Sensor-Based Operational Mode Detection for Manufacturing Alerts

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In the sand oil industry, managing the complex process of converting sand oil into Synthesis Crude Oil (SCO) is challenging due to dynamic systems with multiple stages and hidden operational modes, leading to inefficiencies and production losses, especially when raw material quality is low or equipment is undergoing maintenance.

Innovation Solution

A system and method using historical multivariate sensor data to determine operational modes and recommend actions, employing algorithms like LSTM auto-encoding and fused lasso approaches to identify joint dynamics and configurations of process variables, enabling automation of mode detection and recommendation of control actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated algorithms are used to detect operational modes from sensor data, then productivity is improved through automatic detection, but device complexity increases due to the need for advanced analytic models and multivariate analysis systems

Engineering Contradiction:

Improveautomatic mode detection capabilityVSAvoidcomplexity of analytic models and sensor network

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs self-diagnosis and self-monitoring by automatically detecting operational modes through algorithms that analyze sensor data without requiring external expert intervention. The analytic models self-adjust to identify hidden modes and generate alerts autonomously

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual monitoring and analysis of operational modes is replaced with automated computer algorithms and machine learning models. The mechanical process of expert analysis is substituted with electronic sensor networks and software-based analytic models that process multivariate data

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If advanced analytic models are deployed to identify hidden operational modes, then manufacturing precision is improved through better mode identification, but loss of time increases due to the computational complexity of processing multivariate sensor data

Engineering Contradiction:

Improveaccuracy of operational mode identificationVSAvoidtime required for processing sensor data and generating mode alerts

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The system pre-processes and stores historical sensor data during normal operations, building training datasets in advance. When mode detection is needed, the pre-trained models can quickly analyze new data without requiring extensive real-time computation, reducing detection time while maintaining accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates simplified representations or proxies of complex operational states through sensor data patterns. Instead of analyzing all raw sensor data in real-time, the system uses trained models that have learned to recognize mode patterns, effectively copying the decision-making process in a computationally efficient manner

Inventive Principle:

Principle #26Copying

Data Source

PatentUS11663679B2Generating mode change alerts with automatic detection from sensor data

Publication Date: 2023.05.30 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A system and a method of managing a manufacturing process includes receiving production data relating to the manufacturing process and determining an operational mode associated with the manufacturing process using historical, multivariate senor data. The method may further determine a recommended action to affect production based on the determined operational mode. The operational mode may be based on at least one of: a level of operation in a continuous flow process relating to a joint set of process variables, a representation of a joint dynamic of the set of process variables over a predefined length, and a joint configuration of an uptime/downtime of a plurality of units comprising a process flow.