Information Fusion Technology Research Articles

Research on Online Verification of Relay Protection Setting Value Based on Multi-source Information Fusion Technology and Bow-tie Model

In view of the complexity and flexibility of the current power grid, in order to make relay protection online verification more accurate and effective, a protection importance degree sequence assessment method based on the multi-source information fusion technology and bowtie model is proposed. Firstly, the cause of incorrect protection actions is analyzed by establishing a fault tree through multi-source information fusion technology, and the event tree analysis method is used to deduce the final development result of the event. Combined with the fault tree and the event tree, a bow-tie model is formed to visually and completely describe the whole process of the event. Then the economic loss of the event is analyzed as the basis for assessing the protection importance degree, and the online inspection of the protection setting value is completed from high to low according to the importance degree sequence. Finally, the IEEE 3-machine 9-bus system is used to verify the correctness and rationality of the method through simulation.

Fault Diagnosis Method of Ship Main Machinery Based on Information Fusion Technology

Yan, T. and Liu, X., 2020. Fault diagnosis method of ship main machinery based on information fusion technology. In: Yang, Y.; Mi, C.; Zhao, L., and Lam, S. (eds.), Global Topics and New Trends in Coastal Research: Port, Coastal and Ocean Engineering. Journal of Coastal Research, Special Issue No. 103, pp. 905–908. Coconut Creek (Florida), ISSN 0749-0208.There are many problems in the traditional diagnosis methods of ship main mechanical fault, so the research on the diagnosis method of ship main mechanical fault based on information fusion technology is put forward. According to the actual situation and the existing literature, this paper analyzes the main types of mechanical faults of ships, on this basis, obtains the main mechanical information, processes the information by the polynomial least square method, extracts the main mechanical information characteristic parameters by the neural network algorithm, and introduces the information according to the extracted main mechanical information characteristic parameters of ships Information fusion technology, through the calculation of the diagnosis results, realizes the main mechanical fault diagnosis of the ship based on information fusion technology. The experimental results show that the proposed method is feasible and greatly reduces the diagnostic error, which fully shows that the proposed method has better diagnostic performance.

Design and Research of Intelligent Mobile Robot Based on IOT Information Fusion

Artificial intelligence-based intelligent robots are becoming more and more popular at present, and robot navigation is an instruction issued by the neural network of the robot. Therefore, a variety of sensors need to be distributed in the neural network of the robot to issue commands for the navigation of the robot., Plan the path, and perceive external information and adjust your position during the process. Therefore, the multi-sensor information fusion technology based on the Internet of Things is very important. It can provide a better information foundation for robot navigation, improve the robot navigation system and improve accuracy with the IOT information fusion technology.

Instantaneous Feature Extraction and Time–Frequency Representation of Rotor Purified Orbit Based on Vold–Kalman Filter

As a well-known homologous information fusion technology, the full spectrum is widely used in orbit analysis of rotating machinery. However, due to the average effect of the Fourier transform, the instantaneous features of the axis orbit cannot be obtained in full spectrum. This limits the application of the full spectrum in a nonstationary vibration analysis. The time–frequency representation (TFR) of axis orbit has been proved to be an effective tool for analyzing nonstationary vibration signals. In this article, a new approach of instantaneous features extraction of harmonic axis orbits is proposed. Furthermore, based on these features, an approach to construct the purified orbit TFR (POTFR) is proposed. First, the estimated speed signal is extracted from the TFR of a single-channel signal by data fitting. Guided by the estimated speed signal, the harmonic components of interest are separated by the Vold–Kalman filter. Furthermore, the parameters of each harmonic instantaneous orbit are calculated from the time domain by using the separated harmonic signals. Based on these parameters, high-resolution POTFRs of all the harmonic orbits are constructed. Finally, the POTFR of the original signal is obtained by combining the POTFRs of all the harmonic components. The proposed approach is illustrated by numerical simulation and is further validated using laboratory experimental signals of oil whip and bistable behavior. The start-up signal from a hydroelectric generating set further demonstrates the superiority of the method.

A deep convolutional neural network approach with information fusion for bearing fault diagnosis under different working conditions

In recent years, deep learning-based fault diagnosis methods have drawn lots of attention. However, for most cases, the success of machine learning-based models relies on the circumstance that training data and testing data are under the same working condition, which is too strict for real implementation cases. Combined with the features of robustness of deep convolutional neural network and vibration signal characteristics, information fusion technology is introduced in this study to enhance the feature representation capability as well as the transferability of diagnosis models. With the basis of multi-sensors and narrow-band decomposition techniques, a convolutional architecture named fusion unit is proposed to extract multi-scale features from different sensors. The proposed method is tested on two data sets and has achieved relatively higher generalization ability when compared with several existing works, which demonstrates the effectiveness of our proposed fusion unit for feature extraction on both source task and target task.

