Centrifugal machine full-life-cycle intelligent operation and maintenance system based on edge calculation

Abstract

The invention discloses a centrifuge full life cycle intelligent operation and maintenance system based on edge calculation, and belongs to the field of sewage treatment equipment health management. According to the system, edge calculation and mobile visualization are taken as an overall technical route, and a closed-loop operation and maintenance system from data acquisition, state recognition to visual management is constructed through combination of modular hardware architecture, multi-source data acquisition and edge intelligent analysis. The system is composed of a main control unit, a communication module, a display and interaction module, a power management module and a health management software system, all the modules work cooperatively, and local intelligent analysis and remote visual management of the running state of the centrifugal machine are achieved. Stable operation and maintenance management of a full life cycle such as real-time monitoring, health assessment, fault early warning, alarm and traceability of the operation state of the centrifugal machine is realized, and a comprehensive assessment mechanism of the health state of the equipment is formed, so that the state recognition precision, the fault traceability and the operation and maintenance decision reliability are improved.

Description

Technical Field

[0001] This invention relates to the field of wastewater treatment equipment health management, specifically a centrifuge full lifecycle intelligent operation and maintenance system based on edge intelligence. It integrates multi-sensor data acquisition, edge computing, and mobile visualization functions, aiming to achieve stable operation and maintenance management throughout the entire lifecycle of the centrifuge, including real-time monitoring of its operating status, health assessment, fault early warning, alarms, and source tracing. The system synchronously collects environmental parameters from the wastewater treatment plant and performs multi-dimensional cross-validation and fusion analysis with centrifuge operating parameters to form a comprehensive assessment mechanism for equipment health status, thereby improving the accuracy of status identification, fault source tracing capabilities, and the reliability of operation and maintenance decisions. Background Technology

[0002] With the accelerating pace of industrialization and urbanization, wastewater treatment plants, as crucial infrastructure for ecological environmental protection and resource recycling, directly impact urban environmental safety and sustainable development through their operational stability and treatment efficiency. Sludge dewatering is a critical step in wastewater treatment, with centrifuges serving as core equipment, undertaking the main tasks of solid-liquid separation and sludge-water reduction. Because centrifuges operate under harsh environments of high load, high humidity, and high corrosiveness, they are prone to problems such as bearing wear, rotor imbalance, abnormal vibration, and increased energy consumption. Failure to detect and address these issues promptly can lead to decreased sludge treatment efficiency, equipment damage, and abnormal shutdowns, affecting production continuity and potentially causing environmental risks such as excessive wastewater discharge. Currently, wastewater treatment plants primarily rely on manual inspections, periodic maintenance, and fixed threshold alarms for centrifuge operation and maintenance. This experience-based and periodic maintenance approach has significant limitations: alarm thresholds are difficult to dynamically adjust based on actual operating conditions; manual detection is inefficient and slow to respond; and maintenance is often only performed after significant abnormalities have occurred, leading to either over-maintenance or under-maintenance, wasting resources and failing to prevent sudden shutdowns. Practice has shown that unplanned downtime caused by centrifuge malfunctions is a significant source of operation and maintenance costs for wastewater treatment plants, and equipment reliability issues have become a key factor restricting the improvement of operation and management levels.

[0003] Traditional centrifuge monitoring systems primarily rely on single-signal acquisition, such as monitoring only individual parameters like vibration, temperature, or current. This fails to reflect the overall health status of the equipment through multi-dimensional data fusion. Furthermore, existing systems often employ a closed architecture, lacking data interaction and collaboration between monitoring nodes, creating typical "information silos" that hinder unified monitoring and comprehensive health assessment of the entire system.

[0004] While some centrifuge monitoring systems have attempted to incorporate cloud analytics for fault identification and trend prediction under the trend of intelligentization, such architectures typically rely on stable network connections and high communication bandwidth, making them susceptible to environmental factors. Especially in high-humidity, high-corrosion, or unstable network coverage environments like wastewater treatment plants, communication interruptions can lead to data transmission delays or even loss, failing to meet the requirements for real-time response and continuous analysis.

