scholarly journals Predictive Maintenance: A Novel Framework for a Data-Driven, Semi-Supervised, and Partially Online Prognostic Health Management Application in Industries

2021 ◽  
Vol 11 (8) ◽  
pp. 3380
Author(s):  
Francesca Calabrese ◽  
Alberto Regattieri ◽  
Marco Bortolini ◽  
Mauro Gamberi ◽  
Francesco Pilati
Keyword(s):  
Health Status ◽  
Health Management ◽  
Novelty Detection ◽  
Point Of View ◽  
Operating Conditions ◽  
Predictive Maintenance ◽  
Prognostic Models ◽  
Cloud Infrastructure ◽  
Initial Application ◽  
Prognostic Health Management

Prognostic Health Management (PHM) is a predictive maintenance strategy, which is based on Condition Monitoring (CM) data and aims to predict the future states of machinery. The existing literature reports the PHM at two levels: methodological and applicative. From the methodological point of view, there are many publications and standards of a PHM system design. From the applicative point of view, many papers address the improvement of techniques adopted for realizing PHM tasks without covering the whole process. In these cases, most applications rely on a large amount of historical data to train models for diagnostic and prognostic purposes. Industries, very often, are not able to obtain these data. Thus, the most adopted approaches, based on batch and off-line analysis, cannot be adopted. In this paper, we present a novel framework and architecture that support the initial application of PHM from the machinery producers’ perspective. The proposed framework is based on an edge-cloud infrastructure that allows performing streaming analysis at the edge to reduce the quantity of the data to store in permanent memory, to know the health status of the machinery at any point in time, and to discover novel and anomalous behaviors. The collection of the data from multiple machines into a cloud server allows training more accurate diagnostic and prognostic models using a higher amount of data, whose results will serve to predict the health status in real-time at the edge. The so-built PHM system would allow industries to monitor and supervise a machinery network placed in different locations and can thus bring several benefits to both machinery producers and users. After a brief literature review of signal processing, feature extraction, diagnostics, and prognostics, including incremental and semi-supervised approaches for anomaly and novelty detection applied to data streams, a case study is presented. It was conducted on data collected from a test rig and shows the potential of the proposed framework in terms of the ability to detect changes in the operating conditions and abrupt faults and storage memory saving. The outcomes of our work, as well as its major novel aspect, is the design of a framework for a PHM system based on specific requirements that directly originate from the industrial field, together with indications on which techniques can be adopted to achieve such goals.

Tertiary Nitrification Pilot Plants on Parisian Waste Water

1990 ◽  
Vol 22 (1-2) ◽  
pp. 347-352 ◽  
Author(s):  
C. Paffoni ◽  
B. Védry ◽  
M. Gousailles
Keyword(s):  
Waste Water ◽  
Metropolitan Area ◽  
Fixed Bed ◽  
Point Of View ◽  
Operating Conditions ◽  
Research Center ◽  
Daily Output ◽  
Practical Point ◽  
Fixed Bed Reactors

The Paris Metropolitan area, which contains over eight million inhabitants, has a daily output of about 3 M cu.meters of wastewater, the purification of which is achieved by SIAAP (Paris Metropolitan Area Sewage Service) in both Achères and Valenton plants. The carbon pollution is eliminated from over 2 M cu.m/day at Achères. In order to improve the quality of output water, its tertiary nitrification in fixed-bed reactors has been contemplated. The BIOFOR (Degremont) and BIOCARBONE (OTV) processes could be tested in semi-industrial pilot reactors at the CRITER research center of SIAAP. At a reference temperature of 13°C, the removed load is approximately 0.5 kg N NH4/m3.day. From a practical point of view, it may be asserted that in such operating conditions as should be at the Achères plant, one cubic meter of filter can handle the tertiary nitification of one cubic meter of purified water per hour at an effluent temperature of 13°C.

scholarly journals Transfer Learning for Prognostics and Health Management (PHM) of Marine Air Compressors

2021 ◽  
Vol 9 (1) ◽  
pp. 47
Author(s):  
Magnus Gribbestad ◽  
Muhammad Umair Hassan ◽  
Ibrahim A. Hameed
Keyword(s):  
Transfer Learning ◽  
Data Transfer ◽  
Health Management ◽  
Correct Diagnosis ◽  
Vital Role ◽  
Research Field ◽  
Remaining Useful Life ◽  
Prognostic Models ◽  
Classification Problems ◽  
Air Compressors

Prognostics is an engineering discipline focused on predicting the time at which a system or a component will no longer perform its intended function. Due to the requirements of system safety and reliability, the correct diagnosis or prognosis of abnormal condition plays a vital role in the maintenance of industrial systems. It is expected that new requirements in regard to autonomous ships will push suppliers of maritime equipment to provide more insight into the conditions of their systems. One of the stated challenges with these systems is having enough run-to-failure examples to build accurate-enough prognostic models. Due to the scarcity of enough reliable data, transfer learning is established as a successful approach to improve and reduce the need to labelled examples. Transfer learning has shown excellent capabilities in image classification problems. Little work has been done to explore and exploit the use of transfer learning in prognostics. In this paper, various deep learning models are used to predict the remaining useful life (RUL) of air compressors. Here, transfer learning is applied by building a separate prognostics model trained on turbofan engines. It has been found that several of the explored transfer learning architectures were able to improve the predictions on air compressors. The research results suggest transfer learning as a promising research field towards more accurate and reliable prognostics.

