Logistic regression model for prediction of roof fall risks in bord and pillar workings in coal mines: An approach

doi:10.1016/j.ssci.2008.01.002

Safety Science

Volume 47, Issue 1, January 2009, Pages 88-96

https://doi.org/10.1016/j.ssci.2008.01.002 Get rights and content

Abstract

The roof fall hazards are the major problems in underground coal mines, which are generally unpredictable due to the associated uncertainties arising out of the complexity of geological conditions and variability in mining parameters. During the six year period, 1996–2001, 253 Indian coal miners lost their lives and 401 are seriously injured in 490 different roof fall accidents. In India, 32.7% of the total fatal injuries in coal sectors are due to roof fall in bord and pillar method of workings. This paper attempts to predict the severities of roof fall accidents based on some major contributing parameters using the binary logistic regression model. In total, 128 roof fall accidents for the last few years from five underground coal mines in India having bord and pillar method of working are analyzed for this study. The results revealed that wider gallery width is more prone to major and serious accidents than narrower gallery width. Thin seams are more amenable to major accidents in comparison to thick seams. Unsupported or partially supported roofs have higher risk for contributing major as well as serious accidents. Deep workings are more prone to major accidents as compared to shallow depth workings.

Introduction

Roof falls continue to be one of the greatest single hazards faced by underground coal miners. The hazardous nature of roof falls in underground coal mine operations can be illustrated from the national statistics of mine accidents. During the six year period, 1996–2001, in India, 253 coal miners lost their lives and 401 are seriously injured in 490 different roof fall accidents. 32.7% of the total fatal injuries in Indian coal sectors are due to roof fall in bord and pillar method of working; whereas only 1% of the total fatal injuries due to roof fall are occurring in longwall method of working (DGMS, 1996–2001). The roof fall accident rates are less in longwall faces, since they are very few in number, mostly mechanized covering the working faces with powered roof supports and galleries with the combination of roof bolting, props and bars, and also areas of exposure due to drivage of galleries are much smaller than the bord and pillar method of working (Das, 1984). In underground coal mining, bord and pillar is the method of working, mostly preferable for flat tabular deposits in thin seams, where bords or galleries are driven in the solid coal to form pillars in the development workings. ‘Pillars’ of coal are left behind to support the roof and prevent collapse. Additional support is provided through the use of roof bolts and props. In some cases, the pillars are removed partly or fully in a later operation known as bord and pillar depillaring.

The complexity of geological deposit and variability of mining parameters leads to the occurrences of unwanted roof falls. There are various studies on finding relationship between the roof falls and geological conditions, stress state and mine layout (Molinda et al., 2000, Das, 2000, Phillipson, 2003). Phillipson (2003) emphasized on geological mapping for ultimate benefit of understanding the geology and projecting the zones of adverse ground conditions for the prevention of fatality. The identification of many slickenside features as faults and shear zones, which are true structural geologic features, increases the importance of basic structural geologic mapping in coal mines. Interpreting slickenside formation in terms of structural geology can allow areas of poor ground conditions to be projected ahead of mining, so that additional support measures can be planned in advance. Das (2000) studied the behaviour of coal measure roof rocks during mining, considering the geology and physico-mechanical rock properties. Molinda et al. (2000) performed simple regression analysis with some significant geotechnical variables like overburden, bolt strength, bolt capacity, grout length, density, entry width, coal mine roof rating (CMRR) and intersection span for predicting the roof fall rate. The results showed that there is relationship existing between intersection span and entry width; CMRR and overburden; CMRR and bolt length. For stronger roofs (high CMRR), shorter bolts are required, and there is a positive correlation between CMRR and depth of cover. Depth of cover is one of the major factors for the ground falls, as it is an indirect representation of the horizontal stress (Dolinar et al., 2001, Molinda et al., 2000) affecting the roof geology and the pillar strength. In most of the countries, mine workings having depths less than, or equal to 120 m are regarded as shallow depth category and more than 120 m, as deep mines (Dolinar et al., 2001). In their study, for the guidelines of roof bolt design, though they found statistically, the effect of depth of cover was relatively weak with all other geotechnical variables remaining the same, stated deeper mines are more likely to have high roof fall rates. Besides depth of cover, another important factor is the width of gallery. The relationship of gallery width with factor of safety of pillars has been well established and the immediate roof rocks may be classified as weak, or strong (Das, 1994). The management of roof fall risks in underground coal mines is explained by Duzgun and Einstein (2004) with the probability of roof fall, and cost of consequences by relative cost criterion. They provided two alternative methods of “do nothing” and go for “support improvement” by the cost-benefit analysis in their decision framework. A comparative study is conducted for a group of five underground coal mines in India for the reliability of mine for roof fall accidents and estimation of roof fall risks by Monte Carlo method (Palei and Das, 2005). Their results revealed that the probability of roof fall of a mine did not identify the overall risk, because the other component of risk, i.e. the costs of consequences of such roof fall accidents also play an important role.

