Intelligent operation and maintenance management and control method and system for high-speed production line of cigarette factory

Abstract

The invention belongs to the technical field of product management and control and information, and provides an intelligent operation and maintenance management and control method and system for a high-speed production line of a cigarette factory, and the method comprises the steps: obtaining the original data of production line equipment in real time, synchronously integrating main data from an upstream system, and constructing a basic data set; a built-in algorithm is used for carrying out real-time monitoring and predictive early warning on the health state of the equipment; dynamically generating a maintenance plan and an alternate protection plan based on the real-time operation duration of the equipment, the health score and a predefined strategy; issuing the maintenance plan or the alternate protection plan through a cloud-edge-end architecture, executing and recording key information according to a standard; an execution result and key information are fed back, and multi-dimensional visual analysis is carried out; and on the basis of historical data and an analysis result, continuously optimizing a maintenance strategy and an early warning threshold value, and forming a self-learning optimization closed loop. According to the method, traditional post-maintenance or fixed-period preventive maintenance can be converted into predictive maintenance based on the actual state of the equipment, the system reliability is high, and the operation and maintenance management and control efficiency is high.

Description

Technical Field

[0001] This application relates to the fields of product control and information technology, and in particular to an intelligent operation and maintenance control method and system for high-speed production lines in cigarette factories. Background Technology

[0002] Currently, various cigarette factories in China have developed a variety of intelligent operation and maintenance methods to improve equipment management. For example, patent application CN115660649A discloses an intelligent on-site inspection and maintenance management system for cigarette factories. This system includes a maintenance database that uniformly stores maintenance plans, standards, and records, and uses electronic tags for organization and management. The database is connected to several handheld terminals via a wireless LAN. It also includes built-in modules for flexible equipment inspection, equipment inspection prompts, repair and replacement records, equipment inspection check-in, and equipment status early warning. As a handheld intelligent management system for on-site inspection and maintenance, this system can assist repair personnel in completing targeted and focused on-site inspections while also considering actual production schedules. It provides real-time recording and intelligent fault warnings for on-site repairs, helping to make on-site equipment management more scientific, orderly, and intelligent, effectively solving problems such as inadequate on-site management and strong subjectivity.

[0003] For example, Shaanxi China Tobacco Baoji Cigarette Factory disclosed the application of an intelligent maintenance model in the maintenance of tobacco packaging equipment. Its technical solution usually covers key aspects such as data collection and storage, intelligent maintenance evaluation algorithm, evaluation result generation, maintenance plan docking, and visualization display.

[0004] However, most of the aforementioned existing technologies are planned or preventative maintenance, with a core focus on plan-driven approaches. This approach has significant limitations. The core problem lies in the fact that these methods largely rely on threshold alarm mechanisms, essentially a "passive response" mode. The system only triggers alarms when equipment parameters exceed limits or a fault has already occurred, prompting maintenance personnel to intervene. This leads to insufficient anticipation of potential faults.

[0005] Specifically, this limitation manifests in two aspects: First, at the state perception level, existing methods lack in-depth monitoring and trend analysis of the real-time operating status of equipment, and cannot provide early warning of the decline in equipment health; second, at the decision-making mechanism level, the generation of maintenance tasks is often based on fixed cycles or simple rules, rather than the real-time health status and predictive models of the equipment, thus failing to achieve true predictive maintenance, making it difficult to effectively avoid unplanned downtime, and leaving room for improvement in the accuracy and efficiency of maintenance.

[0006] Therefore, the industry urgently needs to evolve towards a more advanced intelligent operation and maintenance model with real-time status monitoring, predictive early warning, and dynamic decision-making capabilities, thereby achieving a fundamental shift from passive alarms to proactive prediction. Summary of the Invention

[0007] To address the shortcomings of existing technologies, this invention provides an intelligent operation and maintenance management method and system for high-speed production lines in cigarette factories. It can transform traditional reactive maintenance or fixed-cycle preventive maintenance into predictive maintenance based on the actual condition of the equipment. The system has high reliability and high operation and maintenance management efficiency.

