Precise and non-destructive approach for identifying the real concentration based on cured cemented paste backfill using hyperspectral imaging

Abstract

Cemented paste backfill (CPB) is a technology that achieves safe mining by filling the goaf with waste rocks, tailings, and other materials. It is an inevitable choice to deal with the development of deep and highly difficult mines and meet the requirements of environmental protection and safety regulations. It promotes the development of a circular economy in mines through the development of low-grade resources and the resource utilization of waste, and extends the service life of mines. The mass concentration of solid content (abbreviated as "concentration") is a critical parameter for CPB. However, discrepancies often arise between the on-site measurements and the pre-designed values due to factors such as groundwater inflow and segregation within the goaf, which cannot be evaluated after the solidification of CPB. This paper innovatively provides an in-situ non-destructive approach to identify the real concentration of CPB after curing for certain days using hyperspectral imaging (HSI) technology. Initially, the spectral variation patterns under different concentration conditions were investigated through hyperspectral scanning experiments on CPB samples. The results demonstrate that as the CPB concentration increases from 61wt% to 73wt%, the overall spectral reflectance gradually increases, with two distinct absorption peaks observed at 1407 and 1917 nm. Notably, the reflectance at 1407 nm exhibited a strong linear relationship with the concentration. Subsequently, the K-nearest neighbors (KNN) and support vector machine (SVM) algorithms were employed to classify and identify different concentrations. The study revealed that, with the KNN algorithm, the highest accuracy was achieved when K (number of nearest neighbors) was 1, although this resulted in overfitting. When K = 3, the model displayed the optimal balance between accuracy and stability, with an accuracy of 95.03%. In the SVM algorithm, the highest accuracy of 98.24% was attained with parameters C (regularization parameter) = 200 and Gamma (kernel coefficient) = 10. A comparative analysis of precision, accuracy, and recall further highlighted that the SVM provided superior stability and precision for identifying CPB concentration. Thus, HSI technology offers an effective solution for the in-situ, non-destructive monitoring of CPB concentration, presenting a promising approach for optimizing and controlling CPB characteristic parameters.

1. Introduction

Mineral resources serve as a crucial foundation for national economic development and technological advancement [1–4]. However, large-scale resource extraction often results in the significant discharge of solid wastes [5–8], including tailings, phosphogypsum, and coal gangue [9]. These wastes not only occupy extensive land areas but also contribute to severe pollution of surrounding land and groundwater [10–13]. Cemented paste backfill (CPB) offers an effective solution to these challenges by mixing solid waste, cement, and water to create a backfill slurry, which is subsequently transported to the goaf. This method addresses the issues of solid waste disposal and the potential hazards posed by void spaces in mined-out areas [14–16].

The mass concentration of CPB is a critical factor affecting its performance. CPB with higher concentrations generally exhibits greater strength and a more compact microstructure [3,17–18]. The concentration of CPB can be effectively controlled and monitored during its preparation. However, once the CPB reaches the goaf, factors such as groundwater inflow or segregation often lead to discrepancies between the actual concentration and the intended concentration [19–20]. This deviation is a key reason for the variation in CPB performance from the design specifications. Once the CPB has cured for a certain period or when dealing with unfamiliar samples, determining the concentration via visual inspection or basic equipment becomes challenging. In mining operations, for instance, CPB quality is typically monitored using core sampling, followed by uniaxial compressive strength tests to evaluate its strength. However, the CPB concentration remains unknown, and it is uncertain whether the observed strength differences are due to variations in concentration [21]. It is well-known that the concentration measurement of fresh CPB slurry is very easy, while there are no effective methods for identifying the real concentration of CPB after curing for certain d in the goaf. Therefore, under the conditions encountered in the goaf, the ability to rapidly and non-destructively identify the actual concentration of CPB is crucial for accurately controlling backfill parameters and facilitating intelligent backfilling. Furthermore, the absence of real-time non-destructive concentration testing methods for cured CPB renders backfilling strategies difficult to adjust in a timely manner, potentially leading to risks of insufficient filling quality or goaf instability.