and the maintenance state. By defining these states, the system can comprehensively classify and monitor the operation of the device, providing a basis for subsequent state transition analysis and prediction.

[0102] (12) Determine the number of state transitions between different operating states of the machine equipment based on the historical operating data of the machine equipment.

[0103] Specifically, before constructing the state transition model, it is necessary to collect and analyze the historical operating data of the machine equipment to determine the number of transitions between different operating states. First, collect the historical operating data of the equipment, which should include the state records of the equipment at each time point, such as normal operation, high load, failure, or maintenance, etc. Then, perform time series analysis on these data to count the frequency of the equipment transitioning from one state to another. For example, by traversing the historical data, calculate the number of times the equipment transitions from the "normal operation" state to the "high load" state, and the number of times it transitions from the "high load" state to the "failure" state, etc. These statistical results reflect the transition rules of the equipment between different states and provide key data support for constructing the subsequent state transition probability matrix.

[0104] (13) Construct a state transition probability matrix based on the number of state transitions.

[0105] Among them, the state transition probability matrix is a two-dimensional array used to describe the probability of the system's machine equipment transitioning between different operating states. Each element represents the probability of the machine equipment transitioning from one state to another state, which is the core component of the Markov model and is used to quantify the dynamic behavior and state change rules of the machine equipment.

[0106] Specifically, by dividing the number of each state transition by the total number of occurrences of that state, the probability of each state transition can be calculated. For example, if the number of times the equipment transitions from the normal state to the high load state is 10 times, and the total number of occurrences of the normal state is 100 times, then the probability of transitioning from the normal state to the high load state is 0.1.

[0107] After that, fill these calculated probability values into the matrix to obtain the state transition probability matrix.

[0108] (14) Construct a Markov model based on the state space, state transition probability matrix, and the preset initial state distribution data.

[0109] Among them, the initial state distribution data describes the probability distribution of the equipment being in each state at the initial moment. Specifically, by integrating the state space, transition probability matrix, and initial state distribution (such as 90% probability of being in the normal state when the equipment starts), a complete Markov model is formed.

[0110] The Markov model follows the "memoryless" assumption, that is, the next state depends only on the current state. For example, if the device is currently in a high-load state, the model predicts the next state based on the probability distribution of the high-load row in the matrix (such as [0.2, 0.6, 0.1, 0.1]), without considering the previous state history.

[0111] The Markov model utilizes the historical operation data and state transition rules of the device, providing a dynamic and probabilistic prediction method for the system. This enables managers to understand the operation trend of the device in advance, take timely measures to avoid failures, and thus improve the safety and reliability of the device operation.

[0112] In some embodiments, the server 1 is further configured to: determine device maintenance suggestions according to the failure prediction probability, and the device maintenance suggestions include the advance maintenance time, maintenance priority, and maintenance resource allocation.

[0113] Specifically, the server 1 will calculate the failure prediction probability based on the Markov model and combine it with a preset threshold to judge the possibility of the device entering the failure state. If the failure prediction probability exceeds the set threshold, the system will trigger maintenance suggestions. The maintenance suggestions include three aspects: advance maintenance time, maintenance priority, and maintenance resource allocation. The advance maintenance time is determined based on the growth trend of the failure probability and the reliability requirements of the device operation. It is recommended to perform maintenance within a reasonable time before the failure occurs to avoid sudden failures. The maintenance priority is sorted according to the high or low failure probability and the importance of the device, and high-probability failures and key devices are given priority. The maintenance resource allocation considers the urgency of the maintenance task and the availability of resources, and reasonably arranges manpower, material resources, and time to ensure the efficient execution of the maintenance work. In this way, the system can provide scientific guidance for device maintenance, optimize the maintenance plan, and improve the reliability and operation efficiency of the device.

[0114] In some embodiments, the method for the server 1 to predict the failure probability of the machine tool equipment through the Markov model is as follows: S1, define the state space: First, clarify the state space of the machine tool equipment, that is, all possible operating states of the device. These states usually include normal operating state, high-load state, failure state, and maintenance state, etc. The definition of the state space provides a basic framework for subsequent state transition analysis.

