Data fusion method for predicting health state of transmitting station based on digital twinning

Abstract

The invention discloses a data fusion method for predicting the health state of a transmitting station based on digital twinning, and the method comprises the following steps: constructing a virtual entity of the transmitting station, constructing a data source of the transmitting station, fusing health state data, carrying out fault diagnosis and prediction, and carrying out the maintenance decision of the transmitting station: finding out possible hidden danger factors of the transmitting station; all components of the launching pad are predicted and maintained according to a previous strategy, potential faults are reduced, and the use value is maximized. The reliability and the safety of the transmitting station are improved, the digital twin can monitor the state of each part of the transmitting station in real time and identify potential fault problems in advance, the preventive maintenance can reduce accidental faults, improve the safety and the reliability of the transmitting station and avoid transmitting failures caused by the faults, and through real-time data analysis, the reliability of the transmitting station is improved. The health state of the transmitting station is dynamically updated, possible faults are predicted, and a maintenance plan is adjusted according to actual conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of aerospace launch and test technology, and particularly to a data fusion method for predicting the health status of a launch pad based on digital twin. Background Art

[0002] Currently, the domestic methods for restoring the post-launch state of rockets at launch sites basically still follow traditional methods. Especially in the maintenance of launch pads, there are still problems such as scattered maintenance parts, numerous maintenance items, long maintenance time, low maintenance efficiency, and high maintenance costs to varying degrees, which seriously restrict the guarantee efficiency of high-density aerospace missions and the efficient utilization of launch site resources. Summary of the Invention

[0003] The purpose of the present invention is to provide a data fusion method for predicting the health status of a launch pad based on digital twin, so as to solve the foregoing problems existing in the prior art.

[0004] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] A data fusion method for predicting the health status of a launch pad based on digital twin includes the following steps:

[0006] S100. Construct a virtual entity of the launch pad: Construct a virtual entity model, a running parameter model, and a status data model, keep the model status synchronized with the physical entity in real time, and continuously iterate and optimize the virtual entity to meet the requirements of data consistency and integrity;

[0007] S200. Construction of the launch pad data source: Form metadata by collecting sensor parameters, obtaining historical equipment status data, obtaining equipment failure data, and obtaining equipment maintenance record data;

[0008] S300. Fusion of health status data: Fusion data by objectives and in stages, process the multi-dimensional heterogeneous data sources of the launch pad through cleaning, integration, and conversion processes, unify the data format, eliminate garbage data, and input it into the digital entity to ensure the unity of the virtual and the real;

[0009] S400. Fault diagnosis and prediction: First, extract the fault characteristic values of the launch pad, synchronize and simulate the digital entity, compare and analyze the operation results with the historical state data of the launch pad in the fault knowledge base, and then judge the cause of the fault; Second, select the state parameters of the launch pad with strong correlation at multiple times and under different working conditions, establish its operation state law model, and predict the possible fault types and fault locations through data mining simulation experiments;

[0010] S500. Launch pad maintenance decision-making: Find out the potential hidden factors of the launch pad, predict and maintain each component of the launch pad according to the previous strategy, reduce potential faults, and maximize its use value.

[0011] Preferably, step S300 further includes: data layer fusion: used for structurally integrating heterogeneous data from different sources, converting the data into the RDF unified data format with a multi-source data fusion framework, and then performing information fusion through a data fusion algorithm.

[0012] Preferably, data layer fusion is divided into: pixel layer fusion, feature layer fusion, and decision layer fusion;

[0013] Pixel layer fusion is used to divide the data analysis work into three typical stages: the data layer, the feature layer, and the decision layer;

[0014] Feature layer fusion is used to map the feature fusion into a subspace;

[0015] Decision layer fusion uses Logistic regression to predict text and related images of emotions, and finally weights and averages the two prediction probabilities.

