Oil-water separation equipment whole life cycle early warning system based on digital twinning

Abstract

The application provides an oil-water separation equipment whole life cycle early warning system based on digital twinning, comprising a data acquisition module, a twinning modeling module, a data storage module, a data comparison and analysis module, an early warning output module, an industry equipment distribution monitoring module and a multi-dimensional data output module, aiming to overcome the problems of passive alarm, weak fault prediction ability, inaccurate positioning, lack of industry monitoring and insufficient data support in the existing oil-water separation equipment monitoring process, realize early prediction and positioning of single equipment failure through digital twinning technology, and build an industry-level monitoring system to provide customized data support for users, manufacturers and industry management departments, and improve equipment operation efficiency and service life.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance technology, and in particular to a full life cycle early warning system for oil-water separation equipment based on digital twins. Background Technology

[0002] With the large-scale development of the catering industry and the continuous improvement of environmental protection requirements, oil-water separation equipment, as the core environmental protection equipment for treating oily wastewater, has been widely used in catering enterprises, food processing plants, and other scenarios, forming a vast industry equipment network. From a technological development perspective, early oil-water separation equipment relied mainly on manual monitoring, depending on regular inspections by maintenance personnel. This was inefficient and prone to overlooking potential faults. Subsequently, simple sensors were gradually introduced to collect basic operating parameters, but alarms were only triggered after the equipment stopped or obvious abnormalities occurred, which is a "fault-after-response" mode. In recent years, the penetration of IoT and data processing technologies has driven the upgrade of equipment monitoring to real-time data collection, but a full life-cycle management system has not yet been formed, and industry-level monitoring and data support capabilities are seriously insufficient.

[0003] Current technologies typically have weak fault prediction capabilities, often relying on passive alarms. They fail to identify potential risks such as component aging and minor anomalies in advance. Sudden faults can easily lead to interruptions in oily wastewater treatment, causing environmental pollution, and emergency repairs are costly and involve long downtimes. In terms of fault location accuracy, current technologies lack targeted monitoring and analysis logic for core component-specific parameters, requiring maintenance personnel to check each component individually, resulting in low operational efficiency. At the industry level, current technologies have not formed a unified system for monitoring equipment distribution and operational status, making it difficult to grasp the overall operational status of equipment across the entire industry.

[0004] Therefore, there is an urgent need in this field for a full lifecycle early warning system for oil-water separation equipment based on digital twins to solve the above problems. Summary of the Invention

[0005] This invention provides a digital twin-based early warning system for the entire lifecycle of oil-water separation equipment. It aims to overcome the problems of passive alarms, weak fault prediction capabilities, inaccurate positioning, lack of industry monitoring, and insufficient data support in the existing monitoring process of oil-water separation equipment. By using digital twin technology, it enables early prediction and positioning of faults in individual equipment. At the same time, it constructs an industry-level monitoring system, providing customized data support for users, manufacturers, and industry management departments, thereby improving equipment operating efficiency and service life.

[0006] This invention provides a digital twin-based early warning system for the entire lifecycle of oil-water separation equipment, comprising:

[0007] The data acquisition module is used to collect real-time operating parameters of the core components of a single oil-water separator and basic information about the equipment.

[0008] The twin modeling module, which is connected to the data acquisition module, is used to construct and dynamically update a virtual device model that corresponds one-to-one with the physical device and includes a three-dimensional geometric model and multi-physics state information, based on the real-time operating parameters and basic information.

[0009] The data storage module is connected to the data acquisition module and the twin modeling module respectively, and is used to store the real-time operating parameters, the virtual device model, the preset normal parameter library and the industry equipment database;

[0010] The data comparison and analysis module, which is connected to the twin modeling module and the data storage module, is used to perform fault risk prediction and location analysis based on the state of the virtual device model, the comparison results of the real-time operating parameters and the normal parameter database, and to perform industry-level statistical analysis based on the industry equipment database.