Multi-source Information Fusion Technology and Its Engineering Application

With the continuous development of information technology in recent years, information fusion technology, which originated from military applications, plays an important role in various fields. In addition, the rapidly increasing amount of data and the changing lifestyles of people in the information age are affecting the development of information fusion technology. More experts and scholars have focused their attention on the research of image or audio and video fusion or distributed fusion technology. This article summarizes the origin and development of information fusion technology and typical algorithms, as well as the future development trends and challenges of information fusion technology.

Multi-Information Spatial–Temporal LSTM Fusion Continuous Sign Language Neural Machine Translation

There are two basic problems in sign language recognition (SLR): (a) isolated word SLR and (b) continuous SLR. Most of the existing continuous SLR methods are extensions of the isolated word SLR methods. These methods use the isolated word SLR results as the basic module and obtain the sentence recognition results through sentence segmentation and word alignment. However, sentence segmentation and word alignment are often not accurate, resulting in a low sentence recognition accuracy. At the same time, continuous SLR usually requires strict sample labels, leading to the difficult task of manual labeling and limited training data availability. To address these challenges, this paper proposes a bidirectional spatial–temporal LSTM fusion attention network (Bi-ST-LSTM-A) for continuous SLR. This approach avoids problems such as sentence segmentation, word alignment, and tedious manual labeling. Our contributions are summarized as follows: (1) we proposed a sign language video feature representation method using a convolutional neural network (CNN) and spatial–temporal LSTM (ST-LSTM) information fusion technology; and (2) we constructed a uniform neural machine translation framework that can be used for complex continuous SLR and gesture recognition of nonspecific people in nonspecific environments. Experiments were carried out on some large continuous sign language datasets. The sign language recognition accuracy reached 81.22% on the 500 CSL dataset, 76.12% on the RWTH-PHOENIX-Weather dataset and 75.32% on the RWTH-PHOENIX-Weather-2014T dataset, thereby illustrating the effectiveness of the proposed framework.

The Methods of Information Acquisition and Information Fusion of the Photoelectric Sensor-Based Quadrotor Unmanned Aerial Vehicle

When quadrotor unmanned aerial vehicle (UAV) is performing various tasks, even a small angular error will affect the evaluation of the entire motion trajectory. The multiple photoelectric sensor information fusion technology and the ARM microprocessor platform are used to form an attitude reference system for UAV. First, the hardware design of the small quadrotor UAV attitude reference system based on an ARM is introduced. The design framework and information acquisition module are expounded. In terms of the software of the system, the photoelectric sensor is used to receive different kinds of information, and the dynamic loading component is adopted as the solution to the interface diversification problems. Based on the attitude reference system, the collected information needs to be fused. The Kalman filtering is taken as the research object. Combined with the multiple photoelectric sensor information fusion technology, the Kalman filtering method is improved in the data preprocessing, and the low-pass filtering is added. Therefore, the abnormal data is filtered, and the estimated values are converged in a short time. Then, the data fusion is performed by the joint Kalman filter, least-squares fusion, and extended Kalman filter, respectively. During the experimental process, the system is proved to have good robustness, that is, in the case of individual sensor failure, the attitude acquisition section still obtains accurate attitude information of the UAV. The attitude reference system of UAV is realized. With the help of multi-sensor/information fusion technology, the attitude of the UAV is better handled, and its flight stability is improved.

Safety Assessment System of Launching Tower Structure with Multi-information Fusion and Data-driven

In order to monitor and evaluate the impact of rocket launching shock, strain, vibration, typhoon, earthquake and other loads on the launch tower, an online monitoring and evaluation system was established based on multi-sensor information fusion technology in a space launch site. Firstly, the system integrates the information of vibration, pressure, deformation, wind load, temperature and other sensors to comprehensively analyze and evaluate the safety of tower structure, and realizes health diagnosis. Then use 3dmax to draw the 3D simulation model, and realize the real-time 3D display of various monitoring and analysis results based on the 3D visualization and data-driven technologies.

Information Fusion Applied in EV’s Intelligent Integrated Station

The dispatching center in the intelligent integrated station (IIS) collects multi-source information flow such as operating information of electric vehicles (EVs), energy level of the IIS, grid loading level, and power flow between the IIS and the grid. To achieve better management for the energy exchange between the IIS and the grid, this paper applies information fusion technology to the control of IIS. The Boyd’s Observe-Orient-Decide-Act (OODA) process model is introduced to estimate and analyze the multi-source information flow inside and outside the IIS. Two issues associated with the operation of the IIS are studied: (i) the power flow between the IIS and the grid considering operating information of the IIS and the grid; (ii) the charging/discharging order of batteries considering batteries information to assure the number of full-capacity batteries and prolong the battery life. Simulation results suggest that the proposed control strategy based on OODA allows significant improvements in both the user satisfaction and economic operation of the power grid.