[0008] To achieve the above and related objectives, the present invention employs the following technical means:

[0009] The first aspect of this invention provides an intelligent operation and maintenance management method for high-speed production lines in cigarette factories, comprising the following steps:

[0010] Step S100: Acquire raw data from production line equipment in real time and synchronously integrate master data from upstream systems to build a basic dataset;

[0011] Step S200: Based on the basic dataset, use the built-in algorithm to monitor and predict the health status of the equipment in real time; based on the real-time running time of the equipment, health score and predefined strategies, dynamically generate maintenance plans and rotation maintenance plans;

[0012] Step S300: Distribute the maintenance plan or rotational maintenance plan through the cloud-edge-device architecture, execute it according to the standard, and record key information;

[0013] Step S400: Feedback on execution results and key information, and conduct multi-dimensional visualization analysis; based on historical data and analysis results, continuously optimize maintenance strategies and early warning thresholds to form a self-learning optimization loop.

[0014] Furthermore, in step S100, the raw data includes vibration audio data, equipment operating parameters, product rejection data, and energy and material consumption data; the master data includes equipment information, bill of materials, maintenance strategy templates, and personnel and organization data.

[0015] Furthermore, in step S200, the predictive early warning includes: using a built-in algorithm to dynamically determine whether the current basic dataset meets any or all of the early warning conditions. If it does, an early warning is automatically triggered. The early warning conditions include: within a set monitoring period, the key parameters of the equipment exceed the preset normal fluctuation range; within a set statistical period, the cumulative product rejection rate of the equipment exceeds the preset installation threshold.

[0016] Furthermore, in step S200, the maintenance plan includes daily inspection tasks, periodic lubrication tasks, and comprehensive maintenance tasks.

[0017] Furthermore, in step S200, the maintenance plan includes basic plan information, associated equipment information, maintenance task information, execution and feedback information, associated documents and remarks.

[0018] Furthermore, in step S300, the cloud-edge-device architecture includes:

[0019] The central management layer is used for centralized monitoring and decision-making, strategy formulation and management, and data storage and analysis optimization.

[0020] The local aggregation and processing layer is used for data aggregation and preprocessing, real-time control and task dispatch, and network redundancy protection.

[0021] The on-site execution layer is used for data collection, task execution, and result feedback.

[0022] Furthermore, in step S300, the key information includes task execution status information, operation process and resource information, timestamp and responsible person information, and auxiliary proof and explanation information.

[0023] Furthermore, the built-in algorithm includes calculating vibration characteristic values ​​based on vibration audio data.

[0024] Furthermore, in step S400, the multi-dimensional visualization analysis includes time dimension, equipment and production line dimension, indicator type dimension, workstation and cause dimension, and task execution dimension.

[0025] A second aspect of this invention provides an intelligent operation and maintenance management system for high-speed production lines in cigarette factories, comprising:

[0026] The data acquisition and synchronization module is used to acquire raw data from production line equipment in real time and synchronize and integrate master data from upstream systems to build a basic dataset.

[0027] The early warning and plan generation module is used to monitor and predict the health status of equipment in real time based on a basic dataset and using built-in algorithms; it dynamically generates maintenance plans and rotation maintenance plans based on the real-time running time of the equipment, health scores and predefined strategies.

[0028] The plan distribution and execution module is used to distribute maintenance plans or rotational maintenance plans through a cloud-edge-device architecture, execute them according to standards, and record key information.

[0029] The data analysis and optimization module is used to provide feedback on execution results and key information, and to perform multi-dimensional visualization analysis. Based on historical data and analysis results, it continuously optimizes maintenance strategies and early warning thresholds, forming a self-learning optimization loop.

