Reference

Input Tag and Output Tag Field Descriptions

This topic describes the fields that can be viewed in the Input Tag and Output Tag grid.


Column	Description
Actions	In this column, you can select to modify a tag, or you can select to delete a tag. If the tag is configured to generate a calculated value, appears in this column. You can select to view the formula for the calculation.
Name	The name of the tag.
Calculated Estimate	Estimate generated by a user defined expression rather than the reference data selection algorithm.
Description	The description of the tag.
Actual High	Thresholds used in rules to determine whether data is outside of expected limits.
Actual Low
Adaptation High	Upper and lower thresholds used to determine the range of data that can be adapted into models from runtime using the auto-adaptation algorithms.
Adaptation Low
Tag ID	Automatically generated unique ID for the tag. This value cannot be modified.
Measurement Units	The units of measure for the source data of the tag, such as degrees (C) or percentage (%). This is used only as an identifying label and is displayed on the y-axis when the tag is used in model training data charts.
Standard Units	The units of measurement for the source data for the tag.
Data Type	The data format of the tag. The options are Float, Integer, Boolean, String, or Date. The data type cannot be changed once a tag is added and the analytic template is saved.
Tag Type	If the tag is configured to generate a calculated value, appears in this column. You can select to view the formula for the calculation.
Decimal Scale	The number of decimal places included in the tag readings. This value is inherited from templates imported from Classic SmartSignal Blueprint Center. It is not used in APM and cannot be modified.
Step High Threshold	Thresholds used for step-change rules.
Step Low Threshold	Thresholds used for step-change rules.
Notes	Notes about the tag.
Chart Y Min	Chart Y Min and Max values override default chart automatic scaling on the y-axis. In other words, by default, analysis charts are automatically scaled on the y-axis based on tag reading values. For example, if you have a tag with reading values that range from 10 through 30, the bottom of the y-axis in the chart has a value of 10, and the top of the y-axis has a value of 30. If you prefer to see a chart that starts at 0 and ends at 50 in the y-axis, you can enter 0 in the Chart Y Min column and 50 in the Chart Y Max column. Note: If you imported an analytic template from a SmartSignal Classic blueprint, if that blueprint had Chart Y Min and Max values, those values are maintained in APM.
Chart Y Max

Constant Tag Field Descriptions

This topic describes the fields that can be viewed in the Constant Tag grid.

Table 1. Analytic Level Constants
Column	Description
Actions	In this column, you can select to modify a tag, or you can select to delete a tag.
Name	The name of the tag.
Description	The description of the tag.
Data Type	The data format for the tag. The options are Float, Integer, Boolean, String, or Date. Once a tag is added and the analytic template is saved, you cannot modify the data type.
Default Value	The default value for the tag. Note: For constant tags with a type of Date, no default value can be selected.
Notes	Notes about the tag.

Table 2. Model Level Constants
Column	Description
Actions	In this column, you can select to modify a tag, or you can select to delete a tag.
Name	The name of the tag.
Mode	The mode with which the tag is associated.
Model	The model with which the tag is associated.
Description	The description of the tag.
Data Type	The data format for the tag. The options are Float, Integer, Boolean, String, or Date. Once a tag is added and the analytic template is saved, you cannot modify the data type.
Default Value	The default value for the tag. Note: For constant tags with a type of Date, no default value can be selected.
Notes	Notes about the tag.

Modes Field Descriptions

This topic describes the fields that can be viewed in the Modes grid.


Field	Purpose
Actions	In this column, you can select to modify a tag, or you can select to delete a tag.
Name	The name for the mode analytic template.
Description	The description for this mode analytic template.
Expression	The expression used to define the mode condition.
Is Valid	Boolean value used to determine the validity of the expression.
Notes	The notes for this mode analytic template.

Models Field Descriptions

This topic describes the fields that can be viewed in the Models grid.