[0115] S2, collect historical operation data: The server 1 collects historical data from the device operation process. These data record the state changes of the device at different time points, such as switching from the normal operating state to the high-load state, or from the high-load state to the failure state, etc. These data are the key inputs for constructing the state transition probability matrix.

[0116] S3, count the number of state transitions: Analyze the collected historical operation data and count the number of transitions between different states of the device. For example, count the number of times the device transitions from the normal state to the high-load state, and the number of times it transitions from the high-load state to the failure state, etc. These transition counts reflect the state change patterns of the device during actual operation.

[0117] S4. Construct the state transition probability matrix: Based on the state transition counts, calculate the probability of each state transitioning to other states. Specifically, divide the number of times of each state transition by the total number of occurrences of that state to obtain the state transition probability matrix. This matrix describes the probabilities of the device transitioning between different states and is the core part of the Markov model.

[0118] S5. Determine the initial state distribution: Based on the current state or historical data of the device, determine the initial state distribution. The initial state distribution describes the probabilities of the device being in each state at the initial moment. For example, the probability of the device being in the normal state at the initial moment is 0.8, the probability of the high-load state is 0.1, and the probability of the failure state is 0.05, etc.

[0119] S6. Iteratively perform state transition prediction: Server 1 uses the Markov model to iteratively perform state transition prediction processing based on the initial state and the state transition probability matrix. Starting from the initial state, calculate the state distribution of the device at each future time step according to the state transition probability matrix. Through multiple iterations, generate a sequence of state distributions of the device at multiple future time steps.

[0120] S7. Calculate the failure prediction probability: In the generated sequence of state distributions, pay special attention to the probability of the failure state. Server 1 counts the probabilities of the device entering the failure state at each future time step to obtain the failure prediction probability. If the failure prediction probability increases significantly at a certain time step, it indicates that the device may fail at that time step.

[0121] S8. Generate early warnings and maintenance suggestions: Based on the failure prediction probability, Server 1 generates early warning signals to remind the management of the time points when the device may fail. At the same time, combining the failure prediction probability and the device operation performance data, Server 1 provides maintenance suggestions, including the early maintenance time, maintenance priority, and maintenance resource allocation, etc., to help the management take preventive measures in advance to avoid production interruptions caused by device failures.

[0122] Through the above method process, Server 1 can dynamically predict the failure probability of the machine tool equipment using the Markov model, providing strong support for the preventive maintenance and safety management of the equipment.

[0123] In some embodiments, the server 1 is further configured to implement and execute the following steps: (21) Determine the equipment operation performance data of the machine equipment according to the safety door switch data.

[0124] Among them, the equipment operation performance data includes operation time, downtime, and door switch operation frequency.

[0125] The server 1 calculates the operation performance data of the machine equipment by analyzing the collected safety door switch data. These data include the actual operation time of the equipment (the time when the equipment is in the operation state), the downtime (the time when the equipment stops running due to faults or maintenance), and the door switch operation frequency (the number of door switches per unit time). The door switch data can indirectly reflect the operation state of the equipment. For example, frequent door switches may mean frequent equipment downtime or frequent operations, thus affecting the overall operation performance of the equipment.

[0126] Based on these data, the server 1 can provide basic information for subsequent operation efficiency evaluation, helping management personnel understand the actual operation situation of the equipment.

[0127] (22) Determine the operation efficiency indicators of the machine equipment based on the equipment operation performance data.

[0128] Among them, the operation efficiency indicators include availability and performance efficiency.

[0129] Availability is measured by the ratio of the actual operation time of the equipment to the planned production time, which reflects the available degree of the machine equipment and shows the proportion of the machine equipment that can operate normally within the planned time. Generally, the actual operation time of the equipment will not exceed the planned production time.

