scholarly journals Adaptable and Explainable Predictive Maintenance: Semi-Supervised Deep Learning for Anomaly Detection and Diagnosis in Press Machine Data

2021 ◽  
Vol 11 (16) ◽  
pp. 7376
Author(s):  
Oscar Serradilla ◽  
Ekhi Zugasti ◽  
Julian Ramirez de Okariz ◽  
Jon Rodriguez ◽  
Urko Zurutuza
Keyword(s):  
Anomaly Detection ◽  
Null Space ◽  
Model Performance ◽  
Principal Component ◽  
Predictive Maintenance ◽  
Data Driven ◽  
Support Vector ◽  
Operational Conditions ◽  
Detection Model ◽  
Cluster Data

Predictive maintenance (PdM) has the potential to reduce industrial costs by anticipating failures and extending the work life of components. Nowadays, factories are monitoring their assets and most collected data belong to correct working conditions. Thereby, semi-supervised data-driven models are relevant to enable PdM application by learning from assets’ data. However, their main challenges for application in industry are achieving high accuracy on anomaly detection, diagnosis of novel failures, and adaptability to changing environmental and operational conditions (EOC). This article aims to tackle these challenges, experimenting with algorithms in press machine data of a production line. Initially, state-of-the-art and classic data-driven anomaly detection model performance is compared, including 2D autoencoder, null-space, principal component analysis (PCA), one-class support vector machines (OC-SVM), and extreme learning machine (ELM) algorithms. Then, diagnosis tools are developed supported on autoencoder’s latent space feature vector, including clustering and projection algorithms to cluster data of synthetic failure types semi-supervised. In addition, explainable artificial intelligence techniques have enabled to track the autoencoder’s loss with input data to detect anomalous signals. Finally, transfer learning is applied to adapt autoencoders to changing EOC data of the same process. The data-driven techniques used in this work can be adapted to address other industrial use cases, helping stakeholders gain trust and thus promote the adoption of data-driven PdM systems in smart factories.

Data-Driven Analysis of Engine Mission Severity Using Non-Dimensional Groups

2021 ◽  
Author(s):  
Tim Brandes ◽  
Stefano Scarso ◽  
Christian Koch ◽  
Stephan Staudacher
Keyword(s):  
Support Vector Machine ◽  
Computation Time ◽  
Principal Component ◽  
General Term ◽  
Support Vector ◽  
Physical Parameters ◽  
Machine Model ◽  
Precision Error ◽  
Operational Conditions ◽  
Wide Range

Abstract A numerical experiment of intentionally reduced complexity is used to demonstrate a method to classify flight missions in terms of the operational severity experienced by the engines. In this proof of concept, the general term of severity is limited to the erosion of the core flow compressor blade and vane leading edges. A Monte Carlo simulation of varying operational conditions generates a required database of 10000 flight missions. Each flight is sampled at a rate of 1 Hz. Eleven measurable or synthesizable physical parameters are deemed to be relevant for the problem. They are reduced to seven universal non-dimensional groups which are averaged for each flight. The application of principal component analysis allows a further reduction to three principal components. They are used to run a support-vector machine model in order to classify the flights. A linear kernel function is chosen for the support-vector machine due to its low computation time compared to other functions. The robustness of the classification approach against measurement precision error is evaluated. In addition, a minimum number of flights required for training and a sensible number of severity classes are documented. Furthermore, the importance to train the algorithms on a sufficiently wide range of operations is presented.

scholarly journals MACHINE LEARNING METHODS IN MONITORING OPERATING BEHAVIOUR OF MARINE TWO-STROKE DIESEL ENGINE

Transport ◽  
2020 ◽  
Vol 35 (5) ◽  
pp. 462-473
Author(s):  
Aleksandar Vorkapić ◽  
Radoslav Radonja ◽  
Karlo Babić ◽  
Sanda Martinčić-Ipšić
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
Fuel Consumption ◽  
Performance Monitoring ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Operating Parameters ◽  
Detection Model ◽  
Modelling Framework

