Dual Diagnostic System for Industrial Machinery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing abnormality diagnostic systems for industrial machinery face challenges in enhancing diagnostic precision due to resource constraints on machines, leading to false reports and inefficient data communication, particularly when complex algorithms are required and data volume is high, with issues in updating diagnostic models and reference data.
Innovation Solution
A dual-diagnostic system comprising a first diagnostic device on the machine-side computer and a second diagnostic device on a server, where the first device processes and extracts time series data for the second device, reducing communication volume and enabling precise diagnosis even with limited machine-side resources, with the second device comparing results and updating diagnostic information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex diagnostic algorithms are executed on machine-side computers, then diagnostic precision is improved, but resource constraints (CPU and memory) prevent effective implementation
Solution Approach 1:
The diagnostic system is segmented into two parts: a simple diagnostic algorithm executed on the machine-side computer and a complex diagnostic algorithm executed on the server. This segmentation allows each component to perform its designated function within its resource constraints while achieving overall high diagnostic precision through the combination of both algorithms.
2Measurement precision
If all sensor data is transmitted from machine-side controller to server, then diagnostic accuracy is improved, but communication data volume and costs increase significantly
Solution Approach 1:
The system extracts only the essential diagnostic results and relevant time series data from the machine-side computer and transmits them to the server, rather than transmitting all raw sensor data. This extraction approach maintains diagnostic accuracy while significantly reducing communication data volume and associated costs.
3Device complexity
If simple diagnostic algorithms are used on machine-side computers, then resource constraints are satisfied, but false reports occur due to operating conditions differing from design conditions
Solution Approach 1:
The server acts as an intermediary that receives diagnostic results from the machine-side computer and performs additional complex diagnostic analysis. This intermediary processing corrects false reports caused by operating condition variations, thereby improving diagnostic reliability while keeping the machine-side algorithm simple.
4Measurement precision
If complex algorithms are executed only on servers, then diagnostic precision is improved, but communication capacity requirements increase due to need to transmit all sensor data
Solution Approach 1:
The machine-side computer performs preliminary diagnostic processing of sensor data before transmission to the server. This preliminary action reduces the data volume that needs to be communicated while ensuring that the essential information required for precise server-side analysis is preserved, thereby improving communication efficiency without sacrificing diagnostic precision.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An object of the present invention is to provide an abnormality diagnostic system that can enhance diagnostic precision even if a computer arranged on the machine side does not have sufficient throughput in diagnosing a condition of a machine or equipment based upon time series data generated by a sensor and can reduce communication capacity because communication data volume decreases and industrial machinery provided with the abnormality diagnostic system. A diagnostic device on the machine side 2 diagnoses time series data generated by a sensor, acquires a primary diagnostic result, extracts time series data related to the primary diagnostic result and outputs it to a diagnostic device on the server side 3 together with the primary diagnostic result, the diagnostic device on the server side 3 diagnoses the time series data, acquires a secondary diagnostic result, and displays the secondary diagnostic result together with the primary diagnostic result. Besides, the diagnostic device on the server side compares the diagnostic results and updates a diagnostic process of the diagnostic device on the machine side 2 when the diagnostic results are different as a result of the comparison.