A Method for Real-Time Suppression of In-Phase Error of Silicon Micro Gyroscopes

This paper reports a method to suppress the in-phase error of silicon micro gyroscopes in real time, which can realize long-term stability, without significantly affecting the sensor noise. The in-phase error suppression is by periodically changing the polarity of the drive mode, and the bias (zero rate output) decreases from -7.8deg/s to -3.9deg/s, attenuation amplitude of which is about 3.9deg/s. By sampling the output using information fusion technology, low shirt-time noise and bias instability can be obtained without cutting off the gyroscope and adding additional sensors, the bias instability of which is reduce from 35.0 deg/hr to 10.8 deg/hr. The feasibility of the approach was experimentally evaluated using a MEMS gyroscope with the algorithm implementation on FPGA in real-time.

Intelligent identification for working-cycle stages of excavator based on main pump pressure

Abstract An identification of the working stages of the excavator is used as the basis to realize a staged energy-saving control and reduce the fuel consumption. However, existing methods based on computer vision and multi-sensor information fusion technologies have limitations in practical applications. In this paper, an intelligent identification method for the working-cycle stages of an excavator is proposed based on the relationship between the working stages and the main pump pressure waveform. Three machine learning algorithms, a support vector machine (SVM), back propagation neural network (BPNN), and logistic regression (LR), were used to establish the intelligent recognition model. In addition, an intelligent calibration system was established to reduce the effects of human-induced factors and pressure fluctuations on the accuracy when using the original main pump pressure signals. The relationships among the identification accuracy, time window width, and signal sampling frequency were also studied. The results show that the library for support vector machine (LIBSVM) model outperforms the BPNN and LR, recording an accuracy of 94.64% when using the test set and an accuracy of 93.82% with an intelligent calibration system when using the original main pump pressure signals. The optimal time window width and signal sampling frequency are 0.5 s and 20 Hz, respectively. The proposed method is a practical approach to realize the real-time supervision of the working stage of an excavator, providing theoretical support for a staged energy-saving control.

Agglomeration-Monitoring Method for a Fluidized Bed with Multiacoustic Sensors

The acoustic method is sensitive to agglomerations in fluidized bed reactors; however, a single acoustic sensor is not sufficient for industrial-scale reactors with regard to size, environmental noise, and signal pollution. Therefore, a multiacoustic sensor-based monitoring approach is investigated in this study. Different agglomeration warning models are established on the basis of each separate sensor, and then information-fusion technology is introduced. In the modeling process, an early warning method for industrial applications is designed. First, singular value decomposition is introduced for feature extraction to simplify the signal preprocessing and reduce the number of preset parameters. Thereafter, as agglomeration samples are lacking in industrial data, support vector data description (SVDD), an unsupervised learning method, is employed to establish the agglomeration warning model according to samples under normal conditions. As the Boolean outputs of SVDD are not suitable for information fusio...

Guest Editorial Neuro-Robotics Systems: Sensing, Cognition, Learning, and Control

Neuro-robotics systems (NRSs) are the most advanced research in the field of robotics, promoting the seamless exchange of knowledge between neuroscience and robotics. Recent breakthroughs in human brain neuroscience could be applied to robots to improve their perception, cognition, learning, and control abilities, which even help to develop a brain for robots. A challenge of robotics research is to break through technical bottlenecks by the findings in neuroscience and make robots move more flexibly, have more intelligent perception and control, and communicate with humans more naturally. To address the challenge, this special issue focuses on the latest advances in the area of NRS, particularly, the research concentrating on human-like sensing, multimodal information fusion, cognition, learning, and control technology. The development of these technologies aims to bring innovations into robotics and NRSs.

Assessment technique of karst aquifer water abundance in shale gas exploitation area based on multi-source information fusion technology—Fenggang shale gas area case

In the process of shale gas extraction, groundwater resources are easy to be polluted, and a lot of water resources are also needed to ensure the water consumption of hydraulic fracturing technology. Therefore, it is of great significance to analyze and predict the water abundance of aquifers in shale gas extraction areas for the rational protection and utilization of groundwater resources. On the basis of summarizing the main controlling factors of aquifer water abundance in karst area, a multi-source information evaluation model for aquifer water abundance was established based on analytic network process (ANP), and then using the information processing and spatial display functions of geographic information system (GIS) technology, thematic maps of various controlling factors were made and the thematic maps were superimposed. Finally, the evaluation and prediction of aquifer water abundance in Fenggang shale gas extraction area were completed. The evaluation results show that the groundwater in the central, northern, and structural distribution areas of the study area is abundant, and the groundwater in the southeast and southwest is lacking. Multi-source information evaluation method based on GIS-ANP technology is a new method for evaluating aquifer water abundance, and could effectively reflect the aquifer water abundance controlled by multiple factors with very complex formation mechanism, and can also reflect the mutual interaction between factors. It is a viable method for evaluating the aquifer water abundance.

