Machine Anomaly Detection and Diagnosis Incorporating Operational Data Applied to Feed Axis Health Monitoring

2011 ◽  
Author(s):  
Linxia Liao ◽  
Radu Pavel
Keyword(s):  
Anomaly Detection ◽  
Principal Component ◽  
Operating Conditions ◽  
Self Organizing Map ◽  
Test Bed ◽  
Accurate Analysis ◽  
Operating Condition ◽  
Detection And Diagnosis ◽  
Feed Axis ◽  
Operational Data

Solutions for machinery anomaly detection and diagnosis are typically designed on an ad hoc, custom basis, and previous studies have shown limited success in automating or generalizing these solutions. Reusing and maintaining the analysis software, especially when the machine usage pattern or operating condition changes, remains a challenge. This paper outlines a strategy to make use of operational data obtained from the machine’s controller and signals obtained from external sensors to provide an accurate analysis within each operating condition. Operational data collected from the controller is used both for labeling datasets into different operating conditions and for analysis. Principal component analysis (PCA) is adopted to identify critical sensors that can provide useful information. Self-organizing map (SOM)-based anomaly detection and diagnosis methods are used to automatically convert data to easily understandable machine health information for operators. Experiment trials conducted on a feed-axis test-bed demonstrated the effectiveness of incorporating operational data for anomaly detection and diagnosis.

scholarly journals Anomaly Detection in Photovoltaic Production Factories via Monte Carlo Pre-Processed Principal Component Analysis

Energies ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 3951
Author(s):  
Eleonora Arena ◽  
Alessandro Corsini ◽  
Roberto Ferulano ◽  
Dario Alfio Iuvara ◽  
Eric Stefan Miele ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Monte Carlo ◽  
Anomaly Detection ◽  
Principal Component ◽  
Component Analysis ◽  
Operating Conditions ◽  
Production Plant ◽  
Use Case ◽  
Model Errors ◽  
Unseen Data

This paper investigates a use case of robust anomaly detection applied to the scenario of a photovoltaic production factory—namely, Enel Green Power’s 3SUN solar cell production plant in Catania, Italy—by considering a Monte Carlo based pre-processing technique as a valid alternative to other typically used methods. In particular, the proposed method exhibits the following advantages: (i) Outlier replacement, by contrast with traditional methods which are limited to outlier detection only, and (ii) the preservation of temporal locality with respect to the training dataset. After pre-processing, the authors trained an anomaly detection model based on principal component analysis and defined a suitable key performance indicator for each sensor in the production line based on the model errors. In this way, by running the algorithm on unseen data streams, it is possible to isolate anomalous conditions by monitoring the above-mentioned indicators and virtually trigger an alarm when exceeding a reference threshold. The proposed approach was tested on both standard operating conditions and an anomalous scenario. With respect to the considered use case, it successfully anticipated a fault in the equipment with an advance of almost two weeks, but also demonstrated its robustness to false alarms during normal conditions.

OPERATIONAL STATE OF BRIDGES OF UKRAINE

2019 ◽  
pp. 57-68
Author(s):  
Larysa Bodnar ◽  
Petro Koval ◽  
Sergii Stepanov ◽  
Liudmyla Panibratets
Keyword(s):  
Management System ◽  
The State ◽  
Operating Conditions ◽  
Bridge Management ◽  
Bridge Management System ◽  
Program Complex ◽  
Operating Condition ◽  
Software Complex ◽  
Automatic Mode ◽  
The Status

