Data Fusion For Monitoring Research Articles

Data fusion method for aircraft surveillance in flight zone based on Trans-Attention

Aiming at the problem of low monitoring accuracy and position jump of single monitoring source of aircraft in the flight zone, a method of aircraft monitoring data fusion based on Transformer and attention mechanism is proposed. Firstly, the encoder structure of Transformer is used to extract features of each monitoring source data respectively, and then weight values are assigned to different monitoring sources through the attention mechanism. Finally, regression calculation is performed through the fully connected network to obtain the final fusion result. The monitoring data of the surface surveillance radar and the broadcast automatic dependent surveillance system are selected as the fusion source, and the multi-point positioning data is used as the true label. The experimental results show that this method effectively reduces the monitoring error of a single monitoring source, and the fusion effect is better than the long short-term memory network, recurrent neural network and extended Kalman filter fusion method based on the attention mechanism, and the mean absolute error is improved by 2.20%、14.32%and respectively 33.94%.

RESEARCH ON THE STANDARDIZATION AND VISUALIZATION PLATFORM FOR MONITORING AND TESTING DATA OF METRO CIVIL FACILITIES BASED ON BIG DATA

Introduction: With consideration for extensive standardized detection and monitoring data, multi-source data fusion analysis and comparison were implemented at cross-project and inter-regional levels to provide robust data support for the full life-cycle management of metro civil facilities. The purpose of the study was to integrate detection and monitoring data on metro bridges and tunnel structures and address the significant data isolation issue in existing systems and various units. Based on big data and Internet of Things technology, this paper investigates the standardized format of uploading, storage, processing, sharing, and other types of managing detection and monitoring data on metro bridges and tunnel structures. Additionally, a third-party data standardization and visualization platform for bridges and tunnel structures was developed, ensuring integration of detection and monitoring data fusion. In the course of the study, the following methods were used: theoretical analysis and software system development. As a result, the practicability and feasibility of the platform were verified through practical applications.

Landslide displacement prediction model based on multisource monitoring data fusion

This study presents a displacement prediction model that integrating various monitoring data sources to comprehensive landslide monitoring information utilization. The research focuses on the landslide in Lingwan Village, utilizing Ridge Regression (RR) to integrate diverse monitoring data. The fused displacement data undergo decomposition into trend and periodic terms using the Smoothness Priors Approach (SPA). The Autoregressive Integrated Moving Average (ARIMA) model predicts trend and periodic term displacements separately, which are then combined to forecast the overall landslide surface displacement accurately. The RR model demonstrates a strong correlation coefficient of 0.998, indicating high predictive ability. Trend term displacement prediction outperformed periodic term prediction, especially during the rainy season. The RR-SPA-ARIMA model has an average absolute error of 1.73 mm, a mean bias error of −0.08 mm, and a root mean square error of 1.87 mm. The model demonstrates high prediction accuracy.

Research on the Three-Machines Perception System and Information Fusion Technology for Intelligent Work Faces.

The foundation of intelligent collaborative control of a shearer, scraper conveyor, and hydraulic support (three-machines) is to achieve the precise perception of the status of the three-machines and the full integration of information between the equipment. In order to solve the problems of information isolation and non-flow, independence between equipment, and weak cooperation of three-machines due to an insufficient fusion of perception data, a fusion method of the equipment's state perception system on the intelligent working surface was proposed. Firstly, an intelligent perception system for the state of the three-machines in the working face was established based on fiber optic sensing technology and inertial navigation technology. Then, the datum coordinate system is created on the working surface to uniformly describe the status of the three-machines and the spatial position relationship between the three-machines is established using a scraper conveyor as a bridge so that the three-machines become a mutually restricted and collaborative equipment system. Finally, an indoor test was carried out to verify the relational model of the spatial position of the three-machines. The results indicate that the intelligent working face three-machines perception system based on fiber optic sensing technology and inertial navigation technology can achieve the fusion of monitoring data and unified expression of equipment status. The research results provide an important reference for building an intelligent perception, intelligent decision-making, and automatic execution system for coal mines.

Settlement monitoring data fusion approach for high-speed railways based on GNSS and InSAR

Settlement monitoring data fusion approach for high-speed railways based on GNSS and InSAR

An Unsupervised Machine Learning Approach for Monitoring Data Fusion and Health Indicator Construction.

