Multi-sensor Information Research Articles

Expressway danger warning ICV based on multi-sensor information fusion

Expressway danger warning ICV based on multi-sensor information fusion

Research on Comprehensive Safety Monitoring System for Elderly Care Based on Artificial Intelligence and Information Fusion

Nowadays, China has entered into an aging society; how to ensure safety in elderly care has drawn social attention. Through artificial intelligence and multi-information fusion research, combined with the applications of machine learning algorithms, internet of things devices and cloud computing, this paper presents a comprehensive, intelligent safety monitoring system for the elderly in the community and at home. The system collects the daily life data of the elderly through a series of sensors in an all-round, all-time, and non-intrusive manner, and realizes intelligent alarms for high-risk states such as falls, acute illness, abnormal personnel, and gas smoke for the elderly. Through the innovative research of human pose estimation and behavior recognition, and application of multi-sensor information fusion, the system can greatly reduce the occurrence or injury caused by safety incidents in senior care, bringing safe and healthy living environment for the elderly at homes and communities.

Multisensor information fusion method for intelligent fault diagnosis of reciprocating compressor in shale gas development

To address the problems of the poor feature extraction ability and weak data generalization ability of traditional fault diagnosis methods in reciprocating shale gas compressor fault diagnosis applications, in this study, a fault diagnosis method for reciprocating shale gas was developed. This method uses a novel optimized learning method, free energy in persistent contrastive divergence, in deep belief network learning and training. It solves the problem of the deep belief network classification ability degradation in long-term training. The root mean square error is used as the fitness function to search for the optimal parameter combination of the DBN network by using the sparrow search algorithm. At the same time, the learning rate and batch size of the deep belief network, which have a large impact on the training error, are selected for optimization. Then, the original vibration signal is preprocessed by calculating 13 different time domain indicators, and feature-level data and decision-level data are fused in a parallel superposition method to obtain a fused time domain index dataset. Finally, combined with the powerful adaptive feature extraction and nonlinear mapping ability of deep learning, the constructed sample dataset is input to the deep belief network for training, and the deep belief network based on reciprocating shale gas compressor fault diagnosis model is established.

Gear Fault Diagnosis Method Based on Multi-Sensor Information Fusion and VGG.

The gearbox is an important component in the mechanical transmission system and plays a key role in aerospace, wind power and other fields. Gear failure is one of the main causes of gearbox failure, and therefore it is very important to accurately diagnose the type of gear failure under different operating conditions. Aiming at the problem that it is difficult to effectively identify the fault types of gears using traditional methods under complex and changeable working conditions, a fault diagnosis method based on multi-sensor information fusion and Visual Geometry Group (VGG) is proposed. First, the power spectral density is calculated with the raw frequency domain signal collected by multiple sensors before being transformed into a power spectral density energy map after information fusion. Second, the obtained energy map is combined with VGG to obtain the fault diagnosis model of the gear. Finally, two datasets are used to verify the effectiveness and generalization ability of the method. The experimental results show that the accuracy of the method can reach 100% at most on both datasets.

