Multiple Sensor Sources Research Articles

Performance improvement of the self-power control valve based on digital twin technology

Providing stable energy for intelligent pipe network systems is a complex problem. Ball valves are widely used in intelligent pipe network systems, and a self-power control valve is designed by integrating a flow-matching wheel in the ball valve. While the spool is throttling the fluid, a part of the energy can be extracted from the fluid and converted into the power. In order to optimize the energy capturing characteristics of the self-power control valve, the shape of the flow-matching wheel must be designed to form a precise match with the valve cavity. In this paper, a lightweight digital twin of the self-power control valve is developed using an agent model. Based on this, an optimized design method for the flow-matching wheel that can dynamically take into account the operating conditions of the valve in real time, is proposed by combining the agent model with the dynamic data from multiple sensor sources. The research results show that after the twin optimization of the flow-matching wheel, the average value of the energy capturing efficiency is improved by 3.21 % compared to the pre-optimization; the average value of the output power is improved by 20.57 % compared to the pre-optimization.

An evaluation of ECG data fusion algorithms for wearable IoT sensors

In wearable sensing, accurate estimation of physiological parameters is paramount, although these signals can be corrupted by noise. The fusion of data from multiple sensor sources has the potential to enhance accuracy, even in the presence of disruptive noise. This paper aims to introduce and compare various existing state-of-the-art and novel data fusion techniques to improve the reliability of heart rate estimation. The comparisons were implemented using the MIT-BIH Arrhythmia database with additive noise signals taken from MIT Noise Stress Test Database. When it comes to the challenging low signal-to-noise ratio (SNR) regions, the Kalman fusion and the α-trim mean filtering approach exhibits the best performance. The Kalman fusion approach dominates when both channels are corrupted, while the α-trim mean filtering elimination algorithm takes the lead when at least one channel is clean. To make the most of these strengths, we have developed an innovative algorithm that can switch between the two fusion methods based on a signal quality indicator (SQI) that serves as a surrogate SNR. This algorithm outperforms the baseline 2-channel RR-interval averaging approach by ≃54% and ≃21% at SNRs of 20dB and −20dB respectively. Moreover, it outperforms other cutting-edge heart rate estimation methods.

An advanced autonomous forklift based on a networked control system

In warehouses with multiple static and dynamic entities, a forklift needs to process data from multiple sensor sources and take instantaneous decisions. Implementing such complex algorithms on the forklift requires high computational power resulting in increased power consumption as well as complex designs. Due to rapid advances made in communication technology, networked control systems have become quite popular in such applications. In this paper, we implement such a system architecture for autonomous forklifts in warehouses. The forklift, equipped only with sensors and actuators, transmits sensor data to and receives control commands from a remote controller PC with high computation power over a shared network thus making it both computationally and economically efficient.

Physical Layer Security in AF-Based Cooperative SWIPT Sensor Networks

Physical layer security (PLS) with radio frequency (RF) energy harvesting (EH) in wireless sensor networks has received significant interest as a technology for secure information transmission and prolonging the network lifetime, as well as improving energy efficiency. This article investigates PLS for a simultaneous wireless information and power transfer (SWIPT) cooperative network, which consists of multiple sensor sources, one EH relay (R), and one destination (D) in the presence of one eavesdropper (E). Furthermore, a low-complexity, suboptimal, yet efficient sensor source selection scheme is proposed. Specifically, one sensor source is chosen to transmit information to the relay and destination such that it obtains the best channel from sensor sources to the relay. Then, by considering two relaying strategies, termed the direct link plus static power splitting-based relaying (SPSR) and direct link plus optimal dynamic power splitting-based relaying (ODPSR), the performance analysis in terms of intercept probability (IP) and outage probability (OP) is carried out for each one. Notably, the eavesdropper and destination utilize maximal ratio combining (MRC) to incorporate the received signals from the selected sensor source and the relay, which poses new challenges in obtaining the analytical expressions. In this context, we derive analytical expressions for the OP (for SPSR and ODPSR) at the destination and the IP (for SPSR) at the eavesdropper by adopting the series representation of the modified Bessel function. Finally, Monte Carlo simulations are conducted to validate the theoretical analysis and the proposed schemes’ effectiveness. Simulation results show the superiority of our scheme compared to the benchmarks.

