An Improved YOLOv5s-Based Smoke Detection System for Outdoor Parking Lots

In the rapidly evolving urban landscape,outdoor parking lots have become an indispensable part of the city’s transportation system.The growth of parking lots has raised the likelihood of spontaneous vehicle combus-tion,a significant safety hazard,making smoke detection an essential preventative step.However,the complex environment of outdoor parking lots presents additional challenges for smoke detection,which necessitates the development of more advanced and reliable smoke detection technologies.This paper addresses this concern and presents a novel smoke detection technique designed for the demanding environment of outdoor parking lots.First,we develop a novel dataset to fill the gap,as there is a lack of publicly available data.This dataset encompasses a wide range of smoke and fire scenarios,enhanced with data augmentation to ensure robustness against diverse outdoor conditions.Second,we utilize an optimized YOLOv5s model,integrated with the Squeeze-and-Excitation Network(SENet)attention mechanism,to significantly improve detection accuracy while maintaining real-time processing capabilities.Third,this paper implements an outdoor smoke detection system that is capable of accurately localizing and alerting in real time,enhancing the effectiveness and reliability of emergency response.Experiments show that the system has a high accuracy in terms of detecting smoke incidents in outdoor scenarios.

Ash Detection of Coal Slime Flotation Tailings Based on Chromatographic Filter Paper Sampling and Multi-Scale Residual Network

The detection of ash content in coal slime flotation tailings using deep learning can be hindered by various factors such as foam,impurities,and changing lighting conditions that disrupt the collection of tailings images.To address this challenge,we present a method for ash content detection in coal slime flotation tailings.This method utilizes chromatographic filter paper sampling and a multi-scale residual network,which we refer to as MRCN.Initially,tailings are sampled using chromatographic filter paper to obtain static tailings images,effectively isolating interference factors at the flotation site.Subsequently,the MRCN,consisting of a multi-scale residual network,is employed to extract image features and compute ash content.Within the MRCN structure,tailings images undergo convolution operations through two parallel branches that utilize convolution kernels of different sizes,enabling the extraction of image features at various scales and capturing a more comprehensive representation of the ash content information.Furthermore,a channel attention mechanism is integrated to enhance the performance of the model.The combination of the multi-scale residual structure and the channel attention mechanism within MRCN results in robust capabilities for image feature extraction and ash content detection.Comparative experiments demonstrate that this proposed approach,based on chromatographic filter paper sampling and the multi-scale residual network,exhibits significantly superior performance in the detection of ash content in coal slime flotation tailings.

In-pit coal mine personnel uniqueness detection technology based on personnel positioning and face recognition

Since the coal mine in-pit personnel positioning system neither can effectively achieve the function to detect the uniqueness of in-pit coal-mine personnel nor can identify and eliminate violations in attendance management such as multiple cards for one person, and swiping one's cards by others in China at present. Therefore, the research introduces a uniqueness detection system and method for in-pit coal-mine personnel integrated into the in-pit coal mine personnel positioning system, establishing a system mode based on face recognition + recognition of personnel positioning card + release by automatic detection. Aiming at the facts that the in-pit personnel are wearing helmets and faces are prone to be stained during the face recognition, the study proposes the ideas that pre-process face images using the 2D-wavelet-transformation-based Mallat algorithm and extracts three face features: miner light, eyes and mouths, using the generalized symmetry transformation-based algorithm. This research carried out test with 40 clean face images with no helmets and 40 lightly-stained face images, and then compared with results with the one using the face feature extraction method based on grey-scale transformation and edge detection. The results show that the method described in the paper can detect accurately face features in the above-mentioned two cases, and the accuracy to detect face features is 97.5% in the case of wearing helmets and lightly-stained faces.

