Generalized-Gamma MAP Estimation for Fleet Maintenance Forecasting

Solution Overview

Problem

Existing methods for determining distribution parameters for vehicle fleet data require high computational power and data volume, and do not effectively utilize prior beliefs, leading to inefficiencies in forecasting key performance indicators and scheduling maintenance.

Innovation Solution

The method employs Maximum A Posteriori (MAP) estimation using conjugate priors to determine distribution parameters for generalized-gamma family distributions, reducing computational requirements and enabling accurate forecasting of key performance indicators for vehicle fleets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If Maximum Likelihood Estimation or Monte Carlo methods are used to determine distribution parameters, then measurement precision is improved, but use of energy increases and productivity decreases

Engineering Contradiction:

Improvedistribution parameter estimation accuracyVSAvoidcomputational power requirements

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent changes the estimation approach from Maximum Likelihood Estimation or Monte Carlo methods to Maximum A Posteriori estimation with conjugate priors. This parameter change in the mathematical methodology reduces computational complexity while maintaining estimation accuracy, directly resolving the contradiction between measurement precision and energy use.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent employs conjugate priors that enable closed-form solutions, replacing computationally expensive iterative methods. This approach uses simpler, more efficient mathematical operations that consume less computational energy while achieving the same estimation objectives.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

2Measurement precision

If Maximum Likelihood Estimation or Monte Carlo methods are used to determine distribution parameters, then measurement precision is improved, but productivity decreases

Engineering Contradiction:

Improvedistribution parameter estimation accuracyVSAvoidforecasting efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent changes the estimation approach from Maximum Likelihood Estimation or Monte Carlo methods to Maximum A Posteriori estimation with conjugate priors. This parameter change in the mathematical methodology reduces computational complexity while maintaining estimation accuracy, directly resolving the contradiction between measurement precision and energy use.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent uses conjugate priors that incorporate prior beliefs about the distribution parameters before observing data. This preliminary action of encoding prior knowledge into the estimation process accelerates convergence and reduces the computational steps needed to achieve accurate parameter estimates, thereby improving productivity.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If large amounts of data are collected for fleet analysis, then measurement precision is improved, but use of energy increases

Engineering Contradiction:

Improveforecast accuracyVSAvoidcomputational resources

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent changes the estimation approach from Maximum Likelihood Estimation or Monte Carlo methods to Maximum A Posteriori estimation with conjugate priors. This parameter change in the mathematical methodology reduces computational complexity while maintaining estimation accuracy, directly resolving the contradiction between measurement precision and energy use.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent uses conjugate priors that incorporate prior beliefs about the distribution parameters before observing data. This preliminary action of encoding prior knowledge into the estimation process accelerates convergence and reduces the computational steps needed to achieve accurate parameter estimates, thereby improving productivity.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250258494A1Method for Determining Maximum A Posteriori Estimates of Generalized-Gamma Family Distributions

Publication Date: 2025.08.14 THE BOEING CO

AI summary

A method of receiving operation data about a collection of machines. The operation data characterizes one or more aspects of the operation of at least one machine of the collection of machines. The method further includes establishing a first conjugate prior or a second conjugate prior for a first distribution probability density function. The method further includes performing, based on the operation data and the first and second conjugate priors for the first distribution probability density function, a Maximum A Posteriori (MAP) estimation to determine distribution parameters for the first distribution probability density function. The data are samples of the key performance indicator. The method further includes predicting, based on the distribution parameters, a probability the key performance indicator will take a value for a number of the machines. In addition, the method includes scheduling maintenance for the machines based on the probability.