Intelligent operation and maintenance system, method and equipment for steam turbine lubricating oil and storage medium

Abstract

The invention discloses an intelligent operation and maintenance system, method and equipment for steam turbine lubricating oil and a storage medium, and relates to the technical field of industrial digital intelligent operation and maintenance. Zero loss and low delay of data are guaranteed through the data transmission module, and the data fault problem of traditional manual meter reading is solved; static parameters are converted into dynamic trend, residual life and abnormal early warning through a hybrid model of a visual cloud operation and maintenance module, and intelligent conversion from data to decision is realized; and the oil filtering execution module automatically responds to the instruction to complete closed-loop treatment from polluted oil liquid to clean oil liquid without manual intervention, so that real-time monitoring and intelligent analysis of the running state of the steam turbine are realized, an oil filtering system is automatically started when a set threshold value is reached, the oil liquid is ensured to be in a normal state, the maintenance cost is reduced, and the operation and maintenance efficiency is improved.

Description

Technical Field

[0001] This application relates to the technical field of industrial digital intelligent operation and maintenance, and particularly to an intelligent operation and maintenance system, method, device and storage medium for steam turbine lubricating oil. Background Technique

[0002] With the popularization of the concepts of industry and intelligent manufacturing, the intelligentization and digitization of equipment operation and maintenance have become the key trends to improve the reliability and efficiency of industrial equipment. As the core power equipment in industries such as electric power and petrochemical, the stable operation of the lubricating oil system of steam turbines is crucial for ensuring equipment life and improving production efficiency.

[0003] In related technologies, the traditional operation and maintenance of steam turbine lubricating oil mainly rely on manual inspection and regular offline detection. However, the applicant has recognized that this method has obvious defects such as lagging response, discontinuous data, and insufficient fault prediction ability. Moreover, the existing technical system has imperfect supervision of oil product state information and untimely system data feedback. These problems lead to the pollution of steam turbine oil during operation due to factors such as moisture, wear particles, temperature, humidity, and foreign pollutants, which in turn cause increased equipment wear and aging, ultimately resulting in low working efficiency and increased failure rate of oil-using equipment, and even threatening the safe operation of the entire power system. Summary of the Invention

[0004] In view of this, this application provides an intelligent operation and maintenance system, method, device and storage medium for steam turbine lubricating oil, mainly aiming to solve the problems in the existing technology such as lagging response, discontinuous data, and insufficient fault prediction ability, which cause increased equipment wear and aging, ultimately resulting in low working efficiency and increased failure rate of oil-using equipment, and even threatening the safe operation of the entire power system.

[0005] According to the first aspect of this application, an intelligent operation and maintenance system for steam turbine lubricating oil is provided. The system includes a data acquisition module, a data transmission module, a visual oil cloud operation and maintenance module, and an oil filtering execution module; The data acquisition module is used to collect the state parameters of the steam turbine lubricating oil and transmit the state parameters to the data transmission module; The data transmission module is used to store the state parameters and transmit them to the visual oil cloud operation and maintenance module; The visual oil cloud operation and maintenance module is used to perform data analysis on the state parameters using a hybrid machine learning model to obtain an oil health index, visually display the oil health index, and when it is detected that the oil health index belongs to the secondary warning of the grading warning mechanism, generate an oil filtering device start-stop instruction and transmit the oil filtering device start-stop instruction to the oil filtering execution module; The oil filtering execution module is configured to respond to the start / stop instruction of the oil filtering device and perform multi-stage filtering and constant temperature control operations on the steam turbine lubricating oil through an oil filtering assembly.

[0006] According to a second aspect of the present application, there is provided an intelligent operation and maintenance method for steam turbine lubricating oil, the method comprising: Collecting state parameters of the steam turbine lubricating oil based on a data acquisition module; Storing and transmitting the state parameters to a visual oil cloud operation and maintenance module based on a data transmission module; Based on the visual oil cloud operation and maintenance module, performing data analysis on the state parameters by using a hybrid machine learning model to obtain an oil health index, and visually displaying the oil health index; When it is detected based on the visual oil cloud operation and maintenance module that the oil health index belongs to a secondary warning of a grading warning mechanism, generating a start / stop instruction for the oil filtering device, and transmitting the start / stop instruction for the oil filtering device to the oil filtering execution module; Based on the oil filtering execution module responding to the start / stop instruction of the oil filtering device, performing multi-stage filtering and constant temperature control operations on the steam turbine lubricating oil through an oil filtering assembly.

[0007] According to a third aspect of the present application, there is provided a device, comprising a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the system according to any one of the above first aspects are implemented.

[0008] According to a fourth aspect of the present application, there is provided a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the system according to any one of the above first aspects are implemented.

[0009] By means of the above technical solutions, the technical solutions provided by the embodiments of the present application at least have the following advantages: A steam turbine lubricating oil intelligent operation and maintenance system, method, device and storage medium provided by the present application. The present application includes a data acquisition module, a data transmission module, a visual oil cloud operation and maintenance module, and an oil filtration execution module. The data acquisition module is used to collect the state parameters of the steam turbine lubricating oil and transmit the state parameters to the data transmission module. The data transmission module is used to store the state parameters and transmit them to the visual oil cloud operation and maintenance module. The visual oil cloud operation and maintenance module is used to perform data analysis on the state parameters by using a hybrid machine learning model to obtain oil health indicators, visually display the oil health indicators, and generate an oil filtration device start-stop instruction when it is detected that the oil health indicator belongs to the secondary warning of the hierarchical warning mechanism, and transmit the oil filtration device start-stop instruction to the oil filtration execution module. The oil filtration execution module is used to respond to the oil filtration device start-stop instruction and perform multi-stage filtration and constant temperature control operations on the steam turbine lubricating oil through an oil filtration component. Due to the fact that manual inspection relies on experience and the data is lagging, it is difficult to capture the trend of oil deterioration in a timely manner, and equipment failures often occur suddenly. Therefore, in the present application, multi-sensors of the data acquisition module cover multi-dimensional parameters such as the physical, chemical, and morphological properties of the oil; the data transmission module ensures zero data loss and low latency, solving the data fault problem of traditional manual meter reading; the hybrid model of the visual cloud operation and maintenance module converts static parameters into dynamic trends, remaining life, and abnormal warnings, realizing the intelligent conversion from data to decision-making; the oil filtration execution module automatically responds to the instruction to complete the closed-loop processing of contaminated oil to clean oil without manual intervention, so as to realize the real-time monitoring and intelligent analysis of the steam turbine operation state, automatically start the oil filtration system when the set threshold is reached, ensure that the oil is in a normal state, thereby reducing the maintenance cost and improving the operation and maintenance efficiency.

