In this paper, the fully\|mechanized coal face system is thought of as a fuzzy controller, the various factors that have effect on the controller are found and analysis has been made as to how they effect the fully\|m...In this paper, the fully\|mechanized coal face system is thought of as a fuzzy controller, the various factors that have effect on the controller are found and analysis has been made as to how they effect the fully\|mechanized coal face′s production capacity. Based on the above analysis, this paper establishs a series of data analysis models describing the quantitative characteristics of the fully\|mechanized coal face production system. With this series of data models, 90 fully\|mechanized coal faces are processed and the fuzzy control forecasting model of the fully\|mechanized coal faces production capacity is established. This model is accurate and reliable and has achieved good results in practical applicaton.展开更多
In the process of gas hydrate depressurization production,the reasonable depressurization rhythm and depressurization amplitude have significant impact on improving production and reducing engineering geological risks...In the process of gas hydrate depressurization production,the reasonable depressurization rhythm and depressurization amplitude have significant impact on improving production and reducing engineering geological risks.Considering the basic stability of the reservoir,this study constructs mathematical models of gas hydrate decomposition kinetics,multiphase flow in the reservoir,and the disintegration and migration of rock matrix particles containing hydrates.Based on actual data from the first trial production in Japan's Nankai Trough,the validity of the model has been verified.The study analyzed changes in reservoir physical properties and productivity under multi-stage depressurization conditions.The influence of different pressure reduction rhythms on productivity changes and the evolution laws of porosity,permeability and saturation over time and space were discussed.The research disclosed the multi-stage depressurization mode can modulate the decomposition rate and sand production rate of natural gas hydrates through the progressive reduction of reservoir pressure,guaranteeing production capacity while attaining sand production control and minimizing the risk of blockage,thereby striking a balance between production efficiency and sustainability.This study provides a crucial theoretical basis for the design optimization of natural gas hydrate depressurization extraction schemes.The research outcomes not only guide the parameter configuration optimization during depressurization but also offer scientific support for establishing production prediction models.展开更多
Investigating the proton exchange membrane fuel cell(PEMFC)stack performance degradation phenomena is of vital importance for product development.In the study,the 1000 h durability experiment of a 5-kW fuel cell stack...Investigating the proton exchange membrane fuel cell(PEMFC)stack performance degradation phenomena is of vital importance for product development.In the study,the 1000 h durability experiment of a 5-kW fuel cell stack was performed under dynamic cyclic test conditions,and the test data containing 16 key parameters was utilized to develop the performance prediction framework based on long short-term memory(LSTM)model and LSTM model incorporating attention mechanism(Attention-LSTM).Data preprocessing and postprocessing for eight current modes as well as incremental learning approach were also presented.Experimental results show that the voltage degradation ratio is about 2.0%at the total dynamic cyclic duration of 500 h and approximately 4.8%at 1000 h.The degradation ratio at higher stack operating currents is found larger than that of lower operating currents.The calculated voltage degradation speeds among all current modes fall within the range of 25~60μV h^(-1).When it comes to model prediction performances,both LSTM and Attention-LSTM models could effectively capture the voltage variations under current rising and dropping conditions.The LSTM model exhibits superior transient prediction capabilities near current change moments while the Attention-LSTM model demonstrates smaller prediction deviations at relatively stable conditions.When the advanced forecast time reaches or exceeds 200 h,the Attention-LSTM model predictions agree better with the bench test data,and it maintains consistent prediction accuracy across different current modes.The study contributes to fuel cell stack durability performance analysis and degradation prediction.展开更多
文摘In this paper, the fully\|mechanized coal face system is thought of as a fuzzy controller, the various factors that have effect on the controller are found and analysis has been made as to how they effect the fully\|mechanized coal face′s production capacity. Based on the above analysis, this paper establishs a series of data analysis models describing the quantitative characteristics of the fully\|mechanized coal face production system. With this series of data models, 90 fully\|mechanized coal faces are processed and the fuzzy control forecasting model of the fully\|mechanized coal faces production capacity is established. This model is accurate and reliable and has achieved good results in practical applicaton.
基金supported by National Key Research and Development Program(Number 2023YFC2811002)National Natural Science Foundation of China(Number U20B6005-05)+2 种基金111 Project(Number D21025)Open Fund Project of State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation(Number PLN202101)High-end Foreign Expert Introduction Program(Number G2021036005L).
文摘In the process of gas hydrate depressurization production,the reasonable depressurization rhythm and depressurization amplitude have significant impact on improving production and reducing engineering geological risks.Considering the basic stability of the reservoir,this study constructs mathematical models of gas hydrate decomposition kinetics,multiphase flow in the reservoir,and the disintegration and migration of rock matrix particles containing hydrates.Based on actual data from the first trial production in Japan's Nankai Trough,the validity of the model has been verified.The study analyzed changes in reservoir physical properties and productivity under multi-stage depressurization conditions.The influence of different pressure reduction rhythms on productivity changes and the evolution laws of porosity,permeability and saturation over time and space were discussed.The research disclosed the multi-stage depressurization mode can modulate the decomposition rate and sand production rate of natural gas hydrates through the progressive reduction of reservoir pressure,guaranteeing production capacity while attaining sand production control and minimizing the risk of blockage,thereby striking a balance between production efficiency and sustainability.This study provides a crucial theoretical basis for the design optimization of natural gas hydrate depressurization extraction schemes.The research outcomes not only guide the parameter configuration optimization during depressurization but also offer scientific support for establishing production prediction models.
基金supported by the National Key Research and Devel-opment Program of China(No.2023YFE0109200).
文摘Investigating the proton exchange membrane fuel cell(PEMFC)stack performance degradation phenomena is of vital importance for product development.In the study,the 1000 h durability experiment of a 5-kW fuel cell stack was performed under dynamic cyclic test conditions,and the test data containing 16 key parameters was utilized to develop the performance prediction framework based on long short-term memory(LSTM)model and LSTM model incorporating attention mechanism(Attention-LSTM).Data preprocessing and postprocessing for eight current modes as well as incremental learning approach were also presented.Experimental results show that the voltage degradation ratio is about 2.0%at the total dynamic cyclic duration of 500 h and approximately 4.8%at 1000 h.The degradation ratio at higher stack operating currents is found larger than that of lower operating currents.The calculated voltage degradation speeds among all current modes fall within the range of 25~60μV h^(-1).When it comes to model prediction performances,both LSTM and Attention-LSTM models could effectively capture the voltage variations under current rising and dropping conditions.The LSTM model exhibits superior transient prediction capabilities near current change moments while the Attention-LSTM model demonstrates smaller prediction deviations at relatively stable conditions.When the advanced forecast time reaches or exceeds 200 h,the Attention-LSTM model predictions agree better with the bench test data,and it maintains consistent prediction accuracy across different current modes.The study contributes to fuel cell stack durability performance analysis and degradation prediction.
