Visual equipment operation safety monitoring method and system
By unifying the processing and sharing of data from multiple sources, the problem of data silos between equipment monitoring systems has been solved, enabling efficient and accurate equipment safety monitoring and improving the efficiency of equipment status assessment and fault early warning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-29
- Publication Date
- 2026-03-27
AI Technical Summary
In existing technologies, the problem of data silos from multiple sources in industrial equipment prevents data from flowing automatically across systems. Staff need to manually organize the data, resulting in low monitoring efficiency and biased decision-making, which fails to meet the needs of efficient and accurate equipment safety monitoring.
The data access module acquires raw data from multiple devices, performs field extraction and mapping, preprocesses the data at the edge, and uploads it to the cloud. The cloud generates dynamic rules and pushes them to the edge. The edge then processes the data further and transmits it to the data quality optimization module to generate high-quality data for cross-system sharing, combined with visualization and fault warning.
It breaks down cross-system barriers for multi-source device data, reduces manual processing time, improves the accuracy of equipment status judgment and the response speed of fault warning, reduces the maintenance burden on technicians, and adapts to the equipment safety monitoring needs of multiple fields.
Smart Images
Figure CN121742385A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of equipment operation monitoring, in particular to a visual equipment operation safety monitoring method and system. BACKGROUND
[0002] With the popularization of industrial 4.0 and intelligent technology, equipment operation safety monitoring has become the core link to ensure production continuity and reduce safety risks. The current visual equipment operation safety monitoring system collects equipment temperature, speed, pressure, voltage and other operation data through sensors, and presents the data in the form of charts and analog diagrams through a software platform to assist staff in real-time monitoring of equipment status. It is widely used in machine tool monitoring of industrial factory production lines, elevator and air conditioning system monitoring of intelligent buildings, and pressure and leakage monitoring of outdoor oil and gas pipelines. However, the data island problem is prominent in the prior art, which seriously restricts the monitoring effect. The data of different equipment monitoring systems and different departments are independently stored in their own databases or storage units, and there is a lack of unified interaction standard and sharing mechanism.
[0003] In the existing industrial factory, the production line equipment real-time monitoring system, the equipment maintenance management system and the production planning system use independent databases. Not only are the data formats incompatible, but also the interface protocols are different, which leads to the inability of data to automatically flow across systems. Staff need to manually log in to multiple systems to export data one by one and then organize and summarize them to analyze the correlation between the "operation status-historical fault-maintenance plan" of a motor. The single data organization is time-consuming and inefficient, and because of the fragmented data, staff can only determine the equipment status based on the data of a single system. For example, only the "normal temperature" data of the monitoring system is used to determine that the equipment is risk-free, but the information that the "bearing of the equipment has exceeded the service life" in the maintenance system is ignored, which ultimately leads to failure in fault prediction and cannot meet the efficient and accurate equipment safety monitoring requirements.
[0004] Therefore, we propose a visual equipment operation safety monitoring method and system. SUMMARY
[0005] The purpose of the present application is to provide a visual equipment operation safety monitoring method and system to solve the problems raised in the background art.
[0006] To achieve the above-mentioned purpose, the present application provides the following technical solution: a visual equipment operation safety monitoring method and system, comprising the following method steps:
[0007] Step 1: Obtain multi-source equipment operation raw data through a data access module, perform field extraction and mapping processing on the raw data, extract key fields and unify field naming;
[0008] Step two: transmit the processed raw data to the edge processing unit, the edge performs preprocessing operations on the data based on a preset basic rule library, simultaneously collects device state data and rule execution effect data, and uploads to the cloud processing unit at a set period;
[0009] Step three: the cloud processing unit analyzes the received data, generates dynamic rules adapted to the device state and pushes to the edge, and updates the edge rule library; the edge transmits the preprocessed preliminary optimization data to the data quality optimization module;
[0010] Step four: the data quality optimization module performs secondary verification and deep optimization on the preliminary optimization data to generate high-quality data, which is transmitted to the data storage module and the data sharing module respectively;
[0011] Step five: the data sharing module opens cross-system sharing of high-quality data according to preset permissions, the visual display module obtains high-quality data, displays device operation data in multiple forms, generates device operation state evaluation results and fault warning information based on built-in algorithms, and synchronously displays rule iteration logs.
