Damage Detection and Isolation from Limited Experimental Data Using Simple Simulations and Knowledge Transfer

A simulation model can provide insight into the characteristic behaviors of different health states of an actual system; however, such a simulation cannot account for all complexities in the system. This work proposes a transfer learning strategy that employs simple computer simulations for fault diagnosis in an actual system. A simple shaft-disk system was used to generate a substantial set of source data for three health states of a rotor system, and that data was used to train, validate, and test a customized deep neural network. The deep learning model, pretrained on simulation data, was used as a domain and class invariant generalized feature extractor, and the extracted features were processed with traditional machine learning algorithms. The experimental data sets of an RK4 rotor kit and a machinery fault simulator (MFS) were employed to assess the effectiveness of the proposed approach. The proposed method was also validated by comparing its performance with the pre-existing deep learning models of GoogleNet, VGG16, ResNet18, AlexNet, and SqueezeNet in terms of feature extraction, generalizability, computational cost, and size and parameters of the networks.

Usability of Video Observed Therapy with a Notification System to Improve Monitoring of Tuberculosis Treatment in Thailand (Preprint)

BACKGROUND In Thailand, the healthcare system has struggled to cope with the coronavirus disease 2019 (COVID-19), resulting in directly observed therapy (DOT) for tuberculosis (TB) being de-emphasized. Video observed therapy (VOT) or, more specifically, the Thai VOT “TH VOT” system, was then developed to replace DOT. According to the pilot study, the system needed a notification to improve usability and user compliance. The updated version of the TH VOT system thus enabled LINE notifications. OBJECTIVE This study aimed to reassess the user compliance and usability of the updated TH VOT system. METHODS This study was conducted in Hat Yai and Meuang Songkhla districts in Songkhla Province, Southern Thailand. The system was used by not only TB patients but also TB staff as observers in primary health care settings. Some of the observers used the simulated VOT system instead of the actual system due to the lack of participating patients in their jurisdiction. After 30-day usage, VOT session records were analyzed to determine the compliance of the patients and observers. The User Experience Questionnaire (UEQ) was administered to reassess the usability of the system and compare the ratings of the participants with the general benchmark scores of the UEQ. The results were summarized to reveal the user compliance and usability based on three groups: the patient, actual VOT observer, and simulated VOT observer. RESULTS Of the 19 observers, 10 were used the actual VOT, and the remaining 9 used the simulated VOT; there were also 10 TB patients. The patients, actual VOT observers, and simulated observers had about 80%, 65%, and 50% compliance, respectively, in terms of following the standard operating procedures every day. The scores of all groups on all dimensions were well above the average scores. There was no significant difference in any of the dimensional scores among the three groups. CONCLUSIONS The updated version of the TH VOT was deemed usable by both the patients and the healthcare staff. Compliance to use the system was high among the patients but moderate among the observers.

Usage Experience and Capabilities of the VEGA-Science System

Currently, when satellite data volumes grow rapidly and exceed petabyte values and their quality provides reliable analysis of long-term time series, traditional data handling methods assuming local storage and processing may be impossible to implement for small or distributed research teams. Thus, new methods based on modern web technologies providing access to very large distributed data archives are gaining increasing importance. Furthermore, these new data handling solutions should provide not just access but also analysis and processing features, similar to desktop solutions. This paper describes the VEGA-Science web GIS—an open-access novel tool for satellite data processing and analysis. The overview of its architecture and basic technical components is given, but most attention is paid to examples of actual system application for various applied and research tasks. In addition, an overview of projects using the system is given to illustrate its versatility and further development directions are considered.

An improved prognostics model with its application to the remaining useful life of turbofan engine

Machinery prognostics play a crucial role in upgrading machinery service and optimizing machinery operation and maintenance schedule by forecasting the remaining useful life (RUL) of the monitored equipment, which has become more and more popular in recent years. The safety of aviation is one of the issues that people are most concerned about in the field of transportation, since it might cause disastrous loss of life and property once accident happened. The turbofan engine is an important part of the aircraft that provides thrust for plane. With aging, the turbofan engine becomes prone to failures. As a result, it would be worth studying prognostics in turbofan engine to improve the reliability of machinery and reduce unnecessary maintenance cost. Recently, a data-driven prognostics modeling strategy called the classification of predictions strategy (CPS) was proposed, in which the continuous signal and the discrete modes of an actual system come together to achieve RUL estimation. However, machine health states measured from classification rarely have just one potential situation, and this strategy cannot determine whether the fault occurs or not by a certain probability which comes closer to reality. Moreover, since there is no information and prior knowledge of prognostics application, it is hard to obtain the probability of various situations from raw measured data. Hence, based on previous work, this paper proposes an improved prognostics modeling method named the classification of predictions strategy with decision probability (CPS-DP), whose key innovations mainly include three parts: (1) decision probability process (DPP) where each step of multi-step prediction obeys geometric distribution and can judge whether the failure state occurs using the decision probability; (2) decision probability calculation (DPC) algorithm, which is first proposed by this paper and can calculate the values of decision probability without prior knowledge of prognostics application; and (3) withdrawal mechanism optimizer (WMO), which is specially designed to compensate for the shortcomings of DPP and further enhance the performance of the prognostics model. In brief, first, CPS is used to build a basic prognostics model to acquire RUL estimation results, in which the information applied to find the probability has been contained. Later, the mean of RUL estimation errors is figured from the results, which is further employed to calculate the probability using DPC algorithm. Then, CPS-DP can be achieved by means of integrating two parts: DPP and CPS. Furthermore, to further improve the performance, WMO is utilized to optimize CPS-DP with rolling back predictions. Ultimately, an enhanced prognostic model based on CPS-DP is set up through uniting CPS, DPP, and WMO. To validate the proposed method, experimental results on the turbofan engine in 2008 prognostics and health management competition are investigated.

