18212486. METHOD OF LEARNING NEURAL NETWORK, RECORDING MEDIUM, AND REMAINING LIFE PREDICTION SYSTEM simplified abstract (NEC Corporation)
Contents
METHOD OF LEARNING NEURAL NETWORK, RECORDING MEDIUM, AND REMAINING LIFE PREDICTION SYSTEM
Organization Name
Inventor(s)
Masanao Natsumeda of Tokyo (JP)
METHOD OF LEARNING NEURAL NETWORK, RECORDING MEDIUM, AND REMAINING LIFE PREDICTION SYSTEM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18212486 titled 'METHOD OF LEARNING NEURAL NETWORK, RECORDING MEDIUM, AND REMAINING LIFE PREDICTION SYSTEM
Simplified Explanation
The abstract describes a method for training a neural network to predict the remaining life of a target device that requires maintenance. The neural network consists of two models: the first model predicts the remaining life at any given time during the maintenance cycle, while the second model predicts the remaining life at the end of the maintenance cycle. The method involves updating the weight parameter of the first model using the outputs of both models obtained from a dataset of multiple maintenance cycle data.
- The method trains a neural network to predict the remaining life of a target device.
- The neural network consists of two models: one predicts the remaining life at any time during the maintenance cycle, and the other predicts the remaining life at the end of the maintenance cycle.
- The weight parameter of the first model is updated using the outputs of both models obtained from a dataset of multiple maintenance cycle data.
Potential Applications
- Predictive maintenance: This method can be applied to various industries where predicting the remaining life of devices is crucial for efficient maintenance planning.
- Equipment optimization: By accurately predicting the remaining life of a device, companies can optimize their equipment usage and minimize downtime.
- Cost reduction: Predicting the remaining life of a device can help companies plan maintenance activities more effectively, reducing unnecessary maintenance costs.
Problems Solved
- Uncertainty in maintenance planning: This method provides a more accurate prediction of the remaining life of a device, allowing for better planning and scheduling of maintenance activities.
- Downtime reduction: By predicting the remaining life of a device, companies can proactively address maintenance needs, minimizing unexpected breakdowns and reducing downtime.
- Costly maintenance: Accurate predictions of remaining life can help companies avoid unnecessary maintenance activities, reducing costs associated with maintenance and replacement.
Benefits
- Improved maintenance planning: The method enables companies to plan maintenance activities more effectively by predicting the remaining life of a device.
- Increased equipment uptime: By proactively addressing maintenance needs based on accurate predictions, companies can minimize unexpected breakdowns and maximize equipment uptime.
- Cost savings: Accurate predictions of remaining life help companies avoid unnecessary maintenance activities, reducing costs associated with maintenance and replacement.
Original Abstract Submitted
Provided is a method of learning a neural network that predicts a remaining life of a target device that is a maintenance target. The neural network includes: (i) a first model for predicting a remaining life at an arbitrary time of maintenance cycle data, as a value based on an arbitrary reference value; and (ii) a second model for predicting a remaining life at a final time of the maintenance cycle data, as a value based on the reference value. The method comprises updating a weight parameter of the first model so as to predict a remaining life based on an end of the maintenance cycle data, by using an output of the first model and an output of the second model that are obtained from learning data including a plurality of maintenance cycle data.
