Sensor Correlation Mapping for General-Purpose Equipment Operation Support
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional simulation models for supporting mechanical equipment operations are costly to create and specialize, making them not versatile for general use.
Innovation Solution
An information processing device that generates information for supporting mechanical equipment operations by calculating relationship indices from sensor data, allowing for the creation of correlation maps indicative of equipment states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a simulation model composed of physical and chemical model equations is used to obtain an estimated value of the plant, then the accuracy and reliability of the estimated value is improved, but the cost of creating the model and the complexity of the model increases significantly
Solution Approach 1:
The patent creates a virtual copy of the plant's operational states by collecting and storing sensor data representing normal operational states in a database. Instead of using complex physical-chemical simulation models, the system copies real operational data and uses pattern matching against this data to estimate current plant states, thereby achieving reliable estimates without complex modeling.
Solution Approach 2:
The patent replaces the mechanical/mathematical simulation model system with an information processing system. Instead of solving physical and chemical equations, the system uses data collection, storage, and pattern recognition algorithms to estimate plant states, substituting computational mechanics with information-based processing.
2Reliability
If a simulation model composed of physical and chemical model equations is used to obtain an estimated value of the plant, then the accuracy and reliability of the estimated value is improved, but the time and resources required to create and maintain the model increases
Solution Approach 1:
The patent performs preliminary action by collecting and storing sensor data representing normal operational states in advance, before they are needed for estimation. This pre-collected data serves as a reference database that can be quickly queried during operation, eliminating the need for time-consuming model creation and maintenance while enabling rapid state estimation.
3Reliability
If a simulation model is specialized for a specific plant, then the accuracy for that specific plant is improved, but the versatility and adaptability of the system decreases
Solution Approach 1:
The patent creates a universal system that can estimate states for different types of plants by collecting data on normal operational states for each plant type and storing it in a database. The same pattern-matching algorithm can be applied across different plant types, making the system versatile while maintaining accuracy for each specific plant through its dedicated operational data.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided is a general-purpose device that can be used for supporting an operation of mechanical equipment. An information processing device (1A) includes: a data obtaining section (101) configured to obtain sensor data from a plurality of sensors provided in mechanical equipment; a relationship index calculating section (103) configured to calculate a relationship index indicative of a relationship of a group of sensors among the plurality of sensors, on the basis of a state of distribution of sensor data obtained from the respective sensors of the group; and a map generating section (104) configured to generate, with use of the relationship index, a map indicative of a state of the mechanical equipment.