Lubricating state remote monitoring and early warning system based on Internet of Things

Abstract

The invention discloses a lubricating state remote monitoring and early warning system based on the Internet of Things. The system comprises a sensing layer used for collecting data bases in all directions; the acquisition layer can acquire basic data of various high-performance sensors of the sensing layer; data preprocessing and feature extraction are carried out; the network layer provides diversified data transmission channels; the platform layer receives the basic data preprocessed by the acquisition layer; analyzing and processing the data, and outputting an analysis result; and the application layer provides comprehensive service support and a friendly interactive interface for the user. According to the invention, through multi-dimensional monitoring of the oil quality, the lubrication parameters and the equipment state, comprehensive perception of the lubrication state is realized; based on digital twinning and multi-algorithm fusion, precise evaluation and fault early warning of the lubrication state are realized; according to the actual working condition and the lubricating requirement of equipment, the lubricating strategy is adjusted in a self-adaptive mode, and precise lubricating is achieved.

Description

Technical Field

[0001] This invention relates to the field of equipment maintenance technology, and more specifically to a remote monitoring and early warning system for lubrication status based on the Internet of Things. Background Technology

[0002] In wind turbine generator sets, lubrication is required periodically to maintain the equipment's lubrication condition. The lubrication system is crucial for the normal operation of the equipment; poor lubrication can lead to accelerated wear, decreased efficiency, and even equipment damage. Traditional lubrication condition monitoring mainly relies on periodic manual inspections or simple online monitoring systems.

[0003] The following problems exist: the monitoring parameters are limited, usually only basic parameters such as oil pressure and oil temperature are monitored, which cannot fully reflect the lubrication status; the early warning mechanism is simple, mainly based on fixed threshold alarms, and lacks intelligent analysis and prediction capabilities; the maintenance response is lagging, and predictive maintenance cannot be achieved, resulting in a high risk of equipment failure; the remote monitoring capability is insufficient, making it difficult to achieve centralized management and remote operation and maintenance of multiple devices. Summary of the Invention

[0004] Therefore, the present invention provides a remote monitoring and early warning system for lubrication status based on the Internet of Things to solve the problems in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A remote monitoring and early warning system for lubrication status based on the Internet of Things includes a sensing layer, a data acquisition layer, a network layer, a platform layer, and an application layer.

[0007] The perception layer serves as the foundation for comprehensive data acquisition; the perception layer is equipped with a variety of high-performance sensors.

[0008] The acquisition layer is capable of acquiring basic data from various high-performance sensors in the perception layer; performing data preprocessing and feature extraction; executing lubrication control logic; and transmitting the preprocessed basic data to the platform layer through the network layer.

[0009] The network layer provides diverse data transmission channels;

[0010] The platform layer receives the preprocessed basic data from the acquisition layer, analyzes and processes the data, and outputs the analysis results. The platform layer includes a data storage module, a fault diagnosis algorithm module, a lubrication condition assessment model, and a predictive maintenance model.

[0011] The application layer provides users with comprehensive service support and a user-friendly interface; it can transform the data collected by the perception layer and the analysis results of the platform layer into intuitive and easy-to-use business functions.

[0012] Furthermore, the various high-performance sensors include oil quality sensors, lubrication parameter sensors, equipment operation sensors, flow and pressure sensors, and vibration and temperature sensors.

[0013] Furthermore, the oil quality sensor employs micro-spectral analysis technology and capacitive sensing technology, enabling it to accurately monitor key indicators of lubricating oil.

[0014] The flow and pressure sensor group includes a high-precision pressure sensor and a turbine flow meter to monitor the oil supply pressure and flow parameters of the lubrication pipeline in real time.

[0015] The vibration and temperature sensor uses a piezoelectric vibration sensor and a temperature sensor to collect mechanical status data of the equipment during operation;

[0016] The equipment operation sensors include sound pressure sensors and speed sensors, which collect equipment operating noise and speed signals.

[0017] Furthermore: the acquisition layer includes an edge computing gateway, a protocol parsing module, a data caching module, and a secure transmission module;

[0018] The acquisition layer uses a protocol parsing module to convert and process basic data using various industrial protocols; the data caching module is equipped with a local storage unit to ensure data continuity and integrity even in the event of a network interruption; the secure transmission module ensures the security of data transmission; and the edge computing gateway is responsible not only for data acquisition and preprocessing but also for executing local lubrication control logic.