Field	Purpose
Actions	In this column, you can select to modify a tag, or you can select to delete a tag.
Display Name	The name of the model analytic template.
Mode	The mode with which the tag is associated.
Description	Description of the model analytic template.
Estimate Generator	A reference data selection algorithm used to generate estimated values. There are two types of estimate generators: SBM Similarity Based Model VBM Variable Similarity Based Model
Similarity Operator	One of the following algorithms used for modeling: SSCOP2 A similarity operator used during estimate generation. It is most useful for auto associative modeling. It tends to be a more fault tolerant than SSCOP3. SSCOP3 An alternative similarity operator. It provides a smoother estimate of the response variables, and tends to perform better in inferential modeling cases. However, it is less fault tolerant than SSCOP2 which is why we often assume that the predictor (input) variables can be considered good. If it turns out not to be the case, spillover can occur in one or more of the response variables (inferred variables).
Enable VSG	Specifies whether or not virtual signal generation is enabled. If NaNs and/or outliers are encountered and the number of tags containing bad data is below the Maximum % of Bad Tags threshold, the system will fill in the missing or bad data for modeled tags with virtual signal data.
Max Percentage of Bad Tags	The percentage threshold above which the system inhibits virtual signal generation.
Variance Scale Factor	A multiplier for the standard deviation of normal residual signals.
Residual Smoothing - Smoothing Algorithm	Moving Average The simplest of the three smoothing algorithms. It is a moving window technique where the system averages the data within each window to produce the filtered sample for each window. Although simple and computationally efficient, there is an inherent delay in the response of the filter that is proportional to the window size. Also, the presence of a spike in the input data will affect the output signal for the length of the window size. Spline A real-time moving window technique that employs a cubic-spline fit to each of the individual sliding windows. The spline filter can produce a filtered signal with very little delay, but this is more computationally expensive. Also, a spike in the input data results in a shift in the output, but this effect will be short-lived compared to the moving average filter. Olympic This filter is very similar to the Moving Average filter, but the system does not use the maximum and minimum data samples for each window in the calculation of the average value. The resulting filter is very computationally efficient and effective at removing spikes. However, it suffers from the same response delay as the Moving Average filter.
Residual Smoothing - Window Size	The total window (the number of data points or persistence) to use for smoothing.
Residual Smoothing - Spline	A number between 0 and 1, where the value 0 causes the greatest smoothing and a value of 1 results in no smoothing (the output values equal the input values). A typical default value is 0.1.
State Matrix Creation - Down Sample Algorithm	One of the following algorithms that is used when creating the state matrix: Min Max This algorithm finds where the maximum and minimum values for each tag occur and then uses those samples as the basis for the state matrix. If the same vector is identified from two different tags, the redundancy is eliminated. This method provides the minimum number of vectors in the training matrix. Vector Ordering This algorithm is the recommended choice. This algorithm identifies samples to include in the state matrix by spacing the magnitudes of each training snapshot. A training snapshot is a data sample containing a reading from each tag. If the same vector is identified from two different tags the redundancy is eliminated. The appropriate target number of observations in the state matrix is entered in the Target Vectors box. This method is useful for data that contains many states and is non-stationary (i.e., the mean of the tags varies over time). Min Max Split This method applies the MinMax algorithm to equal-sized sections of data. This method returns more data than the MinMax method, so you can use this method if the MinMax method does not return enough observations for model training. When this method is selected, the Reference Data Splits box appears.
Maximum Vectors	The maximum number of vectors to include in the state matrix. This option works with models that have auto adaptation. If the maximum vectors are larger than the target vectors, it will increase the size of the state matrix. For example, if the target vectors is set to 25 and the maximum vectors is set to 50, the first 25 times auto adaptation occurs, the state matrix will become larger, then it will stop increasing at 50. If the maximum vectors is smaller than the target vectors, this field will have no effect.
State Matrix Creation - Target Vectors	The number of vectors that will be targeted when the state matrix is created. Used when Vector Ordering is specified in the Downsample Algorithm box.
VBM - Fixed Size LocalD	Fixed The VBM state matrix will contain exactly this many vectors. Variable The VBM state matrix will select a number of vectors between the minimum and maximum (below).
Similarity Percentile	Threshold used to determine whether or not vectors are different enough from each other to both be considered for the VBM state matrix.
Redundancy Check Time	Specifies when redundancy checks are to be executed (e.g., during runtime or setup of the model).
Reference Data Splits	The number of sections to which the MinMax algorithm should be applied. Used when Min Max Split is specified in the Downsample Algorithm box.
Notes	Notes about the model analytic template.
Created Date	Date the model analytic template was created.
Last Changed Date	Date the model analytic template was last modified.

Model Tags Field Descriptions

This topic describes the fields that can be viewed in the Model Tags grid.