Accident ratio (i.e. reportable injury:serious injury:fatality) studies indicated that there are many more minor injuries experienced than serious injuries and that for the same serious injury there have been numerous property-damage accidents and there are a large number of near-miss cases too. Bhattacherjee (2000) identified that for a group of six Indian coal mines, the four year ratio of reportable injury to serious injury to fatality was 50:5:1. A special attention is paid in this paper on the assessment of the risk of roof fall accidents of different severity in the coal mines having bord and pillar method of workings. The major contributing parameters may be categorized into different groups, which are responsible for unwanted outcomes. The contributing parameters has been grouped into two classes namely (i) geo-mining variables, such as gallery width, mining height, depth of cover, seam thickness, roof support status, and immediate roof and (ii) location variables like roof fall location and the individual mine. A binary logistic regression model is used for this study.

Section snippets

Mine description

Five underground coal mines are considered for the purpose of study and data are collected from those mines. All the mines have bord and pillar method of workings. Out of the five mines, three are located in Eastern India (relevant data collected from these mines from 1991 to 2004) and two are in Southern India (relevant data collected from these mines from 1996 to 2004). Each mine operates six days a week and three shifts a day. The roof supporting is done by systematic support rules (SSR) as

Results

In this section, the correlation between the independent variables are tested and the results obtained from the logistic regression model are explained. The correlation coefficients between the independent variables for case A and case B are presented in Table 3, Table 4, respectively. The logistic model is utilised in establishing the significant differences between categories of the various variables.

Conclusion

This paper focused on evaluation of severities of roof fall accidents in bord and pillar method of working through the application of logistic regression model. Again, logistic regression model deals with probability function and treats each individual as a separate observation to estimate the probabilities. On the basis of the model results, the unsupported, or partially supported roofs are more prone to major accidents than the supported roofs, but the earlier study by Biswas and Zipf (2003)

References (14)

S.K. Das
Observations and classification of roof strata behaviour over longwall coal mining panels in India
International Journal of Rock Mechanics and Mining Sciences
(2000)
H.S.B. Duzgun et al.
Assessment and management of roof fall risks in underground coal mines
Safety Science
(2004)
S.E. Phillipson
Control of coal bed decollement-related slickensides on roof falls in North American Late Paleozoic coal basins
International Journal of Coal Geology
(2003)
A. Bhattacherjee
Coal mine safety – where do we go from here
Journal of Mines, Metals and Fuels
(2000)
Biswas, K., Zipf, R.K., 2003. Root causes of ground fall related incidents in US Mining industry. In: 22nd...
D.K. Cox
The Analysis of Binary Data
(1970)
S.K. Das
Accidents at Moonidih – a comparative analysis of conventional and powered support faces
The Indian Mining and Engineering Journal
(1984)

There are more references available in the full text version of this article.

