2015
DOI: 10.1016/j.jestch.2014.09.007
|View full text |Cite
|
Sign up to set email alerts
|

Determination of minimum sample size for fault diagnosis of automobile hydraulic brake system using power analysis

Abstract: a b s t r a c tHydraulic brake in automobile engineering is considered to be one of the important components. Condition monitoring and fault diagnosis of such a component is very essential for safety of passengers, vehicles and to minimize the unexpected maintenance time. Vibration based machine learning approach for condition monitoring of hydraulic brake system is gaining momentum. Training and testing the classifier are two important activities in the process of feature classification. This study proposes a… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
11
0

Year Published

2016
2016
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 18 publications
(12 citation statements)
references
References 25 publications
0
11
0
Order By: Relevance
“…Some clinical categories showing significant differences ( p  < 0.05) were at insufficient power levels (power < 0.8). It is known that power is related to sample size and, in other words, the power of tests could be promoted by adjusting the effect size of samples [25]. Therefore, for these significant but low-power contingency tables, we made a prediction of the number of donors that could meet a sufficient power level under the premise that the hypothetical cross-tabulations had the same cell percentages as that of 184 non-hypermutated donors.…”
Section: Methodsmentioning
confidence: 99%
“…Some clinical categories showing significant differences ( p  < 0.05) were at insufficient power levels (power < 0.8). It is known that power is related to sample size and, in other words, the power of tests could be promoted by adjusting the effect size of samples [25]. Therefore, for these significant but low-power contingency tables, we made a prediction of the number of donors that could meet a sufficient power level under the premise that the hypothetical cross-tabulations had the same cell percentages as that of 184 non-hypermutated donors.…”
Section: Methodsmentioning
confidence: 99%
“…K-star model has provided 100% classification efficiency for training dataset, whereas 92.7% for testing dataset. Indira et al [19,18] suggested a minimum number of samples (less than ten per each class) required to distinguish the fault conditions in the area of machine learning approach. However, 50 samples per each class were used for classifying the face milling tool conditions in order to get a statistically stable classification accuracy.…”
Section: Classification Using K-starmentioning
confidence: 99%
“…One of the most important safety systems in the vehicle is braking system, which has a decisive impact on the safety level of an active car. In the literature, there is a lot of work about the friction elements of the braking systems [11,14,22,24,25,30] but only few concerning the quality of brake fluid [3,5,17].…”
Section: Introductionmentioning
confidence: 99%
“…The braking performance of the ABS depends on control logics to overcome the time-varying nature of the braking dynamics and many uncertain parameters such as environments, road and friction coefficient [6]. Fault diagnosis is an important process in preventive maintenance of hydraulic brakes [11]. The faults in a hydraulic brake system of an automobile are not fairly noticeable [14].…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation