Causal Model Control for Biologic Batch Quality Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing techniques for controlling biologic pharmaceutical manufacturing environments struggle to accurately and efficiently determine causal relationships between control settings and environment responses, leading to suboptimal production quality and vulnerability to environmental changes.

Innovation Solution

A method involving a causal model that repeatedly selects and adjusts control settings based on measurements of quality, accounting for both controllable and uncontrollable environmental factors, to optimize biologic pharmaceutical production by iteratively updating internal parameters and selecting settings that improve batch quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If modeling-based techniques are used to control manufacturing environments, then the system can passively observe historical data and learn patterns, but the system cannot accurately determine causal relationships and remains vulnerable to environmental changes

Engineering Contradiction:

Improveaccuracy of causal relationship determinationVSAvoidrobustness to environmental changes

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent implements active control techniques where the system actively intervenes in the manufacturing environment by deliberately changing control settings and observing the resulting environment responses. This feedback loop enables the system to generate new knowledge about causal relationships rather than merely observing historical patterns, thereby improving both measurement precision of causal relationships and reliability against environmental changes.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary actions by proactively selecting and applying control settings before actual manufacturing batches are produced. Through randomized controlled experimentation, the system pre-determines causal relationships between control settings and environment responses, allowing it to make more accurate decisions when controlling actual manufacturing processes without being vulnerable to unanticipated environmental changes.

Inventive Principle:

Principle #10Preliminary action

2Loss of information

If active control techniques are used to generate knowledge, then the system can determine causal relationships through experimentation, but the process requires active intervention and control of the environment

Engineering Contradiction:

Improveknowledge generation about causal relationshipsVSAvoidcomplexity of control system

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The system performs self-service by autonomously conducting randomized controlled experiments to generate its own knowledge about causal relationships. The control system independently selects control settings, implements them in the manufacturing environment, observes responses, and updates its understanding of causal relationships without requiring external intervention, thereby reducing information loss while managing complexity through automation.

Inventive Principle:

Principle #25Self-service

3Manufacturing precision

If the system repeatedly selects and adjusts control settings based on causal models, then production quality can be optimized, but the process requires continuous measurement and adjustment of internal parameters

Engineering Contradiction:

Improvebatch qualityVSAvoidmanufacturing throughput

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The system maintains continuous useful action by repeatedly selecting control settings based on the causal model and immediately applying them to manufacturing batches. Rather than periodic adjustments, the system continuously optimizes control settings based on accumulated knowledge of causal relationships, ensuring batch quality is consistently improved without significant interruptions to manufacturing throughput.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The patent replaces traditional mechanical trial-and-error adjustment methods with a computational causal model that systematically determines optimal control settings. This substitution of computational reasoning for physical experimentation accelerates the optimization process, allowing continuous improvement of batch quality while maintaining high manufacturing productivity through faster decision-making.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12099046B2Manufacturing a biologic pharmaceutical using causal models

Publication Date: 2024.09.24 SOLVENTUM INTELLECTUAL PROPERTIES CO

AI summary

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing a process of manufacturing a biologic pharmaceutical. In one aspect, the method comprises repeatedly performing the following: i) selecting a configuration of input settings for manufacturing a batch of a biologic pharmaceutical based on a causal model that measures current causal relationships between input settings and a measure of a quality of batches of the biological pharmaceutical; ii) determining a measure of the quality of a batch of the biological pharmaceutical manufactured using the configuration of input settings; and iii) adjusting, based on the measure of the quality of the batch of the biological pharmaceutical, the causal model.