[0016] Preferably, step S300 further includes: data association analysis, which associates multi-source data of environmental conditions and the working status of associated devices by designing a data association algorithm, and uses association rule mining and machine learning techniques to find potential relationships between the data;

[0017] Preprocess the associated environmental condition data, specifically including: analyzing the environmental configuration effect: establishing an evaluation index system for the environmental configuration effect, and training the environmental configuration effect through multi-source data analysis;

[0018] Preprocess the associated device working status data, specifically including: analyzing the working efficiency of the transmitting station: designing an evaluation model for the working efficiency of the device, and analyzing the working efficiency of the transmitting station using the device performance data.

[0019] Preferably, the implementation method for analyzing the environmental configuration effect includes: determining the evaluation index system for the environmental configuration effect, collecting multi-source data by sensors, analyzing and calculating the multi-source data, and then evaluating the environmental configuration effect.

[0020] Preferably, the implementation method for analyzing the working efficiency of the transmitting station includes: designing an evaluation model for the working efficiency of the device, collecting device performance data, analyzing and calculating the multi-source data, and then evaluating the working efficiency of the device.

[0021] Preferably, the analytic hierarchy process and the fuzzy comprehensive evaluation method are used to design the evaluation model for the working efficiency of the device.

[0022] Preferably, the evaluation methods for designing the evaluation model for the working efficiency of the device include:

[0023] First, determine the evaluation index system, including the normal operation time, operation efficiency, and failure rate indicators of the equipment; then, determine the weights of each index through expert scoring and the analytic hierarchy process method; finally, calculate the comprehensive score of the working efficiency of the transmitting station according to the index values and weights.

[0024] The beneficial effects of the present invention are as follows: The present invention discloses a data fusion method for predicting the health status of a transmitting station based on digital twin, including the following steps: constructing a virtual entity of the transmitting station: constructing a virtual entity model, a running parameter model, and a status data model, keeping the model status synchronized with the physical entity in real time, and continuously iteratively optimizing the virtual entity to meet the requirements of data consistency and integrity; constructing the data source of the transmitting station: forming metadata by collecting sensor parameters, obtaining historical data of equipment status, obtaining equipment failure data, and obtaining equipment maintenance record data; fusing health status data: fusing data by goals and stages, processing multi-dimensional heterogeneous data sources of the transmitting station through cleaning, integration, and transformation processes, unifying the data format, eliminating garbage data, and inputting it into the digital entity to ensure the unity of virtual and real; fault diagnosis and prediction: first, extract the fault characteristic values of the transmitting station, synchronously simulate the digital entity, compare and analyze the operation results with the historical state data of the transmitting station in the fault knowledge base, and then judge the cause of the fault; second, select the state parameters of the transmitting station with strong correlation at multiple times and under different working conditions, establish a model of its operation state law, and predict the possible fault types and fault locations through data mining simulation experiments; maintenance decision-making of the transmitting station: find out the potential hidden factors of the transmitting station, predict and maintain each component of the transmitting station according to the previous strategy, reduce potential faults, and maximize its use value.

[0025] The present invention has the following effects: 1. Improve the reliability and safety of the transmitting station. Digital twin can monitor the status of each part of the transmitting station in real time and identify potential fault problems in advance. This preventive maintenance can reduce the occurrence of unexpected faults, improve the safety and reliability of the transmitting station, and avoid transmission failures caused by faults.

[0026] 2. The present invention optimizes the maintenance plan and resource allocation. Through real-time data analysis, the health status of the transmitting station is dynamically updated and possible faults are predicted, and then the maintenance plan is adjusted according to the actual situation. This changes the traditional fixed-cycle maintenance method, allocates resources more precisely and efficiently, and reduces unnecessary maintenance interventions.

[0027] 3. The present invention reduces the maintenance cost. Through digital twin technology, unnecessary maintenance inspections and fault downtime can be reduced, significantly reducing the overall maintenance cost. In addition, preventive maintenance can also avoid the occurrence of more expensive major faults or accidents.

[0028] 4. The present invention extends the equipment life. Real-time monitoring and fault warning contribute to better management of the workload of the launch pad, avoiding overuse or improper operation, extending the service life of the equipment, and reducing the equipment replacement frequency.

