scholarly journals FMECA and MFCC-Based Early Wear Detection in Gear Pumps in Cost-Aware Monitoring Systems

Electronics ◽  
2021 ◽  
Vol 10 (23) ◽  
pp. 2939
Author(s):  
Geon-Hui Lee ◽  
Ugochukwu Ejike Akpudo ◽  
Jang-Wook Hur
Keyword(s):  
Failure Modes ◽  
Fine Particles ◽  
Extraction Process ◽  
Machine Learning Algorithms ◽  
Test Accuracy ◽  
Gear Pump ◽  
Pump Failure ◽  
Vibration Data ◽  
Gear Pumps ◽  
Criticality Analysis

Gear pump failures in industrial settings are common due to their exposure to uneven high-pressure outputs within short time periods of machine operation and uncertainty. Improving the field and line clam are considered as the solutions for these failures, yet they are quite insufficient for optimal reliability. This research, therefore, suggests a method for early wear detection in gear pumps following an extensive failure modes, effects, and criticality analysis (FMECA) of an AP3.5/100 external gear pump manufactured by BESCO. To replicate this condition, fine particles of iron oxide (Fe2O3) were mixed with the experimental fluid, and the resulting vibration data were collected, processed, and exploited for wear detection. The intelligent wear detection process was explored using various machine learning algorithms following a mel-frequency cepstral coefficient (MFCC)-based discriminative feature extraction process. Among these algorithms, extensive performance evaluation reveals that the random forest classifier returned the highest test accuracy of 95.17%, while the k-nearest neighbour was the most cost efficient following cross validations. This study is expected to contribute to improved evaluations of gear pump failure diagnosis and prognostics.

scholarly journals Texture Recognition Based on Perception Data from a Bionic Tactile Sensor

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5224
Author(s):  
Shiyao Huang ◽  
Hao Wu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Learning Algorithms ◽  
Tactile Sensor ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Test Accuracy ◽  
Texture Recognition ◽  
Vibration Data

Texture recognition is important for robots to discern the characteristics of the object surface and adjust grasping and manipulation strategies accordingly. It is still challenging to develop texture classification approaches that are accurate and do not require high computational costs. In this work, we adopt a bionic tactile sensor to collect vibration data while sliding against materials of interest. Under a fixed contact pressure and speed, a total of 1000 sets of vibration data from ten different materials were collected. With the tactile perception data, four types of texture recognition algorithms are proposed. Three machine learning algorithms, including support vector machine, random forest, and K-nearest neighbor, are established for texture recognition. The test accuracy of those three methods are 95%, 94%, 94%, respectively. In the detection process of machine learning algorithms, the asamoto and polyester are easy to be confused with each other. A convolutional neural network is established to further increase the test accuracy to 98.5%. The three machine learning models and convolutional neural network demonstrate high accuracy and excellent robustness.

ANN-Based Relaying Algorithm for Protection of SVC- Compensated AC Transmission Line and Criticality Analysis of a Digital Relay

2020 ◽  
Vol 13 (3) ◽  
pp. 381-393
Author(s):  
Farhana Fayaz ◽  
Gobind Lal Pahuja
Keyword(s):  
Transmission Line ◽  
Failure Modes ◽  
Reactive Power ◽  
Circuit Breaker ◽  
Research Work ◽  
Back Propagation ◽  
Static Var Compensator ◽  
Data Set ◽  
Ac Transmission ◽  
Criticality Analysis

Background:The Static VAR Compensator (SVC) has the capability of improving reliability, operation and control of the transmission system thereby improving the dynamic performance of power system. SVC is a widely used shunt FACTS device, which is an important tool for the reactive power compensation in high voltage AC transmission systems. The transmission lines compensated with the SVC may experience faults and hence need a protection system against the damage caused by these faults as well as provide the uninterrupted supply of power.Methods:The research work reported in the paper is a successful attempt to reduce the time to detect faults on a SVC-compensated transmission line to less than quarter of a cycle. The relay algorithm involves two ANNs, one for detection and the other for classification of faults, including the identification of the faulted phase/phases. RMS (Root Mean Square) values of line voltages and ratios of sequence components of line currents are used as inputs to the ANNs. Extensive training and testing of the two ANNs have been carried out using the data generated by simulating an SVC-compensated transmission line in PSCAD at a signal sampling frequency of 1 kHz. Back-propagation method has been used for the training and testing. Also the criticality analysis of the existing relay and the modified relay has been done using three fault tree importance measures i.e., Fussell-Vesely (FV) Importance, Risk Achievement Worth (RAW) and Risk Reduction Worth (RRW).Results:It is found that the relay detects any type of fault occurring anywhere on the line with 100% accuracy within a short time of 4 ms. It also classifies the type of the fault and indicates the faulted phase or phases, as the case may be, with 100% accuracy within 15 ms, that is well before a circuit breaker can clear the fault. As demonstrated, fault detection and classification by the use of ANNs is reliable and accurate when a large data set is available for training. The results from the criticality analysis show that the criticality ranking varies in both the designs (existing relay and the existing modified relay) and the ranking of the improved measurement system in the modified relay changes from 2 to 4.Conclusion:A relaying algorithm is proposed for the protection of transmission line compensated with Static Var Compensator (SVC) and criticality ranking of different failure modes of a digital relay is carried out. The proposed scheme has significant advantages over more traditional relaying algorithms. It is suitable for high resistance faults and is not affected by the inception angle nor by the location of fault.