[0130] Performance efficiency is the ratio of the actual output of the equipment to the standard output, which reflects the production efficiency of the machine equipment during operation and is used to evaluate whether the production efficiency of the machine equipment during operation reaches the expected standard.

[0131] Through these operation efficiency indicators, the server 1 can comprehensively evaluate the operation status of the machine equipment and provide data support for optimizing the production process and improving equipment performance.

[0132] (23) Evaluate the operation efficiency of the machine equipment according to the operation efficiency indicators.

[0133] Specifically, based on the calculated operation efficiency indicators, the server 1 comprehensively evaluates the operation efficiency of the machine equipment. By analyzing the availability, it can be judged whether the downtime of the equipment is too much, thus affecting the execution of the production plan; the performance efficiency indicator can reveal whether there are problems of low efficiency during the operation of the equipment, such as equipment faults, improper operations, or process problems.

[0134] Combining these metrics, Server 1 can generate a detailed evaluation report, providing a scientific basis for equipment maintenance, optimization, and management, and helping to improve the overall operating efficiency and production benefits of the cigarette making and packing unit.

[0135] In some embodiments, Server 1 is further specifically configured to substitute the operating efficiency metrics into the operating efficiency evaluation formula to calculate the operating efficiency of the machine equipment. The operating efficiency evaluation formula includes: where Q represents the operating efficiency, A represents the availability, B represents the performance efficiency, w A and w B are weight factors respectively, and k B represents the smoothing coefficient of the performance efficiency.

[0136] In this operating efficiency evaluation formula, the availability A is non-linearly transformed through the sine function, such that the impact of the availability on the operating efficiency is smaller at low availability and larger at high availability. The weight factor w A is used to adjust the importance of the availability in the operating efficiency evaluation, enabling the formula to flexibly adapt to different production requirements and equipment characteristics. This design not only considers the non-linear impact of the availability but also provides a flexible adjustment ability through the weight factor, making the operating efficiency evaluation more scientific and reasonable.

[0137] The logarithmic form w B ·ln(1 + k B ·B) is adopted in the formula to reflect the law of diminishing marginal contribution of the performance efficiency to the operating efficiency. When the performance efficiency is low, each unit increase has a greater contribution to the operating efficiency; while when the performance efficiency approaches the standard value, the marginal contribution of further improvement gradually decreases. This logarithmic relationship is more in line with the difficulty and effect of equipment performance improvement in actual production.

[0138] The weight factors w A and w B are used to balance the contributions of different metrics to the operating efficiency. In actual production, the importance of different metrics may vary. For example, the availability may have a greater impact on the production plan. By adjusting the weight factors, Server 1 can flexibly adjust the contribution degrees of various metrics according to actual needs, making the operating efficiency evaluation more targeted and adaptable.

[0139] The smoothing coefficient k B is used to adjust the contribution curve of the performance efficiency. k B can be adjusted according to the specific characteristics of the equipment and production requirements, enabling the formula to better reflect the efficiency change law in actual production. For example, for some equipment, the improvement of the performance efficiency may be more likely to reach a saturation state. At this time, by adjusting k BTo change the smoothness of the logarithmic curve.

[0140] In some embodiments, the system adopts a B / S (Browser / Server 1) architecture and constructs a system platform by combining Asp.Net technology and a MySQL database. Asp.Net is used as the website development language to develop the user interface and business logic, providing efficient and dynamic web page interaction functions; while MySQL serves as the database management system, responsible for storing and managing the safety door switch signal data, user information, and machine-related data. The server 1 software collects the safety door switch signal data transmitted by the network acquisition control module 3 and stores it in a structured manner in the MySQL database. At the same time, the server 1 is also responsible for managing user permissions and device information to ensure the security and scalability of the system. Management personnel can log in to the system by accessing a specified website address to view the device status and monitoring data. In addition, the system supports projecting the data onto a safety dashboard, converting the data into an image or video stream through a decoder to achieve real-time visual display, facilitating the intuitive monitoring of the device operation by the personnel in the central control room. This architecture not only improves the flexibility and usability of the system but also enhances the efficiency and security of device management through networking and visualization means.

