Bayesian information fusion for degradation analysis of deteriorating products with individual heterogeneity

2018 ◽  
Vol 233 (4) ◽  
pp. 615-622 ◽  
Author(s):  
Junyu Guo ◽  
Hong-Zhong Huang ◽  
Weiwen Peng ◽  
Jie Zhou
Keyword(s):  
Reliability Analysis ◽  
Information Fusion ◽  
Process Model ◽  
High Reliability ◽  
Small Sample Size ◽  
Small Sample ◽  
Gamma Process ◽  
Individual Heterogeneity ◽  
Multiple Sources ◽  
Degradation Analysis

Degradation analysis is a popular and effective method for reliability analysis of long-life and high-reliability products. However, for newly developed products, especially for highly customized products with small sample size, the challenge of sparse degradation observations with product heterogeneity is still an open issue deserving further research. In this article, Bayesian degradation analysis is presented for reliability analysis of products with heterogeneity. The degradation process is modeled by a Gamma process. Random effects are incorporated in the Gamma process model for characterizing the individual heterogeneity. To improve the precision of parameter estimation and degradation analysis, a Bayesian information fusion is presented to leverage degradation information from multiple sources. The proposed model is demonstrated through degradation-based reliability analysis of heavy-duty machine tool’s spindle system, which is characterized as degradation analysis with individual heterogeneity and information fusion.

INSPIRE sustainability internships

2019 ◽  
Vol 20 (3) ◽  
pp. 452-469 ◽  
Author(s):  
Carolyn Susan Hayles
Keyword(s):  
Small Sample Size ◽  
Real Life ◽  
Small Sample ◽  
Multiple Sources ◽  
Student Body ◽  
Content Type ◽  
Study Approach ◽  
Life Context ◽  
The University

Purpose This paper aims to explore the outputs of an internship programme, one of a number of campus-based sustainability activities that have been introduced at the University of Wales, Trinity Saint David, to encourage student-led campus-based greening initiatives. Design/methodology/approach A case study approach was undertaken, allowing the researcher to investigate the programme in its real-life context. The researcher used multiple sources of evidence to gain as holistic a picture as possible. Findings Interns report positive changes in their behaviours towards sustainability, s well as encouraging feedback on their experiential learning, the development of their soft skills and the creation of new knowledge. Moreover, students communicated perceived benefits for their future careers. The reported outcomes reflect mutually beneficial relationships for student and institution, for example, raising the profile of campus greening activities and supporting the University’s aim to embed sustainability throughout its campus, community and culture. Research limitations/implications The researcher recognises the limitations of the research, in particular, the small sample size, which has resulted primarily in qualitative results being presented. Practical implications Feedback from previous interns will be used to shape future internships. In particular, Institute of Sustainable Practice, Innovation and Resource Effectiveness (INSPIRE) will look for opportunities to work more closely with University operations, departments, faculties and alongside University staff, both academic and support staff. Social implications Following student feedback, INSPIRE will give students opportunities for wider involvement, including an opportunity to propose their own projects to shape future internships that meet the needs of student body on campus. Originality/value Despite being one case study from one institution, the research highlights the value of such programmes for other institutions.

Sampling-Based Reliability Analysis Using Deep Feedforward Neural Network (DFNN)

2020 ◽  
Author(s):  
Ungki Lee ◽  
Ikjin Lee
Keyword(s):  
Neural Network ◽  
Reliability Analysis ◽  
Surrogate Model ◽  
Small Sample Size ◽  
Small Sample ◽  
Feedforward Neural Network ◽  
Training Data ◽  
Performance Function ◽  
Design Point ◽  
Previous Design

Abstract Reliability analysis that evaluates a probabilistic constraint is an important part of reliability-based design optimization (RBDO). Inverse reliability analysis evaluates the percentile value of the performance function that satisfies the reliability. To compute the percentile value, analytical methods, surrogate model based methods, and sampling-based methods are commonly used. In case the dimension or nonlinearity of the performance function is high, sampling-based methods such as Monte Carlo simulation, Latin hypercube sampling, and importance sampling can be directly used for reliability analysis since no analytical formulation or surrogate model is required in these methods. The sampling-based methods have high accuracy but require a large number of samples, which can be very time-consuming. Therefore, this paper proposes methods that can improve the accuracy of reliability analysis when the number of samples is not enough and the sampling-based methods are considered to be better candidates. This study starts with the idea of training the relationship between the realization of the performance function at a small sample size and the corresponding true percentile value of the performance function. Deep feedforward neural network (DFNN), which is one of the promising artificial neural network models that approximates high dimensional models using deep layered structures, is trained using the realization of various performance functions at a small sample size and the corresponding true percentile values as input and target training data, respectively. In this study, various polynomial functions and random variables are used to create training data sets consisting of various realizations and corresponding true percentile values. A method that approximates the realization of the performance function through kernel density estimation and trains the DFNN with the discrete points representing the shape of the kernel distribution to reduce the dimension of the training input data is also presented. Along with the proposed reliability analysis methods, a strategy that reuses samples of the previous design point to enhance the efficiency of the percentile value estimation is explained. The results show that the reliability analysis using the DFNN is more accurate than the method using only samples. In addition, compared to the method that trains the DFNN using the realization of the performance function, the method that trains the DFNN with the discrete points representing the shape of the kernel distribution improves the accuracy of reliability analysis and reduces the training time. The proposed sample reuse strategy is verified that the burden of function evaluation at the new design point can be reduced by reusing the samples of the previous design point when the design point changes while performing RBDO.