[0010] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specific embodiments of the present application are specifically given. Brief Description of the Drawings

[0011] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 Shows a schematic diagram of the system architecture of an intelligent operation and maintenance of steam turbine lubricating oil provided by an embodiment of the present application; Figure 2 Shows a schematic diagram of the system architecture of a data acquisition module provided by an embodiment of the present application; Figure 3Shows a schematic diagram of the system architecture of a data transmission module provided by an embodiment of the present application; Figure 4 Shows a schematic diagram of the method flow of intelligent operation and maintenance of steam turbine lubricating oil provided by an embodiment of the present application; Figure 5 Shows a schematic diagram of another method flow of intelligent operation and maintenance of steam turbine lubricating oil provided by an embodiment of the present application; Figure 6 Shows a schematic diagram of the structure of intelligent operation and maintenance of steam turbine lubricating oil provided by an embodiment of the present application; Figure 7 Shows a schematic diagram of the device structure of a device provided by an embodiment of the present application. Detailed implementation manners

[0012] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present application.

[0013] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality" means two or more unless otherwise specifically defined.

[0014] In the present application, unless otherwise clearly specified and limited, the terms "install", "connect", "connection", "fix", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0015] The present application will be described in detail below with reference to the drawings and in combination with embodiments. It should be noted that, without conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0016] Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0017] An embodiment of the present application provides an intelligent operation and maintenance system for steam turbine lubricating oil. As Figure 1 shown, the system includes a data acquisition module 101, a data transmission module 102, a visual oil cloud operation and maintenance module 103, and an oil filtration execution module 104.

[0018] The data acquisition module 101 is used to collect the state parameters of the steam turbine lubricating oil and transmit the state parameters to the data transmission module 102. Traditional methods rely on manual sampling and can only detect limited parameters such as viscosity and particle size, and cannot capture the chemical changes and dynamic characteristics of the oil, resulting in difficult discovery of hidden faults. Therefore, the present application collects multi-dimensional indicators of the oil in real time through a variety of sensors to achieve full-parameter, high-frequency, and non-blind-spot monitoring of the oil state, and can capture precursors of hidden faults such as oil oxidation and additive loss in advance, enabling operation and maintenance to change from passive waiting for faults to active searching for potential hazards.

[0019] The data transmission module 102 is used to store the state parameters and transmit them to the visual oil cloud operation and maintenance module 103. Traditional methods lack a reliable data transmission and storage mechanism, and oil parameters are easily lost and difficult to trace. Therefore, the present application uses a data exchanger and an oil cloud server to ensure zero loss in the data acquisition, storage, and transmission processes, and can also achieve long-term traceability of historical data, providing a data foundation for the full life cycle management of the oil.

[0020] The Visualized Oil Cloud Operation and Maintenance Module 103 is used to perform data analysis on the state parameters by using a hybrid machine learning model to obtain the oil health indicators, visually display the oil health indicators, and when it is detected that the oil health indicators belong to the secondary warning of the hierarchical warning mechanism, that is, the oil health indicators exceed the preset upper limit value but do not exceed the safety limit value, or the trend shows continuous deterioration, such as the viscosity exceeding 1.2 times the new oil standard, the particle size exceeding grade 8, the moisture content exceeding 100 mg / L, etc., generate the start / stop command of the oil filter device, and transmit the start / stop command of the oil filter device to the Oil Filter Execution Module 104, so as to provide timely warnings and maintenance suggestions and improve the operation and maintenance efficiency. The traditional method uses manual interpretation of the oil report, relying on experience, resulting in large differences in conclusions among different operation and maintenance personnel and being unable to predict the future state. Therefore, the Visualized Oil Cloud Operation and Maintenance Module uses a hybrid machine learning model including LSTM, random forest, and SVM, replacing empirical interpretation with algorithms. LSTM can predict the future trend of oil parameters, random forest can quantify the remaining life, and SVM can identify abnormal patterns, making the oil health diagnosis change from subjective and fuzzy judgment to objective and accurate decision-making.

[0021] The Oil Filter Execution Module 104 is used to respond to the start / stop command of the oil filter device and perform multi-stage filtration and constant temperature control operations on the steam turbine lubricating oil through the oil filter components. After the traditional method discovers oil abnormalities, it is necessary to manually coordinate the start of oil filtration / stop, and the whole process takes a long time and cannot be processed in a timely manner. Therefore, this application constructs an automated closed-loop including warning, decision-making, and execution, compressing the abnormal response from manual hours to system minutes, avoiding small abnormalities from delaying into major faults, and ensuring the continuous operation of the equipment.

[0022] Specifically, as Figure 2 shown, the Data Acquisition Module 101 includes a multi-parameter sensing unit 1011, a signal conversion unit 1012, and a transmission unit 1013.