[0012] As a preferred embodiment of the present application, the acquisition of the multi-source device operation raw data in step one is realized through a database interface, an Internet of Things interface, a file interface and a third-party system interface; when the cloud processing unit detects a new data source in step three, an adaptive template is called from a pre-stored multi-type device rule template library, and a dynamic rule is generated after optimization.
[0013] As a preferred embodiment of the present application, the preprocessing operation in step two includes data cleaning, data verification and data conversion; the secondary verification in step four includes cross-data item consistency verification and historical data comparison verification, and the deep optimization includes missing value supplement and abnormal data disposal.
[0014] As a preferred embodiment of the present application, the edge processing unit in step two locally caches the latest rules pushed by the cloud, and continues to perform data preprocessing based on the cached rules when the network is interrupted, and automatically synchronizes the processing data and rule update information during the interruption after the network is restored.
[0015] As a preferred embodiment of the present application, the data sharing in step five is realized through a sharing platform built based on a micro-service architecture, and a role-based access control mechanism is used to assign permissions; data interaction is completed through two interfaces of RESTful API and Web Socket, and data security is guaranteed through transmission encryption, data desensitization and operation logs.
[0016] The application also relates to a visual device operation safety monitoring system, which comprises a data integration module, a cloud-edge collaborative processing engine, a data quality management module, a data sharing interaction module, a visual display analysis module and a data storage module.
[0017] As a preferred embodiment of the application, the data integration module is provided with a database interface, an Internet of Things interface, a file interface and a third-party system interface, which are used for accessing multi-source device operation raw data and performing field extraction and mapping processing to unify field naming.
[0018] As a preferred embodiment of the application, the cloud-edge collaborative processing engine comprises an edge lightweight processing unit and a cloud rule iteration unit; the edge lightweight processing unit is deployed on an edge node close to the device and is provided with a basic rule library and is used for performing data preprocessing, collecting device state and rule execution data; the cloud rule iteration unit is deployed on a central cloud and is used for generating dynamic rules and pushing the dynamic rules to the edge.
[0019] As a preferred embodiment of the application, the basic rule library of the edge lightweight processing unit comprises a data cleaning template, a data verification template and a data conversion template; the cloud rule iteration unit is provided with a multi-type device rule template library and is used for generating dynamic rules by analyzing the data uploaded by the edge through a machine learning algorithm.
[0020] As a preferred embodiment of the application, the visual display analysis module is used for displaying device operation data, state evaluation results, fault early warning information and rule iteration logs and provides multiple visual display forms; and the data storage module is used for storing raw data, preliminary optimized data, high-quality data and analysis results.
[0021] Compared with the prior art, the application has the following beneficial effects:
[0022] The application breaks the cross-system barriers of multi-source equipment data through the cooperation of the data integration module and the data sharing interaction module, realizes the integration and sharing of monitoring, maintenance, production and other data, and provides comprehensive support for equipment state judgment and safety decision-making without manual cross-system data arrangement, avoiding the one-sidedness of decision-making caused by data fragmentation; with the secondary verification and deep optimization of the data quality management module, effectively processing data missing, abnormal, inconsistent and other problems, providing reliable data foundation for visual monitoring and fault warning, reducing monitoring misjudgment and safety accidents caused by low-quality data; relying on the dynamic rule engine of cloud-edge collaboration, edge local processing data reduces transmission delay and network pressure, can quickly respond to emergency fault warning of edge scene, based on cache rules to ensure monitoring continuity when the network is disconnected, and the rules are automatically iterated with the change of equipment state and the addition of data source, without frequent manual configuration, greatly reducing the maintenance burden of technical personnel and the access cost of new equipment, overall improving the efficiency and accuracy of equipment operation safety monitoring, adapting to the needs of industrial production, oil and gas pipeline monitoring and other fields. BRIEF DESCRIPTION OF DRAWINGS
[0023] Other features, objects and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments, made with reference to the accompanying drawings:
[0024] Fig. 1 A flow chart of a visual equipment operation safety monitoring method of the application;
[0025] Fig. 2 A framework diagram of a visual equipment operation safety monitoring system of the application. DETAILED DESCRIPTION
[0026] In order to make the technical means, creative features, purposes and effects achieved by the application easy to understand, the following will further describe the application in combination with specific embodiments.