[0005] From a hardware perspective, existing monitoring systems generally lack modular and standardized design. Sensor placement, signal acquisition, and communication methods are mostly customized. If additional monitoring points or modules need to be added or replaced later, rewiring or modification of the main control circuit is required, which not only increases the workload but also seriously affects the continuity of system operation.

[0006] Furthermore, the centrifuge operating environment is characterized by high concentrations of corrosive gases and high humidity, factors that significantly impact equipment degradation. However, most existing systems lack a correlation analysis mechanism between equipment and environmental parameters, relying solely on individual sensors for simple monitoring, thus failing to achieve collaborative judgment and precise source tracing of fault causes. With the development of smart water management and intelligent equipment management, there is an urgent need for a system capable of multi-source data fusion and local intelligent decision-making at the edge, reducing reliance on the cloud and improving response speed and operational stability.

[0007] Therefore, there is an urgent need for an intelligent management system for the entire lifecycle of centrifuges based on edge computing. This system should be able to achieve multi-source data acquisition, feature extraction, status identification, and trend analysis at the edge device level, maintain stable operation even during network outages, perform health assessments and fault warnings through local computing, and enable data visualization and remote operation and maintenance management through mobile applications. The system should balance reliability and scalability in its hardware design and provide local intelligent diagnostics and decision support in its software functionality. This will create an intelligent operation and maintenance closed loop integrating "collection, analysis, display, and management," supporting the efficient, stable, and intelligent operation of wastewater treatment plants. Summary of the Invention

[0008] Existing centrifuge operation and maintenance management systems generally suffer from problems such as limited monitoring methods, insufficient data analysis capabilities, reliance on manual experience for judgment, and excessive dependence on cloud communication.

[0009] In complex environments such as wastewater treatment plants, centrifuges operate under high humidity, high corrosion, and high load conditions for extended periods, which can easily lead to bearing wear, abnormal vibration, and increased energy consumption. Traditional cloud-based or manual operation and maintenance models struggle to detect potential problems in a timely manner, and monitoring and analysis functions become unusable once the network is interrupted, resulting in poor real-time performance, delayed response, and difficulties in fault location.

[0010] In addition, existing systems mostly adopt a distributed architecture, with information isolated between monitoring nodes, making it impossible to achieve collaborative analysis of equipment operating status and environmental conditions, and also lacking quantifiable health assessment and lifespan prediction mechanisms.

[0011] The present invention aims to provide a centrifuge full life cycle operation and maintenance system that can realize multi-source data fusion analysis and intelligent judgment at the edge, so that it can still operate independently in the event of network instability or interruption, realize health assessment, life prediction, alarm warning and fault tracing, thereby significantly improving the intelligence and reliability of wastewater treatment plant equipment operation and maintenance.

[0012] To address the aforementioned issues, this invention proposes an intelligent operation and maintenance system for the entire lifecycle of centrifuges based on edge computing. This system adopts an overall technical approach of "edge computing + mobile visualization," combining modular hardware architecture, multi-source data acquisition, and edge intelligent analysis to construct a closed-loop operation and maintenance system encompassing data acquisition, status identification, and visualized management.

[0013] The system mainly consists of a main control unit, a communication module, a display and interaction module, a power management module, and a health management software system. The modules work together to achieve local intelligent analysis and remote visual management of the centrifuge's operating status.

[0014] The main control unit adopts a collaborative architecture of industrial-grade embedded processor and microcontroller, responsible for the synchronous acquisition of operating status and environmental parameters, signal preprocessing, feature fusion, and status recognition. The system incorporates a multi-model fusion algorithm to dynamically generate equipment health scores and trend predictions based on real-time monitoring data, and outputs remaining lifespan estimates, providing data support for maintenance decisions. By deploying core computing and judgment logic at the edge, the system can independently complete assessments and alarms even in situations of network instability, significantly reducing reliance on the cloud.

[0015] The communication module supports multiple wired and wireless transmission methods (including Ethernet, 4G / 5G, LoRa, etc.) and can automatically switch according to the on-site network conditions. The system is equipped with local caching and breakpoint resume mechanisms to ensure data integrity and continuity, achieving highly reliable data exchange.

[0016] The display and interaction module shows real-time device operating parameters, health scores, alarm information, and trend curves via a touchscreen. The interface structure follows a logical design of "monitoring—assessment—early warning—source tracing," intuitively reflecting the current and future operating status. When health values ​​are abnormal or lifespan approaches the threshold, the system automatically triggers multi-level alarm prompts and records logs for traceability.