The aim of this article is to enhance performance monitoring of a two-stroke electronically controlled ship propulsion engine on the operating envelope. This is achieved by setting up a machine learning model capable of monitoring influential operating parameters and predicting the fuel consumption. Model is tested with different machine learning algorithms, namely linear regression, multilayer perceptron, Support Vector Machines (SVM) and Random Forests (RF). Upon verification of modelling framework and analysing the results in order to improve the prediction accuracy, the best algorithm is selected based on standard evaluation metrics, i.e. Root Mean Square Error (RMSE) and Relative Absolute Error (RAE). Experimental results show that, by taking an adequate combination and processing of relevant sensory data, SVM exhibit the lowest RMSE 7.1032 and RAE 0.5313%. RF achieve the lowest RMSE 22.6137 and RAE 3.8545% in a setting when minimal number of input variables is considered, i.e. cylinder indicated pressures and propulsion engine revolutions. Further, article deals with the detection of anomalies of operating parameters, which enables the evaluation of the propulsion engine condition and the early identification of failures and deterioration. Such a time-dependent, self-adopting anomaly detection model can be used for comparison with the initial condition recorded during the test and sea run or after survey and docking. Finally, we propose a unified model structure, incorporating fuel consumption prediction and anomaly detection model with on-board decision-making process regarding navigation and maintenance.

scholarly journals Lightweight Anomaly Detection Scheme Using Incremental Principal Component Analysis and Support Vector Machine

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 8017
Author(s):  
Nurfazrina M. Zamry ◽  
Anazida Zainal ◽  
Murad A. Rassam ◽  
Eman H. Alkhammash ◽  
Fuad A. Ghaleb ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Support Vector Machine ◽  
Sensor Networks ◽  
Computational Complexity ◽  
Anomaly Detection ◽  
Principal Component ◽  
Support Vector ◽  
Communication Overhead ◽  
Detection Scheme ◽  
Memory Utilization

Wireless Sensors Networks have been the focus of significant attention from research and development due to their applications of collecting data from various fields such as smart cities, power grids, transportation systems, medical sectors, military, and rural areas. Accurate and reliable measurements for insightful data analysis and decision-making are the ultimate goals of sensor networks for critical domains. However, the raw data collected by WSNs usually are not reliable and inaccurate due to the imperfect nature of WSNs. Identifying misbehaviours or anomalies in the network is important for providing reliable and secure functioning of the network. However, due to resource constraints, a lightweight detection scheme is a major design challenge in sensor networks. This paper aims at designing and developing a lightweight anomaly detection scheme to improve efficiency in terms of reducing the computational complexity and communication and improving memory utilization overhead while maintaining high accuracy. To achieve this aim, one-class learning and dimension reduction concepts were used in the design. The One-Class Support Vector Machine (OCSVM) with hyper-ellipsoid variance was used for anomaly detection due to its advantage in classifying unlabelled and multivariate data. Various One-Class Support Vector Machine formulations have been investigated and Centred-Ellipsoid has been adopted in this study due to its effectiveness. Centred-Ellipsoid is the most effective kernel among studies formulations. To decrease the computational complexity and improve memory utilization, the dimensions of the data were reduced using the Candid Covariance-Free Incremental Principal Component Analysis (CCIPCA) algorithm. Extensive experiments were conducted to evaluate the proposed lightweight anomaly detection scheme. Results in terms of detection accuracy, memory utilization, computational complexity, and communication overhead show that the proposed scheme is effective and efficient compared few existing schemes evaluated. The proposed anomaly detection scheme achieved the accuracy higher than 98%, with (𝑛𝑑) memory utilization and no communication overhead.

Physical-oriented and machine learning-based emission modeling in a diesel compression ignition engine: Dimensionality reduction and regression

2022 ◽  
pp. 146808742110707
Author(s):  
Aran Mohammad ◽  
Reza Rezaei ◽  
Christopher Hayduk ◽  
Thaddaeus Delebinski ◽  
Saeid Shahpouri ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Support Vector Machine ◽  
Factor Analysis ◽  
Dimensionality Reduction ◽  
Principal Component ◽  
Component Analysis ◽  
Data Driven ◽  
Support Vector ◽  
Emission Models ◽  
Emission Modeling