[0030] The beneficial technical effects of this invention are as follows:

[0031] This invention changes the traditional fixed-cycle planned maintenance model, realizing dynamic maintenance plan generation and optimized scheduling of rotation maintenance plans based on the real-time status of equipment. It can intelligently recommend rotation maintenance plans, making maintenance work more targeted and efficient. This invention adopts a cloud-edge-device architecture based on the Industrial Internet, ensuring the intelligence of central management while meeting the requirements of real-time performance and network outage tolerance in industrial settings.

[0032] This invention deeply integrates real-time equipment health status monitoring with maintenance / rotational maintenance services. Through predictive early warning, it enables predictive maintenance, allowing for earlier and more accurate identification of potential equipment failures and proactive intervention.

[0033] This invention can realize a closed-loop data-driven process that integrates data collection, task execution, result analysis, and strategy optimization. Data from each stage is recorded, ensuring the traceability of the maintenance / rotational maintenance process and providing a data foundation for continuous optimization.

[0034] This invention enables intelligent maintenance and rotational management of various equipment on high-speed production lines in cigarette factories, achieving proactive early warning, multi-dimensional in-depth analysis, and improved system configurability, thereby enhancing the refinement and intelligence of production management and the ability to proactively respond to risks.

[0035] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0036] The accompanying drawings, incorporated in and forming part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without inventive effort. In the drawings:

[0037] Figure 1 This is a flowchart of the intelligent operation and maintenance management method for high-speed production lines in cigarette factories, as described in this application.

[0038] Figure 2 This is a framework diagram of the intelligent operation and maintenance management system for high-speed production lines in cigarette factories, as described in this application. Detailed Implementation

[0039] Unless otherwise defined, all technical and / or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should be understood that certain features of the invention (described in the context of separate embodiments for clarity) may also be provided in a single embodiment. Conversely, multiple features of the invention (described in the context of a single embodiment for brevity) may also be provided separately or in any suitable combination or, where appropriate, in any other described embodiment of the invention. Certain features described in the context of various embodiments will not be considered essential features of those embodiments unless the embodiment is inoperable without those elements. The invention is further illustrated below by specific examples; however, it should be noted that the specific process conditions and results described in the embodiments of the invention are merely illustrative and should not be construed as limiting the scope of protection of the invention. All equivalent changes or modifications made in accordance with the spirit and essence of the invention should be covered within the scope of protection of the invention.

[0040] Please see Figure 1 The flowchart of the intelligent operation and maintenance management method for high-speed production lines in cigarette factories, as described in this application, is as follows:

[0041] Step S100: Acquire raw data from production line equipment in real time and synchronously integrate master data from upstream systems to build a basic dataset.

[0042] Specifically, this application collects raw data in real time from equipment on the production line, such as the sensors and control boards of packaging machines ZB and cigarette making machines CJ, including those from Siemens and Beckhoff. This data includes vibration and audio data, which is used to analyze changes in vibration characteristics and detect potential equipment failures in advance. Equipment operating parameters, such as packaging machine output, cigarette making machine output, planned completion rate, finished product rate, downtime, and number of downtimes, are used to provide real-time feedback on the operating status. Product rejection data, such as the number of cigarettes rejected per 10,000 cigarettes at a specific time point and the total downtime and number of downtimes, are used to monitor product quality in real time and locate process or equipment problems. Energy and material consumption data, such as time series data of energy consumption per 10,000 cigarettes and material consumption trends including the loss rate of carton label paper, the loss rate of small box label paper, and the loss rate of filter rods, are used for cost control, abnormal consumption warnings, and the generation of consumption trend reports.

