Pocket Sorter Buffer Loading Using Predicted Item Demand
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing sorting conveyor systems are inefficient in terms of cost and resource utilization due to the buffer being loaded only after receiving specific customer orders, leading to peak loads and high processing volumes at certain times, and low volumes at others, with significant personnel and planning efforts required.
Innovation Solution
A control unit predicts future demand and proactively transfers items to the buffer based on anticipated orders, allowing even utilization of logistics resources and minimizing peak loads by filling the buffer with expected items before order receipt.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If the buffer is loaded only after receiving specific customer orders, then the processing volume is low at other times, but peak loads occur at certain times requiring additional personnel and planning efforts
Solution Approach 1:
The system performs preliminary actions by predicting future customer orders using AI/ML algorithms and proactively transferring items to the buffer before actual orders are received. This advance preparation smooths out peak loads by distributing transfer operations evenly across time, eliminating the need for surge capacity during peak periods while maintaining sufficient processing capacity.
2Productivity
If the buffer is loaded in advance based on predicted demand, then peak loads are minimized, but additional forecasting systems and data processing are required
Solution Approach 1:
The patent introduces an intermediary AI/ML forecasting system that sits between the ERP module and the warehouse management system. This intermediary analyzes historical order data, customer behavior, and external factors to generate predicted demand signals, which then guide the buffer loading process. This intermediary layer simplifies the overall system by decoupling the reactive order processing from proactive inventory preparation.
Solution Approach 2:
The system implements feedback loops where actual order data is continuously compared with predicted demand, and the forecasting model is refined based on prediction accuracy. The control unit monitors buffer stock levels and adjusts transfer operations in real-time based on the difference between predicted and actual orders, creating a self-correcting system that improves over time.
3Loss of time
If items are transferred early to the buffer, then order processing time is reduced, but the buffer requires larger capacity to store predicted items
Solution Approach 1:
The system applies partial action by transferring only the predicted quantity of items to the buffer, not all possible items. The AI forecasting model calculates precise predicted demand based on historical data and external factors, and the system transfers exactly that amount, avoiding over-stocking while ensuring sufficient inventory for predicted orders. This partial transfer approach optimizes buffer utilization without requiring excessive capacity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present invention relates to a system for the optimized use of a sorting conveyor, in particular a pocket sorter, comprising a sorting conveyor configured for assembling items into packing orders corresponding to customer orders, wherein the sorting conveyor has a buffer for the temporary storage of items, and wherein the buffer can be connected to a warehouse by means of a conveyor system; and comprising a system control device configured to: - determine the expected demand for items for a future period; - initiate the transfer of the items corresponding to the expected demand from the warehouse to the buffer; - determine the items actually required for the period based on incoming customer orders; - compare the items actually required with the items in the buffer in order to determine the items missing to fulfill the incoming customer orders;- and to initiate the transfer of the missing items from the warehouse to the buffer.