[0011] The early warning output module, which is connected to the data comparison and analysis module, is used to output graded early warning information to the user based on the results of the fault risk prediction and location analysis.

[0012] An industry equipment distribution monitoring module, which is connected to the data comparison and analysis module, is used to visually monitor the spatial distribution and overall operating status of multiple devices in the industry based on the industry-level statistical analysis results.

[0013] A multi-dimensional data output module, which is connected to the industry equipment distribution monitoring module and the data storage module, is used to generate and provide customized data reports according to different user roles.

[0014] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0015] 1. This invention can monitor the core components of a single device in real time, predict faults in advance, and avoid equipment downtime and environmental pollution. It can also visualize the distribution and operating status of equipment across the entire industry through an industry equipment distribution monitoring module, achieving global control and solving the problems of passive alarms and lack of industry monitoring.

[0016] 2. This invention can provide users with annual operation and maintenance cost reports, avoiding excessive repairs and thus reducing operation and maintenance costs; at the same time, it can provide manufacturers with fault statistics and scenario adaptability data, identify product shortcomings, and support equipment upgrades and iterations; and it can provide industry management departments with macro-operation data to assist in policy formulation and industry planning.

[0017] 3. This invention accurately identifies the location and cause of faults through dedicated parameter monitoring, differentiated comparison logic, and component-level health index calculation, shortening the troubleshooting time. It also outputs reminders, maintenance suggestions, or shutdown instructions according to risk level through a graded early warning mechanism, avoiding excessive maintenance or untimely response.

[0018] 4. This invention can be adapted to oil-water separation equipment of different models and in different scenarios. It can meet diverse needs by adjusting the normal parameter library. At the same time, it is compatible with industry-level data access and can continuously expand its functions as the number of industry equipment grows and technology develops.

[0019] 5. This invention guides equipment to iterate towards high efficiency, environmental protection, and intelligence through full life cycle data accumulation and industry-level statistical analysis, thereby improving the overall operational efficiency of the industry and providing support for the standardization and sustainable development of the catering environmental protection industry.

[0020] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0021] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention, but do not constitute a limitation thereof; in the drawings:

[0022] Figure 1 This is a schematic diagram of the structure of a digital twin-based oil-water separation equipment full life cycle early warning system provided by the present invention. Detailed Implementation

[0023] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0024] Example 1:

[0025] This invention provides a digital twin-based early warning system for the entire lifecycle of oil-water separation equipment. Please refer to [link / reference]. Figure 1 ,include:

[0026] The data acquisition module is used to collect real-time operating parameters of the core components of a single oil-water separator and basic information about the equipment.

[0027] The twin modeling module, which is connected to the data acquisition module, is used to build and dynamically update a virtual device model that corresponds one-to-one with the physical device and includes a three-dimensional geometric model and multi-physics state information, based on real-time operating parameters and basic information.

[0028] The data storage module is connected to the data acquisition module and the twin modeling module respectively, and is used to store real-time operating parameters, virtual device models, preset normal parameter libraries and industry equipment databases;

[0029] The data comparison and analysis module, which is connected to the twin modeling module and the data storage module, is used to perform fault risk prediction and location analysis based on the comparison results between the status and real-time operating parameters of the virtual device model and the normal parameter library, and to perform industry-level statistical analysis based on the industry equipment database.

[0030] The early warning output module, which is connected to the data comparison and analysis module, is used to output graded early warning information to users based on the results of fault risk prediction and location analysis.

[0031] The industry equipment distribution monitoring module, which is connected to the data comparison and analysis module, is used to visualize and monitor the spatial distribution and overall operating status of multiple devices in the industry based on industry-level statistical analysis results.

[0032] The multi-dimensional data output module connects to the industry equipment distribution monitoring module and data storage module to generate and provide customized data reports based on different user roles.

