Sensor Data Plausibility Checks for Industrial Condition Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual monitoring of industrial equipment and processes is labor-intensive and prone to errors due to subjective sensory perceptions, leading to inefficient and inaccurate assessment of equipment health status and process conditions.
Innovation Solution
A method for training a machine-learning model using measurement data from sensors, incorporating a plausibility check to ensure accurate labeling and reduce human error, allowing for automated and efficient condition assessment of equipment and processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual monitoring by human operators is used, then equipment health status can be assessed through sensory perceptions, but the process becomes labor-intensive and costly
Solution Approach 1:
The patent replaces the mechanical manual inspection system with an automated sensor-based monitoring system. Sensors detect equipment conditions and feed data to a machine learning model, eliminating the need for human operators to physically patrol and inspect equipment, thereby reducing labor intensity while maintaining assessment capability
Solution Approach 2:
The system enables self-monitoring of equipment through automated data collection and analysis. The machine learning model automatically processes sensor data and generates health assessments without human intervention, allowing the monitoring system to serve itself and eliminate dependency on manual labor
2Measurement precision
If human operators perform visual inspection to determine process quality, then process conditions can be identified, but the manual process is labor-intensive and time-consuming
Solution Approach 1:
The patent replaces manual visual inspection with automated sensor-based detection systems. Sensors continuously monitor process conditions and feed data to machine learning models that automatically identify abnormalities, eliminating the time required for manual visual inspection while maintaining or improving detection precision
Solution Approach 2:
The automated monitoring system operates continuously without interruption, constantly collecting and analyzing process data. This eliminates the intermittent nature of manual inspections and ensures continuous detection of process conditions, saving time while maintaining precision
3Reliability
If manual sensory perception is used for equipment assessment, then equipment abnormalities can be detected, but errors occur due to subjective perceptions being attributed to wrong equipment
Solution Approach 1:
The patent replaces subjective human sensory perception with objective sensor-based detection. Sensors provide quantifiable data about equipment conditions, and machine learning models objectively analyze this data to identify abnormalities and their sources, eliminating errors caused by subjective human perception and misattribution to wrong equipment
Solution Approach 2:
The system incorporates feedback loops where sensor data is continuously monitored, analyzed by machine learning models, and used to generate actionable insights. The system learns from past data and improves its accuracy over time, providing feedback that reduces identification errors and improves both reliability and measurement precision
Data Source
AI summary
A method for training a machine-learning model to assess at least one condition of industrial equipment, and/or at least one condition of a process running in an industrial plant, based on measurement data gathered by a plurality of sensors, includes: obtaining a plurality of records of measurement data that correspond to a variety of operating situations and a variety of conditions; obtaining, for each record of measurement data, a label that represents a condition in the operating situation characterized by the record of measurement data; and determining a plausibility of at least one record of measurement data, and/or a plausibility of at least one label, based at least in part on a comparison with at least one other record of measurement data, with at least one other label, and/or with additional information about the industrial equipment, and/or about the industrial plant where the industrial equipment resides, and/or about the process.