[0023] The multi-parameter sensing unit 1011 is connected to the signal conversion unit 1012 and is used to collect the flow image of the steam turbine lubricating oil through a visualization sensor. The visualization sensor can complete real-time dynamic image capture within 2-5 seconds in the oil flow state, accurately detect multi-dimensional indicators such as particle size distribution, number concentration, and moisture pollution. Subsequently, through a hybrid machine learning model, the particle morphology characteristics can be intelligently classified according to standards such as ISO / NAS1638 and ASTM, effectively distinguishing particle types such as cutting wear, fatigue wear, dust, and pollution; the fluorescence spectrum signal of the steam turbine lubricating oil is collected through a nano-sensor. Nano-scale quantum dot fluorescent markers (such as CdSe / ZnS quantum dots) are pre-introduced into the lubricating oil to track the aging path of the oil product in real time through the fluorescence spectrum. Using the fluorescence characteristics of different aging products (such as aldehydes and ketones generated by oxidation and nitrogen-containing compounds generated by nitrification) in the oil at specific excitation wavelengths, the fluorescence spectrum signal of the oil during use is collected. Subsequently, by extracting the characteristic fluorescence peaks and comparing them with the established fluorescence database of aging products, combined with the change trend of fluorescence intensity over time, the generation rate of various aging products (such as the generation rate of oxidation and nitrification products) is determined, thereby identifying the path and stage of the oil from initial aging to deterioration. This can achieve visual monitoring of the molecular-level oil deterioration process and break through the limitation of traditional sensors that only monitor macroscopic parameters; the shear resistance signal of the steam turbine lubricating oil is collected through a viscosity sensor, the pollutant concentration signal of the steam turbine lubricating oil is collected through a contamination sensor, the particle size distribution and number concentration signal of the steam turbine lubricating oil are collected through a particle counter, the free water content and dissolved water content signal of the steam turbine lubricating oil are collected through a moisture sensor, and the real-time temperature signal of the steam turbine lubricating oil is collected through a temperature sensor. Through the collaborative design of the visualization sensor for dynamic particle capture, the nano-sensor for molecular-level aging tracking, and multiple conventional sensors for complementing basic parameters by the multi-parameter sensing unit 1011, the problems of difficult particle traceability, difficult aging quantification, and incomplete parameters in traditional oil monitoring are solved.

[0024] The signal conversion unit 1012 is connected to the transmission unit 1013 and is used to perform digital-to-analog conversion on the fluorescence spectrum signal, shear resistance signal, pollutant concentration signal, particle size distribution and number concentration signal, free water content and dissolved water content signal, and real-time temperature signal to obtain state parameters. Since the signal types output by different sensors are messy, direct transmission without processing easily leads to problems such as data ambiguity and transmission packet loss. Therefore, this application performs digital-to-analog conversion and standardized encapsulation on multi-source heterogeneous signals to provide low-noise and high-consistency input for downstream modules and improve the model analysis accuracy.

[0025] The transmission unit 1013 is used to transmit the status parameters to the data transmission module 102. In the traditional method, data is manually sampled and then manually input, which has problems such as high latency and easy errors, and cannot support real-time operation and maintenance decisions. In this application, the data is uploaded in seconds through 5G / WIFI wireless transmission technology.

[0026] Specifically, as Figure 3 shown, the data transmission module 102 includes a data exchanger 1021 and an oil fluid cloud server 1022.

[0027] The data exchanger 1021 is connected to the oil fluid cloud server 1022, and is used to receive the status parameters transmitted by the data acquisition module 101, perform verification and formatting processing on the status parameters, and transmit the processed status parameters to the oil fluid cloud server 1022 to reduce the model analysis error rate.

[0028] The oil fluid cloud server 1022 stores the processed status parameters in the oil fluid status database, and transmits the processed status parameters to the visual oil fluid cloud operation and maintenance module 103.

[0029] Specifically, the visual oil fluid cloud operation and maintenance module 103 is used to input the status parameters into the LSTM neural network of the hybrid machine learning model for time series prediction, mine the long-term dynamic associations of oil fluid parameters, such as the coupled changes of viscosity and temperature, operating duration, etc., to obtain a time series prediction curve. Use the random forest algorithm of the hybrid machine learning model to evaluate the remaining life of the status parameters, perform weighted calculations on multi-dimensional features including particle distribution, water emulsification degree, viscosity change rate, etc., to obtain the remaining life of the oil fluid. Input the status parameters into the support vector machine of the hybrid machine learning model for abnormal pattern recognition to obtain an abnormal classification result, identify tiny abnormal patterns, and improve the early warning accuracy. Take the time series prediction curve, the remaining life of the oil fluid, and the abnormal classification result as oil fluid health indicators, and use visual interaction components to visually display the oil fluid health indicators. Traditional oil fluid analysis relies on a single tool such as manually looking at trend charts, simple threshold alarms, etc., which has problems such as inaccurate trend prediction, fuzzy life assessment, and rough abnormal identification. Therefore, the visual oil fluid cloud operation and maintenance module 103 intuitively shows the oil fluid deterioration direction through the future trend output by LSTM, and early warns of potential risks; accurately guides planned oil change through the remaining life output by the random forest, avoiding waste caused by premature oil change or equipment damage caused by late oil change; identifies abnormal types through SVM, associates equipment components, directly points to faults, and shortens the operation and maintenance response time.

[0030] Specifically, the visual oil fluid cloud operation and maintenance module 103 is used to generate an operation and maintenance attention prompt and visually display the operation and maintenance attention prompt when it detects that the oil fluid health indicator belongs to the first-level warning of the hierarchical early warning mechanism, that is, when the oil fluid health indicator is slightly higher than the preset baseline or the trend fluctuates abnormally but does not significantly exceed the safety limit value.

[0031] When it is detected that the oil health index belongs to the third-level warning of the grading warning mechanism, that is, the oil health index exceeds the safety limit value, or there is a drastic abnormal trend (such as a sudden increase in abrasive particles), a device shutdown protection instruction is generated, and the device shutdown protection instruction is sent to the steam turbine unit to stop the operation of the steam turbine unit, triggering device shutdown protection without manual intervention. The visual oil cloud operation and maintenance module 103 can also achieve remote monitoring and intelligent diagnosis through the cloud platform, support remote intervention by experts, and improve the accuracy and timeliness of fault diagnosis.

