Search

Fault diagnosis is crucial to guarantee safe operation and extend the operating time while preventing the thermal runaway of the lithium-ion battery. This study presents a data-driven thermal runaway diagnosis framework where Bayesian optimization techniques are applied to optimize the hyperparameter of various machine learning techniques. We use different machine learning models such as support vector machine, naive Bayes, decision tree ensemble, and multi-layer perceptron to estimate a high likelihood of causes of thermal runaway by using the experimental measurements of open-source battery failure data. We analyze different evaluation metrics, including the prediction accuracy, confusion metrics, and receiver operating characteristic curves of different models. An experimental evaluation shows that the classification accuracy of the decision tree ensemble outperforms that of other models. Furthermore, the decision tree ensemble provides robust prediction accuracy even with the strictly limited dataset.

This paper applies the MIMO over-the-air computation (MIMO-AirComp) technique to compute the control signal of a distributed control system, including state estimation. The control-based target function is expressed as a nomographic function and efficiently computed through the wireless channel with suitable function decomposition. The proposed scheme leverages local pre-processing at the individual sensor, aggregation through the multiple access channel, and post-processing at the controller to compute the control-oriented nomographic function. We analyze the performance of our proposed scheme in terms of the time delay and computation error compared to a state-of-the-art MIMO time-division multiple access scheme by means of Monte Carlo simulations. Numerical results indicate that the proposed scheme considerably improves control performance, particularly in noisy networks that rely on a large number of wireless sensors, with low complexity for resource-constrained scenarios.

Many studies are undertaken into nuclear power plants (NPPs) in preparation for accidents exceeding design standards. In this paper, we analyze the applicability of various wireless communication technologies as accident countermeasures in different NPP environments. In particular, a commercial wireless communication module (WCM) is investigated by measuring leakage current and packet error rate (PER), which vary depending on the intensity of incident radiation on the module, by testing at a Co-60 gamma-ray irradiation facility. The experimental results show that the WCMs continued to operate after total doses of 940 and 1097 Gy, with PERs of 3.6% and 0.8%, when exposed to irradiation dose rates of 185 and 486 Gy/h, respectively. In short, the lower irradiation dose rate decreased the performance of WCMs more than the higher dose rate. In experiments comparing the two communication protocols of request/response and one-way, the WCMs survived up to 997 and 1177 Gy, with PERs of 2% and 0%, respectively. Since the request/response protocol uses both the transmitter and the receiver, while the one-way protocol uses only the transmitter, then the electronic system on the side of the receiver is more vulnerable to radiation effects. From our experiments, the tested module is expected to be used for design-based accidents (DBAs) of “Category A″ type, and has confirmed the possibility of using wireless communication systems in NPPs.

Quasi-isotropic antennas are promising candidates due to their applications in modern communication systems, where full spatial coverage and/or uniform signal reception is required. In this work, an in-depth review of quasi-isotropic antennas is presented, with the aim of understanding the working principles of such antennas and presenting the recent advancements, challenges, and solutions offered by various researchers. First, different design techniques adopted to achieve quasi-isotropic patterns, such as the use of complementary dipoles, multiple monopoles or dipoles, and an array of discrete elements are discussed. Then, different types of quasi-isotropic antennas—for example, planar, electrically small, 3-D printed, dual-band/wideband, circularly polarized, metamaterial-inspired, and dielectric resonator-based quasi-isotropic antennas—are revisited. Their applications in various technologies, such as RFID, energy harvesting, wireless sensor networks, and the IoT, are briefly explained. Lastly, different key performance parameters, such as complexity of configuration, design approach, physical profile, far field and radiation characteristics, reflection coefficients, operating frequency and bandwidth, gain deviation, and fabrication process, are discussed and tabulated. This review not only provides a guideline but will also help antenna engineers in designing a quasi-isotropic antenna with desirable performance.

MIMO over-the-air computation (MIMO-AirComp) is a recently proposed technique that leverages the superposition property of the multiple access channel to compute the target multifunction of various applications. This article presents how the MIMO-AirComp principle can be applied to the state estimation problem using distributed sensing data. The representative target function is explicitly formulated as a nomographic function matched to the structure of the multiple access channel with the proper processing function. The proposed framework efficiently computes the target multifunction by coordinating local preprocessing at each node, aggregation through the wireless channel, and postprocessing at the fusion center. We analyze and demonstrate that the proposed approach significantly improves the computation throughput for the distributed estimation application. Specifically, the proposed MIMO-AirComp framework outperforms the conventional separated communication and computation approach when the network system relies on noisy measurements obtained by the densely deployed sensors.