[0017] The power management module features voltage regulation, overcurrent, and reverse connection protection, making it suitable for high-humidity and highly corrosive environments and ensuring long-term stable operation. Its modular housing facilitates maintenance and expansion, and can be flexibly configured according to site power supply conditions.

[0018] The accompanying mobile health management system receives analysis results from the edge devices, enabling remote monitoring and event management. The mobile application displays device status, health trends, and alarm records through a graphical interface, supporting anomaly notifications, historical data review, and operation log queries. The system can collaborate with a cloud platform to achieve centralized monitoring of multiple devices and data sharing for operation and maintenance.

[0019] This invention introduces a multi-model fusion health assessment and trend prediction mechanism at the edge, combined with the coupled analysis of operational and environmental parameters, to achieve intelligent management of the entire process from data processing, anomaly identification, early warning and alarm to fault tracing. The system has a compact structure and high functional integration, enabling stable operation and rapid response in complex environments, significantly improving operational efficiency and management level.

[0020] This invention utilizes edge computing technology to achieve local intelligent analysis and decision-making regarding the operating status of centrifuges, enabling the system to possess high real-time performance, strong robustness, and independent operation capabilities. Compared to traditional solutions that rely on cloud-based analysis, this invention significantly reduces communication latency and network dependency risks, maintaining continuous monitoring and alarm functions even in network outage conditions.

[0021] By applying multi-model fusion algorithms, the system can dynamically reflect the health status of equipment and predict its lifespan trend, providing maintenance personnel with a scientific basis for maintenance, reducing unplanned downtime and over-maintenance, and effectively improving equipment availability.

[0022] The system achieves a closed-loop function of "monitoring-early warning-alarm-diagnosis-traceability" at the visualization and interaction levels. Combined with multi-terminal interconnection and alarm push mechanisms on mobile devices, it transforms operation and maintenance management from passive response to proactive prevention. This solution is both versatile and scalable, and can be extended to intelligent operation and maintenance scenarios for other rotating machinery equipment, demonstrating significant technological promotion value and economic benefits. Attached Figure Description

[0023] Figure 1 The exploded view of the edge computing terminal system of the present invention shows the overall hardware architecture with Orange Pi single-board computer as the main control core (1), including 4G communication module (2), power management module (3), top cover (4), data acquisition module (5) including ammonia, methane, hydrogen sulfide, methanethiol, temperature and humidity modules, ventilation hole array (6) and display screen module (7).

[0024] Figure 2 The display module provides a real-time monitoring interface, showing the equipment's operating environment, including ammonia, methane, hydrogen sulfide, methanethiol, temperature, and humidity. It also includes trend curves for H2S and humidity over time and the date.

[0025] Figure 3 The centrifuge operating status interface of the interactive module displays the vibration amplitude, suction water pressure, rotation speed, flow rate, temperature, current, main motor speed, as well as the trend curves and date of health score and remaining lifespan.

[0026] Figure 4 The interactive module displays a device fault analysis graph, showing the fault type, number of faults, and warning / alarm status.

[0027] Figure 5 The star network structure of the LoRa communication module demonstrates the communication topology between the central node and the child nodes.

[0028] Figure 6 The app's UI layout includes a top title area, an environmental monitoring area, a health status area, and an alert event area, showcasing a data visualization structure.

[0029] Figure 7 The system software operation flowchart shows the complete process from data processing and edge computing to transmission to the cloud and the APP. Detailed Implementation

[0030] To make the technical solution of the present invention clearer and more complete, the specific embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the following embodiments are only used to illustrate the present invention and do not constitute a limitation on the scope of protection.

[0031] I. System Overall Structure and Hardware Composition

[0032] This invention provides an intelligent operation and maintenance system for centrifuges throughout their entire lifecycle, based on edge computing. The system comprises a main control unit, a communication module, a display and interaction module, a power management module, and a health management software system. It enables real-time monitoring of centrifuge operating status, health assessment, fault alarms, early warnings, and source tracing analysis on-site. The system adopts a modular design concept, allowing for flexible configuration of sensing units and communication methods according to different operating conditions, ensuring operational stability and maintainability.