[0033] Specifically, this embodiment uses digital twin technology as its core. A data acquisition module acquires real-time operational data of core components and basic equipment information for a single device. A twin modeling module constructs a virtual device model synchronized with the physical device. A data storage module categorizes and stores various types of data. A data comparison and analysis module performs single-device fault prediction and location analysis and industry-level statistical analysis. An early warning output module outputs tiered early warnings based on fault risk levels. An industry equipment distribution monitoring module visualizes the spatial distribution and operational status of industry equipment. A multi-dimensional data output module provides customized data reports for different user roles, forming a complete system covering the entire lifecycle monitoring of a single device and industry-level overall management. This ensures stable equipment operation and provides data support for industry development.

[0034] In one embodiment, the data acquisition module includes a sensor unit deployed in the core components of the oil-water separation equipment, and an equipment information sensing unit;

[0035] The sensor unit includes a first sensor group for collecting the current and voltage of the booster pump, a second sensor group for collecting the current, temperature, speed and vibration of the slag remover, a third sensor group for collecting the current, voltage, power, temperature, torque and noise of the oil scraper, a fourth sensor group for collecting the liquid level signal of the electromagnetic level gauge, a fifth sensor group for collecting the opening time, angle and frequency of the solenoid valve, and a sixth sensor group for collecting the current and voltage of the slag-free system.

[0036] The device information sensing unit is used to obtain the device's identity, geographical location, and installation scenario information through Internet of Things (IoT) technology.

[0037] Specifically, the data acquisition module in this embodiment uses multiple sets of sensor units to collect key operating parameters of the core components of the oil-water separation equipment. The first to sixth sensor groups correspond to the booster pump, slag remover, oil skimmer, electromagnetic level gauge, solenoid valve, and slag-free system, respectively. The collected parameters cover the electrical characteristics, physical state, and action parameters of each component during operation, ensuring comprehensive and targeted data acquisition. The equipment information sensing unit utilizes IoT technology to accurately obtain the unique identifier of the equipment for equipment differentiation, geographical location to support industry-wide monitoring, and installation scenario information to adapt to parameter analysis under different operating conditions, providing complete data input for subsequent modeling, analysis, and monitoring. It should be noted that the principles of the sensors and IoT technology are conventional techniques, and the selection of sensors is determined based on actual applications; this embodiment does not impose any limitations on this.

[0038] In one implementation, the twin modeling module includes a geometric modeling unit, a state mapping unit, and a health assessment unit;

[0039] The geometric modeling unit is used to construct a three-dimensional geometric model with precise dimensions and assembly relationships based on the equipment model and component specifications;

[0040] The state mapping unit is used to map the real-time operating parameters collected by the data acquisition module to the corresponding components of the 3D geometric model, driving the model state to synchronize with the physical device;

[0041] The health assessment unit is used to run a preset health assessment algorithm to calculate the device's real-time health index. The health assessment algorithm is as follows:

[0042] ;

[0043] in, Indicates the device at time The health index is used to quantify the performance degradation status of equipment throughout its entire life cycle. This serves as the initial health baseline value for the equipment. The aging coefficient is related to the equipment materials and workload. From the time it is put into operation to the time The cumulative equivalent runtime, For the first Real-time operating parameters of each core component For this The normal baseline value, For this The weighting coefficients, This represents the total number of real-time running parameters. This is the normalization adjustment constant.

[0044] Specifically, the model can be constructed using laser scanning point cloud modeling, BIM / CAD and Unity engine integration, multiphysics coupling simulation modeling, and physical mechanism-data driven hybrid modeling techniques. This embodiment does not limit the specific methods used.

