Wyniki wyszukiwania - Biblioteka Nauki

1

Analysis and prediction of leak detection in the low-pressure heat treatment of metal equipment

100%

Kłos S. , Patalas-Maliszewska J. , Bazel M.

Eksploatacja i Niezawodność

|

2022

|

tom Vol. 24, no. 4

719--727

EN

The low-pressure heat treatment of metals enables the continuous improvement of the mechanical and plastic properties of products, such as hardness, abrasion resistance, etc. A significant problem related to the operation of vacuum furnaces for heat treatment is that they become unsealed during operation, resulting from the degradation of seals or the thermal expansion of the construction materials. Therefore, research was undertaken to develop a prediction model for detecting leaks in vacuum furnaces, the use of which will reduce the risk of degradation in the charge being processed. Unique experimental studies were carried out to detect leakages in a vacuum pit furnace, simulated using the ENV 116 reference slot. As a consequence, a prediction model for the detection of leaks in vacuum furnaces- which are used in the heat treatment of metals- was designed, using an artificial neural network. (93% for MLP 15-10-1) was developed. The model was implemented in a predictive maintenance system, in a real production company, as an element in the monitoring of the operation of vacuum furnaces.

2

A data-driven predictive maintenance strategy based on accurate failure prognostics

100%

Chen C. , Wang C. , Lu N. , Jiang B. , Xing Y.

|

tom Vol. 23, no. 2

387--394

EN

Maintenance is fundamental to ensure the safety, reliability and availability of engineering systems, and predictive maintenance is the leading one in maintenance technology. This paper aims to develop a novel data-driven predictive maintenance strategy that can make appropriate maintenance decisions for repairable complex engineering systems. The proposed strategy includes degradation feature selection and degradation prognostic modeling modules to achieve accurate failure prognostics. For maintenance decision-making, the perfect time for taking maintenance activities is determined by evaluating the maintenance cost online that has taken into account of the failure prognostic results of performance degradation. The feasibility and effectiveness of the proposed strategy is confirmed using the NASA data set of aero-engines. Results show that the proposed strategy outperforms the two benchmark maintenance strategies: classical periodic maintenance and emerging dynamic predictive maintenance.

3

A comparision of model and signal based condition monitoring and mode separation for predictive maintenance of feed drives

100%

Maier D. , Heisel U.

|

tom Vol. 11, No. 4

138--151

EN

Modern production strategies increase the demand for closer monitoring of the machine's condition. Especially wear affects its condition. This paper deals with the methodology of condition monitoring that can be based on different sources of data such as controller NC CNC and additional sensors. Two main methods for assessment are signal analysis based exclusively on measurement data and a model based method The latter is based on comparing the simulation of the objects behaviour with the acquired data. Ball screw drives are key elements of machine tools. They considerably contribute to the machine's performance. The paper compares two signal-based wear inducing characteristics and discusses the results. Afterwards a model-based approach is discussed.

4

Predictive Maintenance Sensors Placement by Combinatorial Optimization

100%

Borissova D. I. , Mustakerov I. C. , Doukovska L. A.

|

tom Vol. 58, No. 2

153-158

EN

The strategy of predictive maintenance monitoring is important for successful system damage detection. Maintenance monitoring utilizes dynamic response information to identify the possibility of damage. The basic factors of faults detection analysis are related to properties of the structure under inspection, collect the signals and appropriate signals processing. In vibration control, structures response sensing is limited by the number of sensors or the number of input channels of the data acquisition system. An essential problem in predictive maintenance monitoring is the optimal sensor placement. The paper addresses that problem by using mixed integer linear programming tasks solving. The proposed optimal sensors location approach is based on the difference between sensor information if sensor is present and information calculated by linear interpolation if sensor is not present. The tasks results define the optimal sensors locations for a given number of sensors. The results of chosen sensors locations give as close as possible repeating the curve of structure dynamic response function. The proposed approach is implemented in an algorithm for predictive maintenance and the numerical results indicate that together with intelligent signal processing it could be suitable for practical application.

