IMAD-DS: A Dataset for Industrial Multi-Sensor Anomaly Detection Under Domain Shift Conditions

IMAD-DS is a dataset developed for multi-rate multi-sensor anomaly detection (AD) in industrial environments, that considers varying operational and environmental conditions known as domain shifts.

Dataset Overview:

This dataset includes data from two scaled industrial machines: a robotic arm and a brushless motor.

It includes both normal and abnormal data recorded under various operating conditions to account for domain shifts. These shifts are categorized into:

Robotic Arm: The robotic arm is a scaled version of a robotic arm used to move silicon wafers in a factory. Anomalies are created by removing bolts at the nodes of the arm, resulting in an imbalance in the machine.
Brushless Motor: The brushless motor is a scaled representation of an industrial brushless motor. Two anomalies are introduced: first, a magnet is moved closer to the motor load, causing oscillations by interacting with two symmetrical magnets on the load; second, a belt that rotates in unison with the motor shaft is tightened, creating mechanical stress.

The following domain shifts are included in the dataset:

Operational Domain Shifts: Variations caused by changes in machine conditions (e.g., load changes for the robotic arm and speed changes for the brushless motor).

Environmental Domain Shifts: Variations due to changes in background noise levels.

Combinations of operating and environmental conditions divide each machine's dataset into two subsets: the source domain and the target domain. The source domain has a large number of training examples. The target domain, instead, has limited training data. This discrepancy highlights a common issue in the industry where sufficient training data is often unavailable for the target domain, as machine data is collected under controlled environments that do not fully represent the deployment environments.

Data Collection and Processing:

Data is collected using the STEVAL-STWINBX1 IoT Sensor Industrial Node. The sensor used to record the dataset are the following.

·        Analog Microphone (16 kHz)

·        3-axis Accelerometer (6.7 kHz)

·        3-axis Gyroscope (6.7 kHz)

Recordings are conducted in an anechoic chamber to control acoustic conditions precisely

Data Format:
Files are already divided into train and test sets. Inside each folder, each sensor's data is stored in a separate '.parquet' file.

Sensor files related to the same segment of machine data share a unique ID. The mapping of each machine data segment to the sensor files is given in .csv files inside the train and test folders. Those .csv files also contain metadata denoting the operational and environmental conditions of a specific segment.