Control Device Fault Analysis with Automated Knowledge Base

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current industrial plant control systems only provide generic fault messages without offering specific instructions for remedying faults, limiting the operator's ability to effectively address malfunctions.

Innovation Solution

A control device that generates fault messages and transmits historical data to an automated knowledge base, allowing for tailored responses and instructions based on the specific fault, optionally including additional system information, and in some cases, automatically determining corrective actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If generic fault messages are provided to operators, then the system complexity is reduced and ease of operation is improved, but the manufacturing precision of fault diagnosis is insufficient

Engineering Contradiction:
Improveease of fault handlingVSAvoidprecision of fault diagnosis
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

An automated knowledge base acts as an intermediary between the control device and the operator. The knowledge base receives fault messages and historical data from the control device, processes this information, and generates tailored diagnostic responses and remedial instructions. This intermediary system bridges the gap between simple fault notification and complex diagnostic analysis, providing precise diagnosis without increasing operator burden.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Manufacturing precision

If historical data is transmitted to an automated knowledge base for every fault, then the precision of fault analysis is improved, but the loss of time for data transmission and processing increases

Engineering Contradiction:
Improveprecision of fault analysisVSAvoidtime for fault response
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The control device continuously stores historical data during normal operation before faults occur. When a fault happens, the pre-stored data is immediately available for transmission to the knowledge base, eliminating the need for time-consuming data collection during fault conditions. This preliminary data preparation reduces fault response time while maintaining analysis precision.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system prioritizes and accelerates the transmission of critical historical data relevant to fault diagnosis. By identifying and transmitting only the most relevant data subsets rather than complete historical records, the system rushes through the essential information transfer process, minimizing time loss while ensuring sufficient data for precise fault analysis.

Inventive Principle:
Principle #21Skipping (Rushing through)

3Reliability

If tailored remedial instructions are provided based on specific fault analysis, then the reliability of fault resolution is improved, but the device complexity of the control system increases

Engineering Contradiction:
Improveeffectiveness of fault remediationVSAvoidcomplexity of control system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The automated knowledge base serves itself by maintaining a growing repository of fault cases, diagnostic rules, and remedial instructions. The system automatically updates its knowledge base with new fault patterns and solutions learned from previous incidents, enabling self-improving diagnostic capabilities without requiring proportional increases in control system complexity. The knowledge base autonomously generates tailored instructions based on pattern recognition rather than requiring complex real-time analysis in the control device.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3776117B1Comprehensive fault analysis for control devices and industrial technical installations
Publication Date: 2025.12.03 SIEMENS AG
  • EP3776117B1 patent drawingFigure 1
  • EP3776117B1 patent drawingFigure 2
  • EP3776117B1 patent drawingFigure 3

AI summary

The invention relates to a control device (2) of an industrial technical installation (1), which cyclically receives measurement variables (Z) from sensors (5) of the installation (1) in normal operation, determines control variables (C) for actuators (6) of the installation (1) using the measurement variables (Z) and setpoint variables (Z*) and outputs the control variables (C) to the actuators (6). At least for some of the measurement variables (Z), the control device (2) stores the history thereof at least for a limited time period in the normal operation. In the normal operation, the control device monitors the measurement variables (Z) for the occurrence of a fault. If a fault occurs, the control device (2) transmits a fault message (M) identifying the fault and, at least for some of the measurement variables (Z) for which the control device (2) stores the history thereof, the history to a knowledge base (7) operated in an automated manner. The control device receives a reply (A) from the knowledge base (7) in reaction to the transmission of the fault message (M) and the transmitted histories and outputs the reply (A) to an operator (11) of the control device (2) by means of a display device (10). Before the normal operation is carried out, the control device (2) receives specifications (V) from the operator (11). In the normal operation, the control device defines which histories the control device determines in dependence on the specifications. Alternatively or additionally, when a fault occurs the control device determines, in dependence on the specifications (V), which histories the control device transmits to the knowledge base (7) when a fault occurs.