[0029] 5. The present invention improves decision-making efficiency. By performing real-time simulation analysis on the operating state of the launch pad through digital twin, it provides an intuitive display of the health state and fault prediction data, serving for managers to make decisions quickly and efficiently, and continuously improving the scientific and robust level of personnel decision-making.

[0030] 6. The present invention supports operations in complex environments. For complex equipment such as the launch pad, environmental factors (such as climate, vibration, etc.) may affect its performance. By simulating the influence of the above complex environmental factors on the launch pad through digital twin technology, comprehensive data support for equipment maintenance is provided.

[0031] 7. The present invention promotes technological innovation. Using digital twin technology for intelligent predictive maintenance is an advanced method for modern equipment management and maintenance, which not only improves the operation and maintenance efficiency of the launch pad, but also brings more technological innovation to the industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a schematic flow chart of a data fusion method for predicting the health state of a launch pad based on digital twin of the present invention;

[0033] Figure 2 is a schematic flow chart of another embodiment of the present invention;

[0034] Figure 3 is a three-layer data fusion model diagram of the present invention;

[0035] Figure 4 is a predictive maintenance guarantee process based on digital twin of the present invention;

[0036] Figure 5 is a digital twin-based PHM architecture diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0038] For the digital twin-based prediction of the health state of the launch pad, the environmental conditions in the physical world where the launch pad is located are mapped into an environmental model in the digital space, and the behavioral characteristics and physical and chemical properties of the equipment itself are mapped into a multidisciplinary model in the digital space, integrating the failure physics model at the micro scale and the data update model at the macro scale to achieve a fine characterization of the failure mechanism and degradation trend of the launch pad.

[0039] The aforementioned prediction and maintenance of the health status of the launch pad based on digital twin is based on digital twin technology and is divided into five main steps: constructing a virtual entity, constructing a data source, data fusion, pattern recognition, and maintenance decision-making.

[0040] Refer to Figure 1 、 Figure 2 、 Figure 3 、 Figure 4 and Figure 5 A data fusion method for predicting the health status of a launch pad based on digital twin shown in

[0041] S100. Construct a virtual entity of the launch pad: Construct a virtual entity model, a running parameter model, and a status data model, keep the model status synchronized with the physical entity in real time, and continuously iterate and optimize the virtual entity to meet the requirements of data consistency and integrity.

[0042] S200. Construction of the data source of the launch pad: Form metadata by collecting sensor parameters and obtaining historical equipment status data, equipment fault data, and equipment maintenance record data; among them, the sensor collects parameters of the mechanical system, electrical system, and external environment of the launch pad, and the daily operation and maintenance management provides historical equipment status data and maintenance records, and simulates the launch pad fault status data under specific scenarios through simulation tools.

[0043] S300. Fusion of health status data: Fusion data by objectives and in stages, process the multi-dimensional heterogeneous data sources of the launch pad through the processes of cleaning, integration, and transformation, unify the data format, eliminate garbage data, and input it into the digital entity to ensure the unity of the virtual and the real; The data fusion based on stage division is a fusion strategy from an overall perspective, which improves the executability of the fusion process by decomposing the data fusion work objectives.

[0044] The staged data fusion is to fuse the data of different stages in the order of the process. It can fuse the data of all stages separately or only fuse the data of a certain stage.

[0045] S400. Fault diagnosis and prediction: First, extract the fault characteristic values of the launch pad, synchronize the simulation digital entity, compare and analyze the operation results with the historical status data of the launch pad in the fault knowledge base, and then judge the cause of the fault; Second, select the state parameters of the launch pad with strong correlation at multiple times and under different working conditions, establish its operation state law model, and predict the possible fault types and fault locations through data mining simulation experiments.

[0046] S500. Launch pad maintenance decision-making: Find out the potential hidden trouble factors of the launch pad, predict and maintain each component of the launch pad according to the previous strategy, reduce potential faults, and maximize its use value.

