scholarly journals Developing Data Mining-Based Prognostic Models for CF-18 Aircraft

2010 ◽  
Author(s):  
Marvin Zaluski ◽  
Sylvain Le´tourneau ◽  
Jeff Bird ◽  
Chunsheng Yang
Keyword(s):  
Data Mining ◽  
Model Building ◽  
Health Management ◽  
Model Development ◽  
Data Gathering ◽  
Software Tool ◽  
Prognostic Models ◽  
Canadian Forces ◽  
Fusion Data ◽  
Operating Organization

The CF-18 aircraft is a complex system for which a variety of data are systematically being recorded: operational flight data from sensors and Built-In Test Equipment (BITE) and maintenance activities recorded by personnel. These data resources are stored and used within the operating organization but new analytical and statistical techniques and tools are being developed that could be applied to these data to benefit the organization. This paper investigates the utility of readily available CF-18 data to develop data mining-based models for prognostics and health management (PHM) systems. We introduce a generic data mining methodology developed to build prognostic models from operational and maintenance data and elaborate on challenges specific to the use of CF-18 data from the Canadian Forces. We focus on a number of key data mining tasks including: data gathering, information fusion, data pre-processing, model building, and evaluation. The solutions developed to address these tasks are described. A software tool developed to automate the model development process is also presented. Finally, the paper discusses preliminary results on the creation of models to predict F404 No. 4 Bearing and MFC (Main Fuel Control) failures on the CF-18.

scholarly journals Developing Data Mining-Based Prognostic Models for CF-18 Aircraft

2011 ◽  
Vol 133 (10) ◽  
Author(s):  
Marvin Zaluski ◽  
Sylvain Létourneau ◽  
Jeff Bird ◽  
Chunsheng Yang
Keyword(s):  
Data Mining ◽  
Model Building ◽  
Health Management ◽  
Model Development ◽  
Data Gathering ◽  
Software Tool ◽  
Prognostic Models ◽  
Canadian Forces ◽  
Fusion Data ◽  
Operating Organization

The CF-18 (CF denotes Canadian Forces) aircraft is a complex system for which a variety of data are systematically being recorded: flight data from sensors, built-in test equipment data, and maintenance data. Without proper analytical and statistical tools, these data resources are of limited use to the operating organization. Focusing on data mining-based modeling, this paper investigates the use of readily available CF-18 data to support the development of prognostics and health management systems. A generic data mining methodology has been developed to build prognostic models from operational and maintenance data. This paper introduces the methodology and elaborates on challenges specific to the use of CF-18 data from the Canadian Forces. A number of key data mining tasks are examined including data gathering, information fusion, data preprocessing, model building, and model evaluation. The solutions developed to address these tasks are described. A software tool developed to automate the model development process is also presented. Finally, this paper discusses preliminary results on the creation of models to predict F404 no. 4 bearing and main fuel control failures on the CF-18.

scholarly journals SBpipe: a collection of pipelines for automating repetitive simulation and analysis tasks

2017 ◽  
Author(s):  
Piero Dalle Pezze ◽  
Nicolas Le Novère
Keyword(s):  
Parameter Estimation ◽  
Model Building ◽  
Model Simulation ◽  
Profile Likelihood ◽  
Model Development ◽  
Software Tool ◽  
Model Parameters ◽  
Repeat Sequences ◽  
Parameter Estimations ◽  
Consistent Manner

AbstractBackground: The rapid growth of the number of mathematical models in Systems Biology fostered the development of many tools to simulate and analyse them. The reliability and precision of these tasks often depend on multiple repetitions and they can be optimised if executed as pipelines. In addition, new formal analyses can be performed on these repeat sequences, revealing important insights about the accuracy of model predictions.Results: Here we introduce SBpipe, an open source software tool for automating repetitive tasks in model building and simulation. Using basic configuration files, SBpipe builds a sequence of repeated model simulations or parameter estimations, performs analyses from this generated sequence, and finally generates a LaTeX/PDF report. The parameter estimation pipeline offers analyses of parameter profile likelihood and parameter correlation using samples from the computed estimates. Specific pipelines for scanning of one or two model parameters at the same time are also provided. Pipelines can run on multicore computers, Sun Grid Engine (SGE), or Load Sharing Facility (LSF) clusters, speeding up the processes of model building and simulation. SBpipe can execute models implemented in Copasi, Python or coded in any other programming language using Python as a wrapper module. Future support for other software simulators can be dynamically added without affecting the current implementation.Conclusions: SBpipe allows users to automatically repeat the tasks of model simulation and parameter estimation, and extract robustness information from these repeat sequences in a solid and consistent manner, facilitating model development and analysis. The source code and documentation of this project are freely available at the web site: https://pdp10.github.io/sbpipe/.