[0043] Specifically, this application synchronizes master data from upstream systems such as ERP and MES to the local MRO (Maintenance, Repair, and Operation) database. Master data includes equipment information such as equipment number, name, model, production line, and location coordinates; a bill of materials such as material codes and names, used for standardizing replacement records and facilitating material traceability during maintenance; maintenance strategy templates, derived from a pre-defined maintenance standard library, defined through master data synchronization or system pre-setting, storing standardized operational content for maintenance tasks in a maintenance task table, including part names, items, standards, methods, tools, and inspection points, used as templates for automatically generating inspection, lubrication, and maintenance plans, ensuring standardized and refined maintenance operations; and personnel and organizational data, derived from synchronized organizational structure information, including operator information, team information, and production line / workshop organizational structure, used in task allocation, execution records, and review processes.

[0044] Step S200: Based on the basic dataset, use the built-in algorithm to monitor and predict the health status of the equipment in real time; based on the real-time running time of the equipment, health score and predefined strategies, dynamically generate maintenance plans and rotation maintenance plans.

[0045] Specifically, the basic dataset in this application includes equipment vibration audio data and preset warning thresholds (fluctuation cycle, cumulative rejection rate threshold, etc.). This application utilizes a built-in algorithm to perform real-time calculation and analysis on the basic dataset. The algorithm takes two forms: one is as an independent service, i.e., an interface call, which periodically reads and parses the file; the other is encapsulated as a Java class library for direct call by the OPC client. One of the core tasks of the built-in algorithm in this application is to calculate the vibration characteristic value (DAV value) based on the vibration audio data. The DAV value is used to quantify the vibration state of the equipment and is a key indicator for assessing the health of the equipment. This application monitors the changes in the DAV value in real time and compares it with the baseline when the equipment is operating normally to complete the real-time monitoring of the health status. More specifically, the core indicator of the health status in this application is the DAV value, and related indicators include rejection rate, rejection quantity, equipment operating parameters, energy and material consumption, etc.

[0046] Specifically, the predictive early warning mechanism of this application includes: dynamically determining whether the current basic dataset meets any or all of the early warning conditions using a built-in algorithm; if so, an early warning is automatically triggered. The early warning conditions include: within a set monitoring period, the key parameters of the equipment exceed the preset normal fluctuation range; within a set statistical period, the cumulative product rejection rate of the equipment exceeds a preset installation threshold. More specifically, this application sets two levels of early warning conditions. The first early warning condition is a large fluctuation period. When the fluctuation amplitude or frequency of key parameters of the equipment, such as the vibration DAV value, exceeds the fluctuation period early warning value set based on historical data and equipment characteristics, it is judged as abnormal. The second early warning condition is an excessive cumulative rejection rate. The average rejection rate or total rejection volume is calculated cumulatively over a complete statistical period. When this cumulative value exceeds the cumulative rejection rate threshold set based on quality standards and historical performance, an early warning is triggered. The early warning information of this application includes the early warning category (e.g., large fluctuation period, excessive cumulative rejection rate), early warning description, and early warning time. The generated early warning information will be pushed to the web homepage dashboard or the interface of relevant management personnel through the system's notification mechanism, indicating the abnormal equipment, the reason for the early warning, the severity, and the time of occurrence.

[0047] Specifically, this application continuously monitors the cumulative operating time of the equipment, performs real-time assessment of the equipment status through vibration DAV value analysis, obtains a health score, and compares it with a predefined strategy set in the system. For example, when the operating time of equipment ZJ118 reaches 500 hours and the health score is below 90, a maintenance or rotation maintenance plan is triggered.

[0048] Specifically, the triggering of the warning in this application will be directly linked to the maintenance system, which can automatically or prompt management personnel to generate a corresponding maintenance plan. The maintenance plan includes daily inspection tasks, periodic lubrication tasks, and comprehensive maintenance tasks. More specifically, one or more specific, executable maintenance tasks under the maintenance plan of this application are derived from intelligent recommendations (i.e., generated by the algorithm based on health status), manually added items, or predefined maintenance strategy templates. The execution cycle of the maintenance plan of this application can be selected as daily, weekly, monthly, or per shift. The daily inspection tasks (point inspection) of this application are used for daily inspections to discover potential daily issues. Their execution cycle can be short-cycle, high-frequency, daily or per shift, including sensory inspection, instrument parameter inspection, safety device inspection, etc.; the periodic lubrication tasks (lubrication) are used to ensure lubrication of moving parts of the equipment and reduce wear. Their execution cycle is set according to lubrication point requirements, including lubrication point confirmation, lubrication operation, and oil level / pressure check; the comprehensive maintenance tasks (maintenance) are used for systematic inspection, adjustment, and replacement to restore the accuracy and performance of the equipment. Their execution cycle is longer, including inspection, adjustment and replacement of key components, performance calibration, etc.