[0033] (1) Main control unit

[0034] The main control unit is the core of the system. It uses an industrial-grade single-board computer as the edge computing center, which is responsible for the access, preprocessing, feature fusion and status analysis of multi-source sensor data, and independently completes functions such as real-time monitoring, health assessment, fault alarm, early warning and source tracing locally.

[0035] The system can monitor key operating parameters of the centrifuge (vibration, speed, current, flow rate, temperature, etc.) in real time and dynamically assess the health status of the equipment through an adaptive fusion analysis mechanism, generating a health score and trend curve. When abnormal health values ​​or sudden changes in status are detected, the system automatically triggers early warnings or alarms and can record anomaly tracing information for subsequent analysis.

[0036] The main control unit is equipped with multiple interface modules for connecting to operating status sensors and equipment operating environment sensors (including ammonia, hydrogen sulfide, methane, methanethiol, temperature, and humidity sensors). Through multi-sensor collaborative data acquisition and cross-validation, the impact of the centrifuge's operating environment on the equipment's health status can be comprehensively reflected, thereby improving the accuracy and reliability of the assessment.

[0037] (2) Shell and structural design

[0038] like Figure 1 As shown, the system casing is made of high-strength ABS engineering plastic, featuring a lightweight structure and excellent corrosion and impact resistance, making it suitable for high-humidity and highly corrosive working environments such as wastewater treatment plants. The internal casing employs a partitioned structure design with an array of ventilation holes to ensure effective heat dissipation and facilitate independent deployment and maintenance of each module. Externally, it integrates a power interface, status indicator lights, a button control area, and sensor inputs, with a compact and rational layout for easy installation and on-site operation.

[0039] (3) Power Management Module

[0040] The system uses a 12V DC input power supply and has internal voltage regulation and overcurrent protection circuits to ensure continuous and stable power supply in environments with voltage fluctuations or humidity. The modules are individually packaged with detachable mechanical fixing, facilitating maintenance and expansion, and allowing for flexible power supply configurations based on site conditions.

[0041] II. Display and Interaction Module

[0042] The system is equipped with a high-brightness touch screen as a field visualization terminal to display equipment operating status and health assessment results. The display interface follows a logical framework of "monitoring—assessment—early warning and alarm—source tracing" to achieve intuitive information presentation and interactive operation.

[0043] (1) Real-time monitoring interface (e.g.) Figure 2 (as shown)

[0044] Display the centrifuge's operating status parameters, including speed, flow rate, motor current, temperature, vibration amplitude, and changes in the gas concentration, temperature, and humidity of the operating environment.

[0045] (2) Health assessment interface (e.g.) Figure 3 (as shown)

[0046] It displays health scores, lifespan assessments, and trend curves, allowing for real-time observation of equipment status changes.

[0047] (3) Fault analysis interface (e.g.) Figure 4 (as shown)

[0048] Displays fault type, number of occurrences, and corresponding time, and provides alarm level differentiation and event logging.

[0049] (4) Audible and visual alarm function:

[0050] When the system detects an anomaly, the display screen simultaneously triggers an audible and visual alarm, reminding maintenance personnel to promptly check and handle the issue. The display interface supports log playback, allowing traceability of the entire equipment operation process and providing a reliable basis for subsequent analysis and maintenance.

[0051] III. Communication and Data Transmission Mechanisms

[0052] The system communication structure consists of three layers: the field layer, the edge layer, and the cloud layer, which are used to realize multi-node data transmission, edge computing result reporting, and remote visualization.

[0053] (1) Field layer communication (LoRa wireless networking)

[0054] The field layer consists of multiple acquisition nodes, which are connected in a star network using LoRa wireless modules (e.g., Figure 5 As shown in the diagram, the central node is the main control unit. The acquisition nodes are responsible for obtaining equipment operating status and environmental data, which are then processed and transmitted to the main control unit. LoRa communication has long distance, low power consumption, and strong anti-interference capabilities, making it suitable for multi-point deployment in complex environments such as wastewater treatment plants.

