FIELD: methods and devices for metal processing.
SUBSTANCE: invention relates to machine building and can be used in determining presence and location of defect in modules of metal working machines in real time mode. Method comprises determining a geometrical image of a surface of a workpiece in form of a frequency spectrum, reflecting changes in the tool and workpiece vibrations along the normal to the processed surface, comparison of the current geometric image with the reference image, according to the results of which the presence and location of defects in the machine modules is determined. Reference geometric image is realized in the form of recurrent neural networks with long short-term memory, and determination of the presence and location of defects in said modules by deviation of the current geometrical image from the reference is carried out using an intelligent classifier, which is presented in the form of a multilayer perceptron.
EFFECT: use of the invention enables rapid and reliable diagnosis of the state of machine modules.
1 cl, 10 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD FOR OPERATIONAL CONTROL OF PARAMETERS AND DIAGNOSIS OF THE TECHNICAL CONDITION OF SMALL UNMANNED AERIAL VEHICLES (UAV) | 2022 |
|
RU2803903C1 |
METHOD FOR DETERMINING RIGIDITY OF METALWORKING MACHINE TOOL WITH CNC | 2015 |
|
RU2619424C2 |
METHOD AND SYSTEM FOR NONINVASIVE SCREENING PHYSIOLOGICAL PARAMETERS AND PATHOLOGY | 2016 |
|
RU2657384C2 |
METHOD FOR EVALUATION OF GEOMETRICAL SIZES OF WALL DEFECTS IN PIPE SECTION AND WELD SEAMS BY DATA OF MAGNETIC IN-PIPE FLAW DETECTOR, USING UNIVERSAL NEURAL NETWORK MODEL SUITABLE FOR FLAW DETECTORS WITH DIFFERENT DIAMETERS AND MAGNETIC SYSTEMS | 2015 |
|
RU2591584C1 |
STATUS MONITORING FOR NODES OF AUTOMATED PROCESS PRODUCTION SYSTEMS OF CONTINUOUS TYPE | 2014 |
|
RU2580786C2 |
METHOD AND SYSTEM FOR REMOTE IDENTIFICATION AND PREDICTION OF DEVELOPMENT OF EMERGING DEFECTS OF OBJECTS | 2018 |
|
RU2686257C1 |
METHOD FOR X-RAY TOMOGRAPHY AND APPARATUS FOR REALISING SAID METHOD | 2012 |
|
RU2505800C2 |
METHOD OF FORMING TWO-DIMENSIONAL IMAGE OF BIOSIGNAL AND ANALYSIS THEREOF | 2013 |
|
RU2538938C2 |
METHOD FOR OPERATIONAL IDENTIFICATION OF MARINE TARGETS BY THEIR INFORMATION FIELDS BASED ON NEURO-FUZZY MODELS | 2021 |
|
RU2763125C1 |
METHOD FOR DIAGNOSING A COMPLEX OF ON-BOARD EQUIPMENT OF AIRCRAFT BASED ON UNSUPERVISED MACHINE LEARNING WITH AUTOMATIC DETERMINATION OF MODEL TRAINING PARAMETERS | 2023 |
|
RU2818858C1 |
Authors
Dates
2020-07-21—Published
2018-11-12—Filed