Data-Driven Model for Material Flow Delivery Prediction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Material flow systems face challenges in obtaining precise and complete data from suppliers, leading to quality losses and reduced effectiveness in material flow simulation, production planning, and order management.

Innovation Solution

A computer-aided procedure generates a data-driven model using machine learning to process digital data from material flow systems, enabling the creation of a production plan for time and/or quantitative control of technical systems by predicting expected delivery information based on historical data and events.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If manual data collection from suppliers is used, then data completeness can be improved, but time consumption and processing complexity increase

Engineering Contradiction:
Improvedata completenessVSAvoidtime consumption
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system automatically collects and processes delivery data from suppliers without requiring manual intervention. The machine learning model autonomously predicts expected delivery times by processing historical data and event information, eliminating the need for manual data collection while maintaining data completeness.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual data collection processes with automated machine learning-based prediction systems. The machine learning model substitutes for manual analysis by automatically processing historical delivery data, supplier information, and event data to generate expected delivery time predictions.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If machine learning-based prediction is used, then data processing speed is improved, but model complexity and computational requirements increase

Engineering Contradiction:
Improvedata processing speedVSAvoidmodel complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system processes data by transforming it into appropriate formats and structures that machine learning models can effectively process. Historical delivery data, supplier information, and event data are converted into structured parameters that enable efficient machine learning prediction while managing computational complexity.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If historical data is used for training, then prediction accuracy is improved, but data storage requirements and processing complexity increase

Engineering Contradiction:
Improveprediction accuracyVSAvoiddata storage requirements
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The system extracts and processes only the necessary historical data elements required for accurate predictions. By selectively extracting relevant features from historical delivery data, supplier information, and event data, the system maintains prediction accuracy while reducing unnecessary data storage requirements.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP4553725A1Method for computer-aided generation of a data-driven model for the computer-aided processing of digital data of a material flow system, and device
Publication Date: 2025.05.14 SIEMENS DIGITAL LOGISTICS GMBH
  • EP4553725A1 patent drawingFigure 1~2
  • EP4553725A1 patent drawingFigure 3
  • EP4553725A1 patent drawing

AI summary

The invention describes a method for the computer-aided generation of a data-driven model (MO) for the computer-aided processing of digital data from a material flow system (MFS) for the temporal and/or quantitative control of a technical system (TS) by means of a production plan (PP). To generate the production plan (PP), provision information is processed from at least one supplier (L1, L2, L3) of a direct supplier network (LN). The generation of the data-driven model comprises, in step i), the provision of a training data set (TDS) that, for a multitude of past deliveries, includes at least one target provision information (SLD, SLM), at least one actual provision information (ILD, ILM), and at least one event (EVT) that causes or can cause a deviation of the actual provision information (ILD, ILM) from the target provision information (SLD, SLM).In step ii), a machine learning (ML) method is trained using the training data set (TDS), wherein the machine learning (ML) method includes an input for reading in at least one planned future delivery information (SLD, SLM) and at least one event (EVT) before or around the planned delivery time, and an output for outputting expected delivery information (ELD, ELM) as the delivery information, wherein the trained machine learning (ML) method represents the generated data-driven model (MO).