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.

scholarly journals Applying Logistic Regression Data mining techniques for Ethiopian Government Agricultural Open Data Sets

2021 ◽  
Vol 10 (2) ◽  
pp. 473-488
Keyword(s):  
Data Mining ◽  
Logistic Regression ◽  
Agricultural Sector ◽  
Model Building ◽  
Open Data ◽  
Research Process ◽  
Attribute Selection ◽  
Sufficient Evidence ◽  
Vegetable Crops ◽  
Logistic Regression Algorithm

Ethiopia has a great agricultural potential because of its vast areas of fertile land, diverse climate, generally adequate rainfall, and large labor force. With its verified importance to the Ethiopian economy, there is sufficient evidence to show that the potential of the agricultural sector can be expanded considerably by attracting investors towards the sector. This study aims at applying classification techniques in developing a predictive model that can estimate yield production of vegetable crops and the correlation of crops based on their class. In the process of building a model, different steps were undertaken. Among the steps, data collection, data preprocessing and model building and validation were the major ones. Different tasks performed in each step are mentioned as follows. The data were collected Food and Agriculture Organization of the United Nations (FAO). Under preprocessing, data cleaning, discretization and attribute selection were done. The final step was model building and validation and it was performed using the selected tools and techniques. The data mining tool used in this research was Weka. In this software the logistic regression algorithm was selected since it is capable to score more accuracy. After successive experiments were done using this software, a model that can classify crop yield as high, medium and low with better accuracy to the extent of 88.6%. Experimental results show that logistic regression is a very helpful tool to depict the contribution of yield estimation and crop correlation. The reported findings are optimistic, making the proposed model a useful tool in the decision making process. Eventually, the whole research process can be a good input for further indepth research

scholarly journals PUBLIC HEALTH SYSTEM IN INCLUSIVE REGION GROWTH

2021 ◽  
Vol 2021 (2) ◽  
pp. 165-171
Author(s):  
N.Ye. Letunovska ◽  
L.Yu. Saher ◽  
A.P. Nazarenko
Keyword(s):  
Public Health ◽  
Regional Development ◽  
Health Management ◽  
Growth Dynamics ◽  
Software Tool ◽  
The United States ◽  
Inclusive Development ◽  
Human Potential ◽  
Bibliographic Analysis ◽  
Main Research

The article explores the concept of inclusive development of regions, emphasizing the study of the formation and maintenance of a stable level of public health in the scientific literature. For bibliographic analysis, complex scientometric databases Scopus and Dimensions were used to analyze a set of publications formed according to specific criteria using the software tool VOSviewer. The visualization method was used to visualize the obtained results. The search in scientometric databases was carried out by the criterion of the title of the publication, the content of its annotation and keywords. The analysis showed that the main research clusters form groups of scientists' publications from the United States, Great Britain, Australia, and Canada. The small number of publications, but their growth dynamics and the increasing number of citations (according to Google Scholar) indicate a lack of study of inclusive growth in the region in the public health management system and the prospects for its exploration by scientists. According to the analysis, the interest of scientists in solving the problem of public health in ensuring regional development increased in 2020-2021. Much of the publications relate to such areas of knowledge as business, management and accounting. The main areas of research on public health in the development of the regions include the provision of medical services, the health care system, social determinants of health, and the population's state of health. Scientific clusters are gradually being formed around these keywords. The obtained results of the bibliographic analysis form the basis for a better understanding of public health issues, the search for gaps, the solution of which should be worked on in further research. Particular attention is paid to the issue of the COVID-19 pandemic as a crisis-forming factor that hinders the movement of regional development in a promising direction and ensuring the resilience of the system. It is substantiated that the health factor is essential in forming a robust human potential of the country and the growth of labor productivity.

scholarly journals Cardiovascular Disease Prediction and Classification using Modified Teaching Learning Optimization Method

2020 ◽  
Vol 9 (5) ◽  
pp. 808-813
Keyword(s):  
Data Mining ◽  
Cardiovascular Disease ◽  
Social Insurance ◽  
Insurance Industry ◽  
Optimization Method ◽  
Optimization Techniques ◽  
Prognostic Models ◽  
Features Selection ◽  
Teaching Learning ◽  
Clinical Records

Cardiovascular disease (CVD) is possibly the greatest reason for casualty and death rate among the number of inhabitants on the planet. Projection of cardiopathy is viewed as one of the most crucial subjects in the area of clinical records exploration. The measure of information in the social insurance industry is massive. The Data mining process transforms the huge range of unrefined medical service data into meaningful information that can lead to erudite decision and projection. Some recent investigations have applied data exploratory procedures too in CVD estimation. However, only very few studies have revealed the elements that play crucial role in envisioning CVDs. It is imperative to opt for the combination of correct and significant elements that can enhance the functioning of the forecasting prototypes. This study aims to ascertain meaningful elements and data mining procedures that can enrich the correctness of foretelling CVDs. Prognostic models were formulated employing distinctive blend of features selection modified teaching learning optimization techniques, SVM and boosting classification. Here the proposed strategy gives high precision outcomes with existing classification.

scholarly journals Prognostics and health management technology for radar system

2020 ◽  
Vol 309 ◽  
pp. 04009
Author(s):  
Yongle Lyu ◽  
Zhuo Pang ◽  
Chuang Zhou ◽  
Peng Zhao
Keyword(s):  
Model Building ◽  
Health Management ◽  
Radar System ◽  
Prognostics And Health Management ◽  
Failure Model ◽  
Long Distance ◽  
Maintenance System ◽  
Management Technology ◽  
Key Techniques ◽  
Selection Of

Information-based war in the future has a higher requirement to the maintenance and support ability of radar system. Prognostics and Health Management(PHM) technology represents the research hotspot of maintenance system, and following key techniques need to be resolved to research on the radar PHM technology such as the acquirement and selection of health information and fault signs of a radar’s electronical components, mass data warehousing and mining, fusion of multi-source test data and multi-field characteristic information, failure model building and forecasting, automatic decision-making on maintenance, and at the same time improving the self built-in test abilities of radar’s components based on the optimization of Design For Testability(DFT). The radar PHM technology has the trend of “built-in to integrate”, “together with DFT” and “long-distance and distributed”. However, subjected to radar’s complexity and current PHM technique level, radar PHM engineering still meets many challenges, but has bright future.

Sign in / Sign up

Export Citation Format

Share Document