LC Pressure Trace ML Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current liquid chromatography (LC) systems face challenges in quickly identifying equipment setup issues such as empty solvent bottles, reversed solvent bottles, fitting failures, and air injection during sample injection, which can take hours to diagnose and often require additional sample consumption, and users tend to ignore manual entry methods due to perceived errors and extra effort.
Innovation Solution
An LC system equipped with a pressure sensor and a processor that measures pressure parameters like beginning and ending pressures, average pressures for each half of the separation, and their ratios, using a machine learning model to classify operational conditions without user intervention, displaying indicators of normal operation or equipment issues on a display device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual entry methods are used to track solvent bottles, then user control over experiment parameters is improved, but user effort and error probability increase
Solution Approach 1:
The system automatically detects and tracks solvent bottle status using pressure sensors and machine learning algorithms, eliminating the need for manual user input. The LC system self-monitors parameters like beginning pressure, ending pressure, and pressure ratios to determine bottle emptiness, reversing, or fitting failures without requiring user intervention.
2Reliability
If diagnostic procedures are performed to identify equipment setup issues, then system reliability is improved, but time consumption and sample usage increase
Solution Approach 1:
The system continuously monitors pressure parameters during normal LC operations and uses machine learning models to predict equipment setup issues before they affect experiment results. By analyzing beginning pressure, ending pressure, and pressure ratios in real-time, the system identifies problems like empty bottles or fitting failures during the separation process rather than requiring separate diagnostic runs.
3Difficulty of detecting and measuring
If additional sensors or monitoring devices are added to detect equipment issues, then detection capability is improved, but device complexity increases
Solution Approach 1:
The system uses the existing pressure sensor data as an intermediary to infer equipment setup issues. Rather than adding dedicated sensors for each type of fault detection, the machine learning model analyzes patterns in the pressure trace data (beginning pressure, ending pressure, pressure ratios) to indirectly detect empty bottles, reversals, fitting failures, and air injection without increasing hardware complexity.
Data Source
AI summary
An operational condition of a liquid chromatography (LC) system (2110) is detected and displayed without user intervention. A plurality of pressure measurements over time are received from a pressure sensor (2119) of the LC system. A processor (2140) calculates values from the measurements for six parameters including a beginning pressure (PB), an ending pressure (PE), an average pressure (T1) for a first half of the separation, an average pressure (T2) for a second half of the separation, a ratio T1/PB, and a ratio T2/PB. The values of the six parameters are classified as one of one or more operational conditions of the LC system using a machine learning model. The machine learning model is created from values of the six parameters calculated from known separations for each of the one or more operational conditions. The operational condition found from the classification is displayed on a display device (2141).