[0141] The system realizes the remote monitoring and management of the machine operation through the B / S architecture constructed by adopting Asp.Net technology and a MySQL database. Safety administrators, production team leaders, safety section chiefs, and other leaders in the cigarette factory do not need to conduct on-site inspections. They only need to access the specified WEB page through an office computer or view the safety production dashboard to understand the opening and closing status of the machine doors and the current operation situation in real time. Compared with the traditional configuration screen method, the system in this embodiment can increase the door opening and closing records from the original thousands to up to 2 years (configurable) and supports historical query, statistics, and analysis functions, providing more comprehensive maintenance and data support for management personnel and significantly improving the monitoring efficiency and the scientific nature of management decisions.

[0142] In some embodiments, the specific architecture of the safety protection monitoring system for the cigarette making and packing unit is as Figure 3 shown. Among them: The server is the core of the entire system, responsible for data processing and storage. The server is connected to the PLC module through the network, receives the safety door switch data from the PLC, and analyzes and stores it.

[0143] Safety production network: The entire system architecture is in a safety production network to ensure the security and reliability of data transmission.

[0144] The three-layer switch connects the server and the PLC module, responsible for the high-speed forwarding and routing selection of data packets to optimize the network performance.

[0145] PLC modules (including multiple ones, numbered PLC1 to PLCN respectively): The PLC modules are installed on each machine tool device, responsible for collecting the switch status data of the safety doors and sending the data to the server. Each PLC module can manage multiple safety switches (1 to N) and monitor the real-time status of the safety doors.

[0146] The safety switch is a safety sensor installed on the door of the cigarette making and packing unit, used to detect the opening and closing status of the door and send signals to the PLC module.

[0147] Web access clients (1 to N) are included in the user terminals: Management personnel can access the Web program on the server through the Web access clients (such as computers, tablets or mobile phones) to achieve remote monitoring and management of the device status. The clients are connected to the server through the network and can view the switch status, historical records and statistical analysis data of the device in real time.

[0148] The video wall and decoder are used to display the real-time status of the devices at the production site. The decoder converts the data in the server into an image or video stream and transmits it to the video wall for playback, facilitating the on-site operators to intuitively understand the operation of the devices.

[0149] The real-time monitoring console is a management terminal for on-site monitoring, which can be connected to the video wall and decoder to view the device status in real time.

[0150] For the working process of the safety protection monitoring system of the cigarette making and packing unit in this embodiment, reference can also be made to Figure 4 , specifically as follows: 1) System startup and initialization: After the monitoring system starts, initialization operations are first carried out. The PLC module starts to process the switch signals of the safety doors, and at the same time the safety interlock mechanism is activated to ensure that the switch status of the safety doors is consistent with the safety requirements. The server also starts to run, ready to collect the switch signals transmitted by the PLC module.

[0151] 2) The PLC module collects switch signals: The PLC module is installed on the machine tool device and collects the switch status signals of the safety doors in real time. These signals include key information such as the opening and closing status (closed / open) of the door, timestamp, switch duration, switch frequency, etc. The PLC module performs preliminary processing on these signals to ensure the accuracy and integrity of the data.

[0152] 3) The server collects and processes data: The server is connected to the PLC module through the network and collects the processed switch signals in real time. After receiving the data, the server first determines whether the switch status is normal (closed / open / abnormal). If an abnormal status is detected (such as frequent switching or switching at non-normal times), the system will immediately generate a record and trigger an alarm.

[0153] 4) Data storage and update: The server stores the collected switch status data in the database and updates the real-time status of the device simultaneously. The database is used to store the operation records of the device in the long term, including the historical data of the switch status. These data are not only used for real-time monitoring but also support subsequent historical query, statistics, and analysis functions.

[0154] 5) Real-time monitoring and display The server realizes the real-time monitoring of the device status through a Web program. Managers can access the Web program through a Web terminal (such as a computer, tablet, or mobile phone) to view the real-time status and historical records of the device. The core functions of the system include real-time monitoring, historical record query, statistics, and analysis.