Gas concentration monitoring system for small and medium-sized coal mines based on gas-sensing detection and single-chip control

This paper is aimed at the actual conditions of disaster caused by gas in small and medium-sized coal mines. A new gas concentration monitoring system for coal mines is developed on the basis of gas-sensing detection and single-chip control. The monitoring system uses the tin oxide as the main material of N-type semiconductor gas sensors, be- cause it has good sensitive characteristics for the flammable and explosive gas （ such as methane, carbon monoxide）. The QM-N5-semiconductor gas sensor is adopted to detect the output values of the resistance under the different gas con- centrations. The system, designedly, takes the AT89C51 digital chip as the core of the circuit processing hardware structure to analyze and judge the input values of the resistance, and then achieve the control and alarm for going beyond the limit of gas concentration. The gas concentration monitoring system has man）, advantages including simple in struc- ture, fast response time, stable performance and low cost. Thus, it can be widely used to monitor gas concentration and provide early wamings in small and medium-sized coal mines.

Coal mine fire and human escape simulation

Coal mine fire and human escape simulation system is developed based on 3D Max and EON software for the purpose of coal mine safety training.The models,such as miners,roadways,typical equipments,fire and smoke are all constructed in 3D Max.The roadway models derived from real data,functions of each part are determined for the roadway based on the data,and then corresponding tunnel typical equipments are added.Emergency refuge system model is not only an important system model,but also an important destination for fire simulation and human escape.The roaming of the miners through the roadways,the interactive functions between users and computer,the fire process of beginning,spreading,and destroying,the human escape interaction are simulated in EON virtual reality software after these models have been input into it.Besides,collision detection based on hierarchical bounding volumes is also utilized.Simulation results suggest that this strategy can produce realistic virtual state and fire effect.While as part of the coal mine safety simulation and training System(CMSSTS),this work is far from what we expected,and there is more intensive work that should be done.

A Review on Mine Fire Disasters and Assessment of Fire Detection Using a Dual-Cab Suppression System

The health and productivity of mining operations are negatively impacted by coal mine fires, making them dangerous. It happened everywhere, in both working and abandoned coal mines. This study seeks to review and provide technical analytics of potential mine fires and fire detection in a Dual-Cab suppression system. Analysis was done on potential mine fires like spontaneous combustion, flammable gas explosions, and cab vehicle fires. Additionally, a review of the NIOSH experiment was conducted to assess the performance of smoke and flame detectors in a dual-cab suppression system. This study guides both open-pit and underground mining operations. Additionally, a few ideas and suggestions are presented to assist with on-the-job safety analysis, ensuing creative alterations, and technology advancement for the mining industry’s overall safety.

Numerical simulations of full-wave fi elds and analysis of channel wave characteristics in 3-D coal mine roadway models

Currently, numerical simulations of seismic channel waves for the advance detection of geological structures in coal mine roadways focus mainly on modeling two- dimensional wave fields and therefore cannot accurately simulate three-dimensional （3-D） full-wave fields or seismic records in a full-space observation system. In this study, we use the first-order velocity-stress staggered-grid finite difference algorithm to simulate 3-D full-wave fields with P-wave sources in front of coal mine roadways. We determine the three components of velocity Vx, Vy, and Vz for the same node in 3-D staggered-grid finite difference models by calculating the average value of Vy, and Vz of the nodes around the same node. We ascertain the wave patterns and their propagation characteristics in both symmetrical and asymmetric coal mine roadway models. Our simulation results indicate that the Rayleigh channel wave is stronger than the Love channel wave in front of the roadway face. The reflected Rayleigh waves from the roadway face are concentrated in the coal seam, release less energy to the roof and floor, and propagate for a longer distance. There are surface waves and refraction head waves around the roadway. In the seismic records, the Rayleigh wave energy is stronger than that of the Love channel wave along coal walls of the roadway, and the interference of the head waves and surface waves with the Rayleigh channel wave is weaker than with the Love channel wave. It is thus difficult to identify the Love channel wave in the seismic records. Increasing the depth of the receivers in the coal walls can effectively weaken the interference of surface waves with the Rayleigh channel wave, but cannot weaken the interference of surface waves with the Love channel wave. Our research results also suggest that the Love channel wave, which is often used to detect geological structures in coal mine stopes, is not suitable for detecting geological structures in front of coal mine roadways. Instead, the Rayleigh channel wave can be used for the advance detection of geological structures in coal mine roadways.