[0019] Furthermore, the edge computing gateway has built-in lubrication control logic, which maintains the normal operation of the lubrication system according to preset rules when the network is interrupted.

[0020] Furthermore: the network layer includes 4G / 5G wireless networks, Ethernet wired networks, WIFI wireless LANs, dedicated APN networks, and industrial Ethernet;

[0021] Among them, the 4G / 5G wireless network provides the system with wide-area wireless connectivity and supports flexible access for mobile devices; the Ethernet wired network ensures stable connection for key nodes; the WIFI wireless LAN facilitates access for on-site mobile devices; the dedicated APN network establishes a secure dedicated channel for data transmission; and the industrial Ethernet meets the stringent real-time requirements of industrial sites.

[0022] Furthermore: the data storage module adopts a hybrid architecture of time-series database and relational database;

[0023] The fault diagnosis algorithm module is based on a hybrid diagnostic model of rule-based reasoning and case-based reasoning; the lubrication condition assessment model achieves accurate assessment of lubrication condition through a multi-dimensional parameter fusion algorithm.

[0024] The formula for comprehensive evaluation of lubrication condition is:

[0025] ;

[0026] Where S is the overall lubrication condition score; n is the total number of key parameters involved in the evaluation; w i x is the weighting coefficient of the i-th parameter; i f is the real-time measured value of the i-th parameter; i (x i ) is the normalization function for the i-th parameter.

[0027] Furthermore: the predictive maintenance model uses machine learning technology to predict equipment lifespan and maintenance needs based on historical data and real-time monitoring information;

[0028] The formula for calculating the predicted remaining useful life of the equipment is as follows:

[0029] ;

[0030] Where L0 is the initial design life baseline value; λ is the comprehensive degradation rate coefficient, which characterizes the rate of equipment performance degradation; H(t) is the cumulative damage factor, which reflects the cumulative wear and tear of the equipment within time t; and ε is the random error term, which characterizes the prediction uncertainty.

[0031] The formula for calculating the cumulative damage factor is:

[0032] ;

[0033] Where k is the basic aging coefficient; F(τ) is the instantaneous load rate function; and τ is the integral variable.

[0034] The formula for calculating the degradation rate coefficient is:

[0035] ;

[0036] Where ΔM is the rate of change of metal scrap content; M avg The historical average metal debris concentration; σ V The standard deviation of the vibration amplitude; μ V The average difference in vibration amplitude; T excess The percentage of time spent operating at overtemperature; w1, w2, and w3 are the weights of each degradation index; T limit This is the temperature safety threshold.

[0037] Furthermore, the predictive maintenance model incorporates a real-time data feedback mechanism.

[0038] The adaptive correction term is:

[0039] ;

[0040] Where α is the learning rate parameter; y actual This refers to the actual observed value; y predicted These are the model's predicted values.

[0041] Furthermore: the application layer includes a remote monitoring screen, a mobile operation and maintenance APP, a visual configuration, an early warning center, and an operation and management module;

[0042] Among them, the remote monitoring screen uses WebGL technology to visualize the device status; the mobile operation and maintenance APP supports iOS and Android systems, making it convenient for users to monitor and manage anytime and anywhere; the visual configuration function provides a graphical display of device status and configuration interface; the early warning center is responsible for the management and push of multi-level early warning information; and the operation and maintenance management module supports the formulation and execution tracking of maintenance plans.

[0043] The present invention has the following advantages: it achieves comprehensive perception of lubrication status through multi-dimensional monitoring of oil quality, lubrication parameters and equipment status; it achieves accurate assessment of lubrication status and fault early warning based on digital twin and multi-algorithm fusion; and it adaptively adjusts lubrication strategy according to actual equipment operating conditions and lubrication needs to achieve precise lubrication.

[0044] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. Attached Figure Description

[0045] To more intuitively illustrate the prior art and this application, exemplary drawings are provided below. It should be understood that the specific shapes and structures shown in the drawings should not generally be regarded as limiting conditions for implementing this application; for example, based on the technical concept disclosed in this application and the exemplary drawings, those skilled in the art are able to easily make conventional adjustments or further optimizations to the addition / reduction / classification, specific shapes, positional relationships, connection methods, size ratios, etc. of certain units (components).

