scholarly journals Anomaly Detection in a Logistic Operating System Using the Mahalanobis–Taguchi Method

2020 ◽  
Vol 10 (12) ◽  
pp. 4376
Author(s):  
Takumi Asakura ◽  
Wataru Yashima ◽  
Kouki Suzuki ◽  
Makoto Shimotou
Keyword(s):  
Operating System ◽  
Taguchi Method ◽  
Anomaly Detection ◽  
Mahalanobis Distance ◽  
Large Scale ◽  
Continuous Operation ◽  
Transfer System ◽  
Mahalanobis Distances ◽  
Vertical Transfer ◽  
Term Operation

Product delivery via logistic systems is becoming more efficient, rapidly and continuously bringing products to the customer. The continuous operation of logistic equipment, however, can lead to mechanical stoppages due to excessive use. To avoid system failures, fatigue in each part of the system should be monitored, enabling the accurate prediction of potential stoppages and thus promoting overall system efficiency. To date, various kinds of anomaly-detection methodologies have been proposed. Among them, the Mahalanobis–Taguchi method, which simply describes the extent of a failure using the Mahalanobis distance, has been utilized to detect changes in the mechanical condition of facilities. However, the technique has not yet been applied to anomaly detection in a logistic operating system. In this paper, anomaly detection using the Mahalanobis–Taguchi method targeting the operational characteristics of a large-scale vertical transfer system is proposed and the validity of the method is discussed. The calculation used to produce proper values of the Mahalanobis distance is first developed based on simple excitation using a shaker. Mahalanobis distances under conditions of continuous operation of the target vertical transfer system are then obtained; distances for the system in an artificially damaged condition are compared to values produced under normal conditions, and any significant increase is used as an indicator of a problem. The applicability of the approach to a case involving continuous long-term operation is discussed using a simulation in which the target vertical transfer system is in continuous operation over a two-year period.

scholarly journals A Combined Approach for Model-Based PV Power Plant Failure Detection and Diagnostic

Energies ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1261
Author(s):  
Christopher Gradwohl ◽  
Vesna Dimitrievska ◽  
Federico Pittino ◽  
Wolfgang Muehleisen ◽  
András Montvay ◽  
...  
Keyword(s):  
Power Plants ◽  
Large Scale ◽  
Failure Detection ◽  
Energy Yield ◽  
Combined Approach ◽  
Levelized Cost Of Electricity ◽  
Term Operation ◽  
Model Based

Photovoltaic (PV) technology allows large-scale investments in a renewable power-generating system at a competitive levelized cost of electricity (LCOE) and with a low environmental impact. Large-scale PV installations operate in a highly competitive market environment where even small performance losses have a high impact on profit margins. Therefore, operation at maximum performance is the key for long-term profitability. This can be achieved by advanced performance monitoring and instant or gradual failure detection methodologies. We present in this paper a combined approach on model-based fault detection by means of physical and statistical models and failure diagnosis based on physics of failure. Both approaches contribute to optimized PV plant operation and maintenance based on typically available supervisory control and data acquisition (SCADA) data. The failure detection and diagnosis capabilities were demonstrated in a case study based on six years of SCADA data from a PV plant in Slovenia. In this case study, underperforming values of the inverters of the PV plant were reliably detected and possible root causes were identified. Our work has led us to conclude that the combined approach can contribute to an efficient and long-term operation of photovoltaic power plants with a maximum energy yield and can be applied to the monitoring of photovoltaic plants.

scholarly journals Sensor System: A Survey of Sensor Type, Ad Hoc Network Topology and Energy Harvesting Techniques

Electronics ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 219
Author(s):  
Phuoc Duc Nguyen ◽  
Lok-won Kim
Keyword(s):  
Energy Harvesting ◽  
Large Scale ◽  
Ad Hoc ◽  
Sensor Nodes ◽  
Sensor System ◽  
Wireless Sensor ◽  
The Internet ◽  
Original Research ◽  
Energy Scavenging ◽  
Term Operation

People nowadays are entering an era of rapid evolution due to the generation of massive amounts of data. Such information is produced with an enormous contribution from the use of billions of sensing devices equipped with in situ signal processing and communication capabilities which form wireless sensor networks (WSNs). As the number of small devices connected to the Internet is higher than 50 billion, the Internet of Things (IoT) devices focus on sensing accuracy, communication efficiency, and low power consumption because IoT device deployment is mainly for correct information acquisition, remote node accessing, and longer-term operation with lower battery changing requirements. Thus, recently, there have been rich activities for original research in these domains. Various sensors used by processing devices can be heterogeneous or homogeneous. Since the devices are primarily expected to operate independently in an autonomous manner, the abilities of connection, communication, and ambient energy scavenging play significant roles, especially in a large-scale deployment. This paper classifies wireless sensor nodes into two major categories based the types of the sensor array (heterogeneous/homogeneous). It also emphasizes on the utilization of ad hoc networking and energy harvesting mechanisms as a fundamental cornerstone to building a self-governing, sustainable, and perpetually-operated sensor system. We review systems representative of each category and depict trends in system development.

scholarly journals Multi-task learning based Encoder-Decoder: A comprehensive detection and diagnosis system for multi-sensor data