[0049] More specifically, the maintenance tasks in this application also include information such as execution standards, tools, methods, and key record keeping points.

[0050] Specifically, this application compares real-time data with predefined strategies. When triggering conditions are met, a new maintenance schedule plan instance is automatically created. This plan instance automatically associates with relevant devices and calls the standard task template library to generate a specific maintenance schedule task list. The maintenance schedule task list includes basic plan information, associated device information, maintenance schedule task information, execution and feedback information, associated files, and remarks, as follows:

[0051] 1. Basic plan information is used to define unique identifiers, scheduling, and status tracking, including plan number, maintenance rotation date, plan status (such as pending review, issued, completed, etc.), and creation information.

[0052] 2. Associated equipment information is used to clarify the specific objects to be executed in the maintenance task, and supports batch management of multiple devices, including equipment code, equipment type (such as packaging machine, coiling machine, forming machine), and equipment list.

[0053] 3. The maintenance task information is used to define specific maintenance work content to ensure standardized and refined operation. It includes part name (such as drive shaft, gearbox, etc.), maintenance items (such as bolt tightening, oil circuit inspection), operation standards (such as torque value, clearance range, etc.), methods and tools, and task source (including intelligent recommendation, manual addition and standard strategy).

[0054] 4. Execution and feedback information is used to record the task execution process, realize closed management and problem traceability, including execution status (such as normal completion, warranty, incomplete), operation records, replacement records (such as replacement of parts, the material code, name, quantity, reason for replacement and time must be recorded), and abnormal handling (supports the annotation of abnormal situation or additional explanation).

[0055] 5. Associated files and notes are used to provide supporting evidence and flexible information supplementation to enhance task verifiability. This includes uploading on-site photos, diagnostic reports, and other files in formats such as PNG and PDF. Free text can also be added to record special circumstances or temporary instructions outside of standard operating procedures.

[0056] Based on the above, this application for maintenance plan can achieve full life cycle management, refined operation guidance, multi-dimensional traceability, flexibility and scalability, and ensure the efficiency, standardization and auditability of maintenance work.

[0057] More specifically, in this step, when a maintenance / renewal plan needs to be canceled or invalidated, the current maintenance / renewal plan can be deleted directly in the cloud. Alternatively, when a specific task needs to be removed, the specific renewal task can be deleted directly from the renewal task ignore interface, thus adjusting the task.

[0058] Step S300: Distribute the maintenance plan or rotational maintenance plan through the cloud-edge-device architecture, execute it according to the standard, and record key information.

[0059] Specifically, the cloud-edge-device architecture of this application includes:

[0060] 1) Central management layer, used for centralized monitoring and decision-making, such as providing dashboards for output, efficiency, consumption, and health scores, supporting macro-level decisions such as long-term trend analysis, capacity planning, and resource optimization scheduling based on full historical data; strategy formulation and management, such as maintenance strategy management, maintenance schedule planning, threshold and rule configuration; data storage and analysis optimization.

[0061] 2) Local Aggregation and Processing Layer: This layer is used for data aggregation and preprocessing, real-time control and task dispatching, and network redundancy assurance. For example, it receives real-time data (vibration files, operating parameters, rejection signals) uploaded from all OPC clients, executes edge-side algorithms, and performs preliminary data verification, cleaning, and standardization. It receives maintenance / rotational maintenance plans from the cloud and accurately and in real-time distributes them to the corresponding OPC clients, executing simple real-time control logic or rule engines. When the network connection to the cloud is interrupted, this layer can cache task instructions and execution results; even during network interruptions, it can still provide some localized services, such as historical task queries and simple instruction execution, ensuring uninterrupted on-site work.