[0032] Specifically, the oil filtering execution module 104 is used to turn on the oil pump and the inlet valve, close the return valve, drive the steam turbine lubricating oil to pass through the primary filtering component and the secondary filtering component for hierarchical filtering in sequence, and at the same time start the electric heater, and collect the oil temperature in real time through the temperature sensor. Based on the temperature control feedback unit, the heating power is dynamically adjusted according to the oil temperature, so that the viscosity of the steam turbine lubricating oil is maintained within the preset optimal range; when the cleanliness and viscosity of the steam turbine lubricating oil meet the set thresholds, the return valve is opened and the oil pump is closed to ensure that the oil is in a normal state and avoid steam turbine failures. The multi-level filtering removes large particle impurities and micron-sized particles through primary and secondary filtering in sequence, significantly reducing the pollution degree and preventing abrasion caused by the recycling of abrasive particles and pollutants. The electric heater precisely controls the temperature to keep the oil operating within the optimal viscosity range, preventing the decrease in fluidity caused by low temperature or the acceleration of oil aging caused by high temperature. At the same time, in cooperation with the temperature control feedback mechanism, dynamic adjustment and constant temperature control are achieved through the temperature control feedback unit, so as to ensure that the oil continuously lubricates the equipment under clean and stable conditions.

[0033] Specifically, the temperature control feedback unit is used to increase the heating power according to a preset ratio when it is detected that the oil temperature is lower than the lower limit of the target temperature; when it is detected that the oil temperature is higher than the upper limit of the target temperature, the heating power is reduced step by step. Traditional temperature control relies on fixed-power heating, which has problems such as large oil temperature fluctuations, high energy consumption, and inability to adapt to complex working conditions. Therefore, through a dynamic power adjustment algorithm, low-temperature compensation is achieved, that is, when the oil temperature is lower than the target lower limit, the heating power is increased according to a preset ratio to quickly raise the temperature to the optimal range; over-temperature suppression is achieved, that is, when the oil temperature is higher than the target upper limit, the power is reduced step by step, and combined with air-cooled heat dissipation, to prevent the oil from overheating and aging.

[0034] Optionally, a microencapsulated self-healing agent (such as molybdenum disulfide nanoparticles) is pre-added to the lubricating oil. When the multi-parameter sensing unit 1011 determines that there is a risk of oil film rupture by monitoring indicators such as a sudden drop in viscosity, an increase in abrasive particle concentration, and abnormal oil film thickness, it combines electromagnetic field control technology to guide its directional deposition to the worn area and uses ultrasonic waves to trigger the release of the self-healing agent from the microcapsules to achieve real-time repair. This process synergizes with the oil filtration system's oil filtration operation. The intelligent repair system quickly intervenes and remedies in case of sudden risks, enhancing system stability and oil fluid life. Through the self-healing lubricating film generation technology, self-repair can be completed within 1 hour after the early warning of oil film rupture, avoiding downtime losses, reducing the bearing wear rate by 40%, and extending the equipment overhaul cycle.

[0035] The intelligent operation and maintenance system for steam turbine lubricating oil relies on the computing power of the server to provide services to users. The server can be an independent server or a server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, Content Delivery Network (CDN), as well as big data and artificial intelligence platforms.

[0036] The embodiment of the present application provides an intelligent operation and maintenance system for steam turbine lubricating oil. Compared with the prior art, the embodiment of the present application includes a data acquisition module, a data transmission module, a visual oil cloud operation and maintenance module, and an oil filtration execution module; the data acquisition module is used to collect the state parameters of the steam turbine lubricating oil and transmit the state parameters to the data transmission module; the data transmission module is used to store the state parameters and transmit them to the visual oil cloud operation and maintenance module; the visual oil cloud operation and maintenance module is used to perform data analysis on the state parameters by using a hybrid machine learning model to obtain oil health indicators, visually display the oil health indicators, and when it is detected that the oil health indicator belongs to the secondary warning of the grading warning mechanism, generate an oil filtration device start-stop instruction and transmit the oil filtration device start-stop instruction to the oil filtration execution module; the oil filtration execution module is used to respond to the oil filtration device start-stop instruction and perform multi-stage filtration and constant temperature control operations on the steam turbine lubricating oil through an oil filtration component. Since manual inspection depends on experience and the data is lagging, it is difficult to capture the deterioration trend of the oil in a timely manner, and equipment failures often occur suddenly. Therefore, in the present application, multi-sensors of the data acquisition module cover multi-dimensional parameters such as the physical, chemical, and morphological aspects of the oil; the data transmission module ensures zero data loss and low latency, solving the data fault problem of traditional manual meter reading; the hybrid model of the visual cloud operation and maintenance module converts static parameters into dynamic trends, remaining life, and abnormal warnings, realizing the intelligent conversion from data to decision-making; the oil filtration execution module automatically responds to the instruction to complete the closed-loop processing of contaminated oil to clean oil without manual intervention, thereby realizing the real-time monitoring and intelligent analysis of the operating state of the steam turbine, automatically starting the oil filtration system when the set threshold is reached, ensuring that the oil is in a normal state, and further reducing the maintenance cost and improving the operation and maintenance efficiency.

[0037] Further, as Figure 1 a specific implementation of the method, the embodiment of the present application provides an intelligent operation and maintenance method for steam turbine lubricating oil, as Figure 4 shown, the method includes: 201. Collect the state parameters of the steam turbine lubricating oil based on the data acquisition module.