Diagnostic test accuracy for use of machine learning in diagnosis of autism spectrum disorder: A Systematic Review and Meta-Analysis (Preprint)

2019 ◽  
Author(s):  
Sun Jae Moon ◽  
Jin Seub Hwang ◽  
Rajesh Kana ◽  
John Torous ◽  
Jung Won Kim
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
Test Accuracy

BACKGROUND Over the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, its application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder. However, given its complexity and potential clinical implications, there is ongoing need for further research on its accuracy. OBJECTIVE The current study aims to summarize the evidence for the accuracy of use of machine learning algorithms in diagnosing autism spectrum disorder (ASD) through systematic review and meta-analysis. METHODS MEDLINE, Embase, CINAHL Complete (with OpenDissertations), PsyINFO and IEEE Xplore Digital Library databases were searched on November 28th, 2018. Studies, which used a machine learning algorithm partially or fully in classifying ASD from controls and provided accuracy measures, were included in our analysis. Bivariate random effects model was applied to the pooled data in meta-analysis. Subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false negative and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw SROC curves, and obtain area under the curve (AUC) and partial AUC. RESULTS A total of 43 studies were included for the final analysis, of which meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural MRI subgroup meta-analysis (12 samples with 1,776 participants) showed the sensitivity at 0.83 (95% CI-0.76 to 0.89), specificity at 0.84 (95% CI -0.74 to 0.91), and AUC/pAUC at 0.90/0.83. An fMRI/deep neural network (DNN) subgroup meta-analysis (five samples with 1,345 participants) showed the sensitivity at 0.69 (95% CI- 0.62 to 0.75), the specificity at 0.66 (95% CI -0.61 to 0.70), and AUC/pAUC at 0.71/0.67. CONCLUSIONS Machine learning algorithms that used structural MRI features in diagnosis of ASD were shown to have accuracy that is similar to currently used diagnostic tools.

Operation and approximation based on the history of failure modes recorded by SCADA system of Amougdoul Moroccan wind farm using FMECA maintenance model

2021 ◽  
pp. 0309524X2199245
Author(s):  
Kawtar Lamhour ◽  
Abdeslam Tizliouine
Keyword(s):  
Wind Turbines ◽  
Wind Farm ◽  
Failure Modes ◽  
Wind Farms ◽  
Scada System ◽  
History Of ◽  
Criticality Analysis ◽  
Maintenance Model ◽  
Reliability And Availability ◽  
Critical Subsystems

The wind industry is trying to find tools to accurately predict and know the reliability and availability of newly installed wind turbines. Failure modes, effects and criticality analysis (FMECA) is a technique used to determine critical subsystems, causes and consequences of wind turbines. FMECA has been widely used by manufacturers of wind turbine assemblies to analyze, evaluate and prioritize potential/known failure modes. However, its actual implementation in wind farms has some limitations. This paper aims to determine the most critical subsystems, causes and consequences of the wind turbines of the Moroccan wind farm of Amougdoul during the years 2010–2019 by applying the maintenance model (FMECA), which is an analysis of failure modes, effects and criticality based on a history of failure modes occurred by the SCADA system and proposing solutions and recommendations.

Fuzzy risk assessment for electro-optical target tracker

2016 ◽  
Vol 33 (6) ◽  
pp. 830-851 ◽  
Author(s):  
Soumen Kumar Roy ◽  
A K Sarkar ◽  
Biswajit Mahanty
Keyword(s):  
Failure Mode ◽  
Failure Modes ◽  
Linear Equations ◽  
Mode Analysis ◽  
Failure Behavior ◽  
Membership Functions ◽  
Design And Development ◽  
Effect Analysis ◽  
Content Type ◽  
Criticality Analysis

Purpose – The purpose of this paper is to evolve a guideline for scientists and development engineers to the failure behavior of electro-optical target tracker system (EOTTS) using fuzzy methodology leading to success of short-range homing guided missile (SRHGM) in which this critical subsystems is exploited. Design/methodology/approach – Technology index (TI) and fuzzy failure mode effect analysis (FMEA) are used to build an integrated framework to facilitate the system technology assessment and failure modes. Failure mode analysis is carried out for the system using data gathered from technical experts involved in design and realization of the EOTTS. In order to circumvent the limitations of the traditional failure mode effects and criticality analysis (FMECA), fuzzy FMCEA is adopted for the prioritization of the risks. FMEA parameters – severity, occurrence and detection are fuzzifed with suitable membership functions. These membership functions are used to define failure modes. Open source linear programming solver is used to solve linear equations. Findings – It is found that EOTTS has the highest TI among the major technologies used in the SRHGM. Fuzzy risk priority numbers (FRPN) for all important failure modes of the EOTTS are calculated and the failure modes are ranked to arrive at important monitoring points during design and development of the weapon system. Originality/value – This paper integrates the use of TI, fuzzy logic and experts’ database with FMEA toward assisting the scientists and engineers while conducting failure mode and effect analysis to prioritize failures toward taking corrective measure during the design and development of EOTTS.