2021 ◽  
Vol 13 (5) ◽  
pp. 168781402110131
Author(s):  
Junfeng Wu ◽  
Li Yao ◽  
Bin Liu ◽  
Zheyuan Ding ◽  
Lei Zhang
Keyword(s):  
Anomaly Detection ◽  
Event Detection ◽  
Large Scale ◽  
Multivariate Time Series ◽  
Sensor Data ◽  
Unified Framework ◽  
Diagnosis System ◽  
Learning Framework ◽  
Task Learning ◽  
Detection And Diagnosis

As more and more sensor data have been collected, automated detection, and diagnosis systems are urgently needed to lessen the increasing monitoring burden and reduce the risk of system faults. A plethora of researches have been done on anomaly detection, event detection, anomaly diagnosis respectively. However, none of current approaches can explore all these respects in one unified framework. In this work, a Multi-Task Learning based Encoder-Decoder (MTLED) which can simultaneously detect anomalies, diagnose anomalies, and detect events is proposed. In MTLED, feature matrix is introduced so that features are extracted for each time point and point-wise anomaly detection can be realized in an end-to-end way. Anomaly diagnosis and event detection share the same feature matrix with anomaly detection in the multi-task learning framework and also provide important information for system monitoring. To train such a comprehensive detection and diagnosis system, a large-scale multivariate time series dataset which contains anomalies of multiple types is generated with simulation tools. Extensive experiments on the synthetic dataset verify the effectiveness of MTLED and its multi-task learning framework, and the evaluation on a real-world dataset demonstrates that MTLED can be used in other application scenarios through transfer learning.

scholarly journals Inclusion of Warm Pre-Stress Concept in French RPV Structural Integrity Assessment

2016 ◽  
Author(s):  
Dominique Moinereau ◽  
Malik Ait-Bachir ◽  
Stéphane Chapuliot ◽  
Stéphane Marie ◽  
Clémentine Jacquemoud ◽  
...  
Keyword(s):  
Brittle Fracture ◽  
Fracture Resistance ◽  
Large Scale ◽  
Structural Integrity ◽  
Stress Effect ◽  
Local Approach ◽  
Experimental Database ◽  
Term Operation ◽  
Integrity Assessment ◽  
Brittle Fracture Resistance

Evaluation of the fracture resistance of nuclear reactor pressure vessel (RPV) regarding the risk of brittle fracture is a key point in the structural integrity assessment of the component (RPV). Such approach is codified in French RSE-M code, based on a very conservative methodology. With respect to long term operation, an improvement of the present methodology is necessary and in progress to reduce this conservatism. One possible significant improvement is the inclusion of the warm pre-stress (WPS) concept in the assessment. After a short description of the WPS concept, the process engaged in France to allow inclusion of WPS in the integrity assessment is presented. In a first step, experimental and numerical studies have been conducted in France by EDF, CEA and AREVA (also including international collaborations and projects) to demonstrate and validate the beneficial effect of WPS on the brittle fracture resistance of RPV steels. A large panel of experimental results and data is now available obtained on small, medium and large scale specimens on representative RPV steels (including highly irradiated RPV materials). These data have been included in a specific WPS experimental database. Main experiments have been interpreted by refined computations, based on elastic plastic analyses and local approach to cleavage fracture. In a second step, a new criterion (ACE criterion) has been proposed by French organizations (AREVA, CEA and EDF) for an easy simplified evaluation of warm pre-stress effect on the brittle fracture resistance of RPV steels. Accuracy and conservatism of the criterion is verified by comparison to experimental data results and numerical analyses. Finally, implementation of the WPS effect in the French RSE-M code (for in service assessment) is in progress, based on the ACE criterion. The present paper summarizes all these steps leading to codification of WPS in RSE-M code.

Hierarchical Anomaly Detection and Multimodal Classification in Large-Scale Photovoltaic Systems

2019 ◽  
Vol 10 (3) ◽  
pp. 1351-1361 ◽  
Author(s):  
Yingying Zhao ◽  
Qi Liu ◽  
Dongsheng Li ◽  
Dahai Kang ◽  
Qin Lv ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Large Scale ◽  
Photovoltaic Systems ◽  
Multimodal Classification

Numerical Modelling of a District Scale Groundwater Heat Pump Operation: Case Study from Colchester, UK

2021 ◽  
Author(s):  
Taha Sezer ◽  
Abubakar Kawuwa Sani ◽  
Rao Martand Singh ◽  
David P. Boon
Keyword(s):  
Large Scale ◽  
District Level ◽  
Thermal Plume ◽  
Injection Wells ◽  
Term Operation ◽  
Heating And Cooling ◽  
Groundwater Heat Pump ◽  
The Impact

<p>Groundwater heat pumps (GWHP) are an environmentally friendly and highly efficient low carbon heating technology that can benefit from low-temperature groundwater sources lying in the shallow depths to provide heating and cooling to buildings. However, the utilisation of groundwater for heating and cooling, especially in large scale (district level), can create a thermal plume around injection wells. If a plume reaches the production well this may result in a decrease in the system performance or even failure in the long-term operation. This research aims to investigate the impact of GWHP usage in district-level heating by using a numerical approach and considering a GWHP system being constructed in Colchester, UK as a case study, which will be the largest GWHP system in the UK. Transient 3D simulations have been performed pre-construction to investigate the long-term effect of injecting water at 5°C, into a chalk bedrock aquifer. Modelling suggests a thermal plume develops but does not reach the production wells after 10 years of operation. The model result can be attributed to the low hydraulic gradient, assumed lack of interconnecting fractures, and large (>500m) spacing between the production and injection wells. Model validation may be possible after a period operational monitoring.</p>

Sign in / Sign up

Export Citation Format

Share Document