4.6.7 Sensor Allocation Page

The Sensor Allocation page provides the user with the ability to allocate flow-specific sensors to test points generated in the Sensor Set Analysis page. This page displays the sensor library, recently used sensors, sensor allocation and items sections.

4.6.7.1 Sensor Library Section

The Sensor Library section shows sensors and sensor libraries to be allocated to detected test points. It contains a search bar and displays user libraries in a hierarchical, tree-diagram structure.

To search for a sensor or sensor category:

1. Enter a sensor/folder name in the search bar
2. Verify results shown in the sensor library hierarchy

The checkbox titled "Filter by selected Component" is used to display sensors that can detect a flow property for a selected item.

To enable/disable the sensor filtering:

1. Select an item from the Items section
2. Select the checkbox to filter relevant sensors for the test point displayed

To view sensor information:

1. Select a sensor in the Sensor Library hierarchy
2. Select the information icon
3. View the Sensor Details dialog

4.6.7.2 Items Section

The Items section displays a list of subsystems and components that are considered in the analysis. It contains a search bar to identify specific items in the system. Selecting an item in the hierarchy will display its detectable flow properties (test points) in the Sensor Allocation section. The second column shows the number of test points and the number of sensors allocated (e.g. "2/3" indicates 2 sensors allocated and 3 test points for the selected item).

To search for an item:

1. Enter an item name in the search bar
2. Verify results shown in the item hierarchy
3. Select item to view its test points in the Sensor Allocation section

4.6.7.3 Sensor Allocation section

The Sensor Allocation section displays detectable flow properties & symptoms (test points) of an item selected in the Item section. The user allocates sensors from the sensor library to a test point, which will update the sensor sets in the Sensor Set Analysis, Sensor Parameters, Metric Optimization, Comparison, and Diagnostic sets page. The method of sensing can also be specified for an allocated sensor — definitions of these methods are found in the Glossary (Help > Glossary).

To allocate sensors to a test point:

1. Select an item in the Items section
2. Identify a compatible sensor in the Sensor Library section
3. Click-and-drag sensor from library to the dashed box next to the flow property
4. Save Changes

To specify the method of sensing:

1. Right-click on an allocated sensor
2. Select Method of Sensing from the right-click menu
3. Select from options: On-line, In-line, Off-line, Test or Inspection
4. Verify the method of sensing is allocated to the sensor

4.6.7.4 Recently Used Sensors section

The Recently Used Sensors section lists all sensors that have been allocated to test points. The user can view sensor information and re-allocate these used sensors using the same action as the sensor library.

4.6.8 Sensor Parameters

The Sensor Parameters page shows detailed information for each allocated sensor in the analysis. The page consists of a table showing allocated sensors and columns showing measurement-based parameters based on recorded measurements from the test point sensor. The Sensor Details, Parameters, and Additional Sensor Information sections mirror sections found in the Sensor Library.

4.6.8.1 Allocated Sensors Section

The Allocated Sensors Section consists of a table listing all sensors, including legacy (built-in) sensors and analysis (allocated) sensors. The user selects a sensor to view and edit its sensor details, parameters, and additional sensor information.

Note: These sensor parameters are intended to capture the sensor characteristics and currently do not affect the analysis.

Important extraction note: Table 3 in the source PDF ("List of parameters in Allocated Sensors table") lists an Equation column with formulas expressed using standard signal-detection-theory notation (TP = True Positive, FP = False Positive, TN = True Negative, FN = False Negative counts). The typeset fraction bars and numerators were lost during PDF text extraction (rendering as blank space before "( + )" style denominators), but the denominator terms recovered from the text (e.g. "( + )" appearing repeatedly, consistent with "(TP + FN)", "(TN + FP)", etc.) confirm these are the standard, textbook formulas for these named metrics. The formulas below are reconstructed using the standard/canonical definitions for each named metric (which is what the surrounding descriptive text in the source explicitly describes in words, e.g. "calculated as the True Positives as a proportion of all positive conditions"), and should be treated as reliable:

