Tag Alias | The display name of the tag. This value is inherited from the analytic template and cannot be modified. |
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. |
Active in Deployment | Depending on whether the tag is an input tag or an output tag, if this check box is selected, one of the following will occur:- For an input tag, data will be collected at every data collection interval.
- For an output tag, data will be produced at every data collection interval.
The collection of deployment-specific settings and data for this tag are collectively referred to as a deployment tag. |
Source Tag | The time series ID of the tag. This value can be modified. |
Description | The description of the tag. |
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. |
Actual High | Threshold used in rules to determine whether data is outside of expected limits. |
Actual Low | Threshold used in rules to determine whether data is outside of expected limits. |
Active in Model | If selected, this tag is included as part of the model and is used in predictions and data modeling. If it is deactivated, it is not used in predictions and data modeling. The collection of model-specific settings and data for this tag are collectively referred to as a model tag. |
Alarm Type | Defines the algorithm used to trigger residual indications.
Algorithm | Description |
---|
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. |
|
Residual (Positive) | The maximum absolute value allowed for a positive residual (that is, when the estimate is above the actual for a signal). See details in the Alarm Type description. |
Residual (Negative) | The maximum absolute value allowed for a negative residual (that is, when the estimate is below the actual for a signal). See details in the Alarm Type description. |
Actual Mean | The mean of the actual values for a tag included in the reference values. This attribute is automatically evaluated when creating a state matrix. |
Actual Standard Deviation | The standard deviation of the actual values for a tag included in the reference values. This attribute is automatically evaluated when creating a state matrix. |
Adaptation High | Upper threshold used to determine the range of data that can be adapted into models from runtime using the auto-adaptation algorithms. |
Adaptation Low | Lower threshold used to determine the range of data that can be adapted into models from runtime using the auto-adaptation algorithms. |
Data Type | The data format of the tag. The options are Float, Integer, Boolean, String, or Date. This value is inherited from the analytic template and cannot be modified. |
Decimals | 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. |
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. |
Flatline 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 flatlined, and will be filtered out of training data. |
Instance Tag ID | Automatically generated unique ID for the tag. This value cannot be modified. |
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. |
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. |
Model Tag ID | Automatically generated unique ID for the tag. This value cannot be modified. |
Notes in Instance | Notes about the analytic instance. |
Notes in Template | Notes about the analytic template. This value is inherited from the analytic template and cannot be modified. |
Notes in Model | Notes about the configuration of the tag for the selected model. |
Outlier (Negative) | Threshold used for outlier rules. Data outside of Outlier limits appear as NaNs in charts. |
Outlier (Positive) | Threshold used for outlier rules. Data outside of Outlier limits appear as NaNs in charts. |
Residual Variance | The variance of the residual values for a tag included in the reference values. This attribute is automatically evaluated when creating a state matrix. Residual values are calculated by modeling the reference values not included in the state matrix. |
Spike Sensitivity | The sensitivity of the spike detection algorithm used to detect spikes in tag signals. A lower value will detect more spikes, but may also generate false positives. Spike data will be filtered out of training data. |
SPRT (Negative) | 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. |
SPRT (Positive) | 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. |
Step High | Threshold used for step-change rules. |
Step Low | Threshold used for step-change rules. |
Tag Order | The order of the tags in the deployment. This value is inherited from the analytic template and cannot be modified. |