Fault-Tolerant Information Processing via Virtual Sensor Duplication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In automatic driving vehicles and similar systems, the increased number of sensors leads to higher fault probabilities, compromising fault tolerance and reliability, with existing hardware and software measures either increasing hardware size and cost or requiring extensive development time and resources.
Innovation Solution
An information processing apparatus that includes an input data acquisition unit, a fault tolerance requirement acquisition unit, a fault pattern generation unit, a model update unit, and an execution control unit, which acquires and processes sensor data to generate fault patterns and update models to tolerate faults within specified limits, ensuring reliable operation even with faulty sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the number of sensors is increased to perform complicated and advanced information processing, then information processing capability is improved, but fault probability increases and fault tolerance deteriorates
Solution Approach 1:
The system performs preliminary actions by generating multiple candidate results through parallel processing of sensor data with different fault assumptions before actual fault occurrence. The selection unit pre-prepares multiple processing paths assuming various sensor fault patterns, so when a fault actually occurs, the system can immediately select the correct pre-prepared result without delay, maintaining both high processing capability and fault tolerance.
2Reliability
If hardware measures are implemented to multiplex sensors and suppress fault probability, then reliability is improved, but hardware scale becomes large and product cost increases
Solution Approach 1:
Instead of creating physical copies of sensors through hardware multiplexing, the system creates virtual copies by processing the same sensor data through multiple computational paths. The selection unit generates multiple candidate results based on different fault assumptions, effectively copying the processing logic rather than the physical sensors, thereby maintaining fault tolerance without increasing hardware scale.
3Reliability
If software measures are implemented to add processing assuming sensor fault, then fault tolerance is improved, but development time and development cost increase
Solution Approach 1:
The system changes parameters by introducing fault probability weights and selection criteria rather than developing complex fault detection algorithms. The selection unit uses parameter-based selection where each candidate result is associated with a fault assumption and selection probability, allowing the system to adapt to different fault scenarios through parameter adjustment rather than extensive software development.
4Reliability
If multiple candidate results are generated through selection processing, then fault tolerance is improved, but processing time increases
Solution Approach 1:
The system performs preliminary action by pre-generating multiple candidate results through parallel processing before fault occurrence. The selection unit prepares multiple processing paths in advance, each assuming different fault patterns, so when a fault occurs, the system only needs to select from pre-computed results rather than performing extensive real-time analysis, thereby maintaining fast processing speed while improving fault tolerance.
Data Source
AI summary
An information processing apparatus has an input data acquisition unit that acquires a plurality of input data, a fault tolerance requirement acquisition unit that acquires a fault tolerance requirement for the plurality of input data, a training data definition unit that defines an output which satisfies the fault tolerance requirement, a fault pattern generation unit that generates a plurality of fault patterns which include at least one of the plurality of input data based on the plurality of input data and the fault tolerance requirement, a model update unit that updates the information processing model so as to tolerate a fault of the input data satisfying the fault tolerance requirement, and an execution control unit that applies the plurality of input data to the information processing model updated by the model update unit and executes the information processing model.