An attention-based prototypical network for forest fire smoke few-shot detection

Existing almost deep learning methods rely on a large amount of annotated data, so they are inappropriate for forest fire smoke detection with limited data. In this paper, a novel hybrid attention-based few-shot learning method, named Attention-Based Prototypical Network, is proposed for forest fire smoke detection. Specifically, feature extraction network, which consists of convolutional block attention module, could extract high-level and discriminative features and further decrease the false alarm rate resulting from suspected smoke areas. Moreover, we design a metalearning module to alleviate the overfitting issue caused by limited smoke images, and the meta-learning network enables achieving effective detection via comparing the distance between the class prototype of support images and the features of query images. A series of experiments on forest fire smoke datasets and miniImageNet dataset testify that the proposed method is superior to state-of-the-art few-shot learning approaches.

Key technique of a detection sensor for coal mine wire ropes

Wire ropes,employed extensively in coal mine hoists and transportation systems are subject to damage due to wear,corrosion and fatigue.The extent of damage and the carrying capacity of ropes are closely related to the sense of safety by staff and equipments.Magnetic flux leakage detection method(MFL),as an effective method,is these days widely used in detection of broken strands of wire ropes.In order to improve the accuracy of detection of flaws in wire ropes by magnetic flux leakage(MFL),the effect of the distance between a sensor and the surface of a wire rope(i.e.,lift-off) on detection by magnetic flux leakage was in-vestigated.An analysis of the main principles for the choice of lift-off is described by us and a new method that improves the structure of the detector is proposed from the point of view of the design of a magnetic circuit,to restrain the impact of fluctuations of sensor lift-off.The effect of this kind of method is validated by simulation and computation.The results show that the detection sensitivity is markedly increased by this method.Furthermore,the signal-to-noise ratio(SNR) can be increased by over 28%.This method will lend itself to offer reliable scientific information to optimize the structure of excitation devices and improve the accuracy of MFL detection.

Analysis on advanced transient EM detectability of coal mine roadway

The hidden water-bearing structures near the roadway tunnelling face are very likely to cause water seepage accidents in coal mines.Currently,transient electromagnetic(EM)technology has be-come an important method to detect water damage in advance of roadway excavation.In this paper,the time-domain finite element algorithm based on unstructured tetrahedron grids is used to accurate-ly simulate the geological body in front of the roadway excavation face and analyze its response.The authors detect the distance between the roadway excavation face and the low-resistivity water-bearing body,the resistivity difference between the low-resistivity body and surrounding rock,and the influence of the size of the low-resistivity body on the transient EM response.Furthermore,the common types of low-resistivity bodies in the roadway drivage process are used for modeling to analyze the attenuation of the detected EM response when there are low-resistivity bodies in front of the roadway.The research in this paper can help effectively detecting the water-bearing low-resistivity body in front of the roadway drivage and lay a foundation for reducing the risk of water seepage accidents.

Hyperparameter optimization of YOLOv8 for smoke and wildfire detection:Implications for agricultural and environmental safety

In this study,we extensively evaluated the viability of the state-of-the-art YOLOv8 architecture for object detec-tion tasks,specifically tailored for smoke and wildfire identification with a focus on agricultural and environmen-tal safety.All available versions of YOLOv8 were initially fine-tuned on a domain-specific dataset that included a variety of scenarios,crucial for comprehensive agricultural monitoring.The‘large’version(YOLOv8l)was se-lected for further hyperparameter tuning based on its performance metrics.This model underwent a detailed hyperparameter optimization using the One Factor At a Time(OFAT)methodology,concentrating on key param-eters such as learning rate,batch size,weight decay,epochs,and optimizer.Insights from the OFAT study were used to define search spaces for a subsequent Random Search(RS).The final model derived from RS demon-strated significant improvements over the initial fine-tuned model,increasing overall precision by 1.39%,recall by 1.48%,F1-score by 1.44%,mAP@0.50 by 0.70%,and mAP@0.50:0.95 by 5.09%.We validated the enhanced model's efficacy on a diverse set of real-world images,reflecting various agricultural settings,to confirm its ro-bustness in detecting smoke and fire.These results underscore the model's reliability and effectiveness in scenar-ios critical to agricultural safety and environmental monitoring.This work,representing a significant advancement in the field of fire and smoke detection through machine learning,lays a strong foundation for fu-ture research and solutions aimed at safeguarding agricultural areas and natural environments.