[0047] Preferably, step S300 further includes: data layer fusion: used to structurally integrate heterogeneous data from different sources, convert the data into the unified data format of RDF (Resource Description Framework) using a multi-source data fusion framework, and then perform information fusion through a data fusion algorithm.

[0048] Preferably, data layer fusion is divided into: pixel layer fusion, feature layer fusion, and decision layer fusion;

[0049] Pixel layer fusion is used to divide the data analysis work into three typical stages: data layer, feature layer, and decision layer;

[0050] Feature layer fusion is used to map the feature fusion to a subspace; such as surface material recognition.

[0051] Decision layer fusion is used to predict text and related images using Logistic regression sentiment, and finally weighted average the two prediction probabilities.

[0052] Preferably, step S300 further includes: data association analysis, which associates multi-source data of environmental conditions and associated device working states by designing a data association algorithm, and uses association rule mining and machine learning techniques to find potential relationships between the data; the implementation method of data association analysis here is to select an association rule mining algorithm or a machine learning algorithm for data association, and use algorithms such as Apriori, FP-Growth, decision tree, random forest, and support vector machine to analyze frequent item sets in the dataset, and find potential associations between the data through training the model.

[0053] Preprocess the associated environmental condition data, specifically including: analyze the environmental configuration effect: establish an environmental configuration effect evaluation index system, and train the environmental configuration effect through multi-source data analysis; it should be noted that the data association analysis technology stack here includes an association rule mining library (such as pyfpgrowth), a machine learning framework (such as scikit-learn, TensorFlow, PyTorch, etc.), and a data analysis library (such as pandas, numpy, etc.).

[0054] Preprocess the associated device working state data, specifically including: analyze the working efficiency of the transmitting station: design a device working efficiency evaluation model, and analyze the working efficiency of the transmitting station using device performance data.

[0055] Preferably, the implementation method for analyzing the environmental configuration effect includes: determining the evaluation index system for the environmental configuration effect, collecting multi-source data through sensors, analyzing and calculating the multi-source data, and then evaluating the environmental configuration effect. For example, by analyzing temperature and humidity data, etc., to evaluate whether the environmental configuration meets the normal operation requirements of the launch pad. It should be noted here that the technical stack for analyzing the environmental configuration effect includes software (such as UE, Visual Studio 2022), data analysis libraries (such as pandas, numpy), statistical analysis software (such as R, SPSS), and sensor data acquisition software.

[0056] Preferably, the implementation method for analyzing the working efficiency of the launch pad includes: designing an equipment working efficiency evaluation model, collecting equipment performance data, analyzing and calculating multi-source data, and then evaluating the equipment working efficiency. For example, by analyzing data such as the normal operation time, operation efficiency, and failure rate of the launch pad, to evaluate the performance and reliability of the equipment; by analyzing the working status of the launch pad under different environmental conditions, to evaluate the adaptability and durability of the equipment.

[0057] Preferably, the analytic hierarchy process and the fuzzy comprehensive evaluation method are used to design the equipment working efficiency evaluation model.

[0058] Preferably, the evaluation methods for designing the equipment working efficiency evaluation model include:

[0059] Firstly, determine the evaluation index system, including the normal operation time, operation efficiency, and failure rate indexes of the equipment; secondly, determine the weights of each index, which are determined by expert scoring and the analytic hierarchy process method; finally, calculate the comprehensive score of the working efficiency of the launch pad according to the index values and weights.

[0060] It should be noted here that the technical stack for analyzing the working efficiency of the launch pad includes data analysis libraries (such as pandas, numpy), mathematical calculation libraries (such as scipy), and evaluation model libraries. Select the corresponding libraries according to the evaluation methods, such as the ahpy library for the analytic hierarchy process.

[0061] For predictive maintenance based on the digital twin launch pad, it is necessary to focus on the condition monitoring, fault diagnosis, and remaining useful life of the launch pad, and comprehensively assist the physical entity maintenance decision-making.