Preface

The 2022 2nd International Conference on Measurement Control and Instrumentation (MCAI 2022) was held in Guangzhou, China from July 22 to 24, 2022. In view of the current COVID-19 pandemic, it was chosen to be held online. MCAI 2022 promoted research and developmental activities in the fields of “Measurement Control” and “Instrumentation” as well as scientific information interchange between researchers, engineers, and practitioners working all around the world.In the conference, we had the honor of having invited both Prof. Guixiong Liu from South China University of Technology, China and Prof. Zhen Zhou, Guangzhou Hexin Instrument Co., Ltd., China to serve as our Conference General Chairs. The conference consisted of keynote speeches, oral presentations and online Q&A discussion, attracting 100 individuals and institutions worldwide. Primarily, keynote speakers were each allocated 30-45 minutes to hold their speeches. Then in the oral presentations, the excellent papers we had selected were presented by their authors by turns.We were delighted and honored to invite three prominent professors as keynote speakers to deliver their speeches. For a start, Prof. Zongmin Ma from North University of China showed us his research: Non-contact Atomic Force Microscopy Instruments and Atomic Scale Precision Measurements. By developing the ultra-high vacuum non-contact atomic force microscope (NC-AFM), he solved the key technologies of probe vibration control and precise detection, force spectrum measurement, and realized atomic scale imaging characterization in terms of non-destructive imaging of magnetic information and uncoupled measurement of surface charge. Besides, Assoc. Prof. Zhiwei Shi from Guangdong University of Technology, China made a report on Multi-sensor Information Fusion Technology for Intelligent Networked Vehicles. Aiming at the development of intelligent networked vehicles, he proposed a vehicle headlight far-light system based on multi-sensor information fusion, which mainly includes three major parts: information fusion, drive control and optical design, ensuring in a maximum degree the intelligent lighting functions and simple structure, low cost. The wonderful speeches of each keynote speaker had triggered heated discussion. Besides, every participant praised this conference for disseminating useful and insightful knowledge.List of Committee member is available in this pdf.

A Multisensor Cycle-Supervised Convolutional Neural Network for Anomaly Detection on Magnetic Flux Leakage Signals

To improve the validity of magnetic flux leakage (MFL) multisensor signals, anomaly detection has become a significant part of MFL signal processing. The anomalies in MFL are uncertain and have no prior information or labels. Therefore, the detection and location of the anomalies become a difficult issue. Regarding the abovementioned problem, we propose an unsupervised method called multisensor cycle-supervised convolutional neural network (CsCNN). The CsCNN is built including multiple CNNs with the same structure and a cycle-supervised part. The proposed model realizes unsupervised anomaly detection through multiple cycle-supervised CNNs for the first time. Moreover, the latent relationship between multisensor signals is established by CsCNN to take full use of multisensor information. Besides, a dynamic threshold is applied to detect anomalies. In the end, experiments on simulated signals and measured signals are conducted, and CsCNN is compared to the state-of-the-art methods. The results show that the proposed method is effective.

Multi-sensor optimal placement of rotor-bearing system based on fault diagnosability

In view of the current situation that there are few studies on whether the fault signals that may occur in the rotor bearing system can be identified and analyzed in the sensor arrangement, fault diagnosability is applied to the optimal arrangement of the sensors in the rotor bearing system. The preliminary layout of the multi-sensor is carried out by analyzing the transmission path of the vibration signals in the rotor bearing system and based on the minimum path. Secondly, the nonparametric kernel density estimation method calculates the state information’s probability density function. The K-L divergence value is further used to measure fault detectability, fault separability, and fault diagnosability. Then, the correlation function method is used to fuse the multi-sensor information, and the optimal sensor layout is given with the fault diagnosability as an index. Finally, the validity of the method is proved by the experimental laboratory data and the correlation coefficient.

A high-accuracy calibration method for fusion systems of millimeter-wave radar and camera

Multi-sensor information fusion is widely used in the field of unmanned aerial vehicles obstacle avoidance flight, particularly in millimeter-wave (MMW) radar and camera fusion systems. Calibration accuracy plays a crucial role in fusion systems. The low-angle measurement accuracy of the MMW radar usually causes large calibration errors. To reduce calibration errors, a high-accuracy calibration method based on a region of interest (ROI) and an artificial potential field was proposed in this paper. The ROI was selected based on the initial calibration information and the MMW radar’s angle measurement error range from the image. An artificial potential field was established using the pixels of the ROI. Two moving points were set at the left and right ends of the ROI initially. The potential forces of the two moving points are different because the pixels of the obstacle and the background are different in the image. The two moving points were iteratively moved towards each other according to the force until their distance was less than the iteration step. The new calibration point is located in the middle of the final position of the two moving points. In contrast to the existing calibration methods, the proposed method avoids the limitations of low angle measurement accuracy by using image pixels. The experimental results show that the calibration errors decrease by 83.95% and 75.79%, which is significantly improved compared to the traditional methods and indicates the efficiency of the proposed method.