[0046] Figure 1 This is an architectural block diagram of an IoT-based remote monitoring and early warning system for lubrication status, provided as an embodiment of this application. Detailed Implementation

[0047] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. It should be understood that these embodiments are merely for further explanation of the present invention and should not be construed as limiting the scope of protection of the present invention. Technical engineers in the field can make some non-essential improvements and adjustments to the present invention based on the above-described content. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] Please see Figure 1 A remote monitoring and early warning system for lubrication status based on the Internet of Things includes a sensing layer, a data acquisition layer, a network layer, a platform layer, and an application layer.

[0049] The sensing layer is used for comprehensive data acquisition; the sensing layer is equipped with a variety of high-performance sensors, including oil quality sensors, lubrication parameter sensors, equipment operation sensors, flow and pressure sensors, and vibration and temperature sensors.

[0050] Among them, the oil quality sensor uses micro-spectral analysis technology and capacitive sensing technology to accurately monitor key indicators such as viscosity, water content, particulate contamination and metal shavings content of lubricating oil.

[0051] The flow and pressure sensor group includes a high-precision pressure sensor and a turbine flow meter to monitor the oil supply pressure and flow parameters of the lubrication pipeline in real time.

[0052] The vibration and temperature sensor uses a piezoelectric vibration sensor and a PT100 temperature sensor to collect mechanical status data of the equipment during operation.

[0053] The equipment operation sensors include sound pressure sensors and speed sensors, which are used to collect equipment operating noise and speed signals. These sensors provide accurate and comprehensive raw data support for lubrication condition assessment.

[0054] The acquisition layer collects basic data from each sensor in the perception layer; performs data preprocessing and feature extraction; executes lubrication control logic; and transmits the preprocessed basic data to the platform layer through the network layer.

[0055] The acquisition layer includes an edge computing gateway, a protocol parsing module, a data caching module, and a secure transmission module. Among them, the acquisition layer supports the conversion and processing of various industrial protocols such as MODBUS / TCP, PROFIBUS, and OPC UA through the protocol parsing module, realizing the unified acquisition of multi-source heterogeneous data.

[0056] The data caching module is equipped with a local storage unit to ensure the continuity and integrity of data in the event of a network interruption; the secure transmission module uses TLS / SSL encrypted transmission and data signature technology to ensure the security of data transmission.

[0057] Edge computing gateways are not only responsible for data collection and preprocessing, but also for executing local lubrication control logic, effectively reducing the cloud processing burden and improving system response speed and reliability.

[0058] In addition, the edge computing gateway has built-in lubrication control logic, which maintains the normal operation of the lubrication system according to preset rules when the network is interrupted.

[0059] The network layer provides diverse and highly reliable data transmission channels, including 4G / 5G wireless networks, Ethernet wired networks, WIFI wireless LANs, dedicated APN networks, and industrial Ethernet.

[0060] The system utilizes a multi-layered, redundant network architecture, including 4G / 5G wireless networks, to provide wide-area wireless connectivity and support flexible access for mobile devices. An Ethernet wired network ensures stable and reliable connections for critical nodes. A Wi-Fi wireless LAN facilitates access for mobile devices in the field. A dedicated APN network establishes a secure data transmission channel. Industrial Ethernet meets the stringent real-time requirements of industrial environments. This multi-layered, redundant network architecture ensures stable and reliable data transmission under various operating conditions.

[0061] The platform layer receives the preprocessed basic data from the acquisition layer; it then analyzes and processes the data and outputs the analysis results.

[0062] The platform layer includes a data storage module, a fault diagnosis algorithm module, a lubrication condition assessment model, and a predictive maintenance model;

[0063] The data storage module adopts a hybrid architecture of time-series database and relational database to effectively manage massive amounts of monitoring data.

[0064] The fault diagnosis algorithm module is based on a hybrid diagnostic model of rule-based reasoning and case-based reasoning, which can accurately identify system faults; the lubrication status assessment model achieves accurate assessment of lubrication status through a multi-dimensional parameter fusion algorithm.

[0065] The formula for comprehensive evaluation of lubrication condition is:

[0066] ;

[0067] Where S is the overall lubrication condition score (dimensionless), ranging from [0, 1], with a value closer to 1 indicating better lubrication condition; n is the total number of key parameters involved in the evaluation (n=8 in this scheme); wi The weight coefficients of the i-th parameter (∑w) i =1), reflecting the degree of influence of this parameter on lubrication status, determined by domain experts or training with historical data; x i f is the real-time measured value of the i-th parameter; i (x i ) is the normalization function for the i-th parameter, which maps the original measurement value to the interval [0, 1].