[0045] For the health assessment algorithm, among which This is the initial health status baseline value determined by testing when the equipment leaves the factory, usually set to 1 (representing complete health). The coefficient is determined based on the material properties of the core components of the equipment, the design workload, and the aging patterns of similar equipment in the industry; it is a fixed empirical coefficient. By accumulating the time from when the equipment was put into operation to the present. The actual operating time is calculated by combining the load factor under different operating conditions to obtain the equivalent operating time, and the calculation formula is as follows: ,in The variable is the integral variable, representing the boot process from the device ( =0) to the current time At any time between, for The actual operating load of the equipment at any given time (unit: kW, consistent with the rated power unit), that is, the actual output power or power consumption of the equipment at that time. The rated operating load of the equipment (unit: kW) is the standard operating power of the equipment design. For a moment The operating condition correction factor is used to correct for the impact of different operating scenarios (such as ambient temperature, medium concentration, and load fluctuations) on equipment wear. It should be noted that... Data is collected by the sensor group of the data acquisition module. For example, for booster pumps and slag-free systems, data is directly collected by power sensors; for slag removers and oil skimmers, data is collected based on current and voltage sensors and calculated in conjunction with the power factor on the equipment nameplate; for solenoid valves and electromagnetic level gauges, the power factor is calculated according to a fixed proportion of the rated power (e.g., 30% of the rated power is used when running under no-load conditions, and the actual measured value is used when running under load). The calculations can be adjusted based on the actual application, or other existing technologies can be used for calculation. The value; The data acquisition module collects data in real time. Operating parameters of each core component These are the normal reference values ​​for the corresponding parameters of this component under standard operating conditions, stored in the normal parameter library. Based on the importance of this parameter to the overall operation of the equipment, it is determined through industry expert evaluation or statistical analysis of historical failure data, with more important parameters having a higher weighting coefficient. It is a normalization adjustment constant used to limit the calculation results of the parameter deviation term to between 0 and 1, ensuring the rationality of the health index.

[0046] The algorithm uses an initial health baseline value. Based on, through The first item reflects the natural performance degradation of equipment due to material aging and cumulative operation. The subsequent deviation correction item quantifies the impact of the deviation between real-time operating parameters and normal baseline values ​​on the equipment's health status; the greater the deviation, the lower the health index. The final result is... Comprehensive reflection of oil-water separation equipment in time The overall health status is used to quantify the performance degradation of oil-water separation equipment.

[0047] In one implementation, the data storage module includes a normal parameter library, a real-time parameter library, and an industry equipment database;

[0048] The normal parameter library stores the operating parameter thresholds and variation patterns of various equipment components under standard operating conditions;

[0049] The real-time parameter library is used to store the real-time operating parameter sequence and historical operating parameter sequence continuously uploaded by the data acquisition module;

[0050] The industry equipment database stores the geographical location, model, service life, maintenance records, and associated cost data of all oil-water separation equipment connected to the system.

[0051] Specifically, the data storage module in this embodiment adopts a classified storage architecture, storing different types of data in three databases to ensure the orderliness and availability of data management. The normal parameter database is based on industry standards, equipment factory technical documents, and statistical analysis of a large amount of similar equipment's operating data under standard operating conditions to determine the operating parameter thresholds (including upper and lower limits) of various equipment components and the parameter change patterns under normal operating conditions (such as the normal fluctuation range and change trend with operating time), providing a benchmark for subsequent parameter comparison and fault diagnosis. The real-time parameter database receives and stores the operating parameters of each core component uploaded by the data acquisition module in real time, forming a continuous real-time operating parameter sequence, while retaining historical operating parameter sequences to support fault tracing and trend analysis. The industry equipment database comprehensively collects key information of all oil-water separation equipment connected to this system. Among them, geographical location is used to support industry-wide distributed monitoring, model is used to distinguish equipment types and adapt to corresponding parameter standards, service time is used to assist in health assessment, maintenance records are used for fault pattern analysis, and associated cost data is used for cost statistics and analysis, providing data support for industry-level statistical analysis and multi-dimensional data output.

[0052] In one implementation, the data comparison and analysis module includes a single-device analysis unit and an industry analysis unit;

[0053] The single-device analysis unit is used to process the real-time health index output by the twin modeling module. The deviation of key parameters is compared with the thresholds and logical rules in the normal parameter library, and the fault risk level, suspected faulty components and causes are output.

[0054] The industry analysis unit is used to mine data from the industry equipment database, including statistical regional failure rates, average component lifespan, failure type distribution, and identification of abnormal patterns.