[0062] 3) The field execution layer is used for data collection, task execution, and result feedback. For example, it directly connects to equipment PLCs and sensors via industrial protocols such as OPC UA and Modbus to collect raw vibration audio (.wav), equipment status, I / O signals, and other data; it converts raw data from different devices and protocols into a unified format that the system can recognize. It provides operators with a graphical interface displaying details of issued maintenance / rotational maintenance tasks (parts, items, standards, methods, tools); operators execute tasks on-site according to instructions and record execution status, parts replacement information, and upload on-site photos by clicking "Complete" on the interface. The task execution results (status, time, personnel, remarks) are fed back to the "edge" layer in real time, and then synchronized to the "cloud" layer; equipment anomalies or faults discovered on-site can be quickly reported through the edge, triggering an early warning process.

[0063] More specifically, this application takes a maintenance task as an example, and the collaboration of the cloud-edge-device architecture is as follows:

[0064] 1) Cloud: Planners create maintenance rotation plans in the web interface and click "Distribute";

[0065] 2) Cloud-Edge: Planning instructions are sent to the edge server in the workshop via the network;

[0066] 3) Edge-to-End: The edge server accurately pushes tasks to the OPC client of the target machine;

[0067] 4) Terminal: The operator views the task on the OPC terminal, performs maintenance on-site, and clicks submit upon completion;

[0068] 5) End-Edge-Cloud: After the execution results are aggregated and cached by the edge server, they are synchronized back to the central cloud database to update the plan status and are used for subsequent data analysis.

[0069] Specifically, the key information in this application includes task execution status information, operation process and resource information, timestamp and responsible person information, and supporting evidence and explanatory information. The task execution status information is used to track task progress and results in real time, including completion status and completion details (which are coded in detail: 0: Normal completion; 1: Repair requested; 2: Incomplete; 3: Ignored). The operation process and resource information is used to ensure standardized operations and record resource consumption, including methods, tools, and replacement records (material code, material name, quantity, operator, reason for replacement, and replacement time). The timestamp and responsible person information includes task submission time, task issuance time, actual completion time, specific executor, and task issuer or reviewer. Supporting evidence and explanatory information is used to enhance the credibility and flexibility of the task through multimedia and text supplementary information, including document vouchers, which can be linked to on-site photos, diagnostic reports, etc., and the documents must be bound to the task number; the remarks field is a free text field used to record abnormal situations, temporary adjustments, or other non-standard explanations.

[0070] Step S400: Feedback on execution results and key information, and conduct multi-dimensional visualization analysis; based on historical data and analysis results, continuously optimize maintenance strategies and early warning thresholds to form a self-learning optimization loop.

[0071] Specifically, this application utilizes multi-dimensional visualization analysis to transform complex equipment operation data and maintenance execution results into intuitive charts and indicators, providing managers at different levels with real-time situational awareness from a global perspective to detailed analysis, supporting rapid and accurate maintenance / rotational maintenance decisions. Furthermore, this application can quickly pinpoint problems, such as from the production line to individual machines, from overall rejection rates to specific workstations and causes, thereby enabling proactive intervention based on problem identification. Based on historical data trend analysis, this application can improve the evaluation of the effectiveness of maintenance / rotational maintenance strategies, equipment reliability, and resource utilization efficiency; by automatically or manually optimizing early warning thresholds and maintenance / rotational maintenance strategies using the analysis results, it makes operation and maintenance work more precise and efficient, achieving a shift from experience-driven to data-driven approaches.

