As mining operations progressively transition to deeper levels， the production conditions within mines become increasingly complex and challenging. This necessitates an advancement in the sophistication of intelligent equipment and a gradual reduction in on-site personnel.Developing an efficient and precise sche-duling and control system that aligns with these requirements is essential for ensuring intelligent mining ope-rations.Consequently，this study concentrates on optimizing the scheduling of underground gold mines， characterized by multiple equipment and short interval continuity，to enhance mining efficiency and safety.The limitations associated with multi-process， multi-equipment， and intricate coupling in underground gold mining operations have been systematically analyzed and distilled， leading to the formulation of a comprehensive set of scheduling requirements.By developing a combinatorial optimization model for equipment configuration and task allocation， the issue of underground equipment scheduling is conceptualized as a flow shop scheduling problem， with the objectives of minimizing the total duration and the total intervals.A genetic algorithm is utilized to address the model， facilitating dynamic and precise scheduling of mining equipment through short interval adjustments， thereby minimizing task conflicts and equipment idle times.The results of the case study demonstrate that the optimized model can significantly reduce overall operation durations and process intervals across diverse operational scenarios. In large-scale production settings with multiple cycle constraints， a mining efficiency of 72.57 tons per hour is attained.Furthermore， with an 8% failure rate， the delay in total operation time is maintained within 15%.The configuration of scientific equipment and the development of scheduling strategies are crucial for augmenting the production capacity of mining operations.The findings of this study offer an optimized solution for equipment scheduling in underground gold mines， thereby improving overall operational efficiency and safety while ensuring continuous production.

Underground metal mining operations are complex，involving dynamic events，parallel processes，and strict time-space constraints.These operations require the coordination of multiple independent mining equipment，，and process entities to ensure efficient ore extraction.Accurately modeling these operations and replicating the scheduling process iscrucial for optimization.Converting the physicalmining processes into a virtual environment is vital for effective simulation and modeling.This paper introduces a Petri net-based method for modeling and simulation，creating a framework that maps underground mining systems to a simulation space，facilitating dynamic scheduling of mining equipment.The construction of the mining system employs a five-layer architecture for hierarchical planning，establishing a structured framework for the mining operation system.This framework encompasses elements such as thematic domain grouping，thematic domains，business objects，logical entities，and attributes.Fundamentally，the mining operation system is characterized by the dynamic interaction of multiple entity objects across three primary thematic domains：Mining operation space，mining operation equipment，and mining operation processes.Utilizing Petri nets，the interrelationships between theoverall system and its constituent parts，as well as the interactions among components within localized areas，arethoroughly delineated.This approach facilitates the demonstration of event sequences，parallelism，synchronization，and asynchronous characteristics during the mining operation process.It also highlights conflicts，mutual exclusion，uncertainties，and potential deadlock issues within the system，thereby enabling a comprehensive analysis and evaluation of the system.The Generalized Stochastic Petri Net（GSPN） methodology is utilized to model transitions as random variables governed by mathematical distributions，thereby addressing the intricate coupling issues among space，equipment，and processes within the mining operation system.This approach facilitates the assessment of the system’s performance and reliability，yielding key production evaluation metrics such as production efficiency，equipment utilization，and effective working time.A practical simulation，based on an idealized data set constructed in accordance with the standard design stope of the Chambishi copper mine，serves to validate the mining operation system.The simulation results indicate that the total operation progress completion time is 213.77 days，during which 656 mining operation records，are generated.Additionally，a mining operation Gantt chart is constructed to illustrate the operation cycle and strip succession.The findings of this research provide robust support for dynamic scheduling decisions in underground metal mining operations，contributing to the achievement of efficient，safe，and intelligent mine production management.

The smart mining serves as the core engine of the digital transformation in the mining industry. By reviewing the latest global R&D and application advances，this study systematically investigates how key technologies empower the smart development of mining operations.Key technologies play a pivotal role in advancing the smart mining industry，with a primary emphasis on addressing practical production requirements.Research areas encompass the Internet of Things，machine vision，machine hearing，deep learning，big data mining，intelligent sensors，collaborative robots，digital twins，and green mining，among others.The application scenarios within smart mines predominantly involve intelligent control systems，asset management，safety assurance and its associated systems，data management and analysis systems，and monitoring systems.In anticipation of future advancements，the innovation and integrated application of key technologies are poised to serve as the central catalyst for the holistic development of smart mining，emphasizing high quality，sustainability，and enhanced intelligence.By leveraging artificial intelligence and big data technologies，the comprehensive capabilities of mines，such as precise exploration，optimization of mining pathways，reduction of energy consumption and waste，and improvement in resource utilization efficiency，will be significantly enhanced.The integration of digital twins and artificial intelligence is poised to facilitate the comprehensive digital operation of mining enterprises.Complementary technologies，including blockchain，the Internet of Things，cloud computing，and 5G，will enhance the efficiency and precision of remote management and intelligent decision-making processes within the mining sector.This technological synergy will establish a robust foundation for the transformation and modernization of the industry，steering it towards more sustainable，safe，digital，intelligent，and efficient practices.

