A Predictive Maintenance Planning System Implemented on a Web Platform

2020 ◽  
Vol 12 (2) ◽  
pp. 1-21
Author(s):  
Bárbara Romeira ◽  
Ana Moura ◽  
José Paulo Oliveira Santos
Keyword(s):  
Remaining Useful Life ◽  
Operating Conditions ◽  
Predictive Maintenance ◽  
Planning System ◽  
Test Time ◽  
Software Application ◽  
Maintenance Time ◽  
Maintenance Plan ◽  
Plastic Injection ◽  
Web Platform

Predictive maintenance predicts failures and determines the equipment's remaining useful life, which provides maintenance time to plan their interventions, preventing breakdowns or reducing their impact. This paper presents a software application, implemented in a web platform, to support the implementation of a predictive maintenance plan. The developed system currently monitors certain parameters of a plastic injection molding machine. Furthermore, this system has real-time alerts that notify the maintenance team when the measured temperatures are outside the defined limits. Some extras were added, such as the report page, which calculates, automatically, performance indicators, the access management page, and a page that permits the realization of autonomous maintenance interventions, the verification of its fulfilment, and the visualization of the performed interventions' results. After the system's implementation, it was tested in real operating conditions. Following the test time, it was concluded that the desired parameters were measured correctly, which supported the work's continuation.

Prognostics and RUL Estimations of SAC305, SAC105 and SnAg Solders Under Temperature and Vibration Using Long Short-Term Memory (LSTM) Deep Learning

2021 ◽  
Author(s):  
Pradeep Lall ◽  
Tony Thomas ◽  
Ken Blecker
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Short Term Memory ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Short Term ◽  
Term Memory ◽  
Rectangular Pattern ◽  
Useful Life ◽  
Long Short Term Memory

Abstract Prognostics and Remaining Useful Life (RUL) estimations of complex systems are essential to operational safety, increased efficiency, and help to schedule maintenance proactively. Modeling the remaining useful life of a system with many complexities is possible with the rapid development in the field of deep learning as a computational technique for failure prediction. Deep learning can adapt to multivariate parameters complex and nonlinear behavior, which is difficult using traditional time-series models for forecasting and prediction purposes. In this paper, a deep learning approach based on Long Short-Term Memory (LSTM) network is used to predict the remaining useful life of the PCB at different conditions of temperature and vibration. This technique can identify the different underlying patterns in the time series that can predict the RUL. This study involves feature vector identification and RUL estimations for SAC305, SAC105, and Tin Lead solder PCBs under different vibration levels and temperature conditions. The acceleration levels of vibration are fixed at 5g and 10g, while the temperature levels are 55°C and 100°C. The test board is a multilayer FR4 configuration with JEDEC standard dimensions consists of twelve packages arranged in a rectangular pattern. Strain signals are acquired from the backside of the PCB at symmetric locations to identify the failure of all the packages during vibration. The strain signals are resistance values that are acquired simultaneously during the experiment until the failure of most of the packages on the board. The feature vectors are identified from statistical analysis on the strain signals frequency and instantaneous frequency components. The principal component analysis is used as a data reduction technique to identify the different patterns produced from the four strain signals with failures of the packages during vibration. LSTM deep learning method is used to model the RUL of the packages at different individual operating conditions of vibration for all three solder materials involved in this study. A combined model for RUL prediction for a material that can take care of the changes in the operating conditions is also modeled for each material.

scholarly journals A dynamic Bayesian network approach for prognosis computations on discrete state systems

2017 ◽  
Vol 231 (5) ◽  
pp. 516-533 ◽  
Author(s):  
Josquin Foulliaron ◽  
Laurent Bouillaut ◽  
Patrice Aknin ◽  
Anne Barros
Keyword(s):  
Complex Systems ◽  
Bayesian Networks ◽  
Bayesian Network ◽  
Multicomponent System ◽  
Dynamic Bayesian Network ◽  
Dynamic Bayesian Networks ◽  
Remaining Useful Life ◽  
Predictive Maintenance ◽  
Discrete State ◽  
Virtual Maintenance

The maintenance optimization of complex systems is a key question. One important objective is to be able to anticipate future maintenance actions required to optimize the logistic and future investments. That is why, over the past few years, the predictive maintenance approaches have been an expanding area of research. They rely on the concept of prognosis. Many papers have shown how dynamic Bayesian networks can be relevant to represent multicomponent complex systems and carry out reliability studies. The diagnosis and maintenance group from French institute of science and technology for transport, development and networks (IFSTTAR) developed a model (VirMaLab: Virtual Maintenance Laboratory) based on dynamic Bayesian networks in order to model a multicomponent system with its degradation dynamic and its diagnosis and maintenance processes. Its main purpose is to model a maintenance policy to be able to optimize the maintenance parameters due to the use of dynamic Bayesian networks. A discrete state-space system is considered, periodically observable through a diagnosis process. Such systems are common in railway or road infrastructure fields. This article presents a prognosis algorithm whose purpose is to compute the remaining useful life of the system and update this estimation each time a new diagnosis is available. Then, a representation of this algorithm is given as a dynamic Bayesian network in order to be next integrated into the Virtual Maintenance Laboratory model to include the set of predictive maintenance policies. Inference computation questions on the considered dynamic Bayesian networks will be discussed. Finally, an application on simulated data will be presented.