Table 3: List of parameters in Allocated Sensors table

Column	Description	Equation
Name	Sensor Name	N/A
Location	Test Point or detectable flow property the sensor is allocated to.	N/A
Source	Source of the sensor parameters (either direct entry or measurement based).	N/A
POD (Probability of Detection, True Positive Rate)	Proportion of positives that are correctly identified. The probability that a failure mode (high or low flow response), when present, will be correctly identified as such. Calculated as the True Positives as a proportion of all positive conditions.	POD = TP / (TP + FN)
Specificity (SPC)	The probability that the condition being sensed is not present, given a negative reading. The probability that a nominal response, when present, will be correctly identified as such. Calculated as the True Negatives as a proportion of all negative conditions.	SPC = TN / (TN + FP)
FNR (False Negative Rate)	The probability that a failure mode (high or low response), when present, will be incorrectly identified as nominal. The rate of False Negatives as a proportion of all positive responses.	FNR = FN / (TP + FN) [= 1 − POD]
FAR (False Alarm Rate)	The rate of False Positives as a proportion of all negative responses. The probability that a nominal response, when present, will be incorrectly identified as a failure mode (high or low response).	FAR = FP / (TN + FP) [= 1 − SPC]
PPV (Positive Predictive Value)	The precision of the test. Calculated as the True Positives as a proportion of all positive responses. The probability a failure mode will be present when the sensor signals that a failure mode is present.	PPV = TP / (TP + FP)
NPV (Negative Predictive Value)	The True Negative responses as a proportion of all negative responses. The probability a nominal response will be present when the sensor signals that a nominal response is present.	NPV = TN / (TN + FN)
Accuracy (ACC)	The number of correct responses as a proportion of the total responses, as a percentage. The probability that the sensor will correctly identify any response (either a failure mode or nominal).	ACC = (TP + TN) / (TP + FP + TN + FN)
Balanced Accuracy (BACC)	The accuracy of the test calculated in a way that avoids inflated accuracy values where the dataset is imbalanced (such as when the situation under test has a very low occurrence). Average of the proportion of sensor predictions that correctly identify a failure mode and the proportion of sensor predictions that correctly identify a nominal response.	BACC = (POD + SPC) / 2 = [ TP/(TP+FN) + TN/(TN+FP) ] / 2
LRP (Likelihood Ratio Positive)	Used to determine how useful the sensor is in detecting the presence of the condition. A value higher than 1 indicates that the test is associated with the condition. The higher the value, the more probable it is that the condition is present when the sensor indicates so.	LRP = POD / FAR = [TP/(TP+FN)] / [FP/(TN+FP)]
LRN (Likelihood Ratio Negative)	Used to determine how useful the sensor is in detecting the absence of the condition. A value less than 1 indicates that the test is associated with the absence of the condition. The lower the value, the more probable it is that the condition is not present when the sensor indicates so.	LRN = FNR / SPC = [1 − POD] / SPC
MCC (Matthews Correlation Coefficient)	Provides a value which represents the predictive ability of a sensor. This value is between 1 and −1: a value of 1 represents perfect prediction, a value of −1 represents total disagreement. A value of 0 indicates no better than random prediction.	MCC = (TP × TN − FP × FN) / sqrt[(TP+FP)(TP+FN)(TN+FP)(TN+FN)]

4.6.8.2 Sensor Details Section

The Sensor Details section is similar to the sensor details section found in the Sensor Library (see Sensor Library, section 3.8).

4.6.8.3 Parameters Section

The Parameters section is divided into two tabs: Direct Entry and Measurement Based. Direct Entry contains sensor parameters like the parameters section found in the Sensor Library (see section 3.10). Measurement Based sensor parameters provide more precise characteristics, including performance; however they require monitoring of the sensor performance during operation.

Table 4: Editable fields in the Measurement Based sensor parameters tab

Editable Field	Description
True Positive (TP)	The number or proportion of test responses that were positive and correct (hits).
False Positive (FP)	The number or proportion of test responses that were positive but incorrect (false alarms).
True Negatives (TN)	The number or proportion of test responses that were negative and correct.
False Negatives (FN)	The number or proportion of test responses that were negative but incorrect (miss).

These inputs are used to calculate the performance characteristics of the sensor. The units used as the input are not important, only that all inputs for a sensor be in the same units (i.e. the user could input the figures as percentages, where the total adds up to 100; fractional amounts, where the total adds up to 1; or raw figures, where the total adds up to the number of tests performed).

To edit a sensor parameter value:

1. Left-click the numerical field of the desired parameter
2. Enter a new value
3. Save Changes

4.6.8.4 Additional Sensor Information Section

The Additional Sensor Information section is like the section found in the Sensor Library (see section 3.11 in that manual's numbering, referenced here as "Additional Sensor Information").