Liquid Identification in a Microplate Format Based on Thermal and Electrical Sensor Data Fusion

Multidevice synchronous measurement and thus a fusion of data from multiple sensor sources is becoming a fundamental but nontrivial task. Essentially, different sensors have their own limitations and uncertainties; the fusion of the data serves to increase the accuracy of performance. This research aims to expand the possibilities of multiparameter sensing by integrating impedance and thermal sensors into a microplate format for the simultaneous assessment of electrical and thermal properties. The sensor uses a modified transient plane source (TPS) measuring principle to monitor thermal changes and interdigitated electrodes (IDEs) for impedance analysis. The sensor is put to the test in the characterization of different glycerol and NaCl dilutions based on the varying thermal and electrical properties. At last, to demonstrate the added value of data fusion for liquid identification, a proof-of-application experiment shows the identification of fruit juices based on both measurands using a Gaussian mixture model. These experiments already highlight the power of this combined measuring technology in simple liquid identification processes, hence showing great potential to develop advanced diagnostics in various fields, such as healthcare, biology, or food quality by providing the ability to effectively perform parallel impedance and thermal-based measurements.

A multi-sensor approach to calving detection

The advent of remote livestock monitoring systems provides numerous possibilities for improving on-farm productivity, efficiency, and welfare. One potential application for these systems is for the detection of calving events. This study describes the integration of data from multiple sensor sources, including accelerometers, global navigation satellite systems (GNSS), an accelerometer-derived rumination algorithm, a walk-over-weigh unit, and a weather station for parturition detection using a support vector machine approach. The best performing model utilised data from GNSS, the ruminating algorithm, and weather stations to achieve 98.6% accuracy, with 88.5% sensitivity and 100% specificity. The top-ranking features of this model were primarily GNSS derived. This study provides an overview as to how various sensor systems could be integrated on-farm to maximise calving detection for improved production and welfare outcomes.

Blockchain-Based Digital Twins: Research Trends, Issues, and Future Challenges

Industrial processes rely on sensory data for decision-making processes, risk assessment, and performance evaluation. Extracting actionable insights from the collected data calls for an infrastructure that can ensure the dissemination of trustworthy data. For the physical data to be trustworthy, it needs to be cross validated through multiple sensor sources with overlapping fields of view. Cross-validated data can then be stored on the blockchain, to maintain its integrity and trustworthiness. Once trustworthy data is recorded on the blockchain, product lifecycle events can be fed into data-driven systems for process monitoring, diagnostics, and optimized control. In this regard, digital twins (DTs) can be leveraged to draw intelligent conclusions from data by identifying the faults and recommending precautionary measures ahead of critical events. Empowering DTs with blockchain in industrial use cases targets key challenges of disparate data repositories, untrustworthy data dissemination, and the need for predictive maintenance. In this survey, while highlighting the key benefits of using blockchain-based DTs, we present a comprehensive review of the state-of-the-art research results for blockchain-based DTs. Based on the current research trends, we discuss a trustworthy blockchain-based DTs framework. We also highlight the role of artificial intelligence in blockchain-based DTs. Furthermore, we discuss the current and future research and deployment challenges of blockchain-supported DTs that require further investigation.