The Application of Performance Degradation Analysis in Machine Tool Spindle

2015 ◽  
Vol 713-715 ◽  
pp. 585-588
Author(s):  
Wei Hu ◽  
Kai Zeng ◽  
Xiao Cong He ◽  
Gang Wei Cui ◽  
Sheng Wan Yuan ◽  
...  
Keyword(s):  
Machine Tool ◽  
High Reliability ◽  
Test Methods ◽  
Performance Degradation ◽  
Small Sample ◽  
Reliability Test ◽  
Machine Tool Spindle ◽  
Degradation Analysis ◽  
Statistical Analysis Method ◽  
Failure Life

As a key part feature of the machine, machine tool spindle has the characteristics of high reliability and high precision. The traditional test methods used to short the test cycle and analyze failure life of small sample data are inappropriate. Firstly, the reliability testing system of machine tool spindle was expounded; then, research status and the statistical analysis method of the performance degradation analysis used in the reliability test of machine tool spindle system were expounded. The influence to the credibility of the reliability test for machine tool spindle was put forward and analyzed: stress selection, feature selection, failure threshold selection and small sample analysis. Accelerated degradation test was given for further research in the reliability test for machine tool spindle.

scholarly journals Meta-Analysis and Forest Plots for Sustainability of Heavy Load Carrier Equipment Used in the Industrial Mining Environment

2021 ◽  
Vol 13 (15) ◽  
pp. 8672
Author(s):  
Somnath Chattopadhyaya ◽  
Brajeshkumar Kishorilal Dinkar ◽  
Alok Kumar Mukhopadhyay ◽  
Shubham Sharma ◽  
José Machado
Keyword(s):  
Sample Size ◽  
Reliability Analysis ◽  
Small Sample Size ◽  
Meta Analysis ◽  
Small Sample ◽  
Forest Plot ◽  
Large Sample Size ◽  
Heavy Load ◽  
Combining Data ◽  
Load Carrier

It is a common recommendation not to attempt a reliability analysis with a small sample size. However, this is feasible after considering certain statistical methods. One such method is meta-analysis, which can be considered to assess the effectiveness of a small sample size by combining data from different studies. The method explores the presence of heterogeneity and the robustness of the fresh large sample size using sensitivity analysis. The present study describes the approach in the reliability estimation of diesel engines and the components of industrial heavy load carrier equipment used in mines for transporting ore. A meta-analysis is carried out on field-based small-sample data for the reliability of different subsystems of the engine. The level of heterogeneity is calculated for each subsystem, which is further verified by constructing a forest plot. The level of heterogeneity was 0 for four subsystems and 2.23% for the air supply subsystem, which is very low. The result of the forest plot shows that all the plotted points mostly lie either on the center line (line of no effect) or very close to it, for all five subsystems. Hence, it was found that the grouping of an extremely small number of failure data is possible. By using this grouped TBF data, reliability analysis could be very easily carried out.

Hippotherapy and life habits with children with motor deficit and neurodevelopmental impairment: A pilot survey of parents

2021 ◽  
Vol 14 (1) ◽  
pp. 41-49
Author(s):  
Alex Potvin-Bélanger ◽  
Andrew Freeman ◽  
Claude Vincent
Keyword(s):  
Interpersonal Relationships ◽  
Process Model ◽  
Positive Impact ◽  
Small Sample Size ◽  
Descriptive Analysis ◽  
Small Sample ◽  
Motor Deficit ◽  
Life Habit ◽  
Rehabilitation Professionals ◽  
Life Habits

PURPOSE: Hippotherapy is used by rehabilitation professionals to assist children with various diagnoses. Despite parents’ pivotal decision-making role regarding their children’s life and treatment, little is known about their perceptions of hippotherapy’s utility. This pilot study explored parents’ opinions regarding hippotherapy’s impact on their child’s life habits, as guided by the Disability Creation Process model. METHODS: A survey was conducted in September/October 2017 with the parents of children with varied diagnoses receiving hippotherapy in Quebec. The survey asked parents to priority rank life habit categories and then grade hippotherapy’s service characteristics and impact on children’s life habits. Descriptive analysis and proportion tests were used to analyze the data. RESULTS: The parents of 26 children completed the survey. These children were on average seven years old with multiple diagnoses (e.g., autism spectra, developmental delay). A positive impact was perceived for 10 of 12 life habit categories, with a statistically significant association found with Mobility and Interpersonal relationships. It was not possible to calculate the association between the profession involved and hippotherapy effects due to the small sample size. CONCLUSION: This investigation provides some promising results regarding the benefits of hippotherapy for children’s life habits.

A Comparison of the Power of the Paired Samples Rank Transform Statistic to that of Wilcoxon’s Signed Ranks Statistic

1985 ◽  
Vol 10 (4) ◽  
pp. 368-383 ◽  
Author(s):  
R. Clifford Blair ◽  
James J. Higgins
Keyword(s):  
Sample Size ◽  
Treatment Effects ◽  
High Reliability ◽  
Small Sample Size ◽  
Small Sample ◽  
Relative Power ◽  
Normal Theory ◽  
Large Sample ◽  
Paired Samples ◽  
Rank Transform

This study was concerned with the effects of reliability of observations, sample size, magnitudes of treatment effects, and the shape of the sampled population on the relative power of the paired samples rank transform statistic and Wilcoxon’s signed ranks statistic. It was found that factors favoring the Wilcoxon statistic were high reliability of observations, moderate to large sample sizes, and small treatment effects. Factors favoring the rank transform statistic were low reliability of observations, small sample size, and moderate to large treatment effects. It was also noted that the Wilcoxon statistic appeared to maintain the power advantage under normal theory assumptions.

Sign in / Sign up

Export Citation Format

Share Document