Fabricated data detection method
Aspects of the disclosure are directed to receiving numerical product data indicative of a product, the numerical product data comprising numerical values indicative of at least one of chemical composition, radius, tensile strength, a diameter, position and yield strength, and storing the numerical product data in a non-volatile memory device. The numerical product data is processed in a processor to create a plurality of explanatory variables indicative of the numerical product data. Multivariate data analysis is performed on the explanatory variables indicative of the numerical product data, where the multivariate data analysis includes an iterative cluster based outlier detection procedure. A confidence indicator value indicative of the likelihood that the numerical product data includes at least one fabricated or false data entry is generated.
1. A computer-implemented method, executed using a processor, for identifying at least one fabricated or false data entry in test data for a plurality of components, the method comprising:
providing the test data for the plurality of components, the test data relating to at least one of a tensile strength, a diameter, a position, or a yield strength, the test data including a data set for each said component of the plurality of components, each respective said data set including at least one test value, and each said test value having at least one individual digit, a plurality of test values for the test data including the at least one test value of each said data set of the test data;
processing the test data in the processor to create a plurality of explanatory variables for the plurality of test values, each said explanatory variable identifying an attribute of one or more of the at least one individual digit of each said test value of the plurality of test values;
comparing all of the plurality of explanatory variables for the test data by grouping the plurality of explanatory variables using an iterative K-means clustering technique to identify one or more outlier explanatory variables in the grouped plurality of explanatory variables;
generating a confidence indicator on a confidence indicator scale, the confidence indicator value based on an identification of the one or more outlier explanatory variables, the confidence indicator value as a function of the confidence indicator scale representing a likelihood that one or more test values of the plurality of test values is a fabricated or false test value; and
identifying the one or more fabricated or false test values of the plurality of test values, based on the confidence indicator value.
2. The method of claim 1 , where the test data comprises at least one chemical composition test value.
3. The method of claim 1 , where the test data further comprises at least one of data indicative of a manufacturer of the part received, part number, description of the part received, and specification limits of the part received.
4. The method of claim 1 , where the receiving the test data also comprises receiving at least one of chemical composition, true position, radius and air flow.
5. The method of claim 1 , further comprising receiving the plurality of components from the vendor, wherein each said component of the plurality of components is an aircraft gas turbine engine component.
6. The method of claim 1 , wherein a first test value of the plurality of test values is a first mechanical property of a first component of the plurality of components, wherein a second test value of the plurality of test values is a second mechanical property of a second component of the plurality of components, and wherein the first mechanical property is different than the second mechanical property.
7. The method of claim 1 , wherein a first component of the plurality of components is different than a second component of the plurality of components.
8. A system for identifying the presence or absence of a fabricated or false data entry in test data for a plurality of components, the test data relating to at least one of a tensile strength, a diameter, a position, or a yield strength, the test data including a data set for each said component of the plurality of components, each respective said data set including at least one test value, and each said test value having at least one individual digit, a plurality of test values for the test data including the at least one test valve of each said data set of the test data, the system comprising:
a processor in communication with a non-transitory memory storing instructions, which instructions when executed cause the processor to:
process the test data to create a plurality of explanatory variables for the plurality of test values, each said explanatory variable identifying an attribute of one or more of the at least one individual digit of each said test value of the plurality of test values;
compare all of the plurality of explanatory variables for the test data by grouping the plurality of explanatory variables using an iterative K-means clustering technique to identify one or more outlier explanatory variables in the grouped plurality of explanatory variables;
generate a confidence indicator value on a confidence indicator scale, the confidence indicator value based on an identification of the one or more outlier explanatory variables, the confidence indicator value as a function of the confidence indicator scale representing a likelihood of the presence or absence of a fabricated or false test value; and
if the confidence indicator value as a function of the confidence indicator scale indicates the likelihood of the presence of one or more fabricated or false test values within the plurality of test values, identify the one or more said test values likely to be a said fabricated or false test value.
9. The system of claim 8 , wherein the test data further includes at least one chemical composition test value.
10. The system of claim 8 , wherein a first test value of the plurality of test values is a first mechanical property of a first component of the plurality of components, wherein a second test value of the plurality of test values is a second mechanical property of a second component of the plurality of components, and wherein the first mechanical property is different than the second mechanical property.
11. The system of claim 8 , wherein a first component of the plurality of components is different than a second component of the plurality of components.