Passing Valve Detection Using Edge Vibration Sensing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Passing valves in oil and gas plants cause costly leakages, environmental hazards, and health risks due to unintentional fluid flow when valves are not fully closed, often resulting from human error or valve degradation.

Innovation Solution

A data processing system using a piezoelectric sensor to collect vibrational data, apply bandpass filtering, and employ machine learning models to detect passing valves based on feature engineering and significance, enabling on-the-edge detection without network transmission.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If traditional detection methods are used, then detection accuracy may be maintained, but detection time is excessively long

Engineering Contradiction:
Improvedetection timeVSAvoiddetection accuracy
Core Design Contradiction:
Loss of timeVSMeasurement precision

Solution Approach 1:

The detection process is segmented into distinct phases: acoustic signal acquisition, feature extraction (amplitude, frequency, time-domain characteristics), and classification. This segmentation allows parallel processing of different feature types, significantly reducing overall detection time while maintaining accuracy through comprehensive feature analysis.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary action by continuously monitoring and pre-processing acoustic signals in real-time, maintaining a ready state with pre-trained machine learning models. This allows immediate detection and classification when passing valve conditions occur, eliminating startup delays and reducing overall detection time.

Inventive Principle:
Principle #10Preliminary action

2Power

If data is transmitted to cloud or network server for processing, then computational power is increased, but data security and transmission time are compromised

Engineering Contradiction:
Improvecomputational powerVSAvoiddata security
Core Design Contradiction:
PowerVSLoss of information

Solution Approach 1:

The system implements self-service by embedding machine learning models directly in the edge device, enabling it to perform complex computational tasks locally without external assistance. The device autonomously processes acoustic signals, extracts features, and classifies passing valves, eliminating the need for cloud transmission while maintaining high computational power through optimized local processing.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If pressure sensors or flow sensors are used, then detection accuracy may be improved, but system complexity and intrusion into pipes increase

Engineering Contradiction:
Improvedetection accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system replaces mechanical sensors (pressure sensors, flow sensors) with acoustic sensing technology. Acoustic sensors detect vibrations and sound waves generated by fluid passing through closed valves, providing accurate detection without mechanical contact inside pipes. This substitution reduces system complexity by eliminating multiple sensor types and their associated mounting requirements while maintaining high detection accuracy through advanced signal processing.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system significantly reduces detection time by over a thousand-fold and ensures early mitigation of passing valves, enhancing data security and operational efficiency.

Implementation Method 1

A data processing system using a piezoelectric sensor to collect vibrational data

Methodology Applied
Scientific EffectPiezoelectric effect: Piezoelectric Effect

Data Source

PatentUS20250224048A1Detecting passing valves
Publication Date: 2025.07.10 SAUDI ARABIAN OIL CO
  • US20250224048A1 patent drawing
  • US20250224048A1 patent drawing
  • US20250224048A1 patent drawing

AI summary

This disclosure describes systems and methods for detecting passing valves. A method includes acquiring vibrational data from one or more sensors associated with passing valves and non-passing valves; extracting a plurality of features from the vibrational data; determining, based on a feature importance criterion, a subset of the plurality of features having more significance than other features of the plurality of features; training a machine learning model, where inputs to the machine learning model include the set of features; detecting that a valve is a passing valve based on the trained machine learning model, where an input to the trained machine learning model includes the subset of features extracted from vibrational data; and in response to detecting the passing valve, performing a corrective action to resolve the passing valve.