Dynamic Predictive Maintenance Scheduling Using Deep Learning Ensemble for System Health Prognostics

Modern engineering systems are usually equipped with a variety of sensors to measure real-time operating conditions. Based on the condition monitoring data from multiple sensor sources, this paper deals with a dynamic predictive maintenance scheduling using deep learning ensemble for system health prognostics. The deep learning ensemble model is composed of deep autoencoder and bidirectional long short-term memory in series, and aims to accurately estimate the system health state and remaining useful life. The deep autoencoder is used to extract the deep representative features hidden in condition monitoring data, whereas the inclusion of the bidirectional long short-term memory allows learning the temporal correlation information of features in both forward and backward time directions. Thus, the combination of the two models forms an effective model. With obtained prognostic information, optimal maintenance decisions are determined by two designed rules. The first rule presets a reliable remaining useful life threshold to dynamically judge whether maintenance is carried out at current inspection time, while the second one selects a degradation state to dynamically determine whether to place a spare part order. The performance of the proposed dynamic predictive maintenance strategy is measured by the maintenance cost per unit operating time (cost rate) using the aero-engine dataset from NASA. Its effectiveness is demonstrated by comparing with recent publications.

Opportunistic Discovery of Personal Places Using Multi-Source Sensor Data

Modern smartphones and wearables are able to continuously collect significant amounts of sensor data, where such data can be helpful to study a user's mobility or social interaction patterns, but also to deliver various services based on a user's presence at different places during certain times of the day. Therefore, it is important to accurately identify personal places of interest (POIs), such as a user's workplace or home. Such places are usually determined using segmentation of location traces, but frequent gaps in the data (i.e., missing location readings) can result in a large number of small and incomplete segments that should actually be grouped together into a single large segment. This paper presents a segmentation approach that utilizes a user's personal data obtained from multiple sensor sources and devices such as the battery recharge behavior (measured on smartphones), step counts, and sleep patterns (measured by wearables), to opportunistically fill gaps in the user's location traces. Using the data from a mobile crowd sensing study of more than 450 users over a 2-year period, we show that our approach is able to generate fewer, but more complete segments compared to the state of the art.

Planetary gearbox fault diagnosis using bidirectional-convolutional LSTM networks

Gearbox fault diagnosis is expected to significantly improve the reliability, safety and efficiency of power transmission systems. However, planetary gearbox fault diagnosis remains a challenge due to complex responses caused by multiple planetary gears. Model-based gearbox fault diagnosis techniques extract hand-crafted features from sensor data based on underlying physics and statistical analysis, which are not effective in extracting spatial and temporal features automatically. While deep learning methods such as convolutional neural network (CNN) enable automatic feature extraction from multiple sensor sources, they are not capable of extracting spatial and temporal features simultaneously without losing critical feature information. To address this issue, we introduce a novel deep neural network based on bidirectional-convolutional long short-term memory (BiConvLSTM) networks to determine the type, location, and direction of planetary gearbox faults by extracting spatial and temporal features from both vibration and rotational speed measurements automatically and simultaneously. In particular, a CNN determines spatial correlations between two measurements within one time step automatically by combining signals collected from three accelerometers and one tachometer. Long short-term memory (LSTM) networks identify temporal dependencies between two adjacent time steps. By replacing input-to-state and state-to-state operations in the LSTM cell with convolutional operations, the BiConvLSTM can learn spatial correlations and temporal dependencies without losing critical features. Experimental results have shown that the BiConvLSTM network can detect the type, location, and direction of gearbox faults with higher accuracy than conventional deep learning approaches such as CNN, LSTM, and CNN-LSTM.

Optimizing Sensor Deployment for Multi-Sensor-Based HAR System with Improved Glowworm Swarm Optimization Algorithm.

Human activity recognition (HAR) technology that analyzes and fuses the data acquired from various homogeneous or heterogeneous sensor sources has motivated the development of enormous human-centered applications such as healthcare, fitness, ambient assisted living and rehabilitation. The concurrent use of multiple sensor sources for HAR is a good choice because the plethora of user information provided by the various sensor sources may be useful. However, a multi-sensor system with too many sensors will bring large power consumption and some sensor sources may bring little improvements to the performance. Therefore, the multi-sensor deployment research that can gain a tradeoff among computational complexity and performance is imperative. In this paper, we propose a multi-sensor-based HAR system whose sensor deployment can be optimized by selective ensemble approaches. With respect to optimization of the sensor deployment, an improved binary glowworm swarm optimization (IBGSO) algorithm is proposed and the sensor sources that have a significant effect on the performance of HAR are selected. Furthermore, the ensemble learning system based on optimized sensor deployment is constructed for HAR. Experimental results on two datasets show that the proposed IBGSO-based multi-sensor deployment approach can select a smaller number of sensor sources while achieving better performance than the ensemble of all sensors and other optimization-based selective ensemble approaches.