[0068] Predictive maintenance models use machine learning techniques to predict equipment lifespan and maintenance needs based on historical data and real-time monitoring information;

[0069] The formula for calculating the predicted remaining useful life of the equipment is as follows:

[0070] ;

[0071] Where L0 is the initial design life baseline value (provided by the equipment manufacturer or derived from historical data statistics); λ is the comprehensive degradation rate coefficient (affected by multiple factors), characterizing the rate of equipment performance degradation; H(t) is the cumulative damage factor, reflecting the cumulative wear and tear of the equipment within time t; and ε is the random error term (following a normal distribution), characterizing the prediction uncertainty.

[0072] The formula for calculating the cumulative damage factor is:

[0073] ;

[0074] Where k is the basic aging coefficient (related to material properties); F(τ) is the instantaneous load rate function (determined by real-time operating conditions, such as speed, load current, etc.); and τ is the integral variable.

[0075] The formula for calculating the degradation rate coefficient is:

[0076] ;

[0077] Where ΔM is the rate of change of metal scrap content (increment per unit time); M avg σ represents the historical average metal debris concentration. V The standard deviation of the vibration amplitude; μ V The average difference in vibration amplitude; T excess The percentage of time spent operating at excessive temperatures (relative to the safety threshold); w1, w2, and w3 are the weights of each degradation indicator (optimized through machine learning training); T limit This is the temperature safety threshold.

[0078] Introducing a real-time data feedback mechanism allows for the addition of adaptive correction items:

[0079] Where α is the learning rate parameter (controlling the correction magnitude); y actual For actual observed values ​​(such as sudden shutdown events); y predicted These are the model's predicted values.

[0080] The application layer provides users with comprehensive service support and a user-friendly interface;

[0081] The application layer includes a remote monitoring dashboard, a mobile operation and maintenance APP, a visual configuration, an early warning center, and an operation and management module.

[0082] Among them, the remote monitoring screen uses WebGL technology to visualize the device status; the mobile operation and maintenance APP supports iOS and Android systems, making it convenient for users to monitor and manage anytime and anywhere; the visual configuration function provides a graphical display of device status and configuration interface; the early warning center is responsible for the management and push of multi-level early warning information; and the operation and maintenance management module supports the formulation and execution tracking of maintenance plans.

[0083] The application layer can transform the data collected by the perception layer and the analysis results of the platform layer into intuitive and easy-to-use business functions.

[0084] This invention achieves comprehensive perception of lubrication status through multi-dimensional monitoring of oil quality, lubrication parameters, and equipment status; it achieves accurate assessment of lubrication status and fault early warning based on digital twins and multi-algorithm fusion; and it adaptively adjusts lubrication strategies according to actual equipment operating conditions and lubrication needs to achieve precise lubrication.

[0085] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A remote monitoring and early warning system for lubrication status based on the Internet of Things, characterized in that, It includes the perception layer, acquisition layer, network layer, platform layer, and application layer; The perception layer serves as the foundation for comprehensive data acquisition; the perception layer is equipped with a variety of high-performance sensors. The acquisition layer is capable of acquiring basic data from various high-performance sensors in the perception layer; performing data preprocessing and feature extraction; and also executing lubrication control logic. The preprocessed basic data is then transmitted to the platform layer via the network layer. The network layer provides diverse data transmission channels; The platform layer receives the preprocessed basic data from the acquisition layer; The platform analyzes and processes the data and outputs the results; it includes a data storage module, a fault diagnosis algorithm module, a lubrication condition assessment model, and a predictive maintenance model. The application layer provides users with comprehensive service support and a user-friendly interface; it can transform the data collected by the perception layer and the analysis results of the platform layer into intuitive and easy-to-use business functions.

2. The remote monitoring and early warning system for lubrication status based on the Internet of Things according to claim 1, characterized in that, The various high-performance sensors include oil quality sensors, lubrication parameter sensors, equipment operation sensors, flow and pressure sensors, and vibration and temperature sensors.

3. The remote monitoring and early warning system for lubrication status based on the Internet of Things according to claim 2, characterized in that, The oil quality sensor uses micro-spectral analysis technology and capacitive sensing technology to accurately monitor key indicators of lubricating oil. The flow and pressure sensor group includes a high-precision pressure sensor and a turbine flow meter to monitor the oil supply pressure and flow parameters of the lubrication pipeline in real time. The vibration and temperature sensor uses a piezoelectric vibration sensor and a temperature sensor to collect mechanical status data of the equipment during operation; The equipment operation sensors include sound pressure sensors and speed sensors, which collect equipment operating noise and speed signals.