Fast Fault Location Method for Power Distribution Systems Based on Multi-source Information Fusion Technology

Considering that the information uploaded by distribution terminal is often lost or wrong in actual operation, which leads to misjudgement, this paper proposes a new fault location method based on multi-source information fusion technology. The advantage of this method is that multi-source information is used for fault location, which can avoid misjudgement caused by an abnormality of single source information. Firstly, the information uploaded from the remote terminal unit of the distribution automation system is used, and the user complaint information is converted into binary information. The fault information is formed based on the improved binary particle swarm optimization algorithm, and then the improved D-S evidence theory is used to fuse the positioning results of each fault information to obtain the final positioning result. The case study shows that the proposed method is effective and feasible, and can solve the problem when multi-source heterogeneous fault information has unrecognizable anomalies.

Gesture recognition algorithm based on image information fusion in virtual reality

Combining image information fusion theory with machine learning for biometric recognition is an important field in computer vision research in recent years. Based on this, a gesture recognition algorithm based on image information fusion in virtual reality is proposed. Firstly, it introduces the basic concepts and principles of virtual reality and information fusion technology, analyzes the characteristics and basic components of virtual environment system, points out the relationship between human and virtual environment and the impact of virtual environment on people, and gives a virtual reality. Then, the multi-sensor information fusion model of the virtual environment for gesture recognition is proposed. The membership degree and template matching algorithm are further selected for data correlation and gesture recognition in the fusion model. Finally, the design comparison experiment verifies the proposed method. The results show that the proposed multi-sensor information fusion model in the interactive virtual environment achieves the highest recognition success rate of 96.17% and is better than several comparison machine learning methods in recognition time.

Sparse long short-term memory for information fusion in wireless sensor networks

Wireless sensor networks are designed to perceive, gather, and process external environmental information and send it to the observer. However, the transmission of mass information is a challenge to the sensor nodes. To address this challenge, information fusion technologies are proposed to reduce mass redundant data. However, these techniques rarely consider the historical information, and thereby often encounter the difficulty of low prediction accuracy. In order to solve this difficulty, we propose a novel information fusion approach for the cluster heads. The proposed approach is based on time-recurrent neural network, called sparse long short-term memory, which is derived from the long short-term memory network. The sparse long short-term memory uses sparse matrix to reduce the dimension for a high-dimensional coefficient matrix. Therefore, the computational cost of the fusion algorithm is reduced in wireless sensor networks. The simulation results show that the sparse long short-term memory algorith...

Application Research of Multi-source Information Fusion Technology in Power Network Fault Diagnosis

In this paper, a power grid fault diagnosis method based on multi-source information fusion technology is proposed for grid faults. Firstly, the wavelet transform is used to analyze the electrical quantity information of the fault recorder and PMU, and the three fault reliability characterizations of the components are obtained. Secondly, the information fusion based on the improved D-S evidence theory is carried out for each fault characterization, and the comprehensive fault credibility of the components is obtained, and the fault criterion is given. Finally, the fuzzy C-means method is used to make the diagnosis decision of the faulty component, and the final diagnosis result is obtained. The simulation results show that the method combines the electrical quantities of the fault recorder and the PMU to obtain accurate fault diagnosis results, which can effectively reduce the impact of protection and switch refusal misoperation on power grid fault diagnosis. This method has a good application prospect in power system fault diagnosis.

NC Equipment Fault Diagnosis Research in Uncertain Circumstance Based on Information Fusion and Bayesian Networks Integrated

With the development of NC Equipment for the direction of high-speed, high power and high reliability, there are lots of complicated and coupling relationship as well as uncertain elements and information between and among the components. Two theory methods that are combined based on information fusion technology and Bayesian network are proposed in this paper. Firstly, more information fusion method can increase the completeness of the fault information to overcome the disadvantages of the single sensor; Secondly, Bayesian network is one of most effective means which not only can decrease the ambiguity of fault information but also improve the speed of fault diagnosis. At last, the experimental study of NC tool-machines is verified to be valid, which strengthens the practical value.