[0055] (2) Edge layer communication and data interaction

[0056] After receiving data from the acquisition nodes, the main control unit performs local analysis and outputs the results. The system has a local data caching function, which can maintain the continuity of internal data in the event of short-term communication instability, and resume data uploading after communication is restored.

[0057] (3) Remote communication and cloud connection

[0058] The main control unit is equipped with a 4G communication module, enabling data interaction and remote management with the cloud platform. The communication module supports multiple transmission protocols (such as MQTT and HTTP) and can automatically select the optimal transmission path based on network conditions to ensure stable and secure data synchronization.

[0059] IV. Edge Computing and Intelligent Analysis Mechanisms

[0060] The system implements a closed-loop logic of "collection-analysis-judgment-feedback" at the edge, enabling it to make intelligent decisions independently without cloud dependency.

[0061] (1) Data fusion and health assessment

[0062] The main control unit integrates and analyzes multi-dimensional operating parameters and equipment operating environment data to generate a real-time equipment health score. The system can automatically adjust the evaluation parameters based on data fluctuation trends to ensure identification accuracy under different loads and environments.

[0063] (2) Trend prediction and life assessment

[0064] Based on the dynamic changes in historical and real-time data, the system analyzes the operating trends of centrifuges and predicts the direction of changes in key parameters, thereby estimating the remaining lifespan of the equipment and providing maintenance personnel with a reference for maintenance cycles and replacement plans.

[0065] (3) Fault early warning and alarm mechanism

[0066] When the system detects a decline in health score, sudden changes in operating parameters, or abnormal environmental conditions, it automatically triggers a multi-level early warning and alarm mechanism.

[0067] Level 1 warning: Indicates minor abnormalities or abnormal trends;

[0068] Level 2 alarm: A persistent abnormality has been detected;

[0069] Level 3 alarm: Critical parameters exceed limits or equipment may malfunction.

[0070] Alarm information is displayed in real time and accompanied by audible and visual alerts. Alarm logs can also be generated for subsequent tracing.

[0071] (4) Fault tracing mechanism

[0072] Upon alarm or anomaly trigger, the system automatically initiates a source tracing analysis process, performing time-series reverse analysis of key operating parameters to pinpoint the anomaly trigger point and generate a source tracing report. The report includes the anomaly type and possible causes, providing maintenance personnel with intuitive judgment criteria.

[0073] (5) Independent operation capability

[0074] The system's core analysis and judgment are completed locally at the edge, enabling monitoring, alarms, and data logging even in the event of a network outage, ensuring continuous system operation and security.

[0075] V. Cloud Interaction and Remote Management

[0076] (1) Cloud-based interaction and data visualization

[0077] The main control unit uploads its operating status, health score, and alarm records to the cloud platform via a 4G module. The cloud platform stores, visualizes, and analyzes the data for trend analysis (e.g., ...). Figure 6As shown in the figure, it can manage multiple devices simultaneously, enabling centralized monitoring and historical comparative analysis.

[0078] (2) Mobile terminal observation and auxiliary management

[0079] The accompanying mobile application is primarily used for remote monitoring and anomaly detection. The application can display the device's operating status, health indicators, and alarm logs in real time, and instantly notify maintenance personnel via push notifications when an anomaly is detected. The mobile app does not participate in core computing; it serves only as an auxiliary port for remote viewing and management.

[0080] VI. System Workflow

[0081] The system's workflow is as follows Figure 7 As shown, the main steps include:

[0082] (1) Data acquisition: Front-end sensors and acquisition nodes collect data on the centrifuge's operating status and equipment operating environment;

[0083] (2) Data transmission: The collected data is transmitted to the main control terminal via the LoRa network;

[0084] (3) Edge analysis: The main control unit performs feature fusion and state recognition to generate health scores, trend predictions and lifespan estimation results;

[0085] (4) Fault warning and alarm: Trigger a multi-level alarm mechanism based on the assessment results to indicate equipment abnormality;

[0086] (5) Display and source tracing: Alarm information is displayed on the touch screen, and the system starts source tracing analysis and generates a report at the same time;

[0087] (6) Cloud synchronization and remote viewing: The main control terminal uploads the results to the cloud to realize remote access and centralized monitoring.