4. The remote monitoring and early warning system for lubrication status based on the Internet of Things according to claim 1, characterized in that, The acquisition layer includes an edge computing gateway, a protocol parsing module, a data caching module, and a secure transmission module; The acquisition layer uses a protocol parsing module to convert and process basic data using various industrial protocols; the data caching module is equipped with a local storage unit to ensure data continuity and integrity even in the event of a network interruption; the secure transmission module ensures the security of data transmission; and the edge computing gateway is responsible not only for data acquisition and preprocessing but also for executing local lubrication control logic.

5. The remote monitoring and early warning system for lubrication status based on the Internet of Things according to claim 4, characterized in that, The edge computing gateway has built-in lubrication control logic, which maintains the normal operation of the lubrication system according to preset rules when the network is interrupted.

6. The remote monitoring and early warning system for lubrication status based on the Internet of Things according to claim 1, characterized in that, The network layer includes 4G / 5G wireless networks, Ethernet wired networks, WIFI wireless local area networks, dedicated APN networks, and industrial Ethernet. Among them, the 4G / 5G wireless network provides the system with wide-area wireless connectivity and supports flexible access for mobile devices; the Ethernet wired network ensures stable connection for key nodes; the WIFI wireless LAN facilitates access for on-site mobile devices; the dedicated APN network establishes a secure dedicated channel for data transmission; and the industrial Ethernet meets the stringent real-time requirements of industrial sites.

7. The remote monitoring and early warning system for lubrication status based on the Internet of Things according to claim 1, characterized in that, The data storage module adopts a hybrid architecture of time-series database and relational database; The fault diagnosis algorithm module is based on a hybrid diagnostic model of rule-based reasoning and case-based reasoning; the lubrication condition assessment model achieves accurate assessment of lubrication condition through a multi-dimensional parameter fusion algorithm. The formula for comprehensive evaluation of lubrication condition is: ； Where S is the overall lubrication condition score; n is the total number of key parameters involved in the evaluation; w i x is the weighting coefficient of the i-th parameter; i f is the real-time measured value of the i-th parameter; i (x i ) is the normalization function for the i-th parameter.

8. The remote monitoring and early warning system for lubrication status based on the Internet of Things according to claim 1, characterized in that, The predictive maintenance model uses machine learning technology to predict equipment lifespan and maintenance needs based on historical data and real-time monitoring information. The formula for calculating the predicted remaining useful life of the equipment is as follows: ； Where L0 is the initial design life baseline value; λ is the comprehensive degradation rate coefficient, which characterizes the rate of equipment performance degradation; H(t) is the cumulative damage factor, which reflects the cumulative wear and tear of the equipment within time t; and ε is the random error term, which characterizes the prediction uncertainty. The formula for calculating the cumulative damage factor is: ； Where k is the basic aging coefficient; F(τ) is the instantaneous load rate function; and τ is the integral variable. The formula for calculating the degradation rate coefficient is: ； Where ΔM is the rate of change of metal scrap content; M avg The historical average metal debris concentration; σ V The standard deviation of the vibration amplitude; μ V The average difference in vibration amplitude; T excess The percentage of time spent operating at overtemperature; w1, w2, and w3 are the weights of each degradation index; T limit This is the temperature safety threshold.

9. A remote monitoring and early warning system for lubrication status based on the Internet of Things as described in claim 8, characterized in that, The predictive maintenance model incorporates a real-time data feedback mechanism. The adaptive correction term is: ； Where α is the learning rate parameter; y actual This refers to the actual observed value; y predicted These are the model's predicted values.

10. A remote monitoring and early warning system for lubrication status based on the Internet of Things according to claim 1, characterized in that, The application layer includes a remote monitoring screen, a mobile operation and maintenance APP, a visual configuration, an early warning center, and an operation and management module. Among them, the remote monitoring screen uses WebGL technology to visualize the device status; the mobile operation and maintenance APP supports iOS and Android systems, making it convenient for users to monitor and manage anytime and anywhere; the visual configuration function provides a graphical display of device status and configuration interface; the early warning center is responsible for the management and push of multi-level early warning information; and the operation and maintenance management module supports the formulation and execution tracking of maintenance plans.

Images