5

Life cycle costing used for justifying transition to predictive maintenance strategies

100%

Mikler J.

|

tom Vol. 11, No. 4

49--58

EN

As the market imposes constantly increasing levels of reliability and availability of production equipment, it is necessary to shift the focus of maintenance toward predictive strategies. However, as any other investment, implementation of the required condition monitoring systems has to be cost justified. This paper presents a case study showing use of LCC calculations to assess changes of maintenance strategy for a CNC machining centre. It was proven that replacing reactive maintenance tasks with simple condition monitoring and preventive activities results in lower whole life cycle cost of the analysed machining centre.

6

Failure analysis and predictive maintenance of aircraft components

100%

Eliaz N.

Advances in Materials Science

|

2007

|

tom Vol. 7, nr 2(12)

13-25

EN

Implementation of routine condition monitoring techniques, failure analysis protocols and complementary specific research and development (R&D) activities is valuable in preventing failure recurrence. Ferrography is a common technique for condition monitoring, in which small (wear) particles are isolated on a glass slide based upon the interaction between an external magnetic field and the magnetic moments of the particles suspended in a flow stream. Here, the application of ferrography in monitoring the health of aircraft assemblies is reviewed. In addition, several definitions of important terms related to failure analysis are provided, and a recommended failure analysis protocol is discussed. Finally, several case studies of aircraft components that failed due to corrosion-involving mechanisms are summarized, and an example of the application of R&D projects for improved quality assurance and prevention of failure occurrence is given.

7

Research on integrated scheduling of equipment predictive maintenance and production decision based on physical modeling approach

88%

Zhang Q. , Yang L. , Duan J. , Qin J. , Zhou Y.

|

tom Vol. 26, no. 1

art. no. 175409

EN

Equipment performance deteriorates continuously during the production process, which makes it difficult to achieve the expected effect of production decisions made in advance. Predictive maintenance and production decisions integrated scheduling aim to rationalise maintenance activities. It has been extensively researched. However, past studies have assumed that faults obey a specific probability distribution based on historical data. It is difficult to analyse equipment that is brand new into service or has poor historical failure data. Thus, in this paper, we construct a twin model of a device based on a physical modelling approach and tune it to ensure high fidelity of the model. Degradation curves were created based on equipment characteristics and developed maintenance activities.Develop an integrated scheduling model for predictive maintenance and production decisions with the goal of minimising maximum processing time. An improved genetic algorithm is used to solve the problem optimally. Finally, apply a practical scenario to verify the effectiveness of the proposed method.

8

Machine tool ability representation: a review

88%

Sadasivam L. , Archenti A. , Sandberg U.

Journal of Machine Engineering

|

2018

|

tom Vol. 18, No. 2

5--16

EN

Smart manufacturing and predictive maintenance are current trends in the manufacturing industry. However, the holistic understanding of the machine tool health condition in terms of accuracy, functions, process and availability is still unclear. This uncertainty renders the development of models and the data acquisition related to machine tool health condition ineffective. This paper proposes the term machine tool ability as an interconnection between the accuracy, functions, the process and the availability to overcome the lack of the holistic understanding of the machine tool. This will facilitate the further development of qualitative or quantitative methods as well as models. The research highlights the challenges and gaps to understand the machine tool ability.

9

Hybrid feature selection and support vector machine framework for predicting maintenance failures

88%

Tarik M. , Mniai A. , Jebari K.

|

2023

|

tom Vol. 19, no 2

112--124

EN

The main aim of predictive maintenance is to minimize downtime, failure risks and maintenance costs in manufacturing systems. Over the past few years, machine learning methods gained ground with diverse and successful applications in the area of predictive maintenance. This study shows that performing preprocessing techniques such as over¬sampling and feature selection for failure prediction is promising. For instance, to handle imbalanced data, the SMOTE-Tomek method is used. For feature selection, three different methods can be applied: Recursive Feature Elimination, Random Forest and Variance Threshold. The data considered in this paper for simulation are used in literature. They are used to measure aircraft engine sensors to predict engine failures, while the prediction algorithm used is a Support Vector Machine. The results show that classification accuracy can be significantly boosted by using the preprocessing techniques.