[0038] In the embodiment of the present application, traditional manual sampling and monitoring can only obtain limited static parameters such as viscosity and total particle count, and cannot capture the dynamic characteristics and chemical changes of the oil, resulting in difficulty in timely discovering hidden faults. Therefore, through the collaborative collection of multi-type sensors, covering all-dimensional indicators of the physical, chemical, and morphological aspects of the oil, the visual sensor captures the oil flow image, which can analyze the particle movement trajectory and morphology to identify the wear type; the nano sensor collects the fluorescence spectrum, which can monitor the additive loss and the oil oxidation path; sensors such as viscosity, contamination, moisture, and temperature collect basic parameters, which can ensure that the all-dimensional state of the oil is knowable, and can solve the fundamental problems of incomplete, inaccurate, and untimely traditional oil operation and maintenance data.

[0039] 202. Store the status parameters based on the data transmission module and transmit them to the visual oil cloud operation and maintenance module.

[0040] In the embodiment of the present application, traditional data transmission relies on manual copying and simple network transmission, which has problems such as high packet loss rate, high latency, and no verification mechanism. Therefore, reliable verification and low-latency transmission are achieved through the data exchanger and the oil cloud server, which not only ensures the low latency of real-time applications but also reduces the long-term storage cost.

[0041] 203. Based on the visual oil cloud operation and maintenance module, use a hybrid machine learning model to perform data analysis on the status parameters to obtain oil health indicators and visually display the oil health indicators.

[0042] In the embodiment of the present application, through a hybrid machine learning model including LSTM, random forest, and SVM, full-dimensional coverage of oil health diagnosis is achieved, enabling the oil analysis to change from single-dimensional judgment to three-dimensional solid diagnosis, covering the entire scenarios of trend, life, and abnormality, and improving the diagnosis accuracy.

[0043] 204. When it is detected based on the visual oil cloud operation and maintenance module that the oil health indicator belongs to the secondary warning of the hierarchical warning mechanism, generate a start / stop instruction for the oil filter device and transmit the start / stop instruction for the oil filter device to the oil filter execution module.

[0044] In the embodiment of the present application, traditional operation and maintenance also shuts down for small abnormalities such as mild oil pollution, resulting in large production losses; for large abnormalities, no timely intervention is carried out, resulting in equipment damage. When it is detected based on the visual oil cloud operation and maintenance module that the oil health indicator is in a preset interval that requires intervention but does not require shutdown, trigger the oil filter instruction, which not only avoids overreacting and affecting production but also ensures that problems are handled in a timely manner.

[0045] 205. Based on the oil filter execution module responding to the start / stop instruction of the oil filter device, perform multi-stage filtration and constant temperature control operations on the steam turbine lubricating oil through the oil filter components.

[0046] In the embodiment of the present application, through the closed-loop of instruction response, automatic execution, and status feedback, automatic start / stop control, full-process automation, and real-time status feedback are achieved, reducing manpower input, shortening the oil filter response latency, improving the viscosity stability of the oil, and at the same time reducing energy consumption.

[0047] The embodiment of the present application provides an intelligent operation and maintenance method for steam turbine lubricating oil. Compared with the prior art, the embodiment of the present application collects the state parameters of the steam turbine lubricating oil based on the data acquisition module, stores and transmits the state parameters to the visual oil cloud operation and maintenance module based on the data transmission module, and uses a hybrid machine learning model to perform data analysis on the state parameters based on the visual oil cloud operation and maintenance module to obtain the oil health index, and visually displays the oil health index. When it is detected based on the visual oil cloud operation and maintenance module that the oil health index belongs to the secondary warning of the hierarchical warning mechanism, a start-stop instruction for the oil filter device is generated, and the start-stop instruction for the oil filter device is transmitted to the oil filter execution module. Based on the oil filter execution module responding to the start-stop instruction of the oil filter device, a multi-stage filtration and constant temperature control operation is performed on the steam turbine lubricating oil through the oil filter component. Due to the fact that manual inspection depends on experience and the data is lagged, it is difficult to capture the deterioration trend of the oil in a timely manner, and equipment failures often occur suddenly. Therefore, multi-sensors of the data acquisition module cover multi-dimensional parameters such as the physical, chemical, and morphological properties of the oil; the data transmission module ensures zero data loss and low latency, solving the data fault problem of traditional manual meter reading; the hybrid model of the visual cloud operation and maintenance module converts static parameters into dynamic trends, remaining life, and abnormal warnings, realizing the intelligent conversion from data to decision-making; the oil filter execution module automatically responds to the instruction to complete the closed-loop processing of the contaminated oil to the clean oil without manual intervention, thereby realizing the real-time monitoring and intelligent analysis of the operating state of the steam turbine, automatically starting the oil filter system when the set threshold is reached, ensuring that the oil is in a normal state, and further reducing the maintenance cost and improving the operation and maintenance efficiency.

[0048] Further, as a refinement and extension of the specific implementation manner of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, the embodiment of the present application provides another intelligent operation and maintenance method for steam turbine lubricating oil, as Figure 5 shown, the method includes: 301. Collect fluorescence spectrum signals, shear resistance signals, pollutant concentration signals, particle size distribution and number concentration signals, free water content and dissolved water content signals, and real-time temperature signals based on the multi-parameter sensing unit of the data acquisition module.

[0049] In the embodiment of the present application, based on the multi-parameter sensing unit of the data acquisition module, a visualization sensor is used to collect the flow image of the steam turbine lubricating oil. By capturing the oil flow image, the particle movement trajectory and morphology are analyzed to identify cutting wear and fatigue wear particles. A nano-sensor is used to collect the fluorescence spectrum signal of the steam turbine lubricating oil, and the additive loss and the oil oxidation path are monitored by collecting the fluorescence spectrum. A viscosity sensor is used to collect the shear resistance signal of the steam turbine lubricating oil. A contamination sensor is used to collect the pollutant concentration signal of the steam turbine lubricating oil. A particle counter is used to collect the particle size distribution and number concentration signal of the steam turbine lubricating oil. A moisture sensor is used to collect the free water content and dissolved water content signals of the steam turbine lubricating oil. A temperature sensor is used to collect the real-time temperature signal of the steam turbine lubricating oil. The data collected by traditional sensors has problems such as single dimension and high noise, resulting in the downstream analysis model being unable to distinguish particle types and unable to quantify the aging stage. Therefore, through multi-sensor collaborative acquisition, the physical, chemical, and dynamic full-dimensional indicators of the oil are covered, and the fault discovery rate is improved.

