Real-Time Nuisance Fault Detection in Photovoltaic Generation Systems Using a Fine Tree Classifier

Nuisance faults are caused by weather events, which result in solar farms being disconnected from the electricity grid. This results in long stretches of downtime for troubleshooting as data are mined manually for possible fault causes, and consequently, cost thousands of dollars in lost revenue and maintenance. This paper proposes a novel fault detection technique to identify nuisance faults in solar farms. To initialize the design process, a weather model and solar farm model are designed to generate both training and testing data. Through an iterative design process, a fine tree model with a classification accuracy of 96.7% is developed. The proposed model is successfully implemented and tested in real-time through a server and web interface. The testbed is capable of streaming in data from a separate source, which emulates a supervisory control and data acquisition (SCADA) or weather station, then classifies the data in real-time and displays the output on another computer (which imitates an operator control room).

Download Full-text

The Real-Time Fault Analysis of Personal Escape Suit Based on the Object Oriented Model

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.1030-1032.1837 ◽

2014 ◽

Vol 1030-1032 ◽

pp. 1837-1840

Author(s):

Yao Tang ◽

Pei Hu ◽

Qian Hao ◽

Shan Yi Fang ◽

Shi Long Xing

Keyword(s):

Fault Detection ◽

Real Time ◽

Fault Tree ◽

Object Oriented ◽

Fault Analysis ◽

Tree Model ◽

The Real ◽

Actual Equipment ◽

Analysis System

According the actual equipment support demand of rapidly floating escape suit, this paper built the object oriented fault tree model for the rapidly floating escape suit, detailed descried the planning and realization method of the fault detection and analysis system with actual examples.

Download Full-text

Real-time fault detection and process control based on multi-channel sensor data fusion

The International Journal of Advanced Manufacturing Technology ◽

10.1007/s00170-020-06168-y ◽

2021 ◽

Author(s):

Zhijie Xia ◽

Feng Ye ◽

Min Dai ◽

Zhisheng Zhang

Keyword(s):

Fault Detection ◽

Process Control ◽

Data Fusion ◽

Real Time ◽

Sensor Data ◽

Sensor Data Fusion

Download Full-text

A machine learning approach for accurate and real-time DNA sequence identification

BMC Genomics ◽

10.1186/s12864-021-07841-6 ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Yiren Wang ◽

Mashari Alangari ◽

Joshua Hihath ◽

Arindam K. Das ◽

M. P. Anantram

Keyword(s):

Real Time ◽

Dna Sequence ◽

Single Molecule ◽

Identification Accuracy ◽

Measuring System ◽

Identification System ◽

Genetic Sequencing ◽

Sequence Identification ◽

Tree Classifier ◽

Single Mismatch

Abstract Background The all-electronic Single Molecule Break Junction (SMBJ) method is an emerging alternative to traditional polymerase chain reaction (PCR) techniques for genetic sequencing and identification. Existing work indicates that the current spectra recorded from SMBJ experimentations contain unique signatures to identify known sequences from a dataset. However, the spectra are typically extremely noisy due to the stochastic and complex interactions between the substrate, sample, environment, and the measuring system, necessitating hundreds or thousands of experimentations to obtain reliable and accurate results. Results This article presents a DNA sequence identification system based on the current spectra of ten short strand sequences, including a pair that differs by a single mismatch. By employing a gradient boosted tree classifier model trained on conductance histograms, we demonstrate that extremely high accuracy, ranging from approximately 96 % for molecules differing by a single mismatch to 99.5 % otherwise, is possible. Further, such accuracy metrics are achievable in near real-time with just twenty or thirty SMBJ measurements instead of hundreds or thousands. We also demonstrate that a tandem classifier architecture, where the first stage is a multiclass classifier and the second stage is a binary classifier, can be employed to boost the single mismatched pair’s identification accuracy to 99.5 %. Conclusions A monolithic classifier, or more generally, a multistage classifier with model specific parameters that depend on experimental current spectra can be used to successfully identify DNA strands.