Criticality Analysis for Maintenance Purposes of Platform Supply Vessels in Remote Areas

2017 ◽  
Vol 139 (3) ◽  
Author(s):  
A. Marhaug ◽  
A. Barabadi ◽  
E. Stagrum ◽  
K. Karlsen ◽  
A. Olsen ◽  
...  
Keyword(s):  
Failure Modes ◽  
Oil And Gas Industry ◽  
Spare Parts ◽  
Acceptable Level ◽  
Component Level ◽  
Screening Process ◽  
Essential Information ◽  
Remote Areas ◽  
Critical Components ◽  
Criticality Analysis

The oil and gas industry is pushing toward new unexplored remote areas, potentially rich in resources but with limited industry presence, infrastructure, and emergency preparedness. Maintenance support is very important and challenging in such remote areas. A platform supply vessel (PSV) is an essential part of maintenance support. Hence, the acceptable level of its availability performance is high. Identification of critical components of the PSV provides essential information for optimizing maintenance management, defining a spare parts strategy, estimating competence needs for PSV operation, and achieving the acceptable level of availability performance. Currently, there are no standards or guidelines for the criticality analysis of PSVs for maintenance purposes. In this paper, a methodology for the identification of the critical components of PSVs has been developed, based on the available standard. It is a systematic screening process. The method considers functional redundancy and the consequences of loss of function as criticality criteria at the main and subfunction levels. Furthermore, at the component level, risk tools such as failure modes, effects and criticality analysis (FMECA), and fault tree analysis (FTA) will be applied in order to identify the most critical components. Moreover, the application of the proposed approach will be illustrated by a real case study.

Failure mode, effects and criticality analysis improvement by using new criticality assessment and prioritization based approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ammar Chakhrit ◽  
Mohammed Chennoufi
Keyword(s):  
Failure Mode ◽  
Conventional Method ◽  
Fuzzy Inference System ◽  
Risk Evaluation ◽  
Failure Modes ◽  
Fuzzy Inference ◽  
Decision Makers ◽  
Inference System ◽  
Content Type ◽  
Criticality Analysis

Purpose This paper aims to enable the analysts of reliability and safety system to assess the criticality and prioritize failure modes perfectly to prefer actions for controlling the risks of undesirable scenarios. Design/methodology/approach To resolve the challenge of uncertainty and ambiguous related to the parameters, frequency, non-detection and severity considered in the traditional approach failure mode effect and criticality analysis (FMECA) for risk evaluation, the authors used fuzzy logic where these parameters are shown as members of a fuzzy set, which fuzzified by using appropriate membership functions. The adaptive neuro-fuzzy inference system process is suggested as a dynamic, intelligently chosen model to ameliorate and validate the results obtained by the fuzzy inference system and effectively predict the criticality evaluation of failure modes. A new hybrid model is proposed that combines the grey relational approach and fuzzy analytic hierarchy process to improve the exploitation of the FMECA conventional method. Findings This research project aims to reflect the real case study of the gas turbine system. Using this analysis allows evaluating the criticality effectively and provides an alternate prioritizing to that obtained by the conventional method. The obtained results show that the integration of two multi-criteria decision methods and incorporating their results enable to instill confidence in decision-makers regarding the criticality prioritizations of failure modes and the shortcoming concerning the lack of established rules of inference system which necessitate a lot of experience and shows the weightage or importance to the three parameters severity, detection and frequency, which are considered to have equal importance in the traditional method. Originality/value This paper is providing encouraging results regarding the risk evaluation and prioritizing failures mode and decision-makers guidance to refine the relevance of decision-making to reduce the probability of occurrence and the severity of the undesirable scenarios with handling different forms of ambiguity, uncertainty and divergent judgments of experts.

Uncertainty Analysis in Quantitative Risk Assessment

1996 ◽  
Vol 118 (1) ◽  
pp. 121-124 ◽  
Author(s):  
S. Quin ◽  
G. E. O. Widera
Keyword(s):  
Risk Assessment ◽  
Uncertainty Analysis ◽  
Set Theory ◽  
Fuzzy Set ◽  
Fuzzy Set Theory ◽  
Failure Modes ◽  
The Other ◽  
Quantitative Risk Assessment ◽  
Engineering Practice ◽  
Criticality Analysis

Of the quantitative approaches applied to inservice inspection, failure modes, effects,criticality analysis (FMECA) methodology is recommended. FMECA can provide a straightforward illustration of how risk can be used to prioritize components for inspection (ASME, 1991). But, at present, it has two limitations. One is that it cannot be used in the situation where components have multiple failure modes. The other is that it cannot be used in the situation where the uncertainties in the data of components have nonuniform distributions. In engineering practice, these two situations exist in many cases. In this paper, two methods based on fuzzy set theory are presented to treat these problems. The methods proposed here can be considered as a supplement to FMECA, thus extending its range of applicability.

Sign in / Sign up

Export Citation Format

Share Document