A significant part of Ukrainian bridges on public roads is operated for more than 30 years (94 %). At the same time, the traffic volume and the weight of vehicles has increased significantly. Insufficient level of bridges maintenance funding leads to the deterioration of their technical state. The ways to ensure reliable and safe operation of bridges are considered. The procedure for determining the predicted operational status of the elements and the bridge in general, which has a scientific novelty, is proposed. In the software complex, Analytical Expert Bridges Management System (AESUM), is a function that allows tracking the changes in the operational status of bridges both in Ukraine and in each region separately. The given algorithm of the procedure for determining the predicted state of the bridge using a degradation model is described using the Nassie-Schneidermann diagram. The model of the degradation of the bridge performance which is adopted in Ukraine as a normative one, and the algorithm for its adaptation to the AESUM program complex with the function to ensure the probabilistic predicted operating condition of the bridges in the automatic mode is presented. This makes it possible, even in case of unsatisfactory performance of surveys, to have the predicted lifetime of bridges at the required time. For each bridge element it is possible to determine the residual time of operation that will allow predict the state of the elements of the structure for a certain period of time in the future. Significant interest for specialists calls for the approaches to the development of orientated perspective plans for bridge inspection and monitoring of changes in the operational status of bridges for 2009-2018 in Ukraine. For the analysis of the state of the bridge economy, the information is available on the distribution of bridges by operating state related to the administrative significance of roads, by road categories and by materials of the structures. Determining the operating state of the bridge is an important condition for making the qualified decisions as regards its maintenance. The Analytical Expert Bridges Management System (AESUM) which is implemented in Ukraine, stores the data on the monitoring the status of bridges and performs the necessary procedures to maintain them in a reliable and safe operating condition. An important result of the work is the ability to determine the distribution of bridges on the public roads of Ukraine, according to operating conditions established in the program complex of AESUM, which is presented in accordance with the data of the current year. In conditions of limited funding and in case of unsatisfactory performance of surveys, it is possible to make the reasonable management decisions regarding the repair and the reconstruction of bridges. Keywords: bridge management system, operating condition, predicted operating condition, model of degradation, bridge survey plan, highway bridge.

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.

Design Point for Predicting Year-Round Performance of Solar Parabolic Trough Concentrator Systems

2013 ◽  
Author(s):  
Men Wirz ◽  
Matthew Roesle ◽  
Aldo Steinfeld
Keyword(s):  
Operating Conditions ◽  
Transfer Model ◽  
Parabolic Trough ◽  
Specific System ◽  
Simple Method ◽  
Operating Condition ◽  
Average Efficiency ◽  
Design Point ◽  
Yearly Average ◽  
Solar Field

Thermal efficiencies of the solar field of two different parabolic trough concentrator (PTC) systems are evaluated for a variety of operating conditions and geographical locations, using a detailed 3D heat transfer model. Results calculated at specific design points are compared to yearly average efficiencies determined using measured direct normal solar irradiance (DNI) data as well as an empirical correlation for DNI. It is shown that the most common choices of operating conditions at which solar field performance is evaluated, such as the equinox or the summer solstice, are inadequate for predicting the yearly average efficiency of the solar field. For a specific system and location, the different design point efficiencies vary significantly and differ by as much as 11.5% from the actual yearly average values. An alternative simple method is presented of determining a representative operating condition for solar fields through weighted averages of the incident solar radiation. For all tested PTC systems and locations, the efficiency of the solar field at the representative operating condition lies within 0.3% of the yearly average efficiency. Thus, with this procedure, it is possible to accurately predict year-round performance of PTC systems using a single design point, while saving computational effort. The importance of the design point is illustrated by an optimization study of the absorber tube diameter, where different choices of operating conditions result in different predicted optimum absorber diameters.

scholarly journals Hybrid Internal Anomaly Detection System for IoT: Reactive Nodes with Cross-Layer Operation

2018 ◽  
Vol 2018 ◽  
pp. 1-15 ◽  
Author(s):  
Nanda Kumar Thanigaivelan ◽  
Ethiopia Nigussie ◽  
Seppo Virtanen ◽  
Jouni Isoaho
Keyword(s):  
Anomaly Detection ◽  
False Positive ◽  
Detection System ◽  
False Positive Rate ◽  
Security Analysis ◽  
Abnormal Behavior ◽  
Test Bed ◽  
Positive Rate ◽  
Parent Node ◽  
Anomaly Detection System