Deconstruction of Urban Public Space Art Design Using Intelligent Sensor and Information Fusion

The main purpose of smart city is to improve the quality of life, improve the efficiency of life, and save the energy resources of life, which is in line with the current global concept of low-carbon environmental protection, energy saving and emission reduction, and ecological sustainable development. Under the process of smart city, the development of urban public space is also committed to meeting the material and spiritual needs of residents’ lives. For the system hardware design, the street lamp node, and the concentrator node hardware design, the sensing node is composed of multiple sensors. Its main components are temperature sensor, infrared sensor, sound sensor, and light intensity sensor, which, respectively, realize the collection of temperature, infrared, sound, and light intensity information. The street light sensing system uses multisensor information fusion technology to detect the situation of people and vehicles in real time, so that people and vehicles can turn on the street lights and turn off the street lights of unmanned vehicles. Adjust the street light switch according to the intelligent analysis of the lighting demand scene in order to enhance the accuracy of the system to identify the lighting demand scene. This enables the system to provide safe lighting conditions for urban traffic while saving the power consumption of urban lighting. The sensor system of the street light randomly selects the detection results of temperature and humidity within a certain period of time. The error rate of the final test result is 1/2 of that of the traditional test, and the accuracy is far lower than that of the traditional measurement method. Regarding the lighting system of street lamps and public art in urban public spaces, it is worthy of extensive promotion to control street lamp lighting through sensor information fusion technology and reduce energy consumption.

A Review for the Driving Behavior Recognition Methods Based on Vehicle Multisensor Information

The frequent traffic accidents lead to a large number of casualties and large related financial losses every year; this serious state is owed to several factors; among those, driving behavior is one of the most imperative subjects to discuss. Driving behaviors mainly include behavior characteristics such as car-following, lane change, and risky driving behavior such as distraction, fatigue, or aggressive driving, which are of great help to various tasks in traffic engineering. An accurate and reliable method of driving behavior recognition is of great significance and guidance for vehicle driving safety. In this paper, the vehicle multisensor information, vehicle CAN bus data acquisition system, and typical feature extraction methods are summarized at first. And then, several driving behavior recognition models based on machine learning and deep learning are reviewed. Through a detailed analysis of the features of random forests, support vector machines, convolutional neural networks, and recurrent neural networks used to build driving behavior recognition models, the following findings are obtained: the driving behavior model constructed by traditional machine learning model is relatively mature but it is greatly affected by feature extraction, data scale, and model structure, which affects the accuracy of the final driving behavior recognition. Deep learning model based on a neural network has achieved high accuracy in identifying driving behavior, and it may gradually become the mainstream of constructing the driving behavior model with the development of big data, artificial intelligence technology, and computer hardware. Finally, this paper points out some content that needs to be further explored, to provide reference and inspiration for scholars in this field to continue to study the driving behavior recognition model in depth.

Reliability Analysis of Multisensor Fusion Technology in Disaster Nursing Application

The harm and impact of various natural disasters are becoming more and more obvious. Due to the high suddenness of natural disasters and the low efficiency of information sharing, our stress system will still not be able to respond to disasters in time. Therefore, facing the current complex natural environment and the diversity of disasters, we urgently need a practical and comprehensive online collaborative natural disaster protection system. Therefore, this paper proposes a disaster protection application system based on a multisensor information fusion algorithm. Firstly, the software platform of the natural disaster protection system based on multisensor is constructed; the hardware platform of multisensor disaster acquisition is designed. An information fusion algorithm based on Kalman joint filter is proposed. The main problems of joint filter are (1) improving the filtering accuracy, (2) improving the fault-tolerant performance of the filter, and (3) optimizing the fusion algorithm and reducing the amount of calculation and data communication, so as to facilitate real-time implementation of the algorithm. Combined with DS evidence theory, BP neural network, and support vector mechanism, a comprehensive diagnosis model is established. The model uses the preliminary diagnosis results of the BP neural network and support vector machine to carry out the BPA of DS evidence theory, which avoids the blindness caused by human operation. The simulation results show that the comprehensive diagnosis model can significantly improve the prediction accuracy of disasters, solve the uncertainty and fuzziness of diagnosis results of a single diagnosis model, and provide a new method for disaster protection. The results of the BP neural network in the disaster nursing system are fused at the decision level, the results show that the distribution probability corresponding to the fusion disaster category is greater than the threshold value of 0.8, and the diagnosis result can be given immediately. The diagnosis result is completely consistent with the actual disaster category.

