Solder Paste Printer Parameter Prediction for Faster PCB NPI

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The surface mount technology (SMT) process for printed circuit board (PCB) manufacturing is inefficient due to the reliance on trial and error to determine optimal solder paste screen printer (SPSP) printing parameters, leading to high costs and lengthy new product introduction (NPI) times.

Innovation Solution

A system comprising a device that communicates with the SPSP and a solder paste inspection device (SPI) to establish and train prediction models for determining optimal printing parameters, reducing the need for trial and error by using machine learning algorithms to analyze data and provide precise parameter settings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If trial and error method is used to determine printing parameters, then manufacturing precision can be achieved, but productivity is reduced and time is lost

Engineering Contradiction:

Improveprinting parameter optimizationVSAvoidNPI time

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The system performs preliminary actions by collecting printing parameter data and inspection results in advance, training prediction models beforehand, and establishing a database of optimal parameters. When a new product requires printing parameters, the system can quickly retrieve and apply pre-determined optimal settings rather than performing trial and error during the NPI phase, thus reducing NPI time while maintaining manufacturing precision.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical trial-and-error adjustment process with an automated information processing system. The prediction model automatically analyzes product specifications, retrieves optimal printing parameters from the database, and provides recommendations without requiring manual trial printing and adjustment. This substitution of manual mechanical adjustment with automated computational methods significantly reduces time while maintaining or improving parameter optimization quality.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If trial and error method is used to determine printing parameters, then manufacturing precision can be achieved, but loss of time increases

Engineering Contradiction:

Improveprinting parameter optimizationVSAvoidNPI time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where inspection results from the SPI device are fed back into the prediction model to continuously improve parameter recommendations. The system learns from past printing outcomes and adjusts future parameter suggestions, enabling faster convergence to optimal settings without repeated trial and error cycles, thereby reducing time loss while maintaining precision.

Inventive Principle:

Principle #23Feedback

3Manufacturing precision

If trial and error method is used to determine printing parameters, then manufacturing precision can be achieved, but device complexity increases

Engineering Contradiction:

Improveprinting parameter optimizationVSAvoidparameter adjustment process

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system enables self-service by allowing the prediction model to automatically determine optimal printing parameters based on product specifications without requiring manual intervention from placement engineers. The system autonomously queries the database, applies the prediction model, and generates parameter recommendations, eliminating the need for complex manual trial and error processes while maintaining manufacturing precision.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent introduces an intermediary prediction model that mediates between product specifications and printing parameters. Instead of requiring direct manual trial and error adjustment, the prediction model acts as an intelligent intermediary that translates product requirements into optimal printing settings, simplifying the overall process while maintaining precision.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11635743B2Parameters suggestion system of solder paste screen printer including method, device employing method, and non-transitory storage

Publication Date: 2023.04.25 FULIAN PRESION ELECTRONICS (TIANJIN) CO LTD

AI summary

A method to set up the parameters of solder paste screen printer while in a new product introduction (NPI). The method includes establishing a solder-printing database of a predetermined product and a database of different specifications of products, and training a first prediction model by reference to a solder paste screen printer (SPSP) and a solder paste inspection (SPI) based on the solder-printing database. A second prediction model is trained by reference to the SPI based on the database of different products. The method further includes predicting parameters for products with different specifications under multiple sets of printing parameters based on the first and second prediction models. An objective function based on the predicted measurements is established, and a specification of a product and a printing expectation parameters are input to the objective function for outputting many sets of printing-suggestion parameters of the new product.