[0027] This embodiment takes a large automobile parts production plant as an example, which contains indoor production lines and outdoor raw material transportation pipelines, and needs to solve the problems of multi-source data integration, real-time monitoring of edge scene and dynamic adaptation of rules, which will be described in detail below in combination with system deployment and method execution.
[0028] As shown in Figs. 1-2 A visual equipment operation safety monitoring method and system
[0029] The system is as follows:
[0030] The visual equipment operation safety monitoring system used in this embodiment includes a data integration module, a cloud-edge collaborative processing engine, a data quality management module, a data sharing interaction module, a visual display and analysis module, and a data storage module, and the deployment and functions of each module are as follows:
[0031] 1. Data integration module
[0032] The application server deployed in the factory central computer room is provided with a preset database interface, an Internet of Things interface, a file interface and a third-party system interface. After the module is started, each data source is automatically scanned, and key fields such as "equipment number, parameter name, collection time and parameter value" are extracted. Different system fields are uniformly named through a preset "field mapping table" to avoid field confusion.
[0033] 2. Cloud-edge collaborative processing engine
[0034] The cloud-edge collaborative processing engine includes an edge-side lightweight processing unit and a cloud-side rule iteration unit.
[0035] The edge-side lightweight processing unit is deployed in the production line workshop and the edge server is deployed in the outdoor pipeline monitoring point. The edge-side lightweight processing unit is provided with a built-in basic rule library including a "data cleaning template, a data verification template and a data conversion template". The edge-side lightweight processing unit receives the original data transmitted by the data integration module in real time, simultaneously collects device state data and rule execution effect data, and uploads the data to the cloud side at a set period.
[0036] The cloud-side rule iteration unit is deployed in the factory central cloud server and is provided with a rule template library of multiple types of devices. The cloud-side rule iteration unit communicates with the edge side through the MQTT protocol, analyzes the device state changes by using a machine learning algorithm after receiving the data uploaded by the edge side, generates dynamic rules, detects a newly added intelligent sorting robot device, calls a "robot rule template" from the template library, optimizes the rules in combination with the joint temperature and motion accuracy of the robot, and pushes the rules to the edge side to update the rule library.
[0037] 3. Data quality management module
[0038] Another application server deployed in the central computer room receives the preliminary optimized data transmitted by the edge side, performs secondary verification first, performs deep optimization again, and finally generates high-quality data.
[0039] 4. Data sharing and interaction module
[0040] The data sharing and interaction module is deployed in the central cloud and is built based on a micro-service architecture. The data sharing platform is provided with role permissions such as "monitoring operator, device maintainer and production administrator". The data sharing platform provides RESTful API interfaces and WebSocket interfaces, transmits data through the SSL / TLS protocol encryption, desensitizes sensitive information such as device procurement cost, and records all data access operation logs.
[0041] 5. Visual display and analysis module
[0042] Terminal equipment deployed in the factory monitoring center to display the motor speed trend in line chart, the number of equipment failures in column chart, and the real-time pipeline pressure in instrument panel, while generating equipment running state evaluation results and fault warning information; synchronously display the rule iteration log pushed by the cloud for staff to trace the rule changes.
[0043] 6. Data storage module
[0044] Distributed storage server deployed in the central computer room to store raw data, preliminary optimized data, high-quality data, and analysis results, supporting fast data query and long-term backup.
[0045] The method steps are as follows:
[0046] Step 1: Multi-source raw data acquisition and field unification
[0047] Start the data integration module, connect the equipment monitoring system database through the preset database interface, read the real-time motor speed and machine tool machining precision data; receive the temperature and pressure data transmitted by the pipeline sensor through the Internet of Things interface; import this week's production plan file through the file interface; and obtain the equipment procurement time data from the ERP system through the third-party system interface. The module automatically extracts the key fields in each data, unifies the naming according to the "field mapping table", and after completing the raw data processing, transmits it to the edge lightweight processing unit.