ADVANCED TYPES OF CHECKERWORK OF REGENERATIVE HEAT EXCHANGERS FOR GLASS FURNACES

2021 ◽  
pp. 3-10
Author(s):  
O. Koshelnik ◽  
S. Hoisan
Keyword(s):  
Phase Transition ◽  
Heat Exchangers ◽  
Heat Storage ◽  
Point Of View ◽  
Operating Conditions ◽  
Flue Gases ◽  
Regenerative Heat ◽  
Exchange Processes ◽  
Glass Furnaces ◽  
Refractory Bricks

One of the ways to increase glass furnaces energy efficiency is to apply heat exchangers for flue gases thermal potential utilization. Flue gases losses is up to 25-40 % of the total amount of heat supplied in the furnace. These losses are influences by such factors as fuel type, furnace and burners design and manufactured product type. Regenerative heat exchangers with various types of heat storage packing is more efficient for high-power furnaces. Such types of regenerator checkerwork as Cowper checkerwork, two types of Siemens checkerwork, Lichte checkerwork and combined checkerwork have already been sufficiently researched, successfully applied and widely used for glass furnaces of various designs. All of its are made of standard refractory bricks. Basket checkerwork and cruciform checkerwork that are made of fused-cast molded refractory materials have been widely used recently as well. Further improvement of regenerative heat exchangers thermal efficiency only by replacing the checkerwork does not seem possible unless their size being increased. But this enlarging is not always realizable during the modernization of existing furnaces. From this point of view heat storage elements with a phase transition, where metal salts and their mixtures are used as a fusible agent look promising for glass furnaces. These elements can accumulate additional amount of heat due to phase transition, which allows to increase significantly heat exchanger thermal rating without its size and operating conditions changing. However, it is necessary to carry out additional studies of this type of checkerwork dealing with analysis of complex unsteady heat exchange processes in regenerators and selection of appropriate materials that satisfy the operating conditions of regenerative heat exchangers so that the checkerwork can be widely used for glass furnaces.

Health Assessment Based on Fuzzy Synthetic Evaluation for Civil Aircrafts

2011 ◽  
Vol 335-336 ◽  
pp. 985-988
Author(s):  
Bao Hui Jia ◽  
Ze Dong Sun
Keyword(s):  
Health Status ◽  
Health Management ◽  
Health Assessment ◽  
Fuzzy Synthetic Evaluation ◽  
Hydraulic Pump ◽  
Quantitative Level ◽  
Key Technologies ◽  
Civil Aircraft ◽  
Evaluation Algorithm ◽  
Synthetic Evaluation

Health assessment is one of the key technologies for civil aircraft health management system. In order to access the health status of components, subsystems and systems of civil aircrafts, this paper explicitly defines the health status, and presents the fuzzy synthetic evaluation algorithm. Then the model of the evaluated object is established to get the health status of quantitative level. Finally, the method is used for health assessment of aircraft hydraulic pump .The results of simulation show the practicability of this method.

scholarly journals Diagnostic and Prognostic Models for Predictive Maintenance: Multi-Criteria Comparative Analysis

2021 ◽  
Vol 11 (10) ◽  
pp. 40-49
Author(s):  
Mohammed Bouaicha ◽  
◽  
Imad El Adraoui ◽  
Nadia Machkour ◽  
Hassan Gziri ◽  
...  
Keyword(s):  
Comparative Analysis ◽  
Predictive Maintenance ◽  
Prognostic Models ◽  
Industrial System ◽  
Single Model ◽  
Mutual Cooperation ◽  
Industrial Systems ◽  
The Past ◽  
Clear Vision ◽  
The Comparative Study

Predictive maintenance has evolved considerably over the past two decades making this strategy an effective way to monitor the operation of industrial systems, thereby predicting its future states and remaining lifespan. It is therefore developed through a process that begins with the collection of information from the industrial system, the objective of which is its diagnosis or / and its prognosis. This article presents an analysis of single-model and multi-model approaches to the effect of diagnostic and prognostic tasks. This analysis is based on a multi-criteria comparison of the different models in order to provide a clear vision to choose the appropriate approach for predictive maintenance. The relevance of the comparative study is argued by the development of criteria directly impacting performance, reliability, efficiency and mutual cooperation between models. Conclusions are then drawn, in order to identify the appropriate diagnostic and prognostic approach for predictive maintenance.

Sign in / Sign up

Export Citation Format

Share Document