We present a hybrid internal anomaly detection system that shares detection tasks between router and nodes. It allows nodes to react instinctively against the anomaly node by enforcing temporary communication ban on it. Each node monitors its own neighbors and if abnormal behavior is detected, the node blocks the packets of the anomaly node at link layer and reports the incident to its parent node. A novel RPL control message, Distress Propagation Object (DPO), is formulated and used for reporting the anomaly and network activities to the parent node and subsequently to the router. The system has configurable profile settings and is able to learn and differentiate between the nodes normal and suspicious activities without a need for prior knowledge. It has different subsystems and operation phases that are distributed in both the nodes and router, which act on data link and network layers. The system uses network fingerprinting to be aware of changes in network topology and approximate threat locations without any assistance from a positioning subsystem. The developed system was evaluated using test-bed consisting of Zolertia nodes and in-house developed PandaBoard based gateway as well as emulation environment of Cooja. The evaluation revealed that the system has low energy consumption overhead and fast response. The system occupies 3.3 KB of ROM and 0.86 KB of RAM for its operations. Security analysis confirms nodes reaction against abnormal nodes and successful detection of packet flooding, selective forwarding, and clone attacks. The system’s false positive rate evaluation demonstrates that the proposed system exhibited 5% to 10% lower false positive rate compared to simple detection system.

Experimental Results of a PEM System Operated on Hydrogen and Reformate

2008 ◽  
Vol 5 (1) ◽  
Author(s):  
M. Minutillo ◽  
E. Jannelli ◽  
F. Tunzio
Keyword(s):  
Fuel Cell ◽  
Natural Gas ◽  
Large Scale ◽  
Pem Fuel Cell ◽  
Proton Exchange ◽  
Operating Conditions ◽  
Cell Performance ◽  
Pure Hydrogen ◽  
Test Bed ◽  
Fuel Cell Performance

The main objective of this study is to evaluate the performance of a proton exchange membrane (PEM) fuel cell generator operating for residential applications. The fuel cell performance has been evaluated using the test bed of the University of Cassino. The experimental activity has been focused to evaluate the performance in different operating conditions: stack temperature, feeding mode, and fuel composition. In order to use PEM fuel cell technology on a large scale, for an electric power distributed generation, it could be necessary to feed fuel cells with conventional fuel, such as natural gas, to generate hydrogen in situ because currently the infrastructure for the distribution of hydrogen is almost nonexistent. Therefore, the fuel cell performance has been evaluated both using pure hydrogen and reformate gas produced by a natural gas reforming system.

Experimental and Numerical Investigation of Centrifugal Pump Performance When Handling Viscous Fluids

2005 ◽  
Author(s):  
M. H. Shojaee Fard ◽  
M. B. Ehghaghi ◽  
F. A. Boyaghchi
Keyword(s):  
Soviet Union ◽  
Centrifugal Pump ◽  
Turbulent Flows ◽  
Characteristic Curve ◽  
Three Dimensional ◽  
Operating Conditions ◽  
Viscous Fluids ◽  
Test Bed ◽  
Flow Process ◽  
Pump Performance

On the test bed of centrifugal pump, the centrifugal pump performance has been investigated using water and viscous oil as Newtonian fluids, whose kinematic viscosities are 1 × 10−6, 43 × 10−6 and 62 × 10−6 m2/s, respectively. Also, the finite volume method is used to model the three dimensional viscous fluids for different operating conditions. For these numerical simulations the SIMPLEC algorithm is used for solving governing equations of incompressible viscous/turbulent flows through the pump. The κ-ε turbulence model is adopted to describe the turbulent flow process. These simulations have been made with a steady calculation and using the multiple reference frame (MRF) technique to take into account the impeller-volute interaction. Numerical results are compared with the experimental characteristic curve for each viscous fluid. The data obtained allow the analysis of the main phenomena existent in this pump, such as: head, efficiency, power and pressure field changes for different operating conditions. Also, the correction factors for oils are obtained from the experimental for part loading (PL), best efficiency point (BEP) and over loading (OL) and the results are compared with proposed factors by American Hydraulic Institute (HIS) and Soviet Union (USSR). The comparisons between the numerical and experimental results show a good agreement.

Sign in / Sign up

Export Citation Format

Share Document