[0155] 6) Video wall and decoder: For on-site monitoring requirements, the system is equipped with a video wall and a decoder. The decoder converts the device status data in the server into an image or video stream and transmits it to the video wall for playback. The video wall visually displays the real-time operation status of the device, facilitating on-site operators and managers to view it in real time.

[0156] 7) User access and interaction: Users can access the system through a Web terminal and call the Web program to view the device status. The system supports users to access different function modules according to their permissions, such as real-time monitoring, historical record query, statistical analysis, etc. Users can also receive the alarm information generated by the system through the Web interface and take corresponding measures according to the prompts.

[0157] 8.) Implementation of core functions: The core functions of this system include: Real-time monitoring: The switch status of the device is displayed in real time through the Web program and the video wall.

[0158] Historical record query: Users can query the historical switch records of the device to understand the operation trend of the device.

[0159] Statistics and analysis: The system conducts statistical analysis on the switch status data of the device, generates reports and charts, and helps managers optimize the device management strategy.

[0160] 9) System operation and maintenance: The system continuously collects and processes data during operation to ensure the real-time update of the device status. At the same time, the system conducts self-check and maintenance regularly to ensure the stability and reliability of the system. Managers can optimize the maintenance plan and production process of the device based on the data support provided by the system.

[0161] Through the above process, the safety protection monitoring system of the cigarette making and tipping unit realizes the comprehensive monitoring and management of the safety door switch state, improving the safety of equipment operation and management efficiency.

[0162] The system of this embodiment effectively solves the limitations of traditional physical contact sensor monitoring, realizing the centralization, intelligence and real-time of equipment safety protection: First, the global data acquisition and network transmission break the isolation of traditional stand-alone monitoring. Traditional technologies rely on the simple contact signal acquisition of local PLCs (such as only recording the door open / closed state), while this system expands the PLC module to collect the door switch timestamp (accuracy ±1ms), duration (resolution 0.1 second), operation frequency (times / minute) and the unique equipment identification code, forming a multi-dimensional data matrix. For example, a certain unit generates 2,000 door switch event records (including timestamp and equipment ID) in a single day, and transmits them to the server through the industrial Ethernet protocol of a three-layer switch (supporting the IEEE 802.3 standard) with a delay of ≤10ms. Compared with the traditional RS485 bus series architecture (delay >200ms), the data real-time performance is improved by more than 20 times, laying a foundation for centralized management.

[0163] Secondly, the multi-dimensional state modeling on the server side solves the defect of rough determination of traditional local logic. Traditional methods only trigger shutdown based on a single door state, while the server of this system uses a dynamic threshold algorithm (such as sliding window statistics) to analyze the correlation between the door switch frequency and the process beat: when the door switch frequency of a certain unit exceeds 3 times the standard deviation of the mean value of the same production line (such as the normal mean value of 5 times / hour, abnormal value >18 times / hour) and the duration >30 seconds, it is determined as an abnormal operation; at the same time, through the equipment ID, it is associated with the production database (such as the MES system), automatically tracing the operator's work number and equipment maintenance records, forming a fault root cause analysis chain. The actual deployment data shows that this algorithm reduces the false alarm rate from 21% of the traditional solution to 4.5%.

[0164] Furthermore, the remote-local collaborative monitoring system overcomes the efficiency bottleneck of traditional manual patrols. The user terminal accesses the server through the HTTPS protocol, supporting multi-dimensional data visualization (such as the heat map of door switch operations, the curve of equipment health index), and managers can remotely issue maintenance instructions; the on-site safety bulletin board uses an industrial-grade high-brightness LED screen (brightness ≥1500cd / m 2 ) to display the equipment status in real time (such as "The door of Unit 1 is not locked - it has lasted for 25 seconds") and trigger an audible and visual alarm (105dB buzzer + red strobe), reducing the abnormal response time from the average of 42 minutes in the traditional mode to within 3 minutes. The application case of a cigarette factory shows that this system reduces the unplanned shutdown rate of equipment by 57% and reduces annual safety accidents by 82%.