Continuous and Precise Positioning in Urban Environments by Tightly Coupled Integration of GNSS, INS and Vision

Accurate, continuous and seamless state estimation is the fundamental module for intelligent navigation applications, such as self-driving cars and autonomous robots. However, it is often difficult for a standalone sensor to fulfill the demanding requirements of precise navigation in complex scenarios. To fill this gap, this letter proposes to exploit the complementariness of the global navigation satellite system (GNSS), inertial measurement unit (IMU) and vision via a tightly coupled integration method, aiming to achieve continuous and accurate navigation in urban environments. Specifically, the raw GNSS carrier phase and pseudorange measurements, IMU data, and visual features are directly fused at the observation level through a centralized Extended Kalman Filter (EKF) to make full use of the multi-sensor information and reject potential outlier measurements. Furthermore, the widely used high-precision GNSS models including precise point positioning (PPP) and real-time kinematic (RTK) are unified in the proposed integrated system to increase usability and flexibility. We validate the performance of the proposed method on several challenging datasets collected in urban canyons and compare against the loosely coupled and state-of-the-art methods.

The Application of Multisensor Information Fusion Technology in Environmental Restoration

Multisensor information fusion technology is an advanced processing method that is different from classical data processing technology. Capability and operational accuracy, in order to make an effective comprehensive evaluation of environmental quality, the environmental monitoring system built by NB-IoT technology and sensor technology is used to conduct multisensor data fusion research on the collected environmental factors such as temperature, humidity, formaldehyde, PM2.5, and TVOC. At the same time, the two-level parallel fusion method is adopted to evaluate the environmental quality. Before data fusion, median filtering is used to eliminate abnormal data. Then, the Kalman filter algorithm is used to fuse multiple sets of similar sensors to obtain the best value of it. Finally, the fuzzy comprehensive evaluation method is used to fuse the different types of sensors at the decision-making level, in which the weight value is determined by the entropy method and the membership function is Gaussian. The different environment scenarios are tested by using the above algorithms, and the simulation results show that multisensor data fusion can obtain more abundant and effective environmental information, overcome the simplicity and limitation of single-factor sensor for environmental quality assessment, and improve the reliability and accuracy of the overall environmental quality assessment.

Intelligent control method of main road traffic flow based on multi-sensor information fusion

Intelligent control method of main road traffic flow based on multi-sensor information fusion

Tension prediction for the scraper chain through multi-sensor information fusion based on improved Dempster-Shafer evidence theory

This paper deals with a tension prediction strategy for the scraper chain of the scraper conveyor based on multi-sensor information fusion combined with the improved D-S evidence theory (IDST). First, multiple sensors are used to obtain comprehensive information reflecting the working status of the scraper conveyor. Then, four independent artificial neural networks (ANNs) are adopted to perform the preliminary prediction of the tension variation based on the signals obtained by different sensors, and the weight coefficients of different ANNS are employed to construct the basic probability assignments (BPAs) of independent evidences. Finally, the IDST is proposed to fuse the conflicting evidences and utilize the complementary multi-sensor information for accurate tension prediction, thus providing practical guiding significance for state monitoring of the scraper chain. Experimental results indicate that the IDST has specific superiority over other conventional methods in dealing with conflicts of the evidences, as well as improving the accuracy of parameter prediction.

