Design for Manufacturing and Assembly (DFMA) of a Test Bench to Simulate Mechanical Vibrations in Rotating Equipment

2017 ◽  
Author(s):  
Jessica Gissella Maradey Lázaro ◽  
Carlos Adolfo Forero González ◽  
Germán Andrés Ovalle Silva
Keyword(s):  
Test Bench ◽  
Design For Manufacturing ◽  
Normal Operation ◽  
Industrial Processes ◽  
Premature Failure ◽  
Detection Systems ◽  
Wear And Tear ◽  
On Line ◽  
Rotary Equipment ◽  
Great Damage

In the last decade, the reliability and safety of industrial processes have played a very important role in ensuring competitiveness of national and international companies, requiring on-line and off-line fault detection systems that appear in normal operation, and in other cases, the implementation of more robust methodologies for potential failures. Two of the problems that usually occur in the rotary equipment are the mechanical misalignment and imbalance caused mainly by errors in the assembly, non-uniformity in the density of the material, tolerance in the manufacture of parts, which cause great damage in the machines and generating vibrations that cause problems such as heating parts, increased hot oil, increased lubricant dripping through seals, premature failure of bearings, seals, shafts and joints, wear and tear of parts, loss of efficiency in the engine, noise and collateral damage among others. The results of this research provide guidelines for the design, manufacturing and assembly of a test bench to simulate misalignment and imbalance failures under controlled conditions by measuring and monitoring selected variables for study, take into account the benefits of Maintenance Condition Monitoring (CBM) and Design for Manufacturing and Assembly (DFMA) methodology.

Research on On-Line Anti-Icing Technology for Carenary along Electrified Railway

2013 ◽  
Vol 676 ◽  
pp. 321-324
Author(s):  
Lei Guo ◽  
Qun Zhan Li
Keyword(s):  
Simulation Model ◽  
Heat Balance ◽  
Normal Operation ◽  
Balance Equations ◽  
Model Based ◽  
Static Var Generator ◽  
On Line ◽  
Electrified Railway ◽  
The Heat Balance

Accidents of icing on catenary have great impacts on normal operation of trains. An on-line anti-icing technology used static var generator (SVG) for catenary was proposed, which can prevent icing formation without interrupting trains normal operation. The heat balance equations for catenary were solved, whose results were compared with data provided by TB/T 3111 and testing show the equation was correct. The simulation model based on Matlab was bulit , whose results and analysis show the correctness of the method.

scholarly journals Identification of abnormal tribological regimes using a microphone and semi-supervised machine-learning algorithm

Friction ◽  
2021 ◽  
Author(s):  
Vigneashwara Pandiyan ◽  
Josef Prost ◽  
Georg Vorlaufer ◽  
Markus Varga ◽  
Kilian Wasmer
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Industrial Applications ◽  
Supervised Machine Learning ◽  
Normal Operation ◽  
Promising Alternative ◽  
Wear And Tear ◽  
Validation Procedure ◽  
And Performance

AbstractFunctional surfaces in relative contact and motion are prone to wear and tear, resulting in loss of efficiency and performance of the workpieces/machines. Wear occurs in the form of adhesion, abrasion, scuffing, galling, and scoring between contacts. However, the rate of the wear phenomenon depends primarily on the physical properties and the surrounding environment. Monitoring the integrity of surfaces by offline inspections leads to significant wasted machine time. A potential alternate option to offline inspection currently practiced in industries is the analysis of sensors signatures capable of capturing the wear state and correlating it with the wear phenomenon, followed by in situ classification using a state-of-the-art machine learning (ML) algorithm. Though this technique is better than offline inspection, it possesses inherent disadvantages for training the ML models. Ideally, supervised training of ML models requires the datasets considered for the classification to be of equal weightage to avoid biasing. The collection of such a dataset is very cumbersome and expensive in practice, as in real industrial applications, the malfunction period is minimal compared to normal operation. Furthermore, classification models would not classify new wear phenomena from the normal regime if they are unfamiliar. As a promising alternative, in this work, we propose a methodology able to differentiate the abnormal regimes, i.e., wear phenomenon regimes, from the normal regime. This is carried out by familiarizing the ML algorithms only with the distribution of the acoustic emission (AE) signals captured using a microphone related to the normal regime. As a result, the ML algorithms would be able to detect whether some overlaps exist with the learnt distributions when a new, unseen signal arrives. To achieve this goal, a generative convolutional neural network (CNN) architecture based on variational auto encoder (VAE) is built and trained. During the validation procedure of the proposed CNN architectures, we were capable of identifying acoustics signals corresponding to the normal and abnormal wear regime with an accuracy of 97% and 80%. Hence, our approach shows very promising results for in situ and real-time condition monitoring or even wear prediction in tribological applications.