[0048] Step 2: Edge pre-processing and data collection upload
[0049] After the edge lightweight processing unit receives the processed data of step 1, it performs pre-processing based on the basic rule library:
[0050] Data cleaning: filter out data with "motor speed suddenly jumps to far beyond the normal range" through the outlier identification template, and remove repeated transmission data caused by network fluctuations through the repeated value identification template;
[0051] Data verification: verify whether the "equipment number" conforms to the format, and verify whether the collection time is within the current time range;
[0052] Data conversion: convert the machine tool machining speed unit to a unified unit.
[0053] At the same time, the edge collects equipment state data and rule execution effect data, uploads them to the cloud rule iteration unit at a set period; the edge locally caches the latest rules pushed by the cloud, and if the outdoor pipeline monitoring point network is interrupted, it automatically continues to process data based on the cached rules, and synchronizes the processing results and rule update information during the network interruption after the network is restored.
[0054] Step 3: Cloud rule optimization and preliminary data transmission
[0055] After receiving the uploaded data from step 2, the cloud-based rule iteration unit analyzes it using machine learning algorithms:
[0056] Equipment status correlation: When it is found that the parameter fluctuation range expands after the motor running time increases, the speed verification rules of the motor are automatically adjusted and dynamic rules are generated;
[0057] New data source adaptation: If a factory adds a new intelligent sorting robot, after the edge device detects the joint temperature and motion accuracy data of the new data source, it sends a "data source change request" to the cloud. The cloud device then calls the "robot rule template" from the template library, optimizes the cleaning and verification rules based on the robot parameters, and pushes it to the edge device to update the rule library.
[0058] After the cloud sends the dynamic rules to the edge, the edge transmits the pre-processed, initially optimized data to the data quality management module.
[0059] Step 4: Data Quality Optimization to Generate High-Quality Data
[0060] After receiving the preliminary optimization data from step 3, the data quality management module performs a secondary verification:
[0061] Cross-data item consistency verification: Verify the logical relationship of "motor power = voltage × current". If the power calculated from the voltage and current of a certain data item is inconsistent with the collected power, mark it as "to be verified" and notify the maintenance personnel to check the sensor.
[0062] Historical data comparison and verification: Compare the current pipeline temperature with the temperature of the same period in the past 7 days. If the difference is too large and there is no record of environmental changes, trigger manual review. If it is confirmed that the slight sensor offset is the cause, the data is corrected and retained.
[0063] After the secondary verification is completed, in-depth optimization is performed: for pressure data loss in a pipeline due to a brief sensor offline, the average pressure data of adjacent pipelines in the same area during the same period is used to fill the gap; for abnormal data caused by short-term overload of the motor, it is marked as "temporary abnormality" and retained, with relevant information noted. Finally, high-quality data is generated, transmitted to the data storage module for storage, and simultaneously synchronized to the data sharing and interaction module.
[0064] Step 5: Data Sharing and Visualization Analysis
[0065] After receiving the high-quality data from step 4, the data sharing and interaction module opens up sharing according to role permissions:
[0066] The monitoring operator can view real-time motor speed and pipeline pressure visualization charts on the large screen in the monitoring center;
[0067] The maintenance personnel log into the system via computer, call the WebSocket interface to receive fault alerts, and view the historical temperature data of the pipeline.
[0068] The ERP system uses a RESTful API interface to call monthly equipment operation data and generate cost accounting reports;
[0069] All data transmissions are encrypted using SSL / TLS, sensitive information such as equipment procurement costs is anonymized, and relevant information is recorded in operation logs.
[0070] After acquiring high-quality data, the visualization and analysis module displays the motor speed changes over the past 24 hours in a line chart and the number of equipment failures in each workshop this week in a bar chart, generating status assessment results and fault warning information; it also displays rule iteration logs simultaneously, allowing staff to fully understand the equipment status and rule changes.
[0071] Through the above system deployment and method execution, the automotive parts factory has achieved the integration and sharing of multi-source equipment data, significantly improved the response speed of equipment fault warning in edge scenarios, eliminated the need for frequent manual adjustments to rules, and greatly improved the efficiency and accuracy of equipment monitoring, thus meeting the equipment safety monitoring needs in the industrial production field.
[0072] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or basic characteristics. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, it is intended that all variations falling within the meaning and scope of equivalents of the claims be included within the present invention.