[0050] 302. The signal conversion unit based on the data acquisition module performs digital-to-analog conversion on the fluorescence spectrum signal, shear resistance signal, pollutant concentration signal, particle size distribution and number concentration signal, free water content and dissolved water content signal, and real-time temperature signal to obtain the state parameters of the steam turbine lubricating oil.

[0051] In the embodiment of the present application, the signal conversion unit based on the data acquisition module performs digital-to-analog conversion on the fluorescence spectrum signal, shear resistance signal, pollutant concentration signal, particle size distribution and number concentration signal, free water content and dissolved water content signal, and real-time temperature signal to obtain state parameters, and converts the original physical signals collected by the sensors into standardized state parameters that can be recognized and analyzed by the system, which can solve the problem that multi-source heterogeneous signals are difficult to directly use for intelligent analysis and ensure the accuracy of the oil health index analysis.

[0052] 303. The transmission unit based on the data acquisition module transmits the state parameters to the data transmission module.

[0053] In the embodiment of the present application, the transmission unit based on the data acquisition module transmits the state parameters to the data transmission module, ensuring that the oil state data is transferred without delay and loss, and providing real-time and reliable data support for subsequent data verification, storage, and intelligent analysis of the visualization cloud operation and maintenance module.

[0054] 304. The data transmission module stores the state parameters and transmits them to the visualization oil cloud operation and maintenance module.

[0055] In the embodiment of the present application, a data exchanger based on the data transmission module receives the status parameters transmitted by the data acquisition module, verifies and formats the status parameters, eliminates errors, and unifies the formats to ensure data quality. The oil fluid cloud server based on the data transmission module stores the processed status parameters in the oil fluid status database and transmits the processed status parameters to the visual oil fluid cloud operation and maintenance module, which not only retains complete data for the analysis of the entire oil fluid life cycle but also provides real-time and standardized inputs for the hybrid machine learning model, enabling reliable data support for intelligent operation and maintenance functions such as oil fluid health diagnosis and hierarchical early warning.

[0056] 305. Based on the visual oil fluid cloud operation and maintenance module, use the hybrid machine learning model to perform data analysis on the status parameters to obtain oil fluid health indicators and visually display the oil fluid health indicators.

[0057] In the embodiment of the present application, based on the visual oil fluid cloud operation and maintenance module, the status parameters are input into the LSTM neural network of the hybrid machine learning model for time series prediction to obtain a time series prediction curve, realizing the prediction of the oil fluid state trend; the random forest algorithm of the hybrid machine learning model is used to perform multi-dimensional feature quantification on the status parameters to obtain the remaining life of the oil fluid; the status parameters are input into the support vector machine of the hybrid machine learning model for abnormal pattern recognition to locate the fault type and obtain an abnormal classification result; the time series prediction curve, the remaining life of the oil fluid, and the abnormal classification result are used as oil fluid health indicators, and a visual interaction component is used to visually display the oil fluid health indicators, which not only provides comprehensive basis for operation and maintenance personnel for trend prediction, life management, and abnormal early warning but also reduces the threshold of data analysis, greatly improving the forward-looking and accuracy of operation and maintenance.

[0058] 306. When it is detected based on the visual oil fluid cloud operation and maintenance module that the oil fluid health indicator belongs to the secondary warning of the hierarchical early warning mechanism, generate a start / stop instruction for the oil filter device and transmit the start / stop instruction for the oil filter device to the oil filter execution module.

[0059] In the embodiment of the present application, through the hierarchical early warning response mechanism, the precision, automation, and differentiation of oil fluid abnormal handling are realized. Specifically, when it is detected based on the visual oil fluid cloud operation and maintenance module that the oil fluid health indicator belongs to the secondary warning of the hierarchical early warning mechanism, generate a start / stop instruction for the oil filter device and transmit the start / stop instruction for the oil filter device to the oil filter execution module to timely repair problems such as oil fluid cleanliness, avoid the expansion of faults, and ensure that the oil fluid continuously adapts to the equipment operation.

[0060] 307. Based on the oil filter execution module responding to the start / stop instruction of the oil filter device, perform multi-stage filtration and constant temperature control operations on the steam turbine lubricating oil fluid through the oil filter component.

[0061] In the embodiment of the present application, based on the oil filtering execution module, the oil pump and the oil inlet valve are opened, the oil return valve is closed, and the steam turbine lubricating oil is driven to pass through the primary filtering component and the secondary filtering component in sequence for hierarchical filtering. At the same time, the electric heater is started, the oil temperature is collected in real time through the temperature sensor, and impurities are intercepted hierarchically through two-stage filtering, which can improve the cleanliness of the oil, ensure the quality of the lubricating oil, and reduce the risk of equipment wear. Then, based on the temperature control feedback unit, the heating power is dynamically adjusted according to the oil temperature, so that the viscosity of the steam turbine lubricating oil is maintained within the preset optimal range, avoiding the influence of temperature fluctuations on the lubrication performance, accurately maintaining the stability of the oil viscosity, and adapting to the different working conditions of the steam turbine. Specifically, when the oil temperature detected by the temperature control feedback unit is lower than the lower limit of the target temperature, the heating power is increased according to a preset ratio; when the oil temperature detected by the temperature control feedback unit is higher than the upper limit of the target temperature, the heating power is decreased step by step.