Fire and Smoke Phenomenon in West Najaf City —Southwest Iraq

A strange phenomenon of fire taking place at Arruhban area west Bahr-Al Najaf area in Iraq was noticed in 2010 and smoke continued many months;this phenomenon reappeared many years later. This site is part of Bahr-Al Najaf-Iraq NE Arabian plate, located in flat area near an archeological site of Christian temple called Tel Arruhban. To understand the causes for this fire in a non-residential area, field observations from repeated visits between 2010 and 2018 and on-site excavation operations were conducted. The results of analysis of soil samples, and on-site detection for gases and vapors showed that the phenomenon of burning and smoke generated at this site was due to external influences and that the presence of soil rich with organic materials helped to the existence of this phenomenon.

Forest Fire Smoke Detection Method Based on MoAm-YOLOv4 Algorithm

To improve the performance of the forest fire smoke detection model and achieve a better balance between detection accuracy and speed, an improved YOLOv4 detection model (MoAm-YOLOv4) that combines a lightweight network and attention mechanism was proposed. Based on the YOLOv4 algorithm, the backbone network CSPDarknet53 was replaced with a lightweight network MobilenetV1 to reduce the model’s size. An attention mechanism was added to the three channels before the output to increase its ability to extract forest fire smoke effectively. The algorithm used the K-means clustering algorithm to cluster the smoke dataset, and obtained candidate frames that were close to the smoke images;the dataset was expanded to 2000 images by the random flip expansion method to avoid overfitting in training. The experimental results show that the improved YOLOv4 algorithm has excellent detection effect. Its mAP can reach 93.45%, precision can get 93.28%, and the model size is only 45.58 MB. Compared with YOLOv4 algorithm, MoAm-YOLOv4 improves the accuracy by 1.3% and reduces the model size by 80% while sacrificing only 0.27% mAP, showing reasonable practicability.

A method for detecting miners based on helmets detection in underground coal mine videos

In order to monitor dangerous areas in coal mines automatically,we propose to detect helmets from underground coal mine videos for detecting miners.This method can overcome the impact of similarity between the targets and their background.We constructed standard images of helmets,extracted four directional features,modeled the distribution of these features using a Gaussian function and separated local images of frames into helmet and non-helmet classes.Out experimental results show that this method can detect helmets effectively.The detection rate was 83.7%.

Coal–rock interface detection on the basis of image texture features

Based on the stability and inequality of texture features between coal and rock,this study used the digital image analysis technique to propose a coal–rock interface detection method.By using gray level co-occurrence matrix,twenty-two texture features were extracted from the images of coal and rock.Data dimension of the feature space reduced to four by feature selection,which was according to a separability criterion based on inter-class mean difference and within-class scatter.The experimental results show that the optimized features were effective in improving the separability of the samples and reducing the time complexity of the algorithm.In the optimized low-dimensional feature space,the coal–rock classifer was set up using the fsher discriminant method.Using the 10-fold cross-validation technique,the performance of the classifer was evaluated,and an average recognition rate of 94.12%was obtained.The results of comparative experiments show that the identifcation performance of the proposed method was superior to the texture description method based on gray histogram and gradient histogram.

Surface oxidation of carbon dots enables highly selective and sensitive chemiluminescence detection of hydroxyl radical

The rapid quantification of hydroxyl radical (·OH) in real samples is a great challenge due to its highly reactive nature and the potential interferences from other coexisting reactive oxygen species (ROS). Herein, a chemiluminescence (CL) probe (ox-CDs) was rationally developed for the detection of ·OH through controlled oxidation treatment of original CDs (o-CDs) with H_(2)O_(2). Post-oxidation of CDs can reduce the surface defects or functional groups on the CDs, exposing reactive sites capable of effectively reacting with ·OH. The chemical energy generated from redox reaction between ·OH and the ox-CDs can be efficiently utilized to generate strong and selective CL responses to ·OH without interferences from other ROS. Thus, a highly selective and sensitive CL method with a linear range from 0.01 to 150 μM and a detection limit of 3 nM was developed, which was successfully applied for monitoring the ·OH production from cigarette and mosquito coil smoke.