10

Application of selected Levy processes for degradation modelling of long range mine belt using real-time data

75%

Vališ D. , Mazurkiewicz D.

|

2018

|

tom Vol. 18, no. 4

1430--1440

EN

When analysing big data generated by a typical diagnostic system, the maintenance operator has to deal with several problems, including a substantial number of data appearing every second. Maintenance systems, especially those in mining industry additionally require the operator to make reliable predictions and decisions under uncertainty. All this create so called information overload problem, which can be solved in data mining with the use of existing data reduction techniques. Unfortunately, with complex mining machinery operating under diverse conditions more advanced approaches are needed. Effective solutions can be found among non-trivial degradation assessment techniques provided which shall be properly applied. This work proposes new methods to modelling specific system degradation and prognosis for system failure occurrence. The approach presented here does not rely on typical statistical assumptions. This paper relates to mathematical modelling of real diagnostic data with the use of selected stochastic processes – types of Wiener process and Ornstein–Uhlenbeck process. The main novelty and contribution is in the specific forms of above mentioned processes, in the ways how the process parameters were estimated and also in realistic correlation of proposed models to the studied system. Simulated and real case results show that the proposed robust functional analysis reduces bias and provides more accurate false fault detection rates, as compared to the previous method. We hope the outcomes provide applicable inputs for more effective principles of system operation, predictive maintenance policy and risk assessment.

11

Intelligent production systems in the era of Industrie 4.0 – changing mindsets and business models

75%

Uhlmann E. , Hohwieler E. , Geisert C.

Journal of Machine Engineering

|

2017

|

tom Vol. 17, No. 2

5--24

EN

Industrie 4.0 has been becoming one of the most challenging topic areas in industrial production engineering within the last decade. The increasing and comprehensive digitization of industrial production processes allows the introduction of innovative data-driven business models using cyber-physical systems (CPS) and Internet of Things (IoT). Efficient and flexible manufacturing of goods assumes that all involved production systems are capable of fulfilling all necessary machining operations in the desired quality. To ensure this, production systems must be able to communicate and interact with machines and humans in a distributed environment, to monitor the wear condition of functionally relevant components, and to self-adapt their behaviour to a given situation. This article gives an overview about the historical development of intelligent production systems in the context of value-adding business models. The focus is on condition monitoring and predictive maintenance in an availability oriented business model. Technical as well as organizational prerequisites for an implementation in the production industry are critically analysed and discussed on the basis of best practice examples. The paper concludes with a summary and an outlook on future research topics that should be addressed.

12

Prosta metoda detekcji cykli odstawy urobku samojezdnych ładowarek łyżkowych

75%

Stefaniak P. , Skoczylas A. , Koperska W.

|

tom nr 2

33--46

PL

W górnictwie podziemnym rud miedzi transport poziomy urobku realizowany jest za pomocą samojezdnych maszyn załadowczo-odstawczych. Przykładowo, w kopalniach rud miedzi KGHM Polska Miedź S.A., gdzie stosowany jest komorowo-filarowy system eksploatacji złoża, odstawa urobku realizowana jest głównie przy współpracy ładowarek łyżkowych i wozów odstawczych. W przypadku krótszych tras odstawy proces ogranicza się już tylko do ładowarek. Obecnie obserwuje się globalny trend w zakresie rozwoju predykcyjnego utrzymania ruchu maszyn górniczych, nawigacji, jak również optymalizacji produkcji z wykorzystaniem przemysłowego internetu rzeczy (ang. Industrial Internet of Things, IIoT). Rozwój analityki w tym zakresie wymaga niestety pełnego wglądu w przebieg pracy maszyny w wyrobiskach górniczych, zapewniający prowadzenie wielowymiarowych analiz do szerszego zrozumienia kontekstów eksploatacji maszyny. W artykule przedstawiono metodę identyfikacji cykli odstawy, jak również składowych podprocesów, realizowanych w każdym pojedynczym cyklu. Zaproponowany algorytm bazuje na użyciu operacji splotu, w celu detekcji skoków obserwowanych w sygnale ciśnienia z siłownika układu hydraulicznego wychyłu łyżki.