[0165] In summary, the system of this embodiment upgrades the traditional single-point passive protection to a full-domain active security system through the technical loop of high-precision data acquisition - intelligent status analysis - full-scenario monitoring response, achieving a leapfrog improvement in equipment management efficiency and security level.

[0166] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A safety protection monitoring system for a roll-to-roll packaging machine unit, characterized in that: Including servers, switches, control modules and user terminals; The control module is arranged on a machine device of the roll-to-roll packaging unit, and is used to collect safety door switch data of the machine device, wherein the safety door switch data includes at least one of a safety door switch state, a door switch timestamp, a door switch duration, a door switch frequency, and a corresponding device identifier; The server is connected to the control module via the switch, and is used to determine the equipment working status of the machine equipment according to the safety door switch data; The user terminal is connected to the server via the switch and is used to monitor the safety door switch data or the working status of the device.

2. The system according to claim 1, characterized in that It also includes an edge computing module, which is connected to the control module and the server respectively, and is used to perform feature extraction processing on the security door switch data to obtain door switch feature data, and upload the door switch feature data to the server; The server is used to input the door switch feature data into a preset safety door switch identification model to obtain a door switch behavior identification result, and determine whether the working state of the device is normal according to the door switch behavior identification result.

3. The system according to claim 1, characterized in that The safety signboard includes a screen wall and a decoder, wherein the decoder is connected to the server, and is used to decode the working status of the device and convert it into playable image and video stream data, and transmit the image and video stream data to the screen wall for playback.

4. The system according to claim 1, characterized in that It also includes a safety signboard, which is arranged in a central control room and is used to display the working status of the equipment.

5. The system according to claim 1, characterized in that It also includes a visual sensor for capturing an image of a security door of the machine equipment. The visual sensor is connected to the server via the switch. The server is used to verify the security door switch data according to the security door image.

6. The system according to any one of claims 1 to 5, characterized in that: The server is also used to: Determine the current state of the machine equipment as the initial state for state transition prediction; Based on the initial state and the preset Markov model, iteratively perform state transition prediction processing to obtain a state distribution sequence of the machine equipment in multiple future time steps; According to the state distribution sequence, a failure prediction probability of the machine equipment transferring from the current state to a failure state is determined.

7. The system according to claim 6, characterized in that The server is also used to: Determine a state space of the machine equipment, the state space including a plurality of operating states of the machine equipment, the operating state including a normal state, a high load state, a fault state and a maintenance state; Determining the number of state transitions of the machine device between different operating states according to the historical operating data of the machine device; Constructing a state transition probability matrix based on the state transition times; The Markov model is constructed according to the state space, the state transition probability matrix and preset initial state distribution data.

8. The system according to claim 6, characterized in that The server is also used to: An equipment maintenance suggestion is determined according to the fault prediction probability, and the equipment maintenance suggestion includes an advance maintenance time, a maintenance priority, and a maintenance resource allocation.

9. The system according to claim 1, characterized in that The server is also used to: Determine the equipment operation performance data of the machine equipment according to the safety door switch data, wherein the equipment operation performance data includes operation time, downtime and door switch operation frequency; Based on the equipment operation performance data, determine the operation efficiency index of the machine equipment, the operation efficiency index includes availability and performance efficiency, the availability is the ratio of the actual operation time of the machine equipment to the planned production time, and the performance efficiency is the ratio of the actual output of the equipment to the standard output; The operating efficiency of the machine equipment is evaluated according to the operating efficiency index.

10. The system according to claim 9, characterized in that The server is further specifically configured to substitute the operating efficiency index into an operating efficiency evaluation formula to calculate the operating efficiency of the machine device, wherein the operating efficiency evaluation formula includes: Wherein, Q represents the operation efficiency, A represents the availability, B represents the performance efficiency, and w A 、w B are weight factors, k B A smoothing factor representing performance efficiency.

Images