Manufacturing Prediction Models for Cost, Time, and Process Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current manufacturing processes lack reliable and objective tools for predicting production aspects such as time, method, and cost, leading to inaccurate and inconsistent estimates due to reliance on human experience.
Innovation Solution
A predictive system using regression machine learning models trained with manufacturing transaction data from a supply chain, combined with a multi-objective optimization model, to generate accurate and consistent predictions for manufacturing processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If human experience is used to predict manufacturing appraisals, then flexibility and adaptability are maintained, but accuracy and consistency deteriorate
Solution Approach 1:
The patent replaces the mechanical system of human estimation with an automated machine learning system. Regression models process manufacturing transaction data to generate predictions, eliminating the need for human estimators while improving accuracy and consistency of manufacturing appraisals including time, cost, and method predictions.
Solution Approach 2:
The patent introduces machine learning models as an intermediary between raw manufacturing data and prediction outcomes. The models process transaction data through trained algorithms, serving as a mediator that transforms historical data into reliable predictions for manufacturing time, cost, and methodology without requiring human interpretation.
2Reliability
If standardized methodologies are implemented for manufacturing predictions, then consistency improves, but adaptability to unique cases worsens
Solution Approach 1:
The patent implements dynamic prediction capabilities where the machine learning system adapts to unique manufacturing cases while maintaining standardized processing. The regression models can handle varying input parameters and produce customized predictions for each manufacturing request, allowing the system to be both consistent in methodology and adaptable to specific product requirements.
3Productivity
If manual estimation processes are used, then implementation simplicity is maintained, but productivity and efficiency worsen
Solution Approach 1:
The patent replaces manual estimation processes with automated machine learning systems that process manufacturing transaction data. This substitution dramatically improves productivity by eliminating time-consuming human estimation while providing consistent, data-driven predictions for manufacturing time, cost, and methodology across all requests.
Solution Approach 2:
The patent implements a self-service prediction system where the machine learning models automatically generate manufacturing appraisals without requiring human intervention. The system serves itself by processing input data through trained regression models and generating predictions independently, reducing overhead and improving efficiency.
4Measurement precision
If comprehensive data processing is implemented, then prediction accuracy improves, but processing time worsens
Solution Approach 1:
The patent applies preliminary action by pre-processing and training the machine learning models on historical manufacturing transaction data before actual predictions are needed. This upfront preparation allows the system to quickly generate accurate predictions during production without time-consuming data processing, as the models have already learned from comprehensive historical data.
Data Source
AI summary
The subject technology is related to methods and apparatus for training a set of regression machine learning models with a training set to produce a set of predictive values for a pending manufacturing request, the training set including data extracted from a set of manufacturing transactions submitted by a set of entities of a supply chain. A multi-objective optimization model is implemented to (1) receive an input including the set of predictive values and a set of features of a physical object, and (2) generate an output with a set of attributes associated with a manufacture of the physical object in response to receiving the input, the output complying with a multi-objective condition satisfied in the multi-objective optimization model.