[0088] The system of this invention achieves real-time monitoring, health assessment, fault alarm, early warning, and source tracing analysis of centrifuge operating status through edge computing, constructing an intelligent operation and maintenance closed loop of "collection-analysis-display-management". The system features a modular structure, independent decision-making at the edge, a multi-level early warning mechanism, and collaborative analysis of the equipment operating environment, significantly improving the operation and maintenance efficiency and reliability of equipment in industrial sites such as wastewater treatment plants.

Claims

1. A centrifuge full lifecycle intelligent operation and maintenance system based on edge computing, characterized in that, By combining modular hardware architecture, multi-source data acquisition, and edge intelligent analysis, a closed-loop operation and maintenance system is built, from data acquisition and status recognition to visual management. It consists of a main control unit, a communication module, a display and interaction module, a power management module, and a health management software system. The modules work together to achieve local intelligent analysis and remote visual management of the centrifuge's operating status. The main control unit adopts a collaborative architecture of industrial-grade embedded processor and microcontroller, which synchronously acquires operating status and environmental parameters, performs signal preprocessing, feature fusion and status recognition; it has a built-in multi-model fusion algorithm to dynamically generate equipment health scores and trend prediction results based on real-time monitoring data, and outputs remaining life estimates to provide data basis for maintenance decisions; the core computing and judgment logic is deployed at the edge. The communication module supports multiple wired and wireless transmission methods and automatically switches according to the on-site network conditions; it is equipped with local caching and breakpoint resume mechanism to ensure data integrity and continuity and achieve highly reliable data interaction. The display and interaction module shows the device's operating parameters, health score, alarm information, and trend curves in real time through a touch screen; the interface structure follows the pattern of monitoring, evaluation, early warning, and tracing, intuitively reflecting the current and future operating status; when the health value is abnormal or the lifespan is close to the threshold, multi-level alarm prompts are automatically triggered, and logs are recorded for traceability; The power management module features voltage regulation, overcurrent, and reverse connection protection, adapting to high humidity and high corrosion environments to ensure long-term stable operation. The accompanying mobile health management system receives analysis results from the edge device, enabling remote monitoring and event management. The mobile application displays device status, health trends, and alarm records through a graphical interface, supporting anomaly push notifications, historical playback, and operation log queries. This system collaborates with the cloud platform to achieve centralized monitoring of multiple devices and sharing of operation and maintenance data.

2. The intelligent operation and maintenance system for the entire lifecycle of centrifuges based on edge computing as described in claim 1, characterized in that, By introducing a multi-model fusion health assessment and trend prediction mechanism at the edge, combined with the coupled analysis of operation and environmental parameters, intelligent management of the entire process from data processing, anomaly identification, early warning and alarm to fault tracing can be achieved.

3. The intelligent operation and maintenance system for the entire lifecycle of centrifuges based on edge computing as described in claim 1, characterized in that, Edge computing technology enables local intelligent analysis and decision-making regarding the operating status of centrifuges.

4. The intelligent operation and maintenance system for the entire lifecycle of a centrifuge based on edge computing as described in claim 1, characterized in that, The main control unit is the core of the system. It uses an industrial-grade single-board computer as the edge computing center, which is responsible for the access, preprocessing, feature fusion and status analysis of multi-source sensor data, and independently completes real-time monitoring, health assessment, fault alarm, early warning and source tracing functions locally. The system monitors key operating parameters of the centrifuge in real time and dynamically assesses the health status of the equipment through an adaptive fusion analysis mechanism, generating health scores and trend curves. When abnormal health values ​​or sudden changes in status are detected, the system automatically triggers early warnings or alarms and records the abnormality tracing information for subsequent analysis. The main control unit is equipped with multiple interface modules for connecting operating status sensors and equipment operating environment sensors. Through multi-sensor collaborative acquisition and data cross-verification, it comprehensively reflects the impact of the centrifuge operating environment on the equipment's health status, thereby improving the accuracy and reliability of the judgment.

5. The intelligent operation and maintenance system for the entire lifecycle of centrifuges based on edge computing as described in claim 1, characterized in that, The system casing is made of high-strength ABS engineering plastic.

6. The intelligent operation and maintenance system for the entire lifecycle of a centrifuge based on edge computing as described in claim 1, characterized in that, The power management module uses a 12V DC input power supply and has internal voltage regulation and overcurrent protection circuits to ensure continuous and stable power supply in voltage fluctuations or humid environments.