Representing Uncertainty in Physical Security Risk Assessment

The importance of (physical) security is increasingly acknowledged by society and the scientific community. In light of increasing terrorist threat levels, numerous security assessments of critical infrastructures are conducted in practice and researchers propose new approaches continuously. While practical security risk assessments (SRA) use mostly qualitative methods, most of the lately proposed approaches are based on quantitative metrics. Due to little evidence of actual attacks, both qualitative and quantitative approaches suffer from the fundamental problem of inherent uncertainties regarding threats and capabilities of security measures as a result from vague data or the usage of expert knowledge. In quantitative analysis, such uncertainties may be represented by, e.g., probability distributions to reflect the knowledge on security measure performance available. This paper focuses on the impact of these uncertainties in security assessment and their consideration in system design. We show this influence by comparing the results of a scalar evaluation that does not take into account uncertainties and another evaluation based on distributed input values. In addition, we show that the influence is concentrated on certain barriers of the security system. Specifically, we discuss the robustness of the system by conducting quantitative vulnerability assessment as part of the SRA process of an airport structure example. Based on these results, we propose the concept of a security margin. This concept accounts for the uncertain knowledge of the input parameters in the design of the security system and minimizes the influence of these uncertainties on the actual system performance. We show how this approach can be used for vulnerability assessment by applying it to the initially assessed configuration of the airport structure. The results of this case study support our assumptions that the security margin can help in targeted uncertainty consideration leading to reduced system vulnerability.

Design of meteorological intelligent sensor based on POE Technology

An application scheme of Poe based Ethernet technology in meteorological intelligent sensor system is designed. The working principle and implementation method of Ethernet power supply system (POE) based on IEEE802.3af Ethernet power supply industry standard are experimentally analyzed. The power supply part of the meteorological intelligent sensor makes full use of Poe technology to provide current on the network cable transmitting data, which greatly reduces the complexity of the power supply system and improves the reliability of the system power supply design. Through the test of the actual system, the function and performance of the meteorological intelligent transmission system have achieved the expected results.

Construction of E-commerce Personalized Information Recommendation System in the Era of Big Data

With the continuous expansion of the scale of e-commerce, personalized recommendation technology has been widely used. However, the traditional recommendation system has been unable to meet the current needs of data processing, and good big data processing ability has become the basic requirement of the new personalized recommendation system. In addition, traditional recommendation systems are often limited to tangible goods recommendation, and pay less attention to e-commerce logistics service recommendation. In this paper, through the in-depth study of information personalized recommendation service in e-commerce environment, combined with the application background of big data: Taking the user dissimilarity matrix as the recommendation model, we propose IU usercf and UDB slope one recommendation algorithm. The two algorithms based on incremental update recommendation model have good scalability, can effectively deal with big data, and have high prediction accuracy. The proposed algorithm is applied to the actual system, taking e-commerce logistics service as the recommendation object and iu-usercf as the recommendation algorithm, the personalized recommendation system for e-commerce logistics service is constructed. The e-commerce logistics service recommendation system explores the application practice of recommendation algorithm under big data, and enriches the application scenarios of personalized recommendation technology.

Research and Application of Power System Data Anomaly Identification Based on Time Series and Deep Learning

Abnormal data in the power system will reduce the accuracy of system state estimation and affect the safe operation of the power dispatch system. This paper proposes a data anomaly identification model based on time series and neural network, which establishes time series for various measuring points of the control master station, creates a time series group of associated measuring points based on the network topology, and extracts the sample characteristics of the time series. The neural network model is used to realize the intelligent identification of normal data and abnormal data. The neural network recognition results are compared with normal distribution and DBSCAN density clustering methods to verify the abnormal recognition performance of the neural network. Using a provincial power grid dispatch center operating data set as a training and testing sample, it verifies the advancement of the proposed method in the comprehensive performance of anomaly detection recall rate and precision rate and its feasibility in actual system application.

Fault Line Selection of Non-solidly Grounding System Based on EMD and Correlation Analysis of Zero Sequence Current Break-variable

When a single-phase grounding fault occurs in non-solidly grounding system, the zero sequence transient current is nonlinear and non-stationary. Especially when the resonant system is grounded with high resistance, the transient quantity is weak, which brings challenges to data processing. Therefore, empirical mode decomposition (EMD) is proposed to decompose the transient quantity and obtain different intrinsic mode functions (IMF). The IMF with the largest discrimination is selected as the characteristic quantity for correlation analysis. At the same time, considering the existence of unbalanced current in the actual system, in order to avoid the influence of unbalanced current, a single-phase grounding fault line selection algorithm based on EMD decomposition and correlation analysis of zero sequence current break-variable is proposed. Finally, the effectiveness of the method is verified by simulation and field test waveforms.

Stability analysis of microgrid inverter off-grid mode considering nonlinear load

With the large-scale utilization of distributed generation in microgrid, inverter as the connection hub of new energy grid connection, directly affects the operation performance of microgrid. In order to improve the output voltage quality and load capacity of the inverter in the off-grid mode of distributed energy, the stability region of the inverter with load is analyzed by using the impedance analysis method of cascade converter and control theory. The quasi proportional resonant (QPR) double loop control is adopted to realize no static error tracking voltage while increasing bandwidth, and the influence of control parameters on performance is analyzed. At the same time, in order to improve the capacity of inverter with nonlinear load, odd harmonics are introduced into the controller to suppress the influence of low harmonics of load current on output voltage. Finally, the influence of inverter output impedance change, load level, controller parameters and filter parameters on system stability is analyzed through impedance ratio Nyquist curve, which provides corresponding theoretical support and parameter optimization reference for the design of actual system.