[0055] Specifically, the data comparison and analysis module in this embodiment uses two parallel analysis units to realize single-device fault analysis and industry macro data mining, respectively.

[0056] For single-device analysis, first obtain the device's real-time health index output by the twin modeling module. The system analyzes the deviations of key parameters between the real-time operating parameters of each core component and the normal baseline values. Then, it calls the corresponding parameter thresholds and preset logical judgment rules (such as the health index being lower than a certain threshold, parameter deviation exceeding the allowable range and lasting for a certain period of time) from the normal parameter library to perform multi-dimensional comparative analysis. Based on the comparison results, it determines the fault risk level (mild anomaly, moderate anomaly, severe anomaly). Combining the component to which the parameter belongs, the deviation characteristics, and historical fault data, it locates the suspected faulty component and analyzes the possible causes of the fault (such as wear and blockage of the component corresponding to the parameter exceeding the range). This process solves the problem of "where is the fault" through parameter attribution, the problem of "what kind of fault is it" through deviation characteristics, and the problem of "what kind of fault is it most likely to be" through historical data.

[0057] For industry analysis, the analysis is based on the full amount of equipment data stored in the industry equipment database. The data is statistically analyzed, that is, the failure rate of equipment in different regions is calculated to understand regional differences, the average service life of each core component is calculated to identify easily worn parts, the distribution of failure types is calculated to identify the high-incidence failure types, and abnormal patterns in the data are identified, such as a sudden increase in the failure rate in a certain region in a short period of time, or the life of a certain model of equipment component is significantly lower than that of similar products, so as to provide data support for industry management and product optimization.

[0058] In one implementation, the early warning output module includes an early warning generation unit and a communication unit;

[0059] The early warning generation unit is used to generate graded early warning content, including reminders, maintenance suggestions and emergency shutdown instructions, based on the fault risk level output by the data comparison and analysis module.

[0060] The communication unit is used to push warning messages to designated equipment maintenance personnel through one or more of the following methods: audible and visual alarm, SMS gateway, and system backend interface.

[0061] Specifically, the early warning output module in this embodiment is used to generate and push early warning content. Its early warning generation unit generates targeted, tiered early warning content based on the fault risk level determined by the data comparison and analysis module. For example, for minor anomalies, it generates a reminder message containing only a fault indication, informing maintenance personnel to pay attention to the equipment status; for moderate anomalies, it generates early warning content including a description of the fault and specific maintenance suggestions (such as the maintenance location and preliminary handling methods); for severe anomalies, it generates early warning content including a description of the fault's urgency, maintenance instructions, and emergency shutdown suggestions to prevent the fault from escalating. The communication unit adopts a multi-channel push mechanism, issuing a visual alarm at the equipment site via an audible and visual alarm, sending early warning SMS messages to maintenance personnel's mobile phones via an SMS gateway, and displaying an early warning pop-up window on the equipment management platform via the system backend interface, ensuring that early warning information is delivered to designated maintenance personnel in a timely and accurate manner, guaranteeing the timeliness of maintenance response.

[0062] In one implementation, the industry equipment distribution monitoring module includes a map rendering unit and a status visualization unit;

[0063] The map rendering unit is used to render and locate all oil-water separation devices connected to the system on an electronic map;

[0064] The status visualization unit is used to analyze the real-time health index of each device. The fault risk level is marked on the electronic map with different colors or icons, and filtering and aggregation viewing functions are provided by region, model, and years of use.

[0065] Specifically, the industry equipment distribution monitoring module in this embodiment is used to realize the visual monitoring and convenient query of industry equipment. Its map rendering unit accurately renders and marks each oil-water separation device connected to the system on an electronic map based on the geographical location information of the equipment stored in the industry equipment database, realizing an intuitive presentation of the spatial distribution of equipment; the status visualization unit, based on the real-time health index of the equipment output by the twin modeling module, The fault risk level determined by the data comparison and analysis module is marked with differentiated colors (such as green for normal, yellow for mild abnormality, orange for moderate abnormality, and red for severe abnormality) or exclusive icons to make the equipment's operating status clear at a glance. It also provides multi-dimensional filtering functions, allowing maintenance or management personnel to filter and query by equipment location, equipment model, service life, etc., and can also aggregate and view filtered equipment (such as aggregating and displaying the total number of equipment in the region and the number of equipment in each status), to achieve global control and management of the overall operating status of equipment in the industry.