[0062] The remaining useful life can accurately reflect the evolution trend of the equipment health status and improve the robustness of the maintenance strategy.

[0063] Predictive maintenance based on the digital twin launch pad is essentially a type of sequential decision-making problem. By real-time collecting and analyzing the monitoring data of the launch pad, updating its health status and predicting potential fault risks, the maintenance plan is dynamically adjusted.

[0064] The beneficial effects of the present invention are as follows: The present invention discloses a data fusion method for predicting the health status of a launch pad based on digital twin, including the following steps: constructing a virtual entity of the launch pad: constructing a virtual entity model, constructing an operating parameter model, constructing a status data model, keeping the model status synchronized with the physical entity in real time, and continuously iteratively optimizing the virtual entity to meet the requirements of data consistency and integrity; constructing a data source of the launch pad: forming metadata by collecting sensor parameters, obtaining historical equipment status data, obtaining equipment failure data, and obtaining equipment maintenance record data; fusing health status data: fusing data by target and by stage, processing multi-dimensional heterogeneous data sources of the launch pad through cleaning, integration, and conversion processes, unifying the data format, eliminating garbage data, and inputting it into the digital entity to ensure the unity of the virtual and the real; fault diagnosis and prediction: first, extract the fault characteristic values of the launch pad, synchronously simulate the digital entity, compare and analyze the operating results with the historical status data of the launch pad in the fault knowledge base, and then judge the cause of the fault; secondly, select the state parameters of the launch pad with strong correlation at multiple times and under different working conditions, establish a model of its operating state law, and predict the possible fault types and fault locations through data mining simulation experiments; launch pad maintenance decision-making: find out the potential hidden trouble factors of the launch pad, predict and maintain each component of the launch pad according to the previous strategy, reduce potential faults, and maximize its use value.

[0065] The present invention has the following effects: 1. Improve the reliability and safety of the launch pad. Digital twin can monitor the status of each part of the launch pad in real time and identify potential fault problems in advance. This preventive maintenance can reduce the occurrence of unexpected faults, improve the safety and reliability of the launch pad, and avoid launch failures caused by faults.

[0066] 2. The present invention optimizes the maintenance plan and resource allocation. Through real-time data analysis, it dynamically updates the health status of the launch pad and predicts possible faults, and then adjusts the maintenance plan according to the actual situation. This changes the traditional fixed-cycle maintenance method, more precisely and efficiently allocates resources, and reduces unnecessary maintenance interventions.

[0067] 3. The present invention reduces the maintenance cost. Through digital twin technology, it can reduce unnecessary maintenance inspections and fault downtime, significantly reducing the overall maintenance cost. In addition, preventive maintenance can also avoid the occurrence of more expensive major faults or accidents.

[0068] 4. The present invention extends the equipment life. Real-time monitoring and fault warning help to better manage the workload of the launch pad, avoid overuse or improper operation, extend the service life of the equipment, and reduce the equipment replacement frequency.

[0069] 5. The present invention improves decision-making efficiency. By means of digital twin real-time simulation analysis of the operating status of the launch pad, it provides vivid and intuitive display of the health status and fault prediction data, serving for the managers to make decisions quickly and efficiently, and continuously improving the scientific and robust level of personnel decision-making.

[0070] 6. The present invention supports operations in complex environments. For complex equipment such as the launch pad, environmental factors (such as climate, vibration, etc.) may affect its performance. By means of digital twin technology, the impacts of the above complex environmental factors on the launch pad are simulated, and thus comprehensive data support is provided for equipment maintenance.

[0071] 7. The present invention improves technological innovation. Adopting digital twin technology for intelligent predictive maintenance is an advanced way of modern equipment management and maintenance, which not only improves the operation and maintenance efficiency of the launch pad, but also can bring more technological innovation to the industry.