EN

In underground mining of cooper ores, horizontal transport of material is performed using self-propelled machines, especially Load-Haul-Dump machines. For example, in KGHM Polska Miedź S.A. underground mines, where room-and-pillar system is used to deposit exploitation, the haulage process is provided by wheel loaders and haul trucks with suitably adjusted operation configuration. In case of shorter haulage routes, only wheel loaders take part in haulage process. Currently, there is observed a global tendency reliant on develop predictive maintenance as well as navigation or production optimization using Industrial Internet of Things (IIoT). Unfortunately, analytics development in this domain requires full insight into machine’s workflow in mining excavations and multivariate analysis in order widely understanding of machine operating contexts. In this article, a quick method to haulage cycle identification on example of wheel loader has been proposed. Developed algorithm is based on hydraulic pressure signal segmentation which provides to recognize loading operation, haulage and return of machine to mining face after unloading material in dumping point. The method is based on smooth hydraulic pressure signal in order to reduce signal interference but introduce to apply a convolution of smoothed signal with inverted step function. The advantage of the algorithm is its simplicity, high accuracy, robustness and low algorithmic complexity.

13

Predicting length of fatigue cracks by means of machine learning algorithms in the small-data regime

75%

Badora M. , Sepe M. , Bielecki M. , Graziano A. , Szolc T.

|

tom Vol. 23, no. 3

575--585

EN

In this paper several statistical learning algorithms are used to predict the maximal length of fatigue cracks based on a sample composed of 31 observations. The small-data regime is still a problem for many professionals, especially in the areas where failures occur rarely. The analyzed object is a high-pressure Nozzle of a heavy-duty gas turbine. Operating parameters of the engines are used for the regression analysis. The following algorithms are used in this work: multiple linear and polynomial regression, random forest, kernel-based methods, AdaBoost and extreme gradient boosting and artificial neural networks. A substantial part of the paper provides advice on the effective selection of features. The paper explains how to process the dataset in order to reduce uncertainty; thus, simplifying the analysis of the results. The proposed loss and cost functions are custom and promote solutions accurately predicting the longest cracks. The obtained results confirm that some of the algorithms can accurately predict maximal lengths of the fatigue cracks, even if the sample is small.

14

Bariery i szanse implementacji utrzymania predykcyjnego budynków dworcowych

63%

Gajzler M.

|

tom R. 79, nr 11-12

678--683

PL

W artykule poruszono tematykę możliwości wdrożenia utrzymania predykcyjnego budynków dworcowych pod kątem zapewnienia ich niezawodności poprzez utrzymanie należytego stanu technicznego bez wprowadzania ograniczeń w korzystaniu. Omówiono podstawowe strategie utrzymania budynków, w tym zwrócono uwagę na obowiązki wynikające z rygorów prawnych. Na podstawie obserwacji przypadków budynków dworcowych stwierdzono brak wystarczającej infrastruktury sensorycznej do pełnej implementacji utrzymania predykcyjnego. Oprócz tego rozważono możliwości zastosowania rozwiązań umożliwiających implementację podejścia predykcyjnego. Jako alternatywę, w szczególności rozwiązanie pozwalające na akwizycję informacji i danych, przedstawiono własne podejście umożliwiające wspomaganie zarządzania technicznego na podstawie utrzymania predykcyjnego.

EN

The article discusses the possibility of implementing predictive maintenance of station buildings in terms of ensuring their reliability by maintaining proper technical condition without introducing restrictions on use. Basic building maintenance strategies were discussed, including the obligations arising from legal requirements. Based on observations of railway station buildings, it was found that there is no sufficient sensory infrastructure to fully implement predictive maintenance. In addition, potential possibilities of using solutions enabling the implementation of a predictive approach were considered. As an alternative, in particular a solution enabling the acquisition of information and data, an own approach was presented to support technical management based on predictive maintenance.