Observability Decomposition-Based Decentralized Kalman Filter and Its Application to Resilient State Estimation under Sensor Attacks.

This paper considers a discrete-time linear time invariant system in the presence of Gaussian disturbances/noises and sparse sensor attacks. First, we propose an optimal decentralized multi-sensor information fusion Kalman filter based on the observability decomposition when there is no sensor attack. The proposed decentralized Kalman filter deploys a bank of local observers who utilize their own single sensor information and generate the state estimate for the observable subspace. In the absence of an attack, the state estimate achieves the minimum variance, and the computational process does not suffer from the divergent error covariance matrix. Second, the decentralized Kalman filter method is applied in the presence of sparse sensor attacks as well as Gaussian disturbances/noises. Based on the redundant observability, an attack detection scheme by the test and a resilient state estimation algorithm by the maximum likelihood decision rule among multiple hypotheses, are presented. The secure state estimation algorithm finally produces a state estimate that is most likely to have minimum variance with an unbiased mean. Simulation results on a motor controlled multiple torsion system are provided to validate the effectiveness of the proposed algorithm.

Rolling bearing fault diagnosis method based on multi-sensor two-stage fusion

Despite the great achievements of deep learning methods based on a single sensor in fault diagnosis, learning useful information from multi-sensor data is still a challenge. In order to make full use of multi-sensor information and improve the performance of rolling bearing fault diagnosis, a novel multi-sensor information fusion framework is proposed in this paper. First, a multi-sensor-based multi-frequency information fusion method is proposed. The multi-frequency information of each sensor is segmented first to enhance the datasets, and then a weighted fusion rule based on fuzzy entropy is constructed to fuse the information of different frequency components for multi-sensors. Second, a multi-kernel attention convolutional neural network is designed to realize multi-frequency feature capture, fusion, and fault classification of multi-sensors. Finally, two different rolling bearing datasets are used to implement fault diagnosis experiments. Experimental results show that the proposed method outperforms the comparative methods in terms of diagnostic performance and robustness.

Retraction Note: Design and Implementation of Track and Field Training Information Collection and Feedback System Based on Multi-sensor Information Fusion

Retraction Note: Design and Implementation of Track and Field Training Information Collection and Feedback System Based on Multi-sensor Information Fusion

Retraction Note: Residential planning and layout design method based on multi-sensor information fusion

Retraction Note: Residential planning and layout design method based on multi-sensor information fusion

A Fast Data Transmission Method of Vehicle-Road Cooperative Communication Based on the Clustering Algorithm.

In order to improve the security and stability of data transmission in vehicle-road cooperative communication and reduce the error rate of data transmission, a fast data transmission method based on the clustering algorithm is proposed. First, the multisensor information acquisition method of the vehicle networking is used to realize data acquisition and data structure analysis of the vehicle-road cooperative communication, and a data transmission channel model for vehicle-road cooperative communication is constructed. The interference suppression in the data transmission process of the vehicle-road cooperative communication is realized by the matched filter detection algorithm. Then, according to the symbol characteristic distribution of the vehicle-road cooperative communication channel, the baud interval equalization method is used to realize the piecewise equalization adjustment of data transmission for the vehicle-road cooperative communication. With the adaptive error compensation and channel fading suppression, the K-means clustering algorithm is used to carry out the coordinated adjustment to data packets during the rapid data transmission of the vehicle-road cooperative communication. Finally, the adaptive control of data transmission for the vehicle-road cooperative communication is carried out according to the dynamic distribution characteristics of the clustering center so as to reduce the influence of channel fading and intersymbol interference caused by channel spread. The simulation results show that the bit error rate of this method is kept at about 0.05, and the data transmission rate continues to increase, most of which remain above 0.95. This method has strong anti-interference ability for the rapid data transmission of vehicle-road cooperative communication, with lower communication bit error rate, less end-to-end time delay, and higher stability and accuracy of data transmission.