Abnormality Prediction Using Time-Aligned Multiseries Neural Inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for predicting abnormal events using neural networks face challenges in achieving high prediction accuracy when dealing with multiple data time series from different measurement instruments, especially when there are inconsistencies in measurement times and dimensions.
Innovation Solution
A system and method that reconstructs multidimensional array data from multiple data time series, incorporating relative time values, and uses a neural network structure with an input layer, intermediate layers comprising recurrent neural networks, and an output layer to calculate predictive information on abnormal events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If monitoring devices and sensors are increased to enhance detection accuracy, then abnormality detection capability is improved, but device complexity and costs increase
Solution Approach 1:
The patent introduces a natural language processing intermediary that translates complex sensor data and monitoring information into understandable language. This intermediary layer enables accurate abnormality detection without requiring direct complex interactions between multiple sensors and analysis systems, thus improving detection accuracy while managing system complexity through linguistic mediation
Solution Approach 2:
The patent replaces traditional mechanical and electronic monitoring systems with a language-based processing system. By substituting physical sensor networks and complex electronic analysis with natural language processing and text-based anomaly detection, the system achieves high detection accuracy while reducing device complexity and costs
2Adaptability or versatility
If more monitoring devices and sensors are deployed, then detection coverage is improved, but installation costs and system complexity increase
Solution Approach 1:
The patent creates a universal language-based processing system that can handle multiple types of monitoring data and detect various abnormalities across different contexts. This multi-functional approach allows the system to achieve comprehensive detection coverage without requiring separate specialized devices for each monitoring task, thereby reducing overall system complexity
Solution Approach 2:
The natural language processing intermediary serves as a universal mediator that can process and interpret diverse monitoring information from different sources and contexts. This single intermediary component provides broad detection coverage across multiple monitoring scenarios without requiring proportional increases in system complexity
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
A system for abnormality prediction is provided, which is able to precisely predict occurrences of abnormal events by using a neural network even in the case where inconsistency between multiple data time series obtained by a plurality of measurement instruments occurs. The system for abnormality prediction includes: a data reconstruction system configured to reconstruct, from the plurality of data time series, multidimensional array data that includes, as array elements, a plurality of measurement parameters and a plurality of relative time values that are assigned to the measurement parameters, respectively; and an inference calculator configured to calculate predictive information on the abnormal event, by performing calculation based on a neural network structure which includes an input layer for receiving the multidimensional array data, an intermediate layer structure containing one or more recurrent neural networks, and an output layer.