15

Przetwarzanie danych w Centrum Diagnostyki PKP Polskie Linie Kolejowe S.A. – nowe inicjatywy

63%

Madej L. , Gołąbek P.

|

tom Nr 1(115)

59--73

PL

Burzliwy rozwój technologii informatycznych pozwala na pozyskiwanie, przetwarzanie i automatyczną analizę wielkich ilości danych diagnostycznych. Umożliwia to realizację optymalnych pod względem efektywności i kosztu strategii utrzymania infrastruktury kolejowej. Centrum Diagnostyki PKP Polskie Linie Kolejowe S.A. utrzymuje obszerny zbiór danych diagnostycznych i podejmuje działania ku przekształceniu go w wydajną bazę do działań analitycznych, zgodnie ze współczesnymi trendami, znanymi pod hasłem Big Data Analytics. Częścią aktywności w tym zakresie jest pozyskiwanie nowych źródeł danych diagnostycznych. Przykładem jest projekt pilotażowy wdrożenia sieci autonomicznych sensorów bezprzewodowych do monitorowania temperatury szyn. Artykuł opisuje podjęte i planowane działanie wraz z koniecznym kontekstem technologicznym.

EN

Fierce development of IT sector allows for an effective acquisition, processing and automatic analysis of large volumes of diagnostic data. This in turn brings in the possibility of implementing an optimal strategy for railway infrastructure maintenance in terms of both effectiveness and operational costs. The Center for Diagnostics, PKP Polskie Linie Kolejowe S.A. maintains a large database of diagnostic data and puts an effort toward transforming this data set into effective and consistent platform of data analysis according to current trend called Big Data Analytics. A part of an effort in this field is extending the database with new diagnostic data sets. The recent example of such activity is a drive test project of implementing a wireless sensor network for rail temperature monitoring. The undertaken and planned initiatives along with necessary technological context have been described in the paper.

16

Predictive management in the context of industry 4.0

63%

Krynke M.

|

2021

|

tom Vol. 3, Iss. 1

41--52

EN

The article presents information on the potential of Industry 4.0 in the field of maintenance. This work explores the potential and trends of predictive maintenance management in an industrial big data environment. The development of predictive maintenance, its technical challenges and in the context of Industry 4.0 was presented. In addition, a case study that illustrates how maintenance management and predictive maintenance can be applied to the maintenance of wind turbines is discussed.

17

Przegląd metod monitorowania stanu technicznego tranzystorów mocy

63%

Śleszyński W.

|

tom R. 90, nr 6

143--148

PL

W artykule przedstawiono kilka metod monitorowania stanu technicznego tranzystorów mocy, które są lub mogą być wbudowane w układy przekształtnikowe. Celem artykułu jest określenie aktualnego stanu badań na ten temat. Prezentowane metody przeznaczone są do monitorowania istotnych objawów starzenia modułów mocy: rozwarstwiania struktury modułu na skutek termomechanicznego zmęczenia stopu lutowniczego, uszkodzeń połączeń drutowych wewnątrz modułu oraz degradacji izolacji bramkowej.

EN

This paper presents several methods for condition monitoring of power transistors that are or can be embedded in power converters. The aim of this article is to determine the current state of research on that subject. The presented methods are designed to monitor important ageing effects encountered in power modules: structure delamination as a result of thermomechanical solder fatigue, wire-bond lift-off and gate insulation degradation.