Cited by (102)

Comparison of four machine learning methods for occupational accidents based on national data on metal sector in Turkey
2024, Safety Science
Occupational accidents are one of the main problems in production system especially in metal sector. The aim of this study is to develop a predictive framework using machine learning (ML) to identify the causes of fatalities and amputations in the metal sector based on occupational accident data collected by the Turkish Ministry of Labor and Social Security (MLSS) from 2013 to 2018. Researchers have used a variety of strategies to investigate factors and create effective prediction frameworks for lowering occupational accidents. We used random forest (RF), k-nearest neighbour (KNN), gradient boosting method (GBM) and recursive partitioning and regression trees (RPART) to predict accident causes and consequence. Accuracy, precision, recall and f-score is used to measure the performance of ML frameworks. For model validation 10-fold cross validation method was used which increased the accuracy of the frameworks considerably. We extracted important factors which affected the causes of accident at metal sector using feature importance. Analysis proved RF as the best performing framework with highest classification results with 0.9172 accuracy, 0.9618 precision, 0.9518 recall and 0.9568 f-score using all features as compared to other techniques classification of occupational accident severity. To implement preventive controls and interventions in a more targeted way, it is recommended to use the predictive RF algorithm in the analysis of occupational accidents. With these studies, preventive measures can be taken by predicting occupational accidents that may occur in the future.
Critical review on data-driven approaches for learning from accidents: Comparative analysis and future research
2024, Safety Science
Data-driven intelligent technologies are promoting a disruptive digital transformation of human society. Industrial accident prevention is also amid this change. Although many emerging technologies, such as machine learning (ML), are extensively employed in workplace safety, these approaches need to fit the intended safety purpose of accident analysis, risk assessment, adverse outcome prediction, or anomaly detection. Hence, examining the “real-world” need for accident prevention and the advantages of emerging data-driven methodologies to better integrate them is necessary. This study provides a systematic review to clarify the current research status, existing problems, and future insights into these evolving technologies in accident prevention. We present notable gaps and barriers in data-driven accident prevention by analyzing 194 published studies from four perspectives: Paradigm, Model, Data Source, and Purpose. The results demonstrate (1) lack of a systematic framework to guide the application of Big Data (BD) in the field of safety; (2) few prior studies have considered model interpretability; (3) more proactive data needs to be incorporated into accident analysis; (4) safety-related data and domain knowledge need to be further integrated; (5) some recent data-driven techniques are unexplored in safety science. Further, the future research opportunities are discussed based on these findings. Such review may help clarify the mapping of data-driven tasks to safety goals to accelerate the uptake of data-driven technologies in safety or accident analysis research.
Damage constitutive model of uniaxially compressed coal material considering energy dissipation
2023, Journal of Materials Research and Technology
Coal plays a dominant role in China's energy production and consumption, which also serves as the cornerstone for energy security. The constitutive relationship of coal material is of great significance for the quantitative characterization and evaluation of mechanical properties of isolated coal pillars. From an energy perspective, coal failure is driven by energy, and the energy-based damage characterization provides a basis for the establishment of constitutive model. In this study, since the constitutive model based on the classical Lemaitre's hypothesis shows a significant error in presenting the nonlinear constitutive relationship of coal material, a correction coefficient considering the compaction effect of coal material is first introduced. Then, a novel damage constitutive model that can accurately describe the overall compression state of coal material is constructed. Finally, the theoretical model is compared with exiting models using the experimental data of five types of coal material from different mines. The results show that the evolution of energy dissipation damage variable is highly consistent with that of stress–strain relations. The established constitutive model considering energy dissipation and compaction effect can more accurately describe the nonlinear strength and deformation characteristics of coal material than the classical and existing models. Notably, this new model can be effectively extended to the single cyclic compression conditions to reproduce the loading-unloading-reloading process of coal material.
Experimental investigation into damage and failure process of coal-rock composite structures with different roof lithologies under mining-induced stress loading
2023, International Journal of Rock Mechanics and Mining Sciences