A 3D printed, low-profile, electrically small antenna with a quasi-isotropic radiation pattern is presented herein. It is composed of an electric meandered dipole antenna, and the extended arcs from the meander line mimicking the current flow of the loop antenna. A quasi-isotropic radiation pattern is achieved from the total current flow over the proposed structure. Modern stereolithographic 3D printing and nano-polycrystalline copper coating technologies are used to build a prototype. The measured antenna exhibits a good uniformity in terms of the radiation pattern with a maximum gain deviation of 4.5 dB at 959 MHz and a radiation efficiency of 81 %, close to the computed expectations. The electrical size of the antenna ka is 0.48, and its height is λ0/82.32.

Although various deep learning techniques have been proposed to diagnose industrial faults, it is still challenging to obtain sufficient training samples to build the fault diagnosis model in practice. This paper presents a framework that combines wavelet transformation and transfer learning (TL) for fault diagnosis with limited target samples. The wavelet transform converts a time-series sample to a time-frequency representative image based on the extracted hidden time and frequency features of various faults. On the other hand, the TL technique leverages the existing neural networks, called GoogLeNet, which were trained using a sufficient source data set for different target tasks. Since the data distributions between the source and the target domains are considerably different in industrial practice, we partially retrain the pre-trained model of the source domain using intermediate samples that are conceptually related to the target domain. We use a reciprocating pump model to generate various combinations of faults with different severity levels and evaluate the effectiveness of the proposed method. The results show that the proposed method provides higher diagnostic accuracy than the support vector machine and the convolutional neural network under wide variations in the training data size and the fault severity. In particular, we show that the severity level of the fault condition heavily affects the diagnostic performance.

Recent advances in wireless networking, sensing, computing, and control are revolutionizing how physical systems interact with information and physical processes such as Cyber-Physical Systems (CPS), Internet of Things (IoT), and Tactile Internet [...]

In this work, we report on a flexible triboelectric generator (TEG) with a multilayer polymer structure, consisting of a poly(vinylidene fluoride-co-trifluoroethylene) (PVDF-TrFE) layer sandwiched by polydimethylsiloxane (PDMS) layers for the performance enhancement of TEGs. We confirmed that the output performance of the TEG is closely dependent on the structure and polarization direction of the PVDF-TrFE layer. In addition, the PDMS layer serves as the electron trapping layer and suppresses the discharging of the surface charges, boosting the output performance. Furthermore, the polarized PVDF-TrFE layer in the preferred direction contributes to increasing the surface potential during the contact–separation motion. The interaction between these two polymer layers synergistically leads to the boosted output performance of TEGs. Specifically, the maximum peak-to-peak output voltage and current density of 420 V and 50 μA/cm2 generated by the proposed architecture, representing approximately a fivefold improvement compared with the TEG with a single layer, even though the same friction layers were used for contact electrification.

Predicting the remaining useful life (RUL) of mechanical bearings is a challenging industrial task since RUL can differ even for the same equipment due to many uncertainties such as operating condition, model inaccuracy, and sensory noise in various industrial applications. This paper proposes the RUL prediction method combining analytical model-based and data-driven approaches to forecast when a failure will occur based on the time series data of bearings. Feature importance ranking and principal component analysis construct a reliable and predictable health indicator from various statistical time, frequency, and time–frequency domain features of the observed signal. The adaptive sliding window method then optimizes the parameters of the degradation model based on the ridge regression of the time series sequence with the sliding window. The proposed adaptive scheme provides significant performance improvement in terms of the RUL estimation accuracy and robustness against the possible errors of the degradation model compared to the traditional Bayesian approaches.

With the latest standard releases, Bluetooth technology is becoming more and more relevant for building and industrial automation. At the same time, Bluetooth is now becoming fundamental for contact tracing applications, to support monitoring and containment of the COVID-19 pandemic. Critical facilities such as nursing homes and hospitals have been severely exposed to the pandemic, but the currently available short-range wireless technology still faces the fundamental limits of proximity accuracy, battery lifetime, and privacy in those complex indoor environments. The aim of this paper is to investigate effective ways of building an architecture with heterogeneous devices to support contact tracing in critical scenarios such as healthcare facilities, while meeting the required level of accuracy and privacy. A framework based on standard Bluetooth mesh networking technology is proposed, and the research challenges are discussed.

The performance of wireless networks can be greatly influenced by the radiation pattern and polarization of the antennas at the nodes, especially when they are under non-line-of-sight (NLOS) channel environments. In this study, we designed a planar quasi-isotropic antenna based on the combination of a meandered electric dipole and an electrically small loop at a frequency of 2.45 GHz. Its electrical size (ka) is 0.47 and shows a gain deviation of 3.01 dB with radiation efficiency of 82.6% per the simulation. The performance of a wireless link under the line-of-sight and NLOS channels in an indoor environment was measured using the proposed quasi-isotropic antenna as a receiving antenna after validating its radiation and impedance properties experimentally (the measured gain deviation: 5.2 dB, the measured radiation efficiency: 79.2%). This study demonstrates that better properties are achieved using the quasi-isotropic antenna. The quasi-isotropic antenna shows an improved packet delivery ratio (PDR) and received signal strength indicator (RSSI) compared to the results using omni-directional antennas as a transmitting and receiving pair in the NLOS channels. To the best of our knowledge, the experimental validation of the enhancement of wireless link reliability using a quasi-isotropic antenna has not been reported before, and was first carried out in this study.