18

Utrzymanie predykcyjne w budownictwie - szanse i bariery implementacji

63%

Gajzler M.

|

tom nr 12

101--103

PL

W artykule zdefiniowano pojęcie utrzymania predykcyjnego. Na podstawie doświadczeń z jego stosowania w produkcji omówiono koncepcję utrzymania predykcyjnego w budownictwie. W tym celu wykorzystano założenia systemu wspomagania zarządzania technicznego. Dokonano analizy szans i barier systemu z punktu widzenia jego tworzenia i zastosowania. Na tej podstawie sformułowano wnioski wskazujące na zasadność budowy systemu wykorzystującego podejście utrzymania predykcyjnego i jego stosowanie.

EN

The article defines the concept of predictive maintenance. Basis of experience from its use in production, the concept of predictive maintenance in construction was discussed. For this purpose, the assumptions of technical management support system were used. An analysis of the opportunities and barriers of the system from the point of view of its creation and application was made. On this basis, conclusions were formulated indicating the reason of building a system using approach of predictive maintenance and its application.

19

Recurrent Neural Networks for Predictive Maintenance of Mill Fan Systems

63%

Koprinkova-Hristova P. D. , Hadjiski M. B. , Doukovska L. A. , Beloreshki S. V.

|

tom Vol. 57, No. 3

401-406

EN

In the present paper we focus on online monitoring system for predictive maintenance based on sensor automated inputs. Our subject was a device from Maritsa East 2 power plant - a mill fan. The main sensor information we have access to is based on the vibration of the nearest to the mill rotor bearing block. Our aim was to create a (nonlinear) model able to predict on time possible changes in vibrations tendencies that can be early signal for system work deterioration. For that purpose, we compared two types of recurrent neural networks: historical Elman architecture and a recently developed kind of RNN named Echo stet networks (ESN). The preliminary investigations showed better approximation and faster training abilities of ESN in comparison to the Elman network. Direction of future work will be increasing of predications time horizon and inclusion of our predictor at lower level of a complex predictive maintenance system.

20

Performance comparison of machine learning algotihms for predictive maintenance

63%

Gęca J.

|

tom T. 10, nr 3

32--35

EN

The consequences of failures and unscheduled maintenance are the reasons why engineers have been trying to increase the reliability of industrial equipment for years. In modern solutions, predictive maintenance is a frequently used method. It allows to forecast failures and alert about their possibility. This paper presents a summary of the machine learning algorithms that can be used in predictive maintenance and comparison of their performance. The analysis was made on the basis of data set from Microsoft Azure AI Gallery. The paper presents a comprehensive approach to the issue including feature engineering, preprocessing, dimensionality reduction techniques, as well as tuning of model parameters in order to obtain the highest possible performance. The conducted research allowed to conclude that in the analysed case, the best algorithm achieved 99.92% accuracy out of over 122 thousand test data records. In conclusion, predictive maintenance based on machine learning represents the future of machine reliability in industry.

PL

Skutki związane z awariami oraz niezaplanowaną konserwacją to powody, dla których od lat inżynierowie próbują zwiększyć niezawodność osprzętu przemysłowego. W nowoczesnych rozwiązaniach obok tradycyjnych metod stosowana jest również tzw. konserwacja predykcyjna, która pozwala przewidywać awarie i alarmować o możliwości ich powstawania. W niniejszej pracy przedstawiono zestawienie algorytmów uczenia maszynowego, które można zastosować w konserwacji predykcyjnej oraz porównanie ich skuteczności. Analizy dokonano na podstawie zbioru danych Azure AI Gallery udostępnionych przez firmę Microsoft. Praca przedstawia kompleksowe podejście do analizowanego zagadnienia uwzględniające wydobywanie cech charakterystycznych, wstępne przygotowanie danych, zastosowanie technik redukcji wymiarowości, a także dostrajanie parametrów poszczególnych modeli w celu uzyskania najwyższej możliwej skuteczności. Przeprowadzone badania pozwoliły wskazać najlepszy algorytm, który uzyskał dokładność na poziomie 99,92%, spośród ponad 122 tys. rekordów danych testowych. Na podstawie tego można stwierdzić, że konserwacja predykcyjna prowadzona w oparciu o uczenie maszynowe stanowi przyszłość w zakresie podniesienia niezawodności maszyn w przemyśle.