[0072] More specifically, this application's multi-dimensional visualization analysis includes time, equipment and production line, indicator type, workstation and cause, and task execution dimensions. The time dimension tracks indicator trends over time, assessing the stability and cyclical patterns of equipment performance. The equipment and production line dimension clarifies responsibilities from a macro to micro perspective, enabling comparative management; for example, production line rejection trends can be compared to the rejection rates of different production lines. The indicator type dimension monitors different types of core performance indicators, comprehensively evaluating production and operational status, such as plan completion rate, output, yield, and downtime. The workstation and cause dimension pinpoints problems to specific production processes and root causes, enabling precise tracing and targeted improvements; for example, production line rejection distribution displays the rejection volume, rejection rate, and percentage for different rejection reasons at each workstation; total machine rejection comparison supports cause analysis, quickly locating the source of the problem. The task execution dimension monitors and evaluates the efficiency and quality of maintenance work, ensuring the effective implementation of maintenance plans.

[0073] The present invention will be described in detail below through specific examples and embodiments. It should also be understood that the following embodiments are only for specific illustration of the present invention and should not be construed as limiting the scope of protection of the present invention. Any non-essential improvements and adjustments made by those skilled in the art based on the above description of the present invention are within the scope of protection of the present invention. The specific process parameters, etc., in the following examples are merely examples within a suitable range; that is, those skilled in the art can make appropriate selections within the appropriate range based on the description herein, and are not intended to be limited to the specific values ​​in the examples below.

[0074] Example 1

[0075] Take the abnormal fluctuation of the vibration DAV value of the coiling machine on the ZJ17 production line as an example.

[0076] The steps in this embodiment are as follows:

[0077] 1. The vibration sensor on the device collects raw vibration audio data and simultaneously acquires the device's master data, including device code, model, and preset fluctuation warning threshold;

[0078] 2. The edge-side algorithm calculates the DAV value in real time and finds that its fluctuation period and amplitude both exceed the preset fluctuation warning threshold in a short period of time. At this time, a rejection warning is automatically triggered, and the warning category is large fluctuation period.

[0079] Meanwhile, it was detected that the equipment's monthly operating time was close to the maintenance cycle and its health score had declined. A new record was automatically generated in the maintenance schedule, and the maintenance of the winding machine was scheduled for the next working day.

[0080] 3. The wheel maintenance plan is distributed to the OPC client of the ZJ17 production line via the system. The next day, the operator checks the wheel maintenance task list on the OPC industrial control computer. The task clearly requires checking the drive shaft area, including vibration and abnormal noise checks. The standard is that the DAV value is below the first threshold and there is no abnormal noise. Tools such as a stethoscope and vibration analyzer are used. The operator completes the inspection and replaces the bearing on-site, records the replacement information in the system, including material code, name, quantity, and reason, and then submits the task completion status.

[0081] 4. Task completion data is synchronized to the cloud database in real time. Administrators can view detailed records of this maintenance cycle on the web dashboard and see through the equipment health trend chart that the equipment's vibration characteristic values ​​have returned to normal range after the maintenance cycle. The system records the entire process data of this fluctuation warning-maintenance cycle-return to normal operation, which is used to optimize the vibration warning threshold model for this model of equipment, making it more accurate in the future.

[0082] Please see Figure 2 The following is a framework diagram of the intelligent operation and maintenance management system 200 for high-speed production lines in cigarette factories, as described in this application, including:

[0083] The data acquisition and synchronization module 210 is used to acquire raw data from production line equipment in real time and synchronize and integrate master data from upstream systems to build a basic dataset.

[0084] The early warning and plan generation module 220 is used to monitor and predict the health status of equipment in real time based on a basic dataset and using built-in algorithms; and to dynamically generate maintenance plans and rotation maintenance plans based on the real-time running time of the equipment, health score and predefined strategies.

[0085] The plan distribution and execution module 230 is used to distribute maintenance plans or rotational maintenance plans through a cloud-edge-device architecture, execute them according to standards, and record key information.