[0062] When the cleanliness and viscosity of the steam turbine lubricating oil detected by the oil filtering execution module meet the set thresholds, the oil return valve is opened and the oil pump is closed, avoiding excessive oil filtering and wasting energy. Moreover, the whole process is automated, reducing manual intervention and improving the operation and maintenance efficiency. Based on the above process, the advance amount of fault warning can be significantly improved, from the traditional 24 hours to 72 - 120 hours, effectively avoiding the occurrence of equipment failures. In addition, the sensitivity of oil detection is improved, smaller particle contamination can be detected, the cleanliness of the oil quality is ensured, and the maintenance cost is greatly reduced. Through the adaptive maintenance strategy, unnecessary over-maintenance and downtime losses are reduced.

[0063] 308. When the oil health index detected by the visual oil cloud operation and maintenance module belongs to the first-level warning of the hierarchical warning mechanism, a maintenance attention prompt is generated and the maintenance attention prompt is visually displayed.

[0064] In the embodiment of the present application, when the oil health index detected by the visual oil cloud operation and maintenance module belongs to the first-level warning of the hierarchical warning mechanism, a maintenance attention prompt is generated and the maintenance attention prompt is visually displayed, enabling the operation and maintenance personnel to pay attention to the trend change of the oil in advance and intervene at the budding stage of the fault.

[0065] 309. When the oil health index detected by the visual oil cloud operation and maintenance module belongs to the third-level warning of the hierarchical warning mechanism, a device shutdown protection instruction is generated, and the device shutdown protection instruction is sent to the steam turbine unit to stop the operation of the steam turbine unit.

[0066] In the embodiment of the present application, when it is detected by the visual oil liquid cloud operation and maintenance module that the oil liquid health index belongs to the third-level early warning of the hierarchical early warning mechanism, a device shutdown protection instruction is generated and sent to the steam turbine unit to stop the operation of the steam turbine unit, which can effectively block the major damage risk caused by serious abnormal oil liquid to the steam turbine unit and reduce the equipment maintenance cost and shutdown loss. Through this hierarchical mode, it is possible to balance the requirements of continuous equipment operation and fault prevention and control, and transform the operation and maintenance response from manual passive judgment to system automatic and hierarchical disposal, greatly improving the intelligent level of oil liquid operation and maintenance and the equipment protection efficiency.

[0067] From the above process, the structural schematic diagram of an intelligent operation and maintenance of steam turbine lubricating oil proposed in the embodiment of the present application is as follows: As Figure 6 shown, the lubricating oil liquid in the main oil tank of the steam turbine enters the oil filtering module 9, passes through the inlet valve 1, inlet oil filter 2, oil pump 3, and electric heater assembly 4 in sequence, is purified by the primary filtering assembly 5 and the secondary filtering assembly 6, and then passes through the return oil filter 7 and return oil valve 8 to complete the cycle; the visual sensor in the data acquisition and sensing system captures information such as the oil liquid flow image, and the signal acquisition module and transmission module transmit the multi-dimensional oil liquid parameters to the server through the data switch, and the server will synchronize the processed data to the oil liquid cloud, and finally realize data storage, analysis and visual display on the visual oil liquid cloud operation and maintenance platform to support oil liquid health diagnosis, hierarchical early warning and intelligent operation and maintenance decision-making.

[0068] The embodiment of the present application provides an intelligent operation and maintenance method for steam turbine lubricating oil. Compared with the prior art, the embodiment of the present application collects the state parameters of the steam turbine lubricating oil based on a data acquisition module, stores and transmits the state parameters to a visual oil cloud operation and maintenance module based on a data transmission module, and analyzes the state parameters using a hybrid machine learning model based on the visual oil cloud operation and maintenance module to obtain oil health indicators, and visually displays the oil health indicators. When it is detected based on the visual oil cloud operation and maintenance module that the oil health indicator belongs to the secondary warning of the grading warning mechanism, a start-stop instruction for the oil filter device is generated, and the start-stop instruction for the oil filter device is transmitted to an oil filter execution module. Based on the oil filter execution module responding to the start-stop instruction of the oil filter device, a multi-stage filtration and constant temperature control operation is performed on the steam turbine lubricating oil through an oil filter component. Due to the fact that manual inspection depends on experience and the data is lagging, it is difficult to capture the trend of oil deterioration in a timely manner, and equipment failures often occur suddenly. Therefore, multi-sensors of the data acquisition module cover multi-dimensional parameters such as the physical, chemical, and morphological aspects of the oil; the data transmission module ensures zero data loss and low latency, solving the data discontinuity problem of traditional manual meter reading; the hybrid model of the visual cloud operation and maintenance module converts static parameters into dynamic trends, remaining life, and abnormal warnings, realizing the intelligent conversion from data to decision-making; the oil filter execution module automatically responds to the instruction to complete the closed-loop processing of contaminated oil to clean oil without manual intervention, thereby realizing the real-time monitoring and intelligent analysis of the operating state of the steam turbine, automatically starting the oil filter system when the set threshold is reached, ensuring that the oil is in a normal state, and further reducing the maintenance cost and improving the operation and maintenance efficiency.

[0069] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties.

[0070] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0071] The above-described embodiments merely represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

[0072] In an exemplary embodiment, refer to Figure 7, a computer device is also provided. The computer device includes a bus, a processor, a memory, and a communication interface, and may further include an input / output interface and a display device. Among them, each functional unit can complete mutual communication through the bus. The memory stores a computer program, and the processor is used to execute the program stored on the memory to execute the steam turbine lubricating oil intelligent operation and maintenance system in the above embodiments.

[0073] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps of the steam turbine lubricating oil intelligent operation and maintenance system.

[0074] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present application.

[0075] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the drawings are not necessarily essential for implementing the present application.

[0076] Those skilled in the art can understand that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the description of the implementation scenario, or can be correspondingly changed to be located in one or more devices different from the present implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0077] The above serial numbers of the present application are only for description and do not represent the advantages or disadvantages of the implementation scenarios.

