Improved diagnostic and prognostic assessments using health management information fusion

Roemer, Michael; Kacprzynski, Gregory J.; Schoeller, M.

doi:10.1109/autest.2001.948984

Cited by 16 publications

(9 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to improve communications among military researchers and system developers, the Joint Directors of Laboratories (JDL) Data Fusion Working Group, established in 1986, began an effort to codify the terminology related to data fusion. The result of that effort was the creation of a process model for data fusion, and a Data Fusion Lexicon [6,7]. The JDL process model is a functionally-oriented model of data fusion and is intended to be very general and useful across multiple application areas.…”

Section: A a Data Fusion Process Modelmentioning

confidence: 99%

Grain Quality Evaluation Method Based on Combination of BP Neural Networks with D-S Evidence Theory

Tong

Zhi

Zhu

et al. 2009

2009 International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Aiming at the shortcomings of the BP neural network, this paper presents a method for grain condition information fusion based on BP neural networks and D-S evidential theory. This method firstly employs many BP neural network outputs as the inputs of D-S evidence theory. After that, D-S evidence theory is used to fuse with results from all the neural networks, resulting in the grain quality evaluation. Numerical example shows that proposed method improves the various mathematical and computational techniques have been developed and adapted to manipulate and interpret motion data, exactitude and decreases the recognition uncertainty.

show abstract

Section: A a Data Fusion Process Modelmentioning

confidence: 99%

Grain Quality Evaluation Method Based on Combination of BP Neural Networks with D-S Evidence Theory

Tong

Zhi

Zhu

et al. 2009

2009 International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Status of a machine could be specified completely by the multi-sensor data that are captured by the multiple sensors. Additionally, by the fusion of multi-sensor data, an intelligent integration of the sensory data with cooperative, complimentary and competitive qualities in the different levels of the machine can be possible [1,3]. Based on the multi-sensor data fusion, a machine prognosis could be developed and defined as the capability to provide early detection of the precursor and/or incipient fault condition of a machine, and to have the technology and means to manage and predict the progression of this fault condition to the failures [4,5].…”

Section: Multi-sensor Prognosismentioning

confidence: 99%

Product quality prognosis in plastic injection moulding

Huang

Chen

Cheng

et al. 2010

Prod. Eng. Res. Devel.

View full text Add to dashboard Cite

Plastic injection moulding is a typical complex manufacturing process. Its product quality is difficult to assure because of the nonuniform material shrinkage. This research introduces a prognostic concept for predicting the product quality (four edge shrinkages). The prognostic model is developed by path analysis through LISREL which can define the model's reliability when only few sensory data are retrieved from the smoothly running system. The prognostic model is validated by 25 test runs. In each run, each of the nine manufacturing conditions is randomly set at the extreme limit, i.e., either the lower limit or the upper limit. By comparing the actual edge shrinkages defined by the finite element software Moldflow with the results predicted by the prognostic model, this research concludes the prognostic model can successfully predict the quality of products and prevent the production of defective products.

show abstract

“…Bayesian inference can be used to determine the probability that a diagnosis is correct. However, it has the disadvantage of requiring a priori probability distributions, which may not always be available [8].…”

Section: Research Literature Reviewmentioning

confidence: 99%

“…In [8], methods to combine system information (such as test results) to improve the confidence and accuracy of diagnostics are examined. One of the data fusion approaches proposed uses neural networks.…”

Section: Research Literature Reviewmentioning

confidence: 99%

Maintenance Decision-Making Under Prognostic and Diagnostic Uncertainty

Cassady¹,

Nachtmann²,

Pohl³

et al. 2005

View full text Add to dashboard Cite

Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing this collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden to Department of Defense, Washington Headquarters Services, Directorate for Information Operations and Reports (0704-0188), 1215 Jefferson Davis Highway. Suite 1204, Arlington, VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to any penalty for failing to comply with a collection of information If it does not display a currenriy valid OMB control number. PLEASE DO NOT RETURN YOUR FORM TO THE ABOVE ADDRESS. 14. ABSTRACT A key challenge faced by USAF maintenance personnel is the uncertainty associated with the information provided by diagnostic tools. This uncertainty results from accuracy issues associated with individual diagnostic tools, as well as inconsistencies across different diagnostic tools. This uncertainty can make it very difficult for maintenance technicians to choose an appropriate course of action. The end result is the possible omission of necessary maintenance actions and performance of unnecessary actions. Both of these potential mistakes cause additional delays in returning an aircraft to the fleet and increased requirements for spare parts in the supply chain. Therefore, the objective of this project is to develop a methodology based on mathematical modeling that can be used to synthesize diagnostic information and provide a recommended course of action to a technician. This methodology potential could be incorporated into a decision-support tool for maintenance technicians. The activities required to achieve the objective of this project are applied to a hypothetical system. However, the definition of this hypothetical system is such that the system possesses fundamental characteristics like those systems utilized by the US Air Force (and many other organizations). A key challenge faced by USAF maintenance personnel is the uncertainty associated with the information provided by diagnostic tools. This uncertainty can make it very difficult for maintenance technicians to choose an appropriate course of action. The end result is the possible omission of necessary maintenance actions and performance of unnecessary actions. Both of these potential mistakes cause additional delays in returning an aircraft to the fleet and increased requirements for spare parts in the supply chain. Therefore, the objective of this project is to develop a methodology based on mathematical modeling that can be used to synthesize the diagnostic information and provide a recommended course of action to the technician. REPORT DATE SUBJECTFor a hypothetical system that possesses fundamental characteristics like those systems u...

show abstract

Improved diagnostic and prognostic assessments using health management information fusion

Cited by 16 publications

References 2 publications

Grain Quality Evaluation Method Based on Combination of BP Neural Networks with D-S Evidence Theory

Grain Quality Evaluation Method Based on Combination of BP Neural Networks with D-S Evidence Theory

Product quality prognosis in plastic injection moulding

Maintenance Decision-Making Under Prognostic and Diagnostic Uncertainty

Contact Info

Product

Resources

About