[0066] In one implementation, the multi-dimensional data output module includes a report generation engine and an interface adaptation unit;

[0067] The report generation engine is used to call data from the data storage module and the industry equipment distribution monitoring module to automatically generate annual operation and maintenance cost reports for equipment users, product failure statistics and improvement analysis reports for equipment manufacturers, and industry operation and development analysis reports for industry management departments.

[0068] The interface adaptation unit is used to provide corresponding data access interfaces or report download services for users with different roles.

[0069] Specifically, the multi-dimensional data output module in this embodiment provides customized data reporting services and data access support for the core needs of different user roles. Its report generation engine automatically generates three types of specialized reports according to preset report templates by calling the real-time parameter library, normal parameter library, industry equipment database, and visualized statistical data from the industry equipment distribution monitoring module in the data storage module: 1. Annual operation and maintenance cost report for equipment users, including data such as the number of equipment failures, repairs, repair cost details, and spare parts replacement costs, providing a basis for users to formulate annual budgets and optimize operation and maintenance; 2. Product failure statistics and improvement analysis report for equipment manufacturers, including data such as the failure rate of each component of each model, high failure-prone usage stages, and equipment adaptability in different scenarios, providing data support for product design improvement and component optimization and upgrading; 3. Industry operation and development analysis report for industry management departments, including macro data such as industry equipment inventory, overall operating efficiency, average failure rate, and environmental compliance rate, providing a reference for industry policy formulation and development planning. The interface adaptation unit provides data access interfaces with appropriate permissions for users of different roles, such as equipment users, manufacturers, and industry management departments (ensuring that different users can only access data within their own permission scope). It also supports report download services to meet the data usage habits and needs of different users. It should be noted that the report type and template can be designed based on actual applications, and this embodiment does not limit them.

[0070] In one implementation, the health assessment algorithm in the health assessment unit further includes a component-level health index for calculating the health index of components. The core component, composed of individual sub-components, has a health index. The calculation formula is:

[0071] ;

[0072] in, Indicates the first The status score of each sub-component is determined by the deviation of its key parameters and its runtime. This represents the importance coefficient of the sub-component in the overall function; component-level health index. Used to support the data comparison and analysis module for fault location.

[0073] Among them, the status score of sub-components for:

[0074] ;

[0075] For the first Real-time values ​​of key monitoring parameters for each sub-component. for The normal baseline value, The maximum allowable deviation threshold, and These are the contribution coefficients of instantaneous deviation and cumulative historical deviation, respectively.

[0076] Specifically, the health assessment algorithm in this embodiment is used to quantify the health status of core components, providing data support for fault location. This refers to the total number of sub-components included in the core component (e.g., if the slag remover is the core component, it includes sub-components such as motors and reducers). That is, the number of sub-components of that type). For the first The status score of each sub-component is calculated by the deviation of its key operating parameters from normal baseline values ​​and the sub-component's cumulative operating time. The smaller the deviation and the shorter the operating time, and the less it exceeds the design life, the better. The closer to 1 (indicates that the sub-component is in good condition); Let be the importance coefficient of the j-th sub-component in the overall functional implementation of the core component. Based on the degree of influence of the sub-component on the operation of the core component, it can be determined through industry expert evaluation, functional breakdown analysis, and experience. The importance coefficient of the core sub-component is higher.

[0077] In this algorithm, the health status of the core component is jointly determined by the status of its constituent sub-components, which is achieved by scoring the status of each sub-component. According to its importance coefficient The health index of the core components is obtained by performing weighted exponentiation and then multiplying the results. , The closer the value is to 1, the better the health status of the core component; when locating faults, the data comparison and analysis module can compare the health status of each core component. Quickly identify the core component with a low health index, and then combine it with the information of each sub-component of that core component. This allows for further localization of faulty sub-components, significantly improving the efficiency and accuracy of fault location.

