Anomaly detection models
When you run an anomaly detection model on Maximo® Visual Inspection Edge, you can apply rule conditions to anomaly metadata, and view anomaly metadata in inspection images.
Anomaly models that were trained in earlier versions of Maximo Visual Inspection can run out of memory when the models are deployed in Maximo Visual Inspection 8.7. This issue can also occur in older versions of Maximo Visual Inspection and is affected by the number of images that trained the model and the available memory on the corresponding GPU. Anomaly models that are trained in Maximo Visual Inspection 8.7 require up to 8 GB of memory on the corresponding GPU.
Anomaly metadata
Anomaly metadata are the children of detected object metadata. Each object that is detected by an anomaly model can have one or more anomalies. Anomaly metadata does not exist without a parent object.
Anomaly metadata in inspection rules
When you select an anomaly model in an inspection, you can set inspection rule conditions for anomaly count and anomaly confidence. The rule conditions are evaluated similarly to object conditions, but are applied to the anomaly metadata. For more information about rule conditions, see Inspection rules.
Match all or Match any rule conditions
When you select an inspection rule with Match all conditions, object conditions take precedence over anomaly conditions. For example, when you specify an object confidence score, objects must meet that score before anomaly conditions process their anomaly metadata.
When you select an inspection rule with Match any conditions, all conditions are processed for every object.
Anomaly metadata in inspection images
When you select an anomaly model in an inspection, anomaly metadata is displayed with object data in inspection images. Click the anomaly tag to zoom into the selected anomaly. Click the anomaly tag again to toggle back to the full image view.