Experiences With On-Line Explosive De-Slagging at Covanta WTE Facilities

2007 ◽  
Author(s):  
Jeff Vorfeld
Keyword(s):  
Flue Gas ◽  
Boiler House ◽  
Video Camera ◽  
Fugitive Dust ◽  
Close Proximity ◽  
Wear And Tear ◽  
On Line ◽  
Explosive Charges ◽  
Camera Surveillance

An on-line cleaning technique perfected in Europe, which places low-yield explosive charges in close proximity to tube lane pluggage, and uses pre- and post-cleaning video camera surveillance to document results, has been tested at three WTE facilities in the western U.S. operated by Covanta. Testing indicates several tangible benefits relative to the more traditional off-line blasting, water washing (on-line and off-line), and stick blasting (on-line), including: • substantial elimination of cleaning related downtime between maintenance outages; • longer runtimes with less overall fouling and pluggage related ailments; • reduced off-line cleaning time at the beginning of major outages to the benefit of the outage schedule; • exemplary safety of the on-line cleaning process; • less wear and tear on pressure parts and boiler casings; and, • almost no fugitive dust problems in the boiler house that may occur with off-line blasting. The process starts with an initial video survey of fouling conditions. A water-cooled camera with purge air and temperature monitoring is inserted into the flue gas to record the fouling condition of the boiler. Following the survey, a cleaning plan is developed. Shots consist of low-yield detonating cord encased in thin gage aluminum alloy tubing. The charges are positioned in the gas lanes between tubes while being cooled with a water-air mixture and detonated. Following the cleaning effort, a final camera survey is done to verify the cleaning effectiveness, and to follow up with touch-up cleaning if necessary.

Generalized Evidential Processing in Multiple Simultaneous Threat Detection in UNIX

2012 ◽  
pp. 104-120
Author(s):  
Zafar Sultan ◽  
Paul Kwan
Keyword(s):  
Data Fusion ◽  
Detection System ◽  
Set Cover ◽  
Threat Detection ◽  
Fusion Model ◽  
Detection Systems ◽  
Size Groups ◽  
On Line ◽  
And Performance ◽  
Statistical Data Fusion

In this paper, a hybrid identity fusion model at decision level is proposed for Simultaneous Threat Detection Systems. The hybrid model is comprised of mathematical and statistical data fusion engines; Dempster Shafer, Extended Dempster and Generalized Evidential Processing (GEP). Simultaneous Threat Detection Systems improve threat detection rate by 39%. In terms of efficiency and performance, the comparison of 3 inference engines of the Simultaneous Threat Detection Systems showed that GEP is the better data fusion model. GEP increased precision of threat detection from 56% to 95%. Furthermore, set cover packing was used as a middle tier data fusion tool to discover the reduced size groups of threat data. Set cover provided significant improvement and reduced threat population from 2272 to 295, which helped in minimizing the processing complexity of evidential processing cost and time in determining the combined probability mass of proposed Multiple Simultaneous Threat Detection System. This technique is particularly relevant to on-line and Internet dependent applications including portals.

Sign in / Sign up

Export Citation Format

Share Document