A croston-xgboost forecasting method for aero-engine spare demand
A technology of aero-engine and prediction method, which is applied to computer parts, instruments, biological neural network models, etc., and can solve the problems of low accuracy of aero-engine spare demand forecasting
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0016] Specific implementation mode 1: The specific process of the Croston-XGBoost forecasting method for the spare engine demand of the aero-engine in this implementation mode is as follows:
[0017] Step 1. Based on the Croston method, the original observation sequence of intermittent spare demand is converted into a spare demand interval sequence and a spare demand quantity sequence;
[0018] Step 2: Construct the XGBoost model;
[0019] Step 3, based on step 1 and step 2, establish a spare demand interval prediction model and a demand forecast model (Croston-XGBoost spare demand forecast model);
[0020] Step 4: Based on the forecasting model for the interval of demand for spare parts and the forecasting model for demand for spare parts obtained in step 3, predict the deviation from the total cost index.
specific Embodiment approach 2
[0021] Specific embodiment 2: The difference between this embodiment and specific embodiment 1 is that in the first step, based on the Croston method, the original observation sequence of intermittent spare hair demand is converted into a spare demand interval sequence and a spare demand quantity sequence; the specific process for:
[0022] According to the characteristics of spare parts demand, spare parts demand can be divided into continuous demand and discontinuous demand. The characteristic of intermittent spare parts demand is that there are a large number of "0" demand samples mixed in the original observation sequence of spare parts demand. If the occurrence of non-zero demand is defined as spare parts demand response, the characteristics of intermittent spare parts demand response can be expressed as the interval between two adjacent spare parts demand responses is greater than the observation time unit of spare parts demand. According to the judgment standard propose...
specific Embodiment approach 3
[0035] Embodiment 3: The difference between this embodiment and Embodiment 1 or 2 is that the XGBoost model is constructed in the step 2; the specific process is:
[0036] In the demand quantity and demand interval forecasting model, the XGBoost model is expressed as:
[0037]
[0038] Among them, F represents the function space composed of all trees, {f 1 , f 2 ,..., f K} represents the K regression trees to be sought by the XGBoost model, Indicates the predicted value of sample i; x i means y i or d i ;
[0039] When training the prediction model, the optimization goal is generally to minimize the loss function. The loss function of the XGBoost method includes both the prediction error term and the regularization term, which can simultaneously consider the prediction accuracy and the generalization of the model during the model training process. The loss function of the XGBoost model is written as:
[0040]
[0041] in, is the prediction error for sample i, y...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More - R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com