[0086] The data analysis and optimization module 240 is used to provide feedback on execution results and key information, and to perform multi-dimensional visualization analysis. Based on historical data and analysis results, it continuously optimizes maintenance strategies and early warning thresholds, forming a self-learning optimization loop.

[0087] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for intelligent operation and maintenance management of a high-speed production line in a cigarette factory, characterized in that, Includes the following steps: Step S100: Acquire raw data from production line equipment in real time and synchronously integrate master data from upstream systems to build a basic dataset; Step S200: Based on the aforementioned basic dataset, the built-in algorithm is used to perform real-time monitoring and predictive early warning of the device's health status. Based on real-time equipment runtime, health score, and predefined strategies, maintenance plans and rotational maintenance plans are dynamically generated. Step S300: The maintenance plan or the rotational maintenance plan is distributed through the cloud-edge-device architecture, executed according to the standard, and key information is recorded; Step S400: Feed back the execution results and the key information, and perform multi-dimensional visualization analysis; based on historical data and analysis results, continuously optimize maintenance strategies and early warning thresholds to form a self-learning optimization loop.

2. The method according to claim 1, characterized in that, In step S100, the raw data includes vibration audio data, equipment operating parameters, product rejection data, and energy and material consumption data. The master data includes equipment information, bill of materials, maintenance strategy templates, and personnel and organization data.

3. The method according to claim 2, characterized in that, In step S200, the predictive early warning includes: using a built-in algorithm to dynamically determine whether the current basic dataset meets any or all of the early warning conditions. If it does, an early warning is automatically triggered. The early warning conditions include: within a set monitoring period, the key parameters of the equipment exceed the preset normal fluctuation range; within a set statistical period, the cumulative product rejection rate of the equipment exceeds the preset installation threshold.

4. The method according to claim 3, characterized in that, In step S200, the maintenance plan includes daily inspection tasks, regular lubrication tasks, and comprehensive maintenance tasks.

5. The method according to claim 3, characterized in that, In step S200, the maintenance plan includes basic plan information, associated equipment information, maintenance task information, execution and feedback information, associated documents and remarks information.

6. The method according to claim 1, characterized in that, In step S300, the cloud-edge-device architecture includes: The central management layer is used for centralized monitoring and decision-making, strategy formulation and management, and data storage and analysis optimization. The local aggregation and processing layer is used for data aggregation and preprocessing, real-time control and task dispatch, and network redundancy protection. The on-site execution layer is used for data collection, task execution, and result feedback.

7. The method according to claim 6, characterized in that, In step S300, the key information includes task execution status information, operation process and resource information, timestamp and responsible person information, and auxiliary proof and explanation information.

8. The method according to claim 3, characterized in that, The built-in algorithm includes calculating vibration characteristic values ​​based on the vibration audio data.

9. The method according to claim 1, characterized in that, In step S400, the multi-dimensional visualization analysis includes time dimension, equipment and production line dimension, indicator type dimension, workstation and cause dimension, and task execution dimension.

10. An intelligent operation and maintenance management system for high-speed production lines in cigarette factories, characterized in that, include: The data acquisition and synchronization module is used to acquire raw data from production line equipment in real time and synchronize and integrate master data from upstream systems to build a basic dataset. The early warning and plan generation module is used to monitor and predictively warn about the health status of the equipment in real time based on the basic dataset and using built-in algorithms. Based on real-time equipment runtime, health score, and predefined strategies, maintenance plans and rotational maintenance plans are dynamically generated. The plan distribution and execution module is used to distribute the maintenance plan or the rotational maintenance plan through a cloud-edge-device architecture, execute it according to standards, and record key information. The data analysis and optimization module is used to provide feedback on execution results and key information, and to perform multi-dimensional visualization analysis. Based on historical data and analysis results, it continuously optimizes maintenance strategies and early warning thresholds, forming a self-learning optimization loop.

Images