Industrial Machine Fault Prediction Using Learned State Variables
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional fault prediction methods for industrial machines are inadequate in complexity and accuracy, especially as machines become more sophisticated, leading to a need for a more advanced method capable of accurately predicting faults based on real-time conditions.
Innovation Solution
A machine learning device that observes state variables from sensors and internal data, determines fault conditions, and learns using a training dataset to predict faults, with the ability to update based on time-weighted determination data and share learning results across multiple machines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional fault prediction methods are used, then the system is simple to operate, but the measurement precision and reliability of fault detection deteriorate as machine complexity increases
Solution Approach 1:
The system performs self-learning by automatically collecting operational data, identifying normal operation patterns, and establishing baseline behaviors without external intervention. The machine learning device autonomously improves fault detection accuracy by continuously learning from operational data and adapting to specific machine characteristics.
Solution Approach 2:
The system implements feedback mechanisms where fault detection results and operational data are continuously fed back into the learning process. The machine learning device uses determination data about actual faults to refine its understanding of normal versus abnormal patterns, progressively improving detection precision through iterative learning.
2Reliability
If conventional fault prediction methods are used, then the device complexity is low, but the reliability of fault prediction deteriorates for sophisticated machines
Solution Approach 1:
The system performs preliminary learning during normal operation to establish baseline patterns before faults occur. By pre-learning normal operational characteristics and potential failure modes during regular operation, the system builds a knowledge base that enables reliable fault prediction when needed, without requiring complex real-time analysis.
Solution Approach 2:
The machine learning device dynamically adjusts its analysis parameters and decision thresholds based on learned patterns and determination data. By changing parameters such as detection sensitivity, time windows, and pattern matching criteria according to learned machine-specific characteristics, the system achieves reliable predictions adapted to each machine's unique behavior.
3Measurement precision
If machine learning is applied to learn fault conditions, then the fault prediction accuracy improves, but the device complexity and data processing requirements increase
Solution Approach 1:
The learning process is segmented into distinct phases: normal operation pattern learning, fault condition learning using determination data, and prediction execution. By dividing the complex machine learning task into manageable segments with specific objectives, the system achieves high accuracy without overwhelming computational complexity.
Solution Approach 2:
The machine learning device acts as an intermediary layer between raw sensor data and fault prediction decisions. It processes and interprets operational data through learned patterns, translating complex sensor readings into meaningful fault conditions using determination data as guidance, thereby simplifying the overall system architecture.
Data Source
AI summary
A fault prediction system includes a machine learning device that learns conditions associated with a fault of an industrial machine. The machine learning device includes a state observation unit that, while the industrial machine is in operation or at rest, observes a state variable including, e.g., data output from a sensor, internal data of control software, or computational data obtained based on these data, a determination data obtaining unit that obtains determination data used to determine whether a fault has occurred in the industrial machine or the degree of fault, and a learning unit that learns the conditions associated with the fault of the industrial machine in accordance with a training data set generated based on a combination of the state variable and the determination data.