[0078] As for the formula It is used to quantify the real-time status of sub-components, providing basic data for component-level health index calculation, among which... The data acquisition module collects data in real time. The real-time values ​​of the core monitoring quantities of each sub-component (e.g., when the sub-component of the slag remover is the motor, the core monitoring quantities can be current, temperature, etc.); The normal baseline value of the core monitoring quantity corresponding to this sub-component under standard operating conditions is stored in the normal parameter library; The maximum allowable deviation threshold for this core monitoring quantity is determined based on the equipment's factory technical requirements, industry standards, and actual operational safety thresholds. These sources are wide-ranging and are not limited in this embodiment. The instantaneous deviation contribution coefficient is used to adjust the degree of influence of the instantaneous deviation between the real-time parameters of the sub-component and the normal reference value on the condition score. It can be determined through statistical analysis of historical fault data, and the value range is usually 0-1. The cumulative historical deviation contribution coefficient is used to adjust the influence of the total parameter deviation of the sub-component on the status score during the cumulative operating time. It is also determined through statistical analysis of historical fault data, and its value ranges from 0 to 1. The cumulative deviation of the core monitoring quantity of the sub-component from the start of operation to time t is obtained by integrating the real-time deviation data.

[0079] The formula uses 1 as the full score benchmark for the sub-component's condition, and deducts the negative impact of instantaneous deviation and cumulative historical deviation on the condition through two deviation correction terms, where the first term... The second term is used to quantify the effect of instantaneous deviation. Used to quantify the impact of cumulative deviation within a unit equivalent operating time; through Ensure the status score is at least 0 (representing complete failure of the sub-component), and the final result is... The value ranges from 0 to 1, which intuitively reflects the real-time status of the sub-component.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A full lifecycle early warning system for oil-water separation equipment based on digital twins, characterized in that, include: The data acquisition module is used to collect real-time operating parameters of the core components of a single oil-water separator and basic information about the equipment. The twin modeling module, which is connected to the data acquisition module, is used to construct and dynamically update a virtual device model that corresponds one-to-one with the physical device and includes a three-dimensional geometric model and multi-physics state information, based on the real-time operating parameters and basic information. The twin modeling module includes a geometric modeling unit, a state mapping unit, and a health assessment unit; The geometric modeling unit is used to construct a three-dimensional geometric model with precise dimensions and assembly relationships based on the equipment model and component specifications; The state mapping unit is used to map the real-time operating parameters collected by the data acquisition module to the corresponding components of the three-dimensional geometric model, thereby driving the model state to synchronize with the physical device. The health assessment unit is used to run a preset health assessment algorithm to calculate the real-time health index of the device. The health assessment algorithm is as follows: ;in, It represents the health index of the device at time t, and is used to quantify the performance degradation status of the device throughout its entire life cycle; This serves as the initial health baseline value for the equipment. The aging coefficient is related to the equipment materials and workload. The cumulative equivalent running time from the start of operation to time t. For the first Real-time operating parameters of each core component For this The normal baseline value, For this The weighting coefficients, This represents the total number of real-time running parameters. This is the normalization adjustment constant; In the health assessment unit, the health assessment algorithm further includes a method for calculating a component-level health index, for components... The core component, composed of individual sub-components, has a health index. The calculation formula is: ;in, Indicates the first The status score of each sub-component is determined by the deviation of its key parameters and its runtime. The component-level health index represents the importance coefficient of the sub-component within the overall function. Used to support the data comparison and analysis module in fault location; In the health assessment unit, the status score of the sub-component for: ;in, For the first Real-time values ​​of key monitoring parameters for each sub-component. for The normal baseline value, The maximum allowable deviation threshold, and These are the contribution coefficients of instantaneous deviation and cumulative historical deviation, respectively; The data storage module is connected to the data acquisition module and the twin modeling module respectively, and is used to store the real-time operating parameters, the virtual device model, the preset normal parameter library and the industry equipment database; The data comparison and analysis module, which is connected to the twin modeling module and the data storage module, is used to perform fault risk prediction and location analysis based on the state of the virtual device model, the comparison results of the real-time operating parameters and the normal parameter database, and to perform industry-level statistical analysis based on the industry equipment database. The early warning output module, which is connected to the data comparison and analysis module, is used to output graded early warning information to the user based on the results of the fault risk prediction and location analysis. An industry equipment distribution monitoring module, which is connected to the data comparison and analysis module, is used to visually monitor the spatial distribution and overall operating status of multiple devices in the industry based on the industry-level statistical analysis results. A multi-dimensional data output module, which is connected to the industry equipment distribution monitoring module and the data storage module, is used to generate and provide customized data reports according to different user roles.