The prediction of system degradation is very important as it serves as an important basis for the formulation of condition-based maintenance strategies. An effective health indicator (HI) plays a key role in the prediction of system degradation as it enables vital information for critical tasks ranging from fault diagnosis to remaining useful life prediction. To address this issue, a method for monitoring data fusion and health indicator construction based on an autoencoder (AE) and a long short-term memory (LSTM) network is proposed in this study to improve the predictability and effectiveness of health indicators. Firstly, an unsupervised method and overall framework for HI construction is built based on a deep autoencoder and an LSTM neural network. The neural network is trained fully based on the normal operating monitoring data and then the construction error of the AE model is adopted as the health indicator of the system. Secondly, we propose related machine learning techniques for monitoring data processing to overcome the issue of data fusion, such as mutual information for sensor selection and t-distributed stochastic neighbor embedding (T-SNE) for operating condition identification. Thirdly, in order to verify the performance of the proposed method, experiments are conducted based on the CMAPSS dataset and results are compared with algorithms of principal component analysis (PCA) and a vanilla autoencoder model. Result shows that the LSTM-AE model outperforms the PCA and Vanilla-AE model in the metrics of monotonicity, trendability, prognosability, and fitness. Fourthly, in order to analyze the impact of the time step of the LSMT-AE model on HI construction, we construct and analyze the system HI curve under different time steps of 5, 10, 15, 20, and 25 cycles. Finally, the results demonstrate that the proposed method for HI construction can effectively characterize the health state of a system, which is helpful for the development of further failure prognostics and converting the scheduled maintenance into condition-based maintenance.

Multi-sensors data fusion for monitoring of powdered and granule products: Current status and future perspectives

Process Analytical Technology (PAT) is a systematic approach for monitoring of process parameters and product quality attributes and nowadays is considered for continuous processing of many industrial products. It is a mechanism to design, analyse and control manufacturing processes through on-line, in-line, at-line and off-line configurations for monitoring Critical Quality Attributes (CQAs). PAT systems include a combination of reliable in-line sensors, spectroscopic instruments and Multivariate Statistical Methods (MSMs) to provide informative knowledge for quality assessment of powdered and granule products. Nevertheless, monitoring programs of advanced manufacturing processes based on PAT systems typically provide large sets of data which are complex to interpret. The application of appropriate data-driven modelling techniques could assist in the interpretation of complex data matrices to better control of processes. Data fusion is a data-driven approach that could increase performance and robustness of models used for data interpretation to generate more accurate knowledge about process conditions and performance by merging related outputs collected from several instruments and considering synergies from multiple sources. This paper aims at presenting the current state of the art regarding the application of multi-sensors data fusion for powdered and granule manufacturing processes and making a critical review of recent progress and future possible perspectives in this field.

Distributed sensors and neural network driven building earthquake resistance mechanism

<abstract> <p>The anti-seismic support and hanger are firmly connected to the building structure and are anti-seismic support equipment with seismic force as the main load. Real-time and accurate acquisition of the service status of the seismic support and hanger to check and judge whether the seismic support and hanger are in a normal working state is of great significance for practical engineering applications. In this paper, based on distributed sensor technology, a set of intelligent monitoring systems for seismic support and hanger of buildings is established. The sensing equipment installed on the seismic support and hanger senses the signal, and then the data collection, storage and processing are used to accurately judge the seismic support and hanger. Service performance status. To effectively fuse multi-source data in distributed sensor environment, an improved method based on wavelet and neural network data fusion is proposed. Compared with the existing methods, the experimental results show that the proposed method has good robustness. Besides, it has better performance in building seismic multi-source monitoring data fusion and is less affected by the data overlap ratio.</p> </abstract>

A Water Leakage Risk Assessment Model for Shield Tunnel Based on Kalman Filter Data Fusion Method

Multi-source information monitoring and data fusion analysis system has high practical value for the risk management of tunnel structure, especially in complex ground. The analysis of structure health will be getting more comprehensive and real-time with multisource monitoring technologies. Risk warning will be more accurate and timelier. Based on one shield tunnel project, this research analysed the water leakage risk of shield subsea tunnel in unfavourable geological conditions by using the method of geological information and structural monitoring data fusion. Firstly, Kalman filter method was used to denoise the monitoring data, and the effect of different monitoring data was compared; Then, the risk factor of water leakage was analysed, and the relationship between risk factors, geological information and monitoring data was established; Finally, the risk factors based on multi-source monitoring information were fused and analysed by using the improved D-S evidence theory method, and the final analysis results of water leakage risk were obtained. A multisource dynamic risk analysis model of tunnel water leakage was established. The results showed that the Kalman filter method has better noise reduction effect on the high-frequency monitoring data than that of low-frequency monitoring data, and the multi-source dynamic risk analysis model has a good prediction effect on the water leakage risk of tunnel lining in unfavourable ground condition.

