Maintenance Prediction through Sensing Using Hidden Markov Models—A Case Study

Martins, Alexandre; Fonseca, Inácio; Farinha, José Torres; Reis, João; Cardoso, António J. Marques

doi:10.3390/app11167685

Cited by 16 publications

(8 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [46] proposed an approach to perform a prognosis of rotating equipment's health using wavelet transform (WT), a principal component analysis (PCA) and artificial neural networks (ANN) to classify the failure and predict the condition of components, equipment and machines. Martins et al [47] showed how it was possible to classify the health condition of equipment via an HMM with multivariate analysis. Yu [48] proposed an adaptive HMM method that evolved over time to detect equipment failures and component degradation monitoring.…”

Section: Related Workmentioning

confidence: 99%

Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models

et al. 2023

Self Cite

View full text Add to dashboard Cite

The maintenance paradigm has evolved over the last few years and companies that want to remain competitive in the market need to provide condition-based maintenance (CBM). The diagnosis and prognosis of the health status of equipment, predictive maintenance (PdM), are fundamental strategies to perform informed maintenance, increasing the company’s profit. This article aims to present a diagnosis and prognosis methodology using a hidden Markov model (HMM) classifier to recognise the equipment status in real time and a deep neural network (DNN), specifically a gated recurrent unit (GRU), to determine this same status in a future of one week. The data collected by the sensors go through several phases, starting by cleaning them. After that, temporal windows are created in order to generate statistical features of the time domain to better understand the equipment’s behaviour. These features go through a normalisation to produce inputs for a feature extraction process, via a principal component analysis (PCA). After the dimensional reduction and obtaining new features with more information, a clustering is performed by the K-means algorithm, in order to group similar data. These clusters enter the HMM classifier as observable states. After training using the Baum–Welch algorithm, the Viterbi algorithm is used to find the best path of hidden states that represent the diagnosis of the equipment, containing three states: state 1—“State of Good Operation”; state 2—“Warning State”; state 3—“Failure State”. Once the equipment diagnosis is complete, the GRU model is used to predict the future, both of the observable states as well as the hidden states coming out from the HMM. Thus, through this network, it is possible to directly obtain the health states 7 days ahead, without the necessity to run the whole methodology from scratch.

show abstract

Section: Related Workmentioning

confidence: 99%

Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Monitoring the condition of engine oil, understood as a type of preventive maintenance, allows fleet managers to make appropriate decisions before a failure occurs based on the data obtained, their detailed analysis using computer tools, and the detection of change trends [23][24][25][26]. Laboratory methods allow for obtaining detailed information on the physico-chemical properties of lubricating oil.…”

Section: Introductionmentioning

confidence: 99%

Engine Oil Degradation in the Real-World Bus Fleet Test Based on Two Consecutive Operational Intervals

Gołębiowski,

Wolak,

Šarkan

2024

Lubricants

View full text Add to dashboard Cite

The literature on the subject and the results of numerous research experiments indicate that single replacement cycles do not reflect the actual state of oil quality in the context of its degradation. Monitoring the operational quality of the oil in several successive stages allows for a more accurate diagnosis of the optimal oil change time. Therefore, it was decided to investigate the relationship between two consecutive periods of changing the operating oil in an engine. Comparative tests of seven buses included in the fleet were carried out. An important division criterion was taken into account—the operation of city and intercity buses. The HDXRF instrumental chemical analysis method was used to determine changes in the content of abrasive metals, and additives in engine oils. Additionally, the oxidation, nitration, sulfonation, and soot content were assessed using infrared spectroscopy (FTIR) based on the ASTM E2414-10 standard and kinematic viscosity at 40 °C and 100 °C using a Stabinger viscometer according to ASTM D7042. The course of these changes was analyzed in terms of their dynamics. The comparative study aimed to identify trends and sources of differences between the tested oils, as well as to demonstrate the number of exceedances of limit values for the selected parameters.

show abstract

“…By utilizing technologies like Neural Networks for modeling pavement performance in order to improve sustainability [15], companies basically expect to have the highest production while utilizing the fewest resources. For this to happen, it is important that assets have predictive maintenance policies to increase their availability [16][17][18][19].…”

Section: Introduction 1frameworkmentioning

confidence: 99%

Measuring the Performance of a Strategic Asset Management Plan through a Balanced Scorecard

de-Almeida-e-Pais,

Raposo,

Farinha

et al. 2023

Sustainability

Self Cite

View full text Add to dashboard Cite

The purpose of this paper is to propose a tool to measure the performance of a Strategic Asset Management Plan (SAMP) based on a Balanced Scorecard (BSC). The SAMP converts organizational objectives into asset management objectives, as well as specifies the role of the asset management system, providing support to achieve asset management objectives. The SAMP becomes the heart of the organization and integrates the long-term, medium-term, and short-term plans. In the SAMP, the balance among performance, costs, and risks are taken into consideration in order to achieve the organization’s objectives. On the other hand, the SAMP is a guide to set the asset management objectives while describing the role of the Asset Management System (AMS) in meeting these objectives. Since the SAMP is the central figure of AMS, it is important to measure its performance and should be built and improved through an iterative process. This indicates that it is not just a document, it is “the document” that should be treated as a “living being”, which needs to adapt to internal and external changes quickly. The BSC is an excellent tool where, through the appropriate Key Performance Indicators (KPIs), the progress can be measured, and is supported by four perspectives: Financial, Customer, Internal Business Process, and Learning and Growth.

show abstract

Maintenance Prediction through Sensing Using Hidden Markov Models—A Case Study

Cited by 16 publications

References 54 publications

Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models

Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models

Engine Oil Degradation in the Real-World Bus Fleet Test Based on Two Consecutive Operational Intervals

Measuring the Performance of a Strategic Asset Management Plan through a Balanced Scorecard

Contact Info

Product

Resources

About