Download Full-text

Exploring real-time fault detection of high-speed train traction motor based on machine learning and wavelet analysis

Neural Computing and Applications ◽

10.1007/s00521-021-06284-0 ◽

2021 ◽

Author(s):

Yanshu Li

Keyword(s):

Machine Learning ◽

Fault Detection ◽

Wavelet Analysis ◽

Real Time ◽

High Speed ◽

High Speed Train ◽

Traction Motor

Download Full-text

Optimization of Physical Activity Recognition for Real-Time Wearable Systems: Effect of Window Length, Sampling Frequency and Number of Features

Applied Sciences ◽

10.3390/app9224833 ◽

2019 ◽

Vol 9 (22) ◽

pp. 4833 ◽

Cited By ~ 3

Author(s):

Ardo Allik ◽

Kristjan Pilt ◽

Deniss Karai ◽

Ivo Fridolin ◽

Mairo Leier ◽

...

Keyword(s):

Physical Activity ◽

Feature Selection ◽

Real Time ◽

Sampling Frequency ◽

Classification Performance ◽

Window Length ◽

Decision Tree Classifier ◽

Acceleration Signal ◽

Wearable Systems ◽

Tree Classifier

The aim of this study was to develop an optimized physical activity classifier for real-time wearable systems with the focus on reducing the requirements on device power consumption and memory buffer. Classification parameters evaluated in this study were the sampling frequency of the acceleration signal, window length of the classification fragment, and the number of classification features, found with different feature selection methods. For parameter evaluation, a decision tree classifier was created based on the acceleration signals recorded during tests, where 25 healthy test subjects performed various physical activities. Overall average F1-score achieved in this study was about 0.90. Similar F1-scores were achieved with the evaluated window lengths of 5 s (0.92 ± 0.02) and 3 s (0.91 ± 0.02), while classification performance with 1 s were lower (0.87 ± 0.02). Tested sampling frequencies of 50 Hz, 25 Hz, and 13 Hz had similar results with most classified activity types, with an exception of outdoor cycling, where differences were significant. Using forward sequential feature selection enabled the decreasing of the number of features from initial 110 features to about 12 features without lowering the classification performance. The results of this study have been used for developing more efficient real-time physical activity classifiers.

Download Full-text

Real-time model-based fault detection and diagnosis for automated systems

10.1109/dmca.1997.603438 ◽

2002 ◽

Author(s):

E. Jackson

Keyword(s):

Fault Detection ◽

Real Time ◽

Fault Detection And Diagnosis ◽

Automated Systems ◽

Time Model ◽

Model Based ◽

Detection And Diagnosis

Download Full-text

Fault detection algorithms for real-time diagnosis in large-scale systems

10.1117/12.434244 ◽

2001 ◽

Cited By ~ 3

Author(s):

Thiagalingam Kirubarajan ◽

Venkatesh N. Malepati ◽

Somnath Deb ◽

Jie Ying

Keyword(s):

Fault Detection ◽

Real Time ◽

Large Scale ◽

Large Scale Systems ◽

Detection Algorithms ◽

Time Diagnosis

Download Full-text

Human versus Artificial Intelligence: A Data-Driven Approach to Real-Time Process Management During Complex Engineering Design

Journal of Mechanical Design ◽

10.1115/1.4052488 ◽

2021 ◽

pp. 1-38

Author(s):

Joshua Gyory ◽

Nicolas F Soria Zurita ◽

Jay Martin ◽

Corey Balon ◽

Christopher McComb ◽

...

Keyword(s):

Real Time ◽

Design Process ◽

Process Management ◽

Superior Performance ◽

Team Members ◽

Engineering Teams ◽

Complex Design ◽

Data Driven Approach ◽

Complex Engineering ◽

Process Managers

Abstract Managing the design process of teams has been shown to considerably improve problem-solving behaviors and resulting final outcomes. Automating this activity presents significant opportunities in delivering interventions that dynamically adapt to the state of a team in order to reap the most impact. In this work, an Artificial Intelligent (AI) agent is created to manage the design process of engineering teams in real time, tracking features of teams' actions and communications during a complex design and path-planning task with multidisciplinary team members. Teams are also placed under the guidance of human process managers for comparison. Regarding outcomes, teams perform equally as well under both types of management, with trends towards even superior performance from the AI-managed teams. The managers' intervention strategies and team perceptions of those strategies are also explored, illuminating some intriguing similarities. Both the AI and human process managers focus largely on communication-based interventions, though differences start to emerge in the distribution of interventions across team roles. Furthermore, team members perceive the interventions from the both the AI and human manager as equally relevant and helpful, and believe the AI agent to be just as sensitive to the needs of the team. Thus, the overall results show that the AI manager agent introduced in this work is able to match the capabilities of humans, showing potential in automating the management of a complex design process.

Download Full-text