Improving Multimodal Localization Through Self-Supervision

Modern warehouses utilize fleets of robots for inventory management. To ensure efficient and safe operation, real-time localization of each agent is essential. Most robots follow metal tracks buried in the floor and use a grid of precisely mounted RFID tags for localization. As robotic agents in warehouses and manufacturing plants become ubiquitous, it would be advantageous to eliminate the need for these metal wires and RFID tags. Not only do they suffer from significant installation costs, the removal of wires would allow agents to travel to any area inside the building. Sensors including cameras and LiDAR have provided meaningful localization information for many different positioning system implementations. Fusing localization features from multiple sensor sources is a challenging task especially when the target localization task’s dataset is small. We propose a deep-learning based localization system which fuses features from an omnidirectional camera image and a 3D LiDAR point cloud to create a robust robot positioning model. Although the usage of vision and LiDAR eliminate the need for the precisely installed RFID tags, they do require the collection and annotation of ground truth training data. Deep neural networks thrive on lots of supervised data, and the collection of this data can be time consuming. Using a dataset collected in a warehouse environment, we evaluate the performance of two individual sensor models for localization accuracy. To minimize the need for extensive ground truth data collection, we introduce a self-supervised pretraining regimen to populate the image feature extraction network with meaningful weights before training on the target localization task with limited data. In this research, we demonstrate how our self-supervision improves accuracy and convergence of localization models without the need for additional sample annotation.

Modeling perceived quality of haptic impressions based on various sensor data sources

PurposeThis paper aims to provide an approach of modeling haptic impressions of surfaces over a wide range of applications by using multiple sensor sources.Design/methodology/approachA multisensory measurement experiment was conducted using various leather and artificial leather surfaces. After processing of measurement data and feature extraction, different learning algorithms were applied to the measurement data and a corresponding set of data from a sensory study. The study contained evaluations of the same surfaces regarding descriptors of haptic quality (e.g. roughness) by human subjects and was conducted in a former research project.FindingsThe research revealed that it is possible to model and project haptic impressions by using multiple sensor sources in combination with data fusion. The presented method possesses the potential for an industrial application.Originality/valueThis paper provides a new approach to predict haptic impressions of surfaces by using multiple sensor sources.

Causal Model Reconstruction of Complex Energy System Using Probabilistic Network Approach

This paper addresses the challenges in performance monitoring and degradation diagnosing of complex industrial process. A Bayesian network-based model was developed using real operation data of the system, and readings from multiple sensor sources were regarded as evidences to identify the root cause of process variations causing system degradation. An inferring process was executed with the belief network to output possible root causes of the process variation. Then, a probabilistic confidence level of controllable variables was recommended for optimizing operation. A full-scope simulator for the power plant unit is employed as an indispensable test bed for the probabilistic network model. To achieve a decision support simulation, a simulated operation database is generated through varying boundary parameters. The model was re-parameterized with the data from the simulated operation database. The simulation test results show that the model can properly represent the domain knowledge, and the decision advices are effective for such an elaborate work. The probabilistic model can tackle the problems which are indiscernible in conventional thermodynamic model-based analysis.

Achieving a Decision Paradigm for Distributed Warfare Resource Management

The ability to optimally manage distributed warfare assets for collaborative operation significantly increases our military advantage. The primary results include enhanced situational awareness and improvements in fire control, engagement support, operational planning, combat reaction times, threat prioritization, and the list continues. Bettering the use of sensors and weapons in concert with one another–effectively creating a system of distributed systems–provides major payoffs. The effectiveness of managing distributed resources depends on the ability to make complex decisions [1]. The complexity is due in part to the circuitous nature of fusing data from multiple sensor sources to provide a representation of the operational environment from which to redirect sensors for further information optimization and from which to base military operations. The “goodness” of such complex decisions depends on the “goodness” of the information available and the understanding of the situation from a “big picture” perspective. This paper explores distributed resource management (RM) from a decision-based perspective. With an objective of enabling a collaborative system of systems (SoS), a systems approach is proposed to implement a decision paradigm that extends from system conception to operations.