Fault detection and diagnosis is one of the most critical components of preventing accidents and ensuring the system safety of industrial processes. In this paper, we propose an integrated learning approach for jointly achieving fault detection and fault diagnosis of rare events in multivariate time series data. The proposed approach combines an autoencoder to detect a rare fault event and a long short-term memory (LSTM) network to classify different types of faults. The autoencoder is trained with offline normal data, which is then used as the anomaly detection. The predicted faulty data, captured by autoencoder, are put into the LSTM network to identify the types of faults. It basically combines the strong low-dimensional nonlinear representations of the autoencoder for the rare event detection and the strong time series learning ability of LSTM for the fault diagnosis. The proposed approach is compared with a deep convolutional neural network approach for fault detection and identification on the Tennessee Eastman process. Experimental results show that the combined approach accurately detects deviations from normal behaviour and identifies the types of faults within the useful time.

Wireless avionics intra-communication (WAIC) refers to a wireless communication system among electronic components (e.g., sensors and actuators) that are integrated or installed in an aircraft and it is proposed to replace heavy and expensive wired communication cables. Recently, the use of a frequency band (4.2–4.4 GHz) for the WAIC (so-called, WAIC band) has been approved by international telecommunication union (ITU). Accordingly, several existing wireless protocols such as IEEE 802.11 and IEEE 802.15 are being considered as candidate techniques for the intra-avionics sensor network. In this paper, we perform a real field experiment to investigate wireless channel characteristics in intra-avionics sensor networks at the WAIC bands by a software-defined radio platform (universal software radio peripheral, USRP) and self-produced monopole antennas for the WAIC band. Through the experiment, we validated the feasibility of IEEE 802.11 protocol for the intra-avionics sensor network at the WAIC band in real aircraft environments. Furthermore, based on the measurement data, we evaluated the bit error rate (BER) performance of multiple antenna techniques where we considered the maximum ratio combining (MRC) for the multi-antenna receiver and the space-time block coding (STBC) for the multi-antenna transmitter.

The stability guarantee of wireless networked control systems is still challenging due to the complex interaction among the layers and the vulnerability to network faults, such as link and node failures. In this paper, we propose a robust wireless sensor and actuator network (R-WSAN) to maintain the control stability of multiple plants over the spatial-temporal changes of wireless networks. The proposed joint design protocol combines the distributed controller of control systems and the clustering, resource scheduling, and control task sharing scheme of wireless networks over a hierarchical cluster-based network. In particular, R-WSAN decouples the tasks from the inherently unreliable nodes and allows control tasks to share between nodes of wireless networks. Our simulations demonstrate that R-WSAN provides the enhanced resilience to the network faults for sensing and actuation without significantly disrupting the control performance.

The transmission scheduling scheme of wireless networks for industrial control systems is a crucial design component since it directly affects the stability of networked control systems. In this paper, we propose a novel transmission scheduling framework to guarantee the stability of heterogeneous multiple control systems over unreliable wireless channels. Based on the explicit control stability conditions, a constrained optimization problem is proposed to maximize the minimum slack of the stability constraint for the heterogeneous control systems. We propose three transmission scheduling schemes, namely centralized stationary random access, distributed random access, and Lyapunov-based scheduling scheme, to solve the constrained optimization problem with a low computation cost. The three proposed transmission scheduling schemes were evaluated on heterogeneous multiple control systems with different link conditions. One interesting finding is that the proposed centralized Lyapunov-based approach provides almost ideal performance in the context of control stability. Furthermore, the distributed random access is still useful for the small number of links since it also reduces the operational overhead without significantly sacrificing the control performance.

When multiple mobile sensors and actuators share a common wireless mesh backbone network of defence systems, the channel allocation mechanism must guarantee the heterogeneous link requirements under conditions of uncertainty. In this paper, a robust channel allocation mechanism is proposed by exploiting partially overlapped channels for directional multi-channel wireless mesh networks. The approach relies on a chance-constrained optimization problem, in which the objective is to minimize the spectrum usage of the network, and the constraints are the signal-to-interference-plus-noise ratio requirements of links with uncertainty. We convert the proposed integer non-linear optimization problem into a mixed-integer convex problem by using efficient transition and approximation. The optimal channel allocation is obtained by solving the proposed optimization problem which adapts to the heterogeneous link and robustness requirements. The simulation results show that the proposed method ensures the heterogeneous link requirements under uncertain conditions while minimizing the spectrum usage of the network.