Coal burst is essentially a destructive manifestation of stratigraphic structure. Although the failure mechanism of the structure has been extensively studied using experimental and numerical methods, few studies have considered the critical role of the mining stress environment and the roof stratum in structural instabilities. In this paper, uniaxial static-cyclic loading tests were performed on a series of composite specimens with different roof lithologies. The objective is to investigate the damage and failure process of composite specimens under mining-induced stress conditions, particularly the mechanical response and damage evolution to coal and rock under cyclic disturbance. The results indicate that the mechanical behaviour of the composite specimen is closely related to the mechanical properties and interactions of the components, and the coal and rock show various characteristics of deformation and damage under cyclic loading with increasing static stress. A dynamic elastic strain energy (DESE) index based on the energy conversion of the specimen was proposed, which is more consistent with the trend of the P-wave velocity and thereby can well reflect the damage state of the specimen. The variation in the acoustic emission (AE) energy rate implies that the composite specimens experience progressive damage before failure, along with AE events spatially clustered in the failure plane of the weak roof and near the upper and lower boundaries of the coal body. The failure pattern of the composite specimen changes with increasing roof strength from initial structural instability due to tensile splitting or shear failure of the roof to the ejection of localized coal chips near the interface, which is attributed to the lateral tensile stresses on the coal near the interface caused by the mechanical difference and frictional constraint under cyclic unloading.
A causal inference method for improving the design and interpretation of safety research
2023, Safety Science
Although the research into causal effects has always been the core part of safety science, the formal mathematical method to infer causal effects is quite new. With the rapid development of big data technology, safety research based on experience changes to data-driven research. This change improves the reliability and accuracy of safety decision-making to a certain extent. However, researchers pay too much attention to the amount of data and computing power, accelerating the separation of prior knowledge and data. We proposed a systematic method suitable for safety science to carry out quantitative causal inference to study causal problems such as the effectiveness of safety countermeasures. This method aims to integrate safety-related prior knowledge and data organically and provide essential guidance for research design and data collection. Finally, an empirical study was conducted to illustrate how the approach can accurately estimate the rigorous causal relationship between factors and how it can help researchers understand the complex causal mechanism behind the safety or accident phenomenon.
Application of adaptive neuro-fuzzy inference system and differential evolutionary optimization for predicting rock displacement in tunnels and underground spaces
2023, Structures
In this paper, the rock displacement phenomenon was investigated to evaluate and prevent the failure and collapse of tunnels and underground spaces. The historical datasets were then analyzed and used to develop a novel, simpler intelligent model, that provides better accuracy for predicting rock displacement in tunnels/underground spaces, namely the RF-DE-ANFIS model. Whereas the random forest (RF) algorithm played as a robust tool to reduce the number of input variables to make the model’s structure is simpler, the differential evolutionary algorithm (DE) optimized the parameters of the adaptive neuro-fuzzy inference system (ANFIS) under 10-folds cross-validation technique for predicting rock displacement based on the selected input variables (by the RF). The models, such as standalone ANFIS, RF-ANFIS (without the optimization of DE), DE-ANFIS (without the reduction of RF), support vector machine (SVM), RF-SVM, and gene express programming (GEP), were also considered and compared with the RF-DE-ANFIS model to demonstrate the simplicity, as well as high efficiency, of the RF-DE-ANFIS model in predicting rock displacement. The obtained results indicated that the RF-DE-ANFIS model provided the most dominant accuracy (∼86 %) with a simpler structure, and the accuracy was improved by 8 % —12 % compared to the other models. Based on the proposed RF-DE-ANFIS model, the rock displacement phenomenon in tunnels/underground spaces can be early warned and proper solutions can be applied to prevent the failure of tunnels/underground spaces.

View all citing articles on Scopus

View full text

Logistic regression model for prediction of roof fall risks in bord and pillar workings in coal mines: An approach

Abstract

Introduction

Section snippets

Mine description

Results

Conclusion

International Journal of Rock Mechanics and Mining Sciences

Safety Science

International Journal of Coal Geology

Coal mine safety – where do we go from here

Journal of Mines, Metals and Fuels

The Analysis of Binary Data

Accidents at Moonidih – a comparative analysis of conventional and powered support faces

The Indian Mining and Engineering Journal