Feedback Control Fault Detection Using Parallel Program Instances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing hardware fault detection methods in computer-based systems, particularly in autonomous machines, are inefficient and incur significant resource overhead, and are ineffective against unpredictable phenomena like neutron bombardment and electromagnetic interference.
Innovation Solution
Implementing multiple instances of control programs that execute simultaneously and compare their outputs to detect hardware faults, using methods such as round-robin data distribution and majority voting to maintain processor overhead and enhance detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple instances of control programs are executed simultaneously to detect hardware faults, then fault detection accuracy is improved, but processor overhead increases
Solution Approach 1:
The control program is divided into multiple independent instances that execute simultaneously. Each instance processes sensor data independently and generates control commands. By segmenting the program into multiple instances, the system can compare outputs to detect hardware faults while distributing the computational load across different processor cores or processing units, thereby managing overhead.
Solution Approach 2:
The system implements a feedback mechanism where outputs from multiple program instances are continuously compared. When discrepancies are detected between instances, the system identifies potential hardware faults and can trigger corrective actions. This feedback loop enables real-time fault detection without requiring significant additional processing resources beyond the parallel instance execution.
2Reliability
If redundant hardware blocks and repeated processing steps are used to detect and compensate for faults, then system reliability is improved, but area, resource, and power overhead increase
Solution Approach 1:
Instead of using redundant hardware blocks, the system creates software copies of the control program that execute in parallel. Multiple instances of the same program are run simultaneously on available processor resources, comparing their outputs to detect faults. This software-based copying approach achieves fault detection without adding physical hardware complexity.
Solution Approach 2:
The existing processor hardware is used for multiple purposes: it executes the primary control program while simultaneously running multiple instance copies for fault detection. The same processing units serve both control functions and fault detection functions, eliminating the need for dedicated redundant hardware blocks and reducing overall system complexity.
3Reliability
If software-based error detection and correction techniques are implemented, then fault detection capability is improved, but computing overhead and implementation complexity increase
Solution Approach 1:
The fault detection functionality is merged with the primary control program execution. Multiple instances of the control program itself are used for detection, rather than implementing separate error detection software. This merging approach reduces implementation complexity by using the existing control logic for both control and fault detection purposes.
Solution Approach 2:
The control program instances perform self-diagnosis by comparing their own outputs. Each instance independently executes the control logic and generates commands, then these outputs are compared to detect discrepancies. The system uses its own operational data for fault detection without requiring external monitoring software, reducing implementation complexity.
Data Source
AI summary
Systems and methods for detecting hardware faults in computer-based feedback control systems. Multiple instances of the system control program(s) are run on system processors. System sensor data are input to each instance, and the control commands output by each instance are compared. As instantiations of the same programs receive largely the same sensor data, differences between output commands may indicate the presence of one or more hardware faults.