Security Monitoring Data Fusion Method Based on ARIMA and LS-SVM

Using the Autoregressive Integrated Moving Average Model (ARIMA) and least squares support vector machine model (LS-SVM), the data of the security monitoring data obtained during the security supervision process is data fusion, and the data is reduced by data. After the components are analyzed, the accident prediction is performed based on the improvement of data processing efficiency. Finally, the main data analysis (PCA) of the 15-dimensional data is used to reduce the dimension to the 7-dimensional data based on the accuracy of the information. After that, the data fusion technology is used to fuse the data to establish the ARIMA-LS-SVM combination. The model uses the combined forecasting model to predict and analyze the safety production accidents, and uses the actual data to verify. The results show that the data fusion technology can improve the efficiency of data processing. The model fits the time series of safety accidents well. The high prediction accuracy can help the company’s safety production accident prediction in the future.

Preliminary Study on Data Fusion Based on Internet of Things of Eucalyptus Plantation

Eucalyptus is the main fast-growing and high-yielding tree species in southern China and is the main source of wood production. Over the years, there have been many reports that eucalyptus is a water pump and that eucalyptus causes serious damage to understory vegetation. In this paper, a sensor network of eucalyptus plantation has been established in Yinling branch of Gaofeng Forest Farm in Guangxi, the main eucalyptus producing province. The sensor network can monitor the DBH changes, trunk runoff, soil moisture, environmental information and so on of eucalyptus in the stand in real time. The collected data are uploaded to the artificial forest Internet of Things monitoring information cloud management system established in this paper. This paper introduces the functions of the cloud management system in detail. On this basis, this paper discusses the fusion of high-frequency information collected from monitoring points to meet different data requirements. The research on data fusion in this paper is very preliminary. In the conclusion part, the future research on long-term monitoring data fusion of eucalyptus forest is prospected.

Structural health monitoring data fusion for in-situ life prognosis of composite structures

A novel framework to fuse structural health monitoring (SHM) data from different in-situ monitoring techniques is proposed aiming to develop a hyper-feature towards more effective prognostics. A state-of-the-art Non-Homogenous Hidden Semi Markov Model (NHHSMM) is utilized to model the damage accumulation of composite structures, subjected to fatigue loading, and estimate the remaining useful life (RUL) using conventional as well as fused SHM data. Acoustic Emission (AE) and Digital Image Correlation (DIC) are the selected in-situ SHM techniques. The proposed methodology is applied to open hole carbon/epoxy specimens under fatigue loading. RUL estimations utilizing features extracted from each SHM technique and after data fusion are compared, via established and newly proposed prognostic performance metrics.

Multi-sensor fusion of data for monitoring of Huangtupo landslide in the three Gorges Reservoir (China)

There hides a certain relationship among various monitoring data in a landslide, and the mining of this relationship is of significance to landslide research. In this paper, we first collect multiple monitoring data of riverside 1# slump-mass of Huangtupo landslide, the Three Gorges Reservoir Region, China, including Global Positioning System (GPS) monitoring data, inclinometer data, reservoir water level, rainfall, water content, crack width, groundwater level and temperature data, etc. By adopting the combination of quantitative statistics and qualitative simulation method for multi-sensor fusion monitoring data analysis, we overcome the one-sidedness of using a single method or single data type. The result of fusion analysis has indicated that in time periods with low rainfall or when the rainfall is not the major factor, main factors affecting landslide movement are crack development, water content of the landslide and water level of the Three Gorges Reservoir. Compared with the actual monitoring data, the fusion analysis results has a maximum error of 1.9%, which shows a good effect.

Adaptive neuro-fuzzy fusion of multi-sensor data for monitoring of CNC machining

PurposeAcoustic emission (AE) could be used for prevention and detection of tool errors in Computer Numerical Control (CNC) machining. The purpose of this study is to analyze the AE form of CNC machining operations.Design/methodology/approachExperimental measurements were performed with three sensors on the CNC lathe to collect the data of the CNC machining. Adaptive neuro-fuzzy inference system (ANFIS) was applied for the fusion from the sensors’ signals to determine the strength of the signal periodic component among the sensors.FindingsThere were three inputs, namely, spindle speed, feed rate and depth of cut. ANFIS was also used to determine the inputs’ influence on the prediction of strength of the signal periodic component. Variable selection process was used to select the most dominant factors which affect the prediction of strength of the signal periodic component.Originality/valueResults were shown that the spindle speed has the most dominant effect on the strength of the signal periodic component.

Technology for Transformer Fault Diagnosis with Detection and Monitoring Data Fusion

Fault diagnosis is an effective means to assure the safe operation of power system. In this paper, a detection and monitoring of transformer fault diagnosis of multi-source data fusion technology is introduced. Based on the correlation distance, to calculate the relationship between detection and monitoring data and equipment failure, using the weight function to set fault indicators, status online monitoring data over the fault indicators, judging the equipment what kind of failure is happened, improving the precision of fault diagnosis.