Column	Description
Actions	In this column, you can select to modify a tag, or you can select to delete a tag.
Name	The name of the tag.
Is In Model	If selected, this analytic template tag will be included as part of the model blueprint. The collection of model-specific settings and data for this tag are collectively referred to as a model tag.
Mode	The mode with which the tag is associated.
Model	The model with which the tag is associated.
Alarm Type	Defines the algorithm used to trigger residual indications. None Disables residual indications for the residual signal for the tag. SPRT This is a specialized decision algorithm called the Sequential Probability Ratio Test (SPRT). The system can apply it when the residuals are normally distributed and serially uncorrelated. The algorithm uses a statistical hypothesis testing technique to determine if the mean of the residual has shifted in the positive or negative direction. Residual Threshold This is the default value. It triggers a residual indication if the residual signal of the tag exceeds the value in the Positive Residual Threshold column or falls below the value in the Negative Residual Threshold column. Smoothed Residual Threshold Triggers a residual indication if the smoothed residual signal of the tag exceeds the value in the Residual + Threshold column or falls below the value in Residual - Threshold column. This method is used to remove spike data and noise from the residuals.
Is Independent	Inferential models use an observation of measured signal values to generate one or more estimated signal values not present in the observation of measured signal values. When using this method, this field indicates whether the independent variables should represent all of the drivers for the dependent output variables.
Is Driver	Any tags with this selected will be looked at to determine if a new operating state is occurring to trigger auto adaptation. At least one tag must be checked to enable auto-adaptation.
Residual Variance	Used to set a custom value of residual variance for use by the SPRT algorithm. If not set, each Asset will use the variance if the residual across its training data. Do not change this setting without fully understanding what it does.
Negative Outlier Threshold	Threshold used for outlier rules.
Positive Outlier Threshold	Threshold used for outlier rules.
Negative Residual Threshold	The maximum absolute value allowed for a negative residual (i.e., when the estimate is below the actual for a signal). See details in the Alarm Type column.
Positive Residual Threshold	The maximum absolute value allowed for a positive residual (i.e., when the estimate is above the actual for a signal). See details in the Alarm Type column.
Negative SPRT Sensitivity	The negative values for the sensitivity of the SPRT. This value is multiplied by the standard deviation of the residual, which in turn defines the amount of negative change in the residual mean that must occur to constitute an alarm.
Positive SPRT Sensitivity	The positive values for the sensitivity of the SPRT. This value is multiplied by the standard deviation of the residual, which in turn defines the amount of positive change in the residual mean that must occur to constitute an alarm.
Model Tag Display Name	The display name of the tag.
Data Type	The data format for the tag. The options are Float, Integer, Boolean, String, or Date.
Tag Type	The type of tag (i.e., Input, Output, or Constant).
Description	The description of the tag.
Filter High	The upper filtering threshold. This field sets the upper threshold value for filtering of tag signals to remove data outside the normal operating range. Any tag data greater than this value is considered an outlier. Outliers will be filtered out of training data.
Filter Low	The lower filtering threshold. This field sets the lower threshold value for filtering of tag signals to remove data outside the normal operating range. Any tag data less than this value is considered an outlier. Outliers will be filtered out of training data.
Flat Line Number	If the data for this tag remains at the same level for more than this number of data points, the data will be considered to be flat lined, and will be filtered out of training data.
Spike Sensitivity	The sensitivity of the spike detection algorithm used to detect spikes in tag signals. A higher value will detect more spikes, but may also generate false positives. Spike data will be filtered out of training data. Do not change this setting without fully understanding what it does.
Notes	The notes for the tag.

Diagnostic Rules Field Descriptions

This topic describes the fields that can be viewed in the Diagnostic Rules grid.


Field	Purpose
Actions	In this column, you can select to modify a tag, or you can select to delete a tag.
Name	The name for the diagnostic rule.
Expression	The expression used to define the mode condition.
Is Valid	Boolean value used to determine the validity of the expression.
Startup Suppression Poll Cycles	Specifies the number of poll cycles the rule will be suppressed (that is, not evaluated) after the asset enters a new mode.
Active	Boolean values that determines whether the tag is active or inactive.
Description	The description for the diagnostic rule.
Notes	The notes for the diagnostic rule.

Tag Rules Field Descriptions

This topic describes the fields that can be viewed in the Tag Rules grid.


Field	Purpose
Actions	In this column, you can select to modify a tag, or you can select to delete a tag.
Display Name	Displays the name of the rule. A green check mark displayed next to the name field indicates that the item is ready to be used. A yellow triangle indicates that the rule is not ready to be used. Hover over the yellow triangle to see which information is missing from the rule.
Description	A description for this rule.
Mnemonic	Abbreviation used to identify the rule to assist with references in diagnostics rules.
Suppression Poll Cycle	Specifies the number of poll cycles the rule will be suppressed (that is, not evaluated) after the asset enters a new mode.
Priority	The priority of the rule; affects display of advisories in the application.
Message	Configures the message that will appear for the advisory. There are four options that can be displayed in the message: Source Tag, Description, Alias, and Asset.
Expression	The expression used to define the mode condition.
Notes	Notes for this rule.