Using Polynomial Smoothing and Data Bounding for the Detection of Adverse Process Changes in a Chemical Process

Self Cite

A series of repeated nuclear material balances forms a time series of often autocorrelated observations. Outliers, deviations from an in-control production process or time series pattern, indicate an out-of-control situation relative to the process norm. In this paper various methods, especially neural networks, will be examined with respect to their use to detect nuclear material diversions or losses more rapidly and accurately than currently used methods. The neural network technique will be enhanced with the use of a simulation computer program for creating the training data set. This simulation approach provides the opportunity of including outliers of various types in a data set for training the neural network because an actual process data set used for training possibly may not have outliers. In this paper, the methods will be compared on their ability to identify outliers and reduce false alarms. These methods were tested on data sets of nuclear material balances with known removals, and the results are tabulated and described. Based on these results, we believe the algorithms used will assist the nuclear industry in process control, provide a new approach to nuclear material safeguards, and also provide a new approach to training neural networks for process control applications.

Section: B Nuclear Materials Safeguards and Related Research Methodsmentioning

confidence: 99%

Section: B Nuclear Materials Safeguards and Related Research Methodsmentioning

confidence: 99%

Section: B Nuclear Materials Safeguards and Related Research Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Neural Network Approach to the Detection of Nuclear Material Losses

Hamburg¹,

Booth²,

Weinroth³

1996

Self Cite

“…We will compare the LOWES smoother and the 4253EH and 3RSSH RMS smoothers to the Savitsky-Golay based polynomial smoothers of Sebastian et al , It should be noted that the outlier detection subroutine for process control (ODSPC), developed by Sebastian et al, , was used with the robust smoothers considered here as well as with the polynomial smoother. The first author developed computer programs to implement these smoothers in combination with Sebastian's ODSPC.…”

Section: Proposed Algorithms For the Detection Of Outliers Based On R...mentioning

confidence: 99%

The Use of Robust Smoothers in Nuclear Material Safeguards

and

Booth

Sebastian

1997

It has previously been shown that smoothing algorithms can provide the basis for a method to detect nuclear material diversions and losses and moreover can also provide a general approach to industrial statistical process control. The present paper extends this result by showing that a set of robust smoothers also produces equivalent methods that can be used in nuclear material safeguards algorithms. Further, it is shown that these smoothers are somewhat more sensitive to loss points than the previously studied smoothers. The method is illustrated on real data.

“…All three methods did not detect any loss in the second removal period (nos. [23][24][25][26][27][28][29][30][31][32][33][34] until near the end at point no. 33.…”

Section: Testing the Algorithms On Data Sets With Known Diversionsmentioning

confidence: 99%

Using polynomial smoothing and data bounding for the detection of nuclear material diversions and losses

Sebastian¹,

Booth²,

Hu³

1995

Self Cite

Successive nuclear material balances form a time series of often autocorrelated observations. Significiant deviations from the underlying in-control process model or time series pattern, i.e., outliers, indicate an adverse process change or out-of-control situation relative to the model. This paper uses these ideas to demonstrate a method for detecting nuclear material losses earlier than currently used models and thus helps to alleviate a problem which is growing to world crisis proportions. The process control capabilities of these methods were successfully tested on two autocorrelated data sets of nuclear material balances with known removals. These algorithms should be of assistance to the nuclear engineer involved in process control. A. INTRODUCTIONIn Nuclear Materials Accounting the goal is to accurately discover material losses (e.g., leakage or theft) as early as possible to minimize the threat to life and property. Despite some progress, control against leakage, theft, or loss of radioactive material has continued to be a problem. International terrorist activity and the desire of renegade nations to become nuclear powers make the threat of theft very real. Only recently it was discovered that controls for weapon grade nuclear materials are grossly deficient in the former Soviet Union as evidenced by several instances of stolen plutonium and uranium being found in Germany.1 Possible scenarios regarding the theft of weapons grade material are frightening.