7. The intelligent operation and maintenance system for the entire lifecycle of a centrifuge based on edge computing as described in claim 1, characterized in that, The system communication structure consists of three layers: the field layer, the edge layer, and the cloud layer, which are used to realize multi-node data transmission, edge computing result reporting, and remote visualization. The field layer consists of multiple acquisition nodes, which form a star network through LoRa wireless modules, with the central node being the main control unit. The data acquisition node is responsible for acquiring equipment operating status and operating environment data, and transmitting them to the main control terminal after preliminary processing. After receiving data from the acquisition nodes, the main control unit performs local analysis and outputs the results. The main control unit is equipped with a 4G communication module to enable data interaction and remote management with the cloud platform; the communication module supports multiple transmission protocols and automatically selects the optimal transmission path according to the network status to ensure the stability and security of data synchronization.

8. The intelligent operation and maintenance system for the entire lifecycle of centrifuges based on edge computing as described in claim 1, characterized in that, Includes the following steps: (1) Data fusion and health assessment; The main control unit integrates and analyzes multi-dimensional operating parameters and equipment operating environment data to generate equipment health scores in real time; The evaluation parameters are automatically adjusted based on data fluctuation trends to ensure recognition accuracy under different loads and environments; (2) Trend prediction and life assessment; Based on the dynamic changes in historical and real-time data, the system analyzes the operating trend of the centrifuge and predicts the direction of change of key parameters, thereby estimating the remaining life of the equipment and providing maintenance personnel with a reference for maintenance cycles and replacement plans. (3) Fault early warning and alarm mechanism; When the system detects a decline in health score, a sudden change in operating parameters, or abnormal environmental conditions, it automatically triggers a multi-level early warning and alarm mechanism. Level 1 warning: Indicates minor abnormalities or abnormal trends; Level 2 alarm: A persistent abnormality has been detected; Level 3 alarm: Critical parameters exceed limits or equipment may malfunction; Alarm information is displayed in real time with audible and visual alerts, and alarm logs can be generated for subsequent tracing. (4) Fault tracing mechanism; After an alarm or anomaly is triggered, the system automatically initiates the source tracing analysis process, performs time-series reverse analysis on key operating parameters, locates the anomaly trigger point, and generates a source tracing report. The report includes the anomaly type and possible causes, providing maintenance personnel with an intuitive basis for judgment. (5) Independent operation capability; The system's core analysis and judgment are completed locally at the edge, enabling monitoring, alarms, and data logging even in the event of a network outage, ensuring continuous system operation and security.

9. The intelligent operation and maintenance system for the entire lifecycle of a centrifuge based on edge computing as described in claim 1, characterized in that, The cloud-based interaction and remote management process is as follows: (1) Cloud-based interaction and data visualization; The main control unit uploads the operating status, health score and alarm records to the cloud platform through the 4G module; the cloud stores, visualizes and analyzes the data and manages multiple devices at the same time, realizing centralized monitoring and historical comparison analysis; (2) Mobile terminal observation and auxiliary management; A companion mobile application is used for remote observation and anomaly reception; the application can display the device's operating status, health index and alarm logs in real time, and immediately remind maintenance personnel through push notifications when an anomaly is detected; the mobile device does not participate in core computing, but serves as an auxiliary port for remote viewing and management.

10. The intelligent operation and maintenance system for the entire lifecycle of a centrifuge based on edge computing as described in claim 1, characterized in that, Includes the following steps: (1) Data acquisition: Front-end sensors and acquisition nodes collect data on the centrifuge's operating status and equipment operating environment; (2) Data transmission: The collected data is transmitted to the main control terminal via the LoRa network; (3) Edge analysis: The main control unit performs feature fusion and state recognition to generate health scores, trend predictions and lifespan estimation results; (4) Fault warning and alarm: Trigger a multi-level alarm mechanism based on the assessment results to indicate equipment abnormality; (5) Display and source tracing: Alarm information is displayed on the touch screen, and the system starts source tracing analysis and generates a report at the same time; (6) Cloud synchronization and remote viewing: The main control terminal uploads the results to the cloud to realize remote access and centralized monitoring.

Images