Anomaly Detection Module for APC Sensor Data Validation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Advanced process controllers (APCs) in industrial process systems are vulnerable to computing incorrect set-points due to low-quality sensor data, leading to potential system failures, especially in harsh environments or when sensors are faulty or clogged.

Innovation Solution

A computer system that monitors the technical status of industrial process systems using an interface module for receiving sensor data, an anomaly detection module applying Machine Learning Models to identify abnormal conditions, and a post-processor to determine root causes, allowing for the deactivation of APCs to prevent incorrect set-point calculations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If APCs use sensor data for computing set-points, then control functionality is provided, but system reliability deteriorates when sensor data quality is low

Engineering Contradiction:
Improvecontrol functionalityVSAvoidsystem reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary anomaly detection on sensor data before the APC uses it for control calculations. The anomaly detection module analyzes sensor data in advance to identify potential issues, and only data passing this preliminary check is forwarded to the APC, preventing unreliable data from compromising control functionality.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary anomaly detection module between the sensor data source and the APC. This intermediary layer filters and validates sensor data, acting as a mediator that protects the APC from processing low-quality data while maintaining the control functionality of the system.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If the system monitors and detects anomalies in sensor data, then reliability is improved, but device complexity increases

Engineering Contradiction:
Improvesystem reliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The anomaly detection module operates autonomously, automatically analyzing sensor data and identifying anomalies without requiring external intervention. The system self-monitors and self-validates the quality of its input data, improving reliability through self-service mechanisms rather than adding complex external monitoring systems.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system segments the control architecture into distinct functional modules: sensor data acquisition, anomaly detection, and APC control. This segmentation allows the anomaly detection function to be added as a separate, manageable component rather than integrating complexity into the existing APC, making the overall system more maintainable and understandable.

Inventive Principle:
Principle #1Segmentation

3Object-affected harmful factors

If the system deactivates APCs upon anomaly detection, then harmful factors are prevented, but productivity decreases

Engineering Contradiction:
Improveharmful factorsVSAvoidproductivity
Core Design Contradiction:
Object-affected harmful factorsVSProductivity

Solution Approach 1:

The system uses inexpensive, easily replaceable sensors that can be quickly swapped if anomalies are detected. Rather than deactivating the entire APC system, the solution allows for rapid replacement of faulty sensor components, preventing harmful effects while minimizing impact on overall system productivity through quick recovery.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Solution Approach 2:

The system dynamically adjusts its response to anomalies based on their severity and type. Rather than always deactivating the APC, the system can apply different strategies including partial deactivation, continued operation with monitoring, or rapid sensor replacement, optimizing the balance between preventing harmful effects and maintaining productivity.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3379357B1Computer system and method for monitoring the technical state of industrial process systems
Publication Date: 2019.07.10 ABB (SCHWEIZ) AG
  • EP3379357B1 patent drawingFigure 1
  • EP3379357B1 patent drawingFigure 2
  • EP3379357B1 patent drawingFigure 3A~3C

AI summary

Computer system (100), computer-implemented method and computer program product are provided for monitoring the technical status of an industrial process system (300) being under control of an advanced process controller (APC). The industrial process system (300) has an operation (330) for processing flow materials. The advanced process controller (APC) is responsive to one or more sensor signals (320). The computer system (100) includes an interface module (110) configured to receive technical status data (321) describing the current technical state of the industrial process system (300) with regards to a respective processing component or the processed material wherein the technical status data (321) corresponds to or is derived from the one or more sensor signals (320). Further, the interface outputs an anomaly alert (AA) in case of an anomaly detection for the industrial process system to enable deactivating of the advanced process controller (APC). The computer system further includes an anomaly detection module (120) to apply one or more Machine Learning Models (MLMn) to the received technical status data (321) to analyze the technical status data for detecting one or more indicators of an abnormal technical status prevailing in the industrial process system. The one or more Machine Learning Models (MLMn) are trained on historic raw or pre-processed sensor data. The anomaly detection module generates the anomaly alert (AA) based on the one or more indicators.