scholarly journals Transfer Learning with Deep Recurrent Neural Networks for Remaining Useful Life Estimation

2018 ◽  
Vol 8 (12) ◽  
pp. 2416 ◽  
Author(s):  
Ansi Zhang ◽  
Honglei Wang ◽  
Shaobo Li ◽  
Yuxin Cui ◽  
Zhonghao Liu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Recurrent Neural Networks ◽  
Prediction Models ◽  
Learning Algorithm ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Training Data ◽  
Good Prediction ◽  
Useful Life

Prognostics, such as remaining useful life (RUL) prediction, is a crucial task in condition-based maintenance. A major challenge in data-driven prognostics is the difficulty of obtaining a sufficient number of samples of failure progression. However, for traditional machine learning methods and deep neural networks, enough training data is a prerequisite to train good prediction models. In this work, we proposed a transfer learning algorithm based on Bi-directional Long Short-Term Memory (BLSTM) recurrent neural networks for RUL estimation, in which the models can be first trained on different but related datasets and then fine-tuned by the target dataset. Extensive experimental results show that transfer learning can in general improve the prediction models on the dataset with a small number of samples. There is one exception that when transferring from multi-type operating conditions to single operating conditions, transfer learning led to a worse result.

Experimental and Analytical Characterization of Alternative Aviation Fuel Sprays Under Realistic Operating Conditions

2018 ◽  
Author(s):  
Andrew Corber ◽  
Nader Rizk ◽  
Wajid Ali Chishty
Keyword(s):  
Experimental Data ◽  
Alternative Fuels ◽  
Laser Sheet ◽  
National Research Council ◽  
Diagnostic System ◽  
Operating Conditions ◽  
Aviation Fuel ◽  
Injection System ◽  
Test Time

The National Jet Fuel Combustion Program (NJFCP) is an initiative, currently being led by the Office of Environment & Energy at the FAA, to streamline the ASTM jet fuels certification process for alternative aviation fuels. In order to accomplish this objective, the program has identified specific applied research tasks in several areas. The National Research Council of Canada (NRC) is contributing to the NJFCP in the areas of sprays and atomization and high altitude engine performance. This paper describes work pertaining to atomization tests using a reference injection system. The work involves characterization of the injection nozzle, comparison of sprays and atomization quality of various conventional and alternative fuels, as well as use of the experimental data to validate spray correlations. The paper also briefly explores the application viability of a new spray diagnostic system that has potential to reduce test time in characterizing sprays. Measurements were made from ambient up to 10 bar pressures in NRC’s High Pressure Spray Facility using optical diagnostics including laser diffraction, phase Doppler anemometry (PDA), LIF/Mie Imaging and laser sheet imaging to assess differences in the atomization characteristics of the test fuels. A total of nine test fluids including six NJFCP fuels and three calibration fluids were used. The experimental data was then used to validate semi-empirical models, developed through years of experience by engine OEMs and modified under NJFCP, for predicting droplet size and distribution. The work offers effective tools for developing advanced fuel injectors, and generating data that can be used to significantly enhance multi-dimensional combustor simulation capabilities.

scholarly journals Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

2021 ◽  
Vol 7 ◽  
pp. e795
Author(s):  
Pooja Vinayak Kamat ◽  
Rekha Sugandhi ◽  
Satish Kumar
Keyword(s):  
Deep Learning ◽  
Anomaly Detection ◽  
Short Term Memory ◽  
Rotating Machinery ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Learning Models ◽  
Vibration Data ◽  
Degradation Data ◽  
Useful Life

Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy functioning of the machinery, however, RUL is ill-defined. To address this issue, this study recommends using anomaly monitoring during both RUL estimator training and operation. Essential time-domain data is extracted from the raw bearing vibration data, and deep learning models are used to detect the onset of the anomaly. This further acts as a trigger for data-driven RUL estimation. The study employs an unsupervised clustering approach for anomaly trend analysis and a semi-supervised method for anomaly detection and RUL estimation. The novel combined deep learning-based anomaly-onset aware RUL estimation framework showed enhanced results on the benchmarked PRONOSTIA bearings dataset under non-varying operating conditions. The framework consisting of Autoencoder and Long Short Term Memory variants achieved an accuracy of over 90% in anomaly detection and RUL prediction. In the future, the framework can be deployed under varying operational situations using the transfer learning approach.