Hybrid Deep VGG-NET Convolutional Classifier for Video Smoke Detection

Real-time wild smoke detection utilizing machine based identification method is not produced proper accuracy,and it is not suitable for accurate prediction.However,various video smoke detection approaches involve minimum lighting,and it is required for the cameras to identify the existence of smoke particles in a scene.To overcome such challenges,our proposed work introduces a novel concept like deep VGG-Net Convolutional Neural Network(CNN)for the classification of smoke particles.This Deep Feature Synthesis algorithm automatically generated the characteristics for relational datasets.Also hybrid ABC optimization rectifies the problem related to the slow convergence since complexity is reduced.The proposed real-time algorithm uses some pre-processing for the image enhancement and next to the image enhancement processing;foreground and background regions are separated with Otsu thresholding.Here,to regulate the linear combination of foreground and background components alpha channel is applied to the image components.Here,Farneback optical flow evaluation technique diminishes the false finding rate and finally smoke particles are classified with the VGG-Net CNN classifier.In the end,the investigational outcome shows better statistical stability and performance regarding classification accuracy.The algorithm has better smoke detection performance among various video scenes.

Research on Full Space Transient Electro-magnetism Technique for Detecting Aqueous Structures in Coal Mines

Based on the transmitting theory of "smoke ring effect", the transient electromagnetism technique was used in coal mines to detect abnormal areas of aquiferous structures in both roofs and floors of coal seams and in front of excavated roadways. Survey devices, working methods and techniques as well as data processing and interpretation are discussed systematically. In addition, the direction of mini-wireframe emission electromagnetic wave of the full space transient electromagnetism technique was verified by an underground borehole for water detection and drainage. The result indicates that this technique can detect both horizontal and vertical development rules of abnormal water bodies to a certain depth below the floor of coal seams and can also detect the abnormal, low resistance water bodies within a certain distance of roofs. Furthermore, it can detect such abnormal bodies in ahead of the excavated roadway front. Limited by the underground environment, the full space transient electromagnetism technique can detect to a depth of only 120 m or so.

Damage and deterioration mechanism and curing technique of concrete structure in main coal cleaning plants

Concrete structures in main coal cleaning plants have been rebuilt and reinforced in the coal mines of the Shanghai Datun Energy Sources Co. Ltd., the first colliery of the Pingdingshan Coal Co. Ltd. and the Sanhejian mine of the Xuzhou Mining Group Co. Ltd. In these projects, the operating environment and reliability of concrete structures in the main plants of the three companies were investigated and the safety of the structures inspected. Qualitative and quantitative analyses were made on the special natural, technological and mechanical environments around the structures. On the basis of these analyses, we discuss the long-term, combined actions of the harsh natural (corrosive gases, liquids and solids) and mechanical environments on concrete structures and further investigated the damage and deteriorating mechanisms and curing techniques of concrete structures in the main coal cleaning plants. Our study can provide a theoretical basis for ensuring the reliability of concrete structures in main coal cleaning plants.

Digital image processing-based automatic detection algorithm of cross joint trace and its application in mining roadway excavation practice

This paper proposes a digital image processing-based detection algorithm for cross joint traces of coal roadway heading face.Initially,the acquired images were preprocessed,i.e.,adaptive correction was conducted for non-uniform illumination images based on the 2D gamma function.The edge detection algorithm was then applied to extract the edges of the structural plane,followed by the filtration of the non-structural plane noises.Moreover,the Hough transform algorithm was applied to extract the linear edges;finally,the edges were locally connected in accordance with the angle and distance criteria.The experimental results show that this algorithm can be used to reduce the noise caused by non-uniform illumination and avoid the mutual interference of multi-scale edges,so as to effectively extract the traces of the cross joint.Furthermore,Q-system and rock mass rating(RMR),were applied to conduct a quantitative evaluation on the stand-up time of unsupported roof in the four test images.The Q-system quality scores are 26.7,43.3,3.1,and 6.7,and the RMR quality scores are 56.84,58.73,48.42,and 51.42,respectively.The stand-up time of unsupported roofs with a span of 4.6 m are 30,36,7.7 and 14 d,respectively.