Claims

1. A data fusion method for predicting the health status of a launch station based on digital twins, characterized in that: The following steps are involved: S100, constructing a launch pad virtual entity: constructing a virtual entity model, an operation parameter model, and a state data model, keeping the model state synchronized with the physical entity in real time, and continuously iterating and optimizing the virtual entity to meet data consistency and integrity requirements; S200, construction of a launch station data source: forming metadata by collecting sensor parameters and acquired equipment status history data, acquired equipment failure data, and acquired equipment maintenance record data; S300, fusion of health status data: fusion of data by target and stage, processing of multi-dimensional heterogeneous data sources of the launch station through cleaning, integration and conversion processes, unification of data formats, elimination of junk data, input of digital entities, and ensuring the unity of virtual and real; S400, Fault diagnosis and prediction: First, by extracting the launch station fault characteristic values, synchronously simulating the digital entity, comparing and analyzing the operation results with the launch station historical status data in the fault knowledge base, and then determining the cause of the fault; secondly, by selecting the launch station status parameters with strong correlation at multiple times and under different working conditions, establishing its operating status law model, and predicting the possible fault type and fault location through data mining simulation experiments; S500, Launch pad maintenance decision: Identify potential hidden dangers in the launch pad, and maintain the various components of the launch pad according to previous strategies to reduce potential failures and maximize its use value.

2. The data fusion method for predicting the health status of a launch station based on digital twin according to claim 1 is characterized in that: The step S300 also includes: data layer fusion: used to perform structured integration of heterogeneous data from different sources, convert the data into RDF unified data format using a multi-source data fusion framework, and then perform information fusion through a data fusion algorithm.

3. The data fusion method for predicting the health status of a launch station based on digital twin according to claim 2 is characterized in that: The data layer fusion is divided into: pixel layer fusion, feature layer fusion and decision layer fusion; The pixel-level fusion is used to divide the data analysis work into three typical stages: data layer, feature layer and decision layer; The feature layer fusion is used to map the feature fusion to the subspace; The decision layer is integrated, and Logistic regression is used to predict the sentiment of text and related images, and finally the two prediction probabilities are weighted averaged.

4. The data fusion method for predicting the health status of a launch station based on digital twins according to claim 3 is characterized in that: The step S300 also includes: data association analysis, by designing a data association algorithm to associate multi-source data of environmental conditions and associated equipment working status, and using association rule mining and machine learning technology to find out the potential relationship between the data; Preprocess the associated environmental condition data, including: Analyze the effect of environmental configuration: Establish an environmental configuration effect evaluation index system, and analyze the effect of training environmental configuration through multi-source data; Preprocess the associated equipment working status data, specifically including: Analysis of the launch station working efficiency: By designing an equipment working efficiency evaluation model, the equipment performance data is used to analyze the launch station working efficiency.

5. The data fusion method for predicting the health status of a launch station based on digital twins according to claim 4 is characterized in that: The implementation method of the environmental construction effect analysis includes: determining an environmental construction effect evaluation index system, collecting multi-source data with sensors, analyzing and calculating the multi-source data, and then evaluating the environmental construction effect.

6. The data fusion method for predicting the health status of a launch station based on digital twins according to claim 4 is characterized in that: The implementation method of the launch station work efficiency analysis includes: designing an equipment work efficiency evaluation model, collecting equipment performance data, analyzing and calculating multi-source data, and then evaluating the equipment work efficiency.

7. The data fusion method for predicting the health status of a launch station based on digital twins according to claim 6 is characterized in that: The design equipment working efficiency evaluation model adopts hierarchical analysis method and fuzzy comprehensive evaluation method.

8. The data fusion method for predicting the health status of a launch station based on digital twins according to claim 7 is characterized in that: The evaluation method of the design equipment working efficiency evaluation model includes: The first step is to determine the evaluation index system, including the equipment's normal operating time, operating efficiency and failure rate indicators; then the weight of each indicator is determined through expert scoring and hierarchical analysis method; finally, the comprehensive score of the launch station's working efficiency is calculated based on the indicator value and weight.

Images