Utility-based bandwidth adaptation in mission-oriented wireless sensor networks

This article develops a utility-based optimization framework for resource sharing by multiple competing missions in a mission-oriented wireless sensor network (WSN) environment. Prior work on network utility maximization (NUM) based optimization has focused on unicast flows with sender-based utilities in either wireline or wireless networks. In this work, we develop a generalized NUM model to consider three key new features observed in mission-centric WSN environments: i) the definition of the utility of an individual mission (receiver) as a joint function of data from multiple sensor sources; ii) the consumption of each sender's (sensor) data by multiple missions; and iii) the multicast-tree-based dissemination of each sensor's data flow, using link-layer broadcasts to exploit the “wireless broadcast advantage” in data forwarding. We show how a price-based, distributed protocol (WSN-NUM) can ensure optimal and proportionally fair rate allocation across multiple missions, without requiring any coordination among missions or sensors. We also discuss techniques to improve the speed of convergence of the protocol, which is essential in an environment as dynamic as the WSN. Further, we analyze the impact of various network and protocol parameters on the bandwidth utilization of the network, using a discrete-event simulation of a stationary wireless network. Finally, we corroborate our simulation-based performance results of the WSN-NUM protocol with an implementation of an 802.11b network.

Multisource, Multidestination, Multirelay Wireless Networks

Networks with multiple source–destination pairs, involving possibly multicast, and where there are multiple nodes that can serve as potential relay nodes, are considered. A multisource, multirelay coding scheme is developed. In this scheme, each source's information is sent to its destination nodes via a multirelay route, with the multiple multirelay routes operating concurrently even when they intersect with each other, in the same spirit as code-division multiple access (CDMA). It is found that in the generalization to multiple sources, backward decoding achieves higher rates than sliding-window decoding. The routing structure where a joint backward decoding can be performed is characterized. The achievable rate region is found to combine aspects of both multiple relay and multiple access. Potential applications of this coding scheme to sensor networks are discussed. In particular, the exact capacity for the data downloading problem in sensor networks, where there are multiple sensor sources and one sink or collector node, is established for certain geometries when there is phase fading that is unknown to the transmitter.

Multimodal Industrial Inspection and Analysis

Diagnosis of complex engineering systems requires the use of multiple sensor sources to acquire information. In this paper we present a survey of multimodal data acquisition systems for nondestructive testing (NDT) and engineering analysis. We begin with a summary of the relative strengths and weaknesses of individual NDT modalities. Thereafter we present existing multimodal inspection hardware systems that use complementary NDT sensors. The advantages of such multimodal data acquisition over conventional single modality sensors in inspection and analysis are highlighted. Possible approaches to fuse complementary multimodal sensor data are discussed. We conclude with possible directions for the future development of multimodal inspection systems.

A Bayesian network approach to root cause diagnosis of process variations

This paper addresses the challenges inherent in root cause diagnosis of process variations in a production machining environment. We develop and present a process monitoring and diagnosis approach based on a Bayesian belief network for incorporating multiple process metrics from multiple sensor sources in sequential machining operations to identify the root cause of process variations and provide a probabilistic confidence level of the diagnosis. The vast majority of previous work in machining process monitoring has focused on single-operation tool wear monitoring. The focus of the present work is to develop a methodology for diagnosing the root cause of process variations that are often confounded in process monitoring systems, namely workpiece hardness, stock size, and tool wear variations. To achieve this goal, multiple sensor metrics have been identified with statistical correlations to the process faults of interest. Data from multiple sensors on sequential machining operations are then combined through a causal belief network framework to provide a probabilistic diagnosis of the root cause of the process variation.