[0073] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.
Claims
1. A method and system for visually monitoring the safe operation of equipment, characterized in that: The methods and steps include the following: Step 1: Obtain raw operating data from multiple devices through the data access module, perform field extraction and mapping processing on the raw data, extract key fields and unify field naming; Step 2: Transmit the processed raw data to the edge processing unit. The edge unit performs preprocessing operations on the data based on the preset basic rule base, and at the same time collects device status data and rule execution effect data, and uploads them to the cloud processing unit according to the set period. Step 3: The cloud processing unit analyzes the received data, generates dynamic rules adapted to the device status, and pushes them to the edge to update the edge rule library; The edge device transmits the pre-processed, initially optimized data to the data quality optimization module; Step 4: The data quality optimization module performs secondary verification and in-depth optimization on the preliminary optimized data to generate high-quality data, which is then transmitted to the data storage module and the data sharing module respectively. Step 5: The data sharing module opens up cross-system sharing of high-quality data according to preset permissions. The visualization module obtains high-quality data, displays equipment operation data in multiple forms, and generates equipment operation status assessment results and fault warning information based on built-in algorithms, while simultaneously displaying rule iteration logs.
2. The method and system for visually monitoring the safe operation of equipment according to claim 1, characterized in that: The acquisition of raw data from multiple devices in step one is achieved through database interfaces, IoT interfaces, file interfaces, and third-party system interfaces. In step three, when the cloud processing unit detects a new data source, it calls the appropriate template from the pre-stored multi-type device rule template library, optimizes it, and generates dynamic rules.
3. The method and system for visually monitoring the safe operation of equipment according to claim 1, characterized in that: The preprocessing operations in step two include data cleaning, data verification, and data transformation; the secondary verification in step four includes cross-data item consistency verification and historical data comparison verification; and the deep optimization includes missing value supplementation and abnormal data handling.
4. The method and system for visually monitoring the safe operation of equipment according to claim 1, characterized in that: In step two, the edge processing unit locally caches the latest rules pushed from the cloud. When the network is interrupted, it continues to perform data preprocessing based on the cached rules. After the network is restored, it automatically synchronizes the processed data and rule update information during the interruption.
5. The method and system for visually monitoring the safe operation of equipment according to claim 1, characterized in that: The data sharing described in step five is achieved through a sharing platform built on a microservice architecture, and permissions are allocated using a role-based access control mechanism. Data interaction is completed through two interfaces: RESTful API and Web Socket, and data security is ensured through transmission encryption, data anonymization, and operation logs.
6. A visual equipment operation safety monitoring system, applicable to the visual equipment operation safety monitoring method according to any one of claims 1-5, characterized in that: It includes a data integration module, a cloud-edge collaborative processing engine, a data quality management module, a data sharing and interaction module, a visualization and analysis module, and a data storage module.
7. The method and system for visualizing equipment operation safety monitoring according to claim 6, characterized in that: The data integration module has pre-set database interface, IoT interface, file interface and third-party system interface, which are used to access raw data from multiple sources of devices, perform field extraction and mapping processing, and unify field naming.
8. A visual equipment operation safety monitoring system according to claim 6, characterized in that: The cloud-edge collaborative processing engine includes a lightweight edge processing unit and a cloud rule iteration unit. The lightweight edge processing unit is deployed at the edge node closest to the device and has a built-in basic rule library for performing data preprocessing, collecting device status and rule execution data. The cloud rule iteration unit is deployed in the central cloud for generating dynamic rules and pushing them to the edge.
9. A visual equipment operation safety monitoring system according to claim 8, characterized in that: The basic rule base of the edge lightweight processing unit includes data cleaning templates, data verification templates, and data transformation templates; the cloud rule iteration unit pre-stores a rule template library for multiple types of devices and uses machine learning algorithms to analyze data uploaded from the edge to generate dynamic rules.
10. A visual equipment operation safety monitoring system according to claim 6, characterized in that: The visualization and analysis module is used to display equipment operation data, status assessment results, fault warning information and rule iteration logs, and provides a variety of visualization display formats; the data storage module is used to store raw data, preliminary optimization data, high-quality data and analysis results.