Natural gas pipeline tiny leakage detection method based on sound signals

Abstract

The invention provides a natural gas pipeline tiny leakage detection method based on a sound signals. By taking the sound signal fluctuating most intensely during pipeline tiny leakage as a main signal, and temperature, pressure and flow rate signals as secondary signals, a deep convolution neural net based on multiparameter is established, and the probability of tiny leakage of a natural gas pipeline is determined through studying data of the main signal and the secondary signals; in addition, a deep restricted boltzmann machine model is designed specifically for the isomerism of multiparameter data, the multiparameter data is subjected to pre-training, an optimal weight value matrix and an optimal offset value are obtained and act as a weight initial value and an offset value initial value of a deep convolution neural net model. With the adoption of the method, an accuracy rate of pipeline tiny leakage accident judgment is increased greatly, the probability of a large safety accident is reduced, and the rescue efficiency of a natural gas pipeline accident is improved.

Description

technical field [0001] The invention relates to the technical field of safety detection of natural gas transmission pipelines, in particular to a detection method for gas station pipeline microleakage based on sound signals. Background technique [0002] As a clean energy, natural gas has been widely used to effectively alleviate energy shortage and environmental pollution. Therefore, compressed natural gas (abbreviated as CNG) filling station has become an important national infrastructure construction project. Since 2010, CNG vehicles have grown at a rate of 16% year by year, and strengthening the safety of CNG filling stations has important social significance. According to statistics, the number of CNG refueling stations across the country has increased from about 2,400 at the end of 2012 to about 3,000 at the end of June 2013, and 473,000 new natural gas vehicles have been added, and the total inventory has reached 1.577 million, a year-on-year increase of 40. %. [...

AI Technical Summary

Problems solved by technology

[0006] (2) There are many factors that cause micro-leakage in pipelines. Physical equations can be established between some of these factors, but many parameters in the equations cannot be measured in reality, and it is difficult to construct a probability function that includes all influencing factors. Therefore, now There are methods that usually focus on the analysis of certain parameter values, resulting in inaccurate calculation results

In fact, each parameter has a certain influence on the judgment result, but it cannot be set artificially or randomly.

[0008] The above problems will inevitably affect the rapid and accurate judgment of the occurrence of gas station pipeline micro-leakage accidents, and become a bottleneck restricting the scientific development of natural gas transportation and ensuring the safety of gas stations

Images