scholarly journals A Study on the Predictive Maintenance Algorithms Considering Load Characteristics of PMSMs to Drive EGR Blowers for Smart Ships

Energies ◽  
2021 ◽  
Vol 14 (18) ◽  
pp. 5744
Author(s):  
Sung-An Kim
Keyword(s):  
Electric Motor ◽  
Nox Reduction ◽  
Operation Time ◽  
Remaining Useful Life ◽  
Predictive Maintenance ◽  
Exhaust Gas ◽  
Electrical Failure ◽  
Information And Communication ◽  
Load Characteristics ◽  
Drive Systems

Exhaust gas recirculation (EGR) is a NOx reduction technology that can meet stringent environmental regulatory requirements. EGR blower systems must be used to increase the exhaust gas pressure at a lower rate than the scavenging air pressure. Electric motor drive systems are essential to rotate the EGR blowers. For the effective management of the EGR blower systems in smart ships, there is a growing need for predictive maintenance technology fused with information and communication technology (ICT). Since an electric motor accounts for about 80% of electric loads driven by the EGR, it is essential to apply the predictive maintenance technology of the electric motor to maximize the reliability and operation time of the EGR blower system. Therefore, this paper presents the predictive maintenance algorithm to prevent the stator winding turn faults, which is the most significant cause of the electrical failure of the electric motors. The proposed algorithm predicts the remaining useful life (RUL) by obtaining the winding temperature value by considering the load characteristics of the electric motor. The validity of the proposed algorithm is verified through the simulation results of an EGR blower system model and the experimental results derived from using a test rig.

Remaining Useful Life Estimation for PEMFC in Dynamic Operating Conditions

2016 ◽  
Author(s):  
Zhongliang Li ◽  
Samir Jemei ◽  
Rafael Gouriveau ◽  
Daniel Hissel ◽  
Noureddine Zerhouni
Keyword(s):  
Remaining Useful Life ◽  
Operating Conditions ◽  
Life Estimation ◽  
Dynamic Operating ◽  
Useful Life

scholarly journals Combining chronicle mining and semantics for predictive maintenance in manufacturing processes

Semantic Web ◽  
2020 ◽  
Vol 11 (6) ◽  
pp. 927-948 ◽  
Author(s):  
Qiushi Cao ◽  
Ahmed Samet ◽  
Cecilia Zanni-Merk ◽  
François de Bertrand de Beuvron ◽  
Christoph Reich
Keyword(s):  
Data Mining ◽  
Hybrid Approach ◽  
Failure Prediction ◽  
Operating Conditions ◽  
Predictive Maintenance ◽  
Semantic Gap ◽  
Manufacturing Processes ◽  
Temporal Constraints ◽  
Industrial Data ◽  
The Future

Within manufacturing processes, faults and failures may cause severe economic loss. With the vision of Industry 4.0, artificial intelligence techniques such as data mining play a crucial role in automatic fault and failure prediction. However, due to the heterogeneous nature of industrial data, data mining results normally lack both machine and human-understandable representation and interpretation of knowledge. This may cause the semantic gap issue, which stands for the incoherence between the knowledge extracted from industrial data and the interpretation of the knowledge from a user. To address this issue, ontology-based approaches have been used to bridge the semantic gap between data mining results and users. However, only a few existing ontology-based approaches provide satisfactory knowledge modeling and representation for all the essential concepts in predictive maintenance. Moreover, most of the existing research works merely focus on the classification of operating conditions of machines, while lacking the extraction of specific temporal information of failure occurrence. This brings obstacles for users to perform maintenance actions with the consideration of temporal constraints. To tackle these challenges, in this paper we introduce a novel hybrid approach to facilitate predictive maintenance tasks in manufacturing processes. The proposed approach is a combination of data mining and semantics, within which chronicle mining is used to predict the future failures of the monitored industrial machinery, and a Manufacturing Predictive Maintenance Ontology (MPMO) with its rule-based extension is used to predict temporal constraints of failures and to represent the predictive results formally. As a result, Semantic Web Rule Language (SWRL) rules are constructed for predicting the occurrence time of machinery failures in the future. The proposed rules provide explicit knowledge representation and semantic enrichment of failure prediction results, thus easing the understanding of the inferred knowledge. A case study on a semi-conductor manufacturing process is used to demonstrate our approach in detail. The evaluation of results shows that the MPMO ontology is free of bad practices in the structural, functional, and usability-profiling dimensions. The constructed SWRL rules posses more than 80% of True Positive Rate, Precision, and F-measure, which shows promising performance in failure prediction.

Sign in / Sign up

Export Citation Format

Share Document