[0078] The above discloses only several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any change that can be thought of by those skilled in the art should fall within the protection scope of the present application.

Claims

1. An intelligent operation and maintenance system for steam turbine lubricating oil, characterized in that, It includes a data acquisition module, a data transmission module, a visual oil fluid cloud operation and maintenance module, and an oil filtering execution module; The data acquisition module is used to collect the state parameters of the steam turbine lubricating oil fluid and transmit the state parameters to the data transmission module; The data transmission module is used to store the state parameters and transmit them to the visual oil fluid cloud operation and maintenance module; The visual oil fluid cloud operation and maintenance module is used to perform data analysis on the state parameters by using a hybrid machine learning model to obtain oil fluid health indicators, visually display the oil fluid health indicators, and when it is detected that the oil fluid health indicators belong to the secondary warning of the hierarchical warning mechanism, generate an oil filtering device start-stop instruction and transmit the oil filtering device start-stop instruction to the oil filtering execution module; The oil filtering execution module is used to respond to the oil filtering device start-stop instruction and perform multi-stage filtering and constant temperature control operations on the steam turbine lubricating oil fluid through an oil filtering component.

2. The system according to claim 1, wherein The data acquisition module includes a multi-parameter sensing unit, a signal conversion unit, and a transmission unit; The multi-parameter sensing unit is connected to the signal conversion unit and is used to collect the flow image of the steam turbine lubricating oil fluid through a visual sensor, collect the fluorescence spectrum signal of the steam turbine lubricating oil fluid through a nano sensor, collect the shear resistance signal of the steam turbine lubricating oil fluid through a viscosity sensor, collect the pollutant concentration signal of the steam turbine lubricating oil fluid through a contamination sensor, collect the particle size distribution and number concentration signal of the steam turbine lubricating oil fluid through a particle counter, collect the free water content and dissolved water content signal of the steam turbine lubricating oil fluid through a moisture sensor, and collect the real-time temperature signal of the steam turbine lubricating oil fluid through a temperature sensor; The signal conversion unit is connected to the transmission unit and is used to perform digital-to-analog conversion on the fluorescence spectrum signal, the shear resistance signal, the pollutant concentration signal, the particle size distribution and number concentration signal, the free water content and dissolved water content signal, and the real-time temperature signal to obtain the state parameters; The transmission unit is used to transmit the state parameters to the data transmission module.

3. The system according to claim 1, wherein The data transmission module includes a data exchanger and an oil fluid cloud server; The data exchanger is connected to the oil fluid cloud server and is used to receive the state parameters transmitted by the data acquisition module, perform verification and formatting processing on the state parameters, and transmit the processed state parameters to the oil fluid cloud server; The oil fluid cloud server stores the processed state parameters in an oil fluid state database and transmits the processed state parameters to the visual oil fluid cloud operation and maintenance module.

4. The system according to claim 1, characterized in that, The visual oil fluid cloud operation and maintenance module is used to input the state parameters into the LSTM neural network of the hybrid machine learning model for time series prediction to obtain a time series prediction curve; Use the random forest algorithm of the hybrid machine learning model to evaluate the remaining life of the state parameters to obtain the remaining life of the oil fluid; Input the state parameters into the support vector machine of the hybrid machine learning model for abnormal pattern recognition to obtain an abnormal classification result; Take the time series prediction curve, the remaining oil life, and the abnormal classification result as the oil health indicators, and use a visual interaction component to visually display the oil health indicators.

5. The system according to claim 1, wherein The visual oil cloud operation and maintenance module is used to generate an operation and maintenance attention prompt and visually display the prompt when it is detected that the oil health indicator belongs to the first-level warning of the hierarchical warning mechanism. When it is detected that the oil health indicator belongs to the third-level warning of the hierarchical warning mechanism, generate an equipment shutdown protection instruction and send the instruction to the steam turbine unit to stop the operation of the steam turbine unit.

6. The system according to claim 1, wherein The oil filtering execution module is used to turn on the oil pump and the inlet valve, close the return valve, drive the steam turbine lubricating oil to pass through the primary filtering component and the secondary filtering component for hierarchical filtering in sequence, and at the same time start the electric heater to collect the oil temperature in real time through the temperature sensor. Based on the temperature control feedback unit, dynamically adjust the heating power according to the oil temperature so that the viscosity of the steam turbine lubricating oil is maintained within a preset optimal range. When the cleanliness and viscosity of the steam turbine lubricating oil meet the set thresholds, open the return valve and close the oil pump.

7. The system according to claim 6, wherein The temperature control feedback unit is used to increase the heating power in a preset proportion when it is detected that the oil temperature is lower than the lower limit of the target temperature. When it is detected that the oil temperature is higher than the upper limit of the target temperature, reduce the heating power step by step.

8. An intelligent operation and maintenance method for steam turbine lubricating oil, characterized in that, It includes: Collect the state parameters of the steam turbine lubricating oil based on the data acquisition module. Store and transmit the state parameters to the visual oil cloud operation and maintenance module based on the data transmission module. Based on the visual oil cloud operation and maintenance module, use a hybrid machine learning model to perform data analysis on the state parameters to obtain oil health indicators and visually display the oil health indicators. When it is detected based on the visual oil cloud operation and maintenance module that the oil health indicator belongs to the second-level warning of the hierarchical warning mechanism, generate an oil filtering device start-stop instruction and transmit the instruction to the oil filtering execution module. Based on the oil filtering execution module responding to the oil filtering device start-stop instruction, perform multi-stage filtering and constant temperature control operations on the steam turbine lubricating oil through the oil filtering component.

9. An apparatus, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the system according to any one of claims 1 to 7.

10. A storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by the processor, it implements the steps of the system according to any one of claims 1 to 7.

Images