Why the future of rock mass classification systems requires revisiting their empirical past

Yang, Beverly; Mitelman, Amichai; Elmo, Davide; Stead, Doug

doi:10.1144/qjegh2021-039

Cited by 17 publications

(12 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Paraphrasing the words of Smith [10], we need to consider that in rock engineering most practitioners and academics continue seeking answers in the same research areas that yielded answers before, ignoring that research yields a diminishing return if we do not search for new directions. This discussion is a further demonstration that industry standards should not be immune of revisions and well-informed improvements to ensure that they are the best available solution [8].…”

Section: What Philosophy Can Teach Us About Innovationmentioning

confidence: 97%

“…Note that the author of the rock mass rating system (RMR, Bieniawski, [7]), was amongst the co-authors of the 2017 publication [5]. We describe the resistance to abandon what indeed is a quality index suffering from important limitations [8] as the industry standard paradox. The purpose of industry standards (and guidelines) is to act in ways that regular and predictable engineering decisions can be made.…”

Section: What Philosophy Can Teach Us About Innovationmentioning

confidence: 99%

“…As an example, let us examine a system in which the number of fractures sets and fracture frequency is measured along the Y-axis (vertical axis) and the characteristics of the fractures surfaces is measured along the X-axis. The measurements could be either ordinal measurements (qualitative characterisation transformed into quantitative values) or interval measurements [8]. We could use a decreasing scale of 10 to 1 on the Y-axis (notation 10Y, 9Y, etc.…”

Section: Solving the Irreversibility Problem: A Reformed Approach To ...mentioning

confidence: 99%

See 2 more Smart Citations

The Allegory of the Rock Engineering Cave

Elmo

Yang

Shapka-Fels

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Geoscientists and engineers are part of a system that produces changes to the world we live in. As machines are expected to gradually replace humans in various technical tasks (e.g., data collection and data characterisation), it becomes crucial to apply critical thinking and to question the foundations of commonly accepted practices. The challenge is to accept that empirical methods are shaped by cognitive biases, which result from our mind interpreting data by a process of data simplification. Indeed, it is possible to draw an analogy between rock engineering methods and Plato’s Allegory of the Cave. The fire casting the shadows along the cave walls represents the process of quantification of qualitative assessments of commonly accepted data collection methods. The chains holding the engineers as prisoners in the cave are empirical methods accepted as industry standards despite important limitations. Engineering judgment alone will not allow engineers to break free of those chains, and to emerge from the confined spaces of the cave and see things for what they really are (i.e., introduce truly objective data collections methods that better reflect failure mechanisms). In this paper the authors use philosophical arguments to justify the need to “dequantify” the GSI classification system and to teach us that engineering design should always be driven by the important questions of how, why, and whether.

show abstract

Section: What Philosophy Can Teach Us About Innovationmentioning

confidence: 97%

Section: What Philosophy Can Teach Us About Innovationmentioning

confidence: 99%

Section: Solving the Irreversibility Problem: A Reformed Approach To ...mentioning

confidence: 99%

See 1 more Smart Citation

The Allegory of the Rock Engineering Cave

Elmo

Yang

Shapka-Fels

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…All this raises important questions surrounding the scientific validity of RQD's development and RQD itself, especially since it is now being used in projects with attributes outside of the original database. Similar concerns could be raised for most of the empirical methods used in rock engineering design, which were developed using case studies that were much more limited in terms of their geology and project scope compared to today's challenges [16], and the Hoek-Brown failure criterion [17], which Hoek stated "was offered as a temporary solution to an urgent problem" and wanted replaced with "a set of well-researched predictive tools which were adequately substantiated by field studies and back analyses of real rock engineering case histories" (17). Given the propensity of ML to propagate biases and flaws in its dataset, rock engineers should minimize the use of these flawed and biased features in ML models.…”

Section: Data Preparation Techniquesmentioning

confidence: 98%

Data preparation for machine learning in rock engineering

Yang

Nazari

Elmo

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Digitalization in rock engineering has resulted in significant technological advancements and the increasing use of machine learning techniques. As rock engineering transitions into becoming more data-driven, machine learning can help rock engineers improve the efficiency and utilization of large data sets in the design process. While machine learning is a powerful tool, the success of machine learning algorithms is intrinsically related to the quality and quantity of data available. It is commonly accepted that machine learning algorithms that are trained on poor quality data will result in poor and inaccurate (i.e. highly subjective) results. To limit the human factors that result from using data that represent qualitative assessments rather than objective measurements of physical properties, it is imperative to improve the data analysis and preparation/labelling process. Data preparation is especially important when applying machine learning to rock engineering problems due to the inductive and empirical nature of the design process as a result of the inherent variability of geological materials. Despite data preparation accounting for more than half of the machine learning process, there is limited research on data preparation for machine learning in rock engineering. This paper aims to fill this gap by providing a set of guidelines on the necessary data preparation steps for applying machine learning to rock engineering problems, thereby helping rock engineers improve the performance of their machine learning models.

show abstract

“…Numerous studies have been performed for the assessment of rock mass quality. For instance, Terzaghi’s rock-load classification scheme can be considered as the first empirical rock mass classification system 3 . Thereafter, various other evaluation methods have also been proposed based on different engineering practices.…”

Section: Introductionmentioning

confidence: 99%

Rock mass classification prediction model using heuristic algorithms and support vector machines: a case study of Chambishi copper mine

Zhou

et al. 2022

Sci Rep

View full text Add to dashboard Cite

The rock mass is one of the key parameters in engineering design. Accurate rock mass classification is also essential to ensure operational safety. Over the past decades, various models have been proposed to evaluate and predict rock mass. Among these models, artificial intelligence (AI) based models are becoming more popular due to their outstanding prediction results and generalization ability for multiinfluential factors. In order to develop an easy-to-use rock mass classification model, support vector machine (SVM) techniques are adopted as the basic prediction tools, and three types of optimization algorithms, i.e., particle swarm optimization (PSO), genetic algorithm (GA) and grey wolf optimization (GWO), are implemented to improve the prediction classification and optimize the hyper-parameters. A database was assembled, consisting of 80 sets of real engineering data, involving four influencing factors. The three combined models are compared in accuracy, precision, recall, F1 value and computational time. The results reveal that among three models, the GWO-SVC-based model shows the best classification performance by training. The accuracy of training and testing sets of GWO-SVC are 90.6250% (58/64) and 93.7500% (15/16), respectively. For Grades I, II, III, IV and V, the precision value is 1, 0.93, 0.90, 0.92, 0.83, the recall value is 1, 1, 0.93, 0.73, 0.83, and the F1 value is 1, 0.96, 0.92, 0.81, 0.83, respectively. Sensitivity analysis is performed to understand the influence of input parameters on rock mass classification. It shows that the sensitive factor in rock mass quality is the RQD. Finally, the GWO-SVC is employed to assess the quality of rocks from the southeastern ore body of the Chambishi copper mine. Overall, the current study demonstrates the potential of using artificial intelligence methods in rock mass assessment, rendering far better results than the previous reports.

show abstract

Why the future of rock mass classification systems requires revisiting their empirical past

Cited by 17 publications

References 36 publications

The Allegory of the Rock Engineering Cave

The Allegory of the Rock Engineering Cave

Data preparation for machine learning in rock engineering

Rock mass classification prediction model using heuristic algorithms and support vector machines: a case study of Chambishi copper mine

Contact Info

Product

Resources

About