The development of internal combustion engines is affected by the exhaust gas emissions legislation and the striving to increase performance. This demands for engine-out emission models that can be used for engine optimization for real driving emission controls. The prediction capability of physically and data-driven engine-out emission models is influenced by the system inputs, which are specified by the user and can lead to an improved accuracy with increasing number of inputs. Thereby the occurrence of irrelevant inputs becomes more probable, which have a low functional relation to the emissions and can lead to overfitting. Alternatively, data-driven methods can be used to detect irrelevant and redundant inputs. In this work, thermodynamic states are modeled based on 772 stationary measured test bench data from a commercial vehicle diesel engine. Afterward, 37 measured and modeled variables are led into a data-driven dimensionality reduction. For this purpose, approaches of supervised learning, such as lasso regression and linear support vector machine, and unsupervised learning methods like principal component analysis and factor analysis are applied to select and extract the relevant features. The selected and extracted features are used for regression by the support vector machine and the feedforward neural network to model the NOx, CO, HC, and soot emissions. This enables an evaluation of the modeling accuracy as a result of the dimensionality reduction. Using the methods in this work, the 37 variables are reduced to 25, 22, 11, and 16 inputs for NOx, CO, HC, and soot emission modeling while maintaining the accuracy. The features selected using the lasso algorithm provide more accurate learning of the regression models than the extracted features through principal component analysis and factor analysis. This results in test errors RMSETe for modeling NOx, CO, HC, and soot emissions 19.22 ppm, 6.46 ppm, 1.29 ppm, and 0.06 FSN, respectively.

scholarly journals Anomaly detection and event mining in cold forming manufacturing processes

2020 ◽  
Author(s):  
Diego Nieves Avendano ◽  
Daniel Caljouw ◽  
Dirk Deschrijver ◽  
Sofie Van Hoecke
Keyword(s):  
Anomaly Detection ◽  
Missing Values ◽  
Acoustic Emissions ◽  
Irregular Sampling ◽  
Predictive Maintenance ◽  
Data Driven ◽  
Normal Operation ◽  
Cold Forming ◽  
Event Prediction ◽  
Event Mining

Abstract Predictive maintenance is one of the main goals within the Industry 4.0 trend. Advances in data-driven techniques offer new opportunities in terms of cost reduction, improved quality control, and increased work safety. This work brings data-driven techniques for two predictive maintenance tasks: anomaly detection and event prediction, applied in the real-world use case of a cold forming manufacturing line for consumer lifestyle products by using acoustic emissions sensors in proximity of the dies of the press module. The proposed models are robust and able to cope with problems such as noise, missing values, and irregular sampling. The detected anomalies are investigated by experts and confirmed to correspond to deviations in the normal operation of the machine. Moreover, we are able to find patterns which are related to the events of interest.

scholarly journals Multi-step streamflow forecasting using data-driven non-linear methods in contrasting climate regimes

2013 ◽  
Vol 16 (3) ◽  
pp. 671-689 ◽  
Author(s):  
Daniel J. Karran ◽  
Efrat Morin ◽  
Jan Adamowski
Keyword(s):  
Wavelet Transforms ◽  
Model Performance ◽  
Probability Of Detection ◽  
Data Driven ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Lead Times ◽  
Streamflow Forecasting ◽  
Non Linear ◽  
Using Data

Considering the popularity of using data-driven non-linear methods for forecasting streamflow, there has been no exploration of how well such models perform in climate regimes with differing hydrological characteristics, nor has the performance of these models, coupled with wavelet transforms, been compared for lead times of less than 1 month. This study compares the use of four different models, namely artificial neural networks (ANNs), support vector regression (SVR), wavelet-ANN, and wavelet-SVR in a Mediterranean, Oceanic, and Hemiboreal watershed. Model performance was tested for 1, 2 and 3 day forecasting lead times, measured by fractional standard error, the coefficient of determination, Nash–Sutcliffe model efficiency, multiplicative bias, probability of detection and false alarm rate. SVR based models performed best overall, but no one model outperformed the others in more than one watershed, suggesting that some models may be more suitable for certain types of data. Overall model performance varied greatly between climate regimes, suggesting that higher persistence and slower hydrological processes (i.e. snowmelt, glacial runoff, and subsurface flow) support reliable forecasting using daily and multi-day lead times.

Sign in / Sign up

Export Citation Format

Share Document