Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Engineering machinery recognition method and recognition device based on improved MFCC (Mel Frequency Cepstrum Coefficient) sound features

A technology of construction machinery and sound characteristics, applied in the field of construction machinery identification methods and identification devices, can solve the problems of the influence of analysis results, the difficulty of collecting vibration signals, and the identification effect is not particularly ideal, so as to improve the identification effect and reduce the false alarm rate. Effect

Inactive Publication Date: 2015-12-09
ZHEJIANG TUWEI ELECTRICITY TECH
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the prior art, a moving vehicle recognition system based on video images has been proposed, mainly based on vehicle license plates and vehicle types. The recognition effect is not particularly ideal
However, in the experiments at the subway construction site, it was found that the complexity of the construction site and the randomness of damage events made it difficult to collect vibration signals, which greatly affected the analysis results

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Engineering machinery recognition method and recognition device based on improved MFCC (Mel Frequency Cepstrum Coefficient) sound features
  • Engineering machinery recognition method and recognition device based on improved MFCC (Mel Frequency Cepstrum Coefficient) sound features
  • Engineering machinery recognition method and recognition device based on improved MFCC (Mel Frequency Cepstrum Coefficient) sound features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] A kind of engineering machinery (such as: hydraulic impact hammer, excavator, cutting machine, electric hammer) identification method based on improved MFCC sound feature comprises:

[0047] The step of building the sound sample library is to obtain the sound of each group of samples containing the construction machinery in advance.

[0048] In the sample sound collection step, the sound array collection equipment is used to collect samples when working at different distances from the construction machinery, and each group of construction machinery sounds is collected by the same equipment at different collection distances.

[0049] The sample sound segmentation step is to divide the sound of each group of engineering machinery into multiple regions according to the set time as a time segment structure.

[0050] The sample feature extraction step is to extract corresponding sample features from the construction machinery sounds in each group of samples, and all sample f...

Embodiment 2

[0076] A kind of construction machinery identification method based on sound feature of the present invention, it comprises:

[0077] The step of building the sample library is to obtain the sound of each group of samples in advance including the sound of the construction machinery at different distances in the near, middle and far distances. In the specific implementation process, the reason why the sound samples under the three different collection distances of near, middle and far are selected is that when the distances from the sound array of construction machinery are different, the characteristics of the collected sound samples are different. If there is a large gap, the sound attenuation is very large at a long distance. Using the sound features of different distances as a template can improve the detection accuracy and accuracy.

[0078] The sample sound segmentation step is to divide the sound of each construction machine in each group of samples into multiple regions...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an engineering machinery recognition method and a recognition device based on improved MFCC (Mel Frequency Cepstrum Coefficient) sound features. The method comprises a step of building a sound sample library, a step of acquiring sample sounds, a step of dividing the sample sounds in regions, and a step of extracting sound sample features. According to the step of extracting the sound sample features, corresponding sample features are extracted from each about 1.7s sound folder respectively, and the step comprises substeps: pre-treatment is carried out, a Hamming window is added, FFT transformation is carried out, through a Mel triangular filter bank, a mean and a variance are solved, transpose is solved, FFT transformation is carried out, logarithmic operation is carried out through a filter bank, and DCT transformation is carried out. The method also comprises a step of building a sample feature model and a step of recognizing a target sound. According to the engineering machinery recognition method and the recognition device based on the improved MFCC (Mel Frequency Cepstrum Coefficient) sound features, false alarms can be reduced, and the recognition performance can be improved.

Description

technical field [0001] The invention belongs to the technical field of speech recognition, and in particular relates to an engineering machinery recognition method and a recognition device based on improved MFCC sound features. Background technique [0002] With the rapid development of my country's modernization, the proportion of power lines is increasing. For the protection of underground cables, laying methods with high resistance to external forces such as buried pipes and tunnels are usually used to make them less affected by the natural environment. However, cables are often damaged by construction machinery such as excavators and pile drivers during use, and the advantages of safe and reliable cable power supply are seriously affected. Therefore, preventing cable power supply from being damaged by external force has become an urgent problem to be solved by the power system operation department. [0003] The establishment of an intelligent construction machinery ide...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/26
Inventor 曹九稳赵拓王瑞荣黄强王建中
Owner ZHEJIANG TUWEI ELECTRICITY TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products