Methane Gas Prediction Model in Underground Coalmines: A Deep Learning Approach DOI

Tharun Satla,

Srikanth Jannu,

Chaitanya Thuppari

и другие.

Опубликована: Дек. 14, 2023

The environment of underground coal mines (UCMs) is susceptible to many environmental problems and consequential hazard. Among those problems, mine fire a liable threat that causes the loss lives workers other valuable infrastructure resources in mines. Moreover, methane gas concentration area one major explosion. Therefore, continuous monitoring very important for prediction UCMs. Internet Things (IoT), nowadays, widely utilized For purpose monitoring, deploy sensor nodes region UCMs sense conditions transfer information base station further process. As data are estimated indistinct nature, it necessary consider taking precautions. In this paper, we propose method predict by using multilayer perceptron. perceptron model applied on dataset sequentially train dividing into training testing datasets. model. On hand, evaluate trained overall process implemented at sink instead control stations. case any hazardous situation, takes immediate actions based sensed rather than station. simulated WEKA tool different hazard conditions. This more reliable works effectively when compared existing models kind hazards situations results show accuracy proposed outperforms models.

Язык: Английский

Optimization Model for Mine Backfill Scheduling Under Multi-Resource Constraints DOI Open Access
Yuhang Liu, Guoqing Li, Jie Hou

и другие.

Minerals, Год журнала: 2024, Номер 14(12), С. 1183 - 1183

Опубликована: Ноя. 21, 2024

Addressing the resource constraints, such as manpower and equipment, faced by mine backfilling operations, this study proposed an optimization model for backfill scheduling based on Resource-Constrained Project Scheduling Problem (RCPSP). The considered backfilling’s multi-process, multi-task, multi-resource characteristics, aiming to minimize total delay time. Constraints included operational limits, requirements, availability. goal was determine optimal configurations each stope’s steps. A heuristic genetic algorithm (GA) employed solution. To handle equipment unavailability, a new encoding/decoding ensured availability continuous operations. Case verification using real data highlights advantages of model, showing 20.6% decrease in completion time, 8 percentage point improvement utilization, 47.4% reduction overall time compared traditional methods. This work provides reference similar mines promotes intelligent mining practices.

Язык: Английский

Процитировано

0
Methane Gas Prediction Model in Underground Coalmines: A Deep Learning Approach DOI

Tharun Satla,

Srikanth Jannu,

Chaitanya Thuppari

и другие.

Опубликована: Дек. 14, 2023

The environment of underground coal mines (UCMs) is susceptible to many environmental problems and consequential hazard. Among those problems, mine fire a liable threat that causes the loss lives workers other valuable infrastructure resources in mines. Moreover, methane gas concentration area one major explosion. Therefore, continuous monitoring very important for prediction UCMs. Internet Things (IoT), nowadays, widely utilized For purpose monitoring, deploy sensor nodes region UCMs sense conditions transfer information base station further process. As data are estimated indistinct nature, it necessary consider taking precautions. In this paper, we propose method predict by using multilayer perceptron. perceptron model applied on dataset sequentially train dividing into training testing datasets. model. On hand, evaluate trained overall process implemented at sink instead control stations. case any hazardous situation, takes immediate actions based sensed rather than station. simulated WEKA tool different hazard conditions. This more reliable works effectively when compared existing models kind hazards situations results show accuracy proposed outperforms models.

Язык: Английский

Процитировано

0