2. The system according to claim 1, characterized in that, The data acquisition module includes a sensor unit deployed in the core components of the oil-water separation equipment, and an equipment information sensing unit; The sensor unit includes a first sensor group for collecting the current and voltage of the booster pump, a second sensor group for collecting the current, temperature, speed and vibration of the slag remover, a third sensor group for collecting the current, voltage, power, temperature, torque and noise of the oil scraper, a fourth sensor group for collecting the liquid level signal of the electromagnetic level gauge, a fifth sensor group for collecting the opening time, angle and frequency of the solenoid valve, and a sixth sensor group for collecting the current and voltage of the slag-free system. The device information sensing unit is used to obtain the device's identity, geographical location, and installation scenario information through Internet of Things (IoT) technology.

3. The system according to claim 1, characterized in that, The data storage module includes the normal parameter library, the real-time parameter library, and the industry equipment database; The normal parameter library stores the operating parameter thresholds and variation patterns of various equipment components under standard operating conditions. The real-time parameter library is used to store the real-time operating parameter sequence and historical operating parameter sequence continuously uploaded by the data acquisition module; The industry equipment database is used to store the geographical location, model, service life, maintenance records, and associated cost data of all oil-water separation equipment connected to the system.

4. The system according to claim 3, characterized in that, The data comparison and analysis module includes a single-device analysis unit and an industry analysis unit; The single-device analysis unit is used to process the real-time health index output by the twin modeling module. The deviation of key parameters is compared with the thresholds and logical rules in the normal parameter library to output the fault risk level, suspected faulty components and causes. The industry analysis unit is used to mine data in the industry equipment database. The mining includes statistical analysis of regional failure rates, average component lifespan, failure type distribution, and identification of abnormal patterns.

5. The system according to claim 4, characterized in that, The early warning output module includes an early warning generation unit and a communication unit; The early warning generation unit is used to generate graded early warning content, including reminders, maintenance suggestions and emergency shutdown instructions, based on the fault risk level output by the data comparison and analysis module. The communication unit is used to push the warning content to designated equipment maintenance personnel through one or more of the following methods: audible and visual alarm, SMS gateway, and system backend interface.

6. The system according to claim 4, characterized in that, The industry equipment distribution monitoring module includes a map rendering unit and a status visualization unit; The map rendering unit is used to render and locate all oil-water separation devices connected to the system on an electronic map; The status visualization unit is used to analyze the real-time health index of each device. The fault risk level is indicated on the electronic map with different colors or icons, and filtering and aggregation viewing functions are provided by region, model, and service life.

7. The system according to claim 1, characterized in that, The multi-dimensional data output module includes a report generation engine and an interface adaptation unit; The report generation engine is used to call the data from the data storage module and the industry equipment distribution monitoring module to automatically generate annual operation and maintenance cost reports for equipment users, product failure statistics and improvement analysis reports for equipment manufacturers, and industry operation and development analysis reports for industry management departments. The interface adaptation unit is used to provide corresponding data access interfaces or report download services for users with different roles.

Images