In the intricate setting of mining operations，identifying foreign objects on conveyor belts transporting high-magnetic ore is hindered by significant scene interference and substantial recognition challenges.To address the issues of frequent loss of foreign object edge information and the considerable difficulty in achieving real-time，high-speed responses in high-magnetic environments，we propose an image recognition and detection methodology grounded in deep learning techniques.Initially，a dataset of foreign objects on conveyor belts is constructed.To address the issue of image blurring，which arises from the high-speed operation of the belt conveyor and the limited data acquisition frequency of industrial cameras，the dark channel defogging technique is employed to preprocess the data，thereby enhancing image clarity.Subsequently，the core architecture of YOLOV8 is refined by incorporating a dynamic attention mechanism and substituting standard convolution with snake convolution.The dynamic attention mechanism enables the model to dynamically allocate focus during input data processing.Concurrently，the integration of snake convolution in place of traditional convolution，in conjunction with C2f，significantly enhances the model’s capacity to process image details.This unique structure facilitates the capture of a broader spectrum of local and global features，thereby substantially reducing the model’s rates of false positives and missed detections concerning buried foreign objects.In conclusion，the YOLOV8 architecture has been enhanced through the integration of a dynamic detection head，which allows for flexible adaptation to multi-scale and multi-directional detection requirements.This modification aims to improve the model’s adaptability and optimize the reduction of computational parameters，thereby significantly enhancing its real-time performance in complex environments.Experimental results demonstrate that the model achieves an average detection accuracy of 96.4%，a recall rate of 91%，and an average detection time of merely 29 milliseconds.The algorithm presented in this paper de-monstrates an enhancement in average detection accuracy and recall by 5.2% and 6.2%，respectively，compared to the original network，thereby confirming its efficacy.This improved algorithm adequately satisfies the demands for precise detection and real-time performance in the context of mine belt transportation，offering substantial support for advancing mine safety management and operational efficiency.

Autonomous driving technology plays a crucial role in the development of smart mines，with its primary challenge being the safe navigation of vehicles within the intricate and dynamic environments of open-pit mines.Mining roads are frequently characterized by a high density of diverse obstacles，including rockslides，water pits，and ruts，which present in various forms and are widely dispersed.These conditions pose substantial safety risks to the autonomous operation of mining vehicles.At present，although numerous road obstacle detection algorithms have been proposed，their detection accuracy is frequently constrained by the distinctive conditions present in open-pit mines，thereby hindering their ability to satisfy practical application requirements.This study presents a road obstacle detection algorithm for open-pit mines based on RT-DETR.The algorithm integrates the RepViT network within the encoder phase to augment the model’s feature extraction capabilities，thereby facilitating a more precise capture of the characteristic information of road obstacles.In the decoder section，the algorithm employs channel compression pruning techniques，which significantly decrease the model’s computational complexity and enhance detection speed.Furthermore，it incorporates the RepAttC3 module，augmented with an attention mechanism，thereby enhancing the model’s capability to detect multi-scale and small target obstacles.To evaluate the algorithm’s efficacy，a dataset comprising road obstacle images from various mines，seasons，and scenarios was assembled，specifically focusing on open-pit mine road obstacles.The experimental findings indicate that the algorithm exhibits superior performance in identifying road obstacles within open-pit mines，achieving an average detection accuracy of 92.7%，a comprehensive detection accuracy of 96.6%，and a detection speed of 12.3 milliseconds.In comparison to existing road obstacle detection algorithms，the proposed algorithm demonstrates distinct advantages in detecting multi-scale and small target obstacles，thereby offering more precise and efficient obstacle detection for vehicles operating in open-pit mining environments.It offers robust technical support for the development of autonomous driving technology in open-pit mines，further advancing the progress of smart mine construction.

The open-pit mining area is a complex scene，and the traveling obstacle detection is seriously interfered by dust noise such as dust and particles，which makes it difficult to accurately identify obstacles，especially at night when the light is poor，which is not conducive to correct decision-making，thus affecting the safety and overall efficiency of unmanned operation.In view of the above problems，a YOLOv8n-based YOLOv8n-Enhanced algorithm for detecting traveling obstacles in open-pit mining areas was proposed.The algorithm is mainly improved in three aspects：Firstly，for the problems of serious interference by dust noise and poor light at night，a C2fCA module structure was proposed instead of the original C2f module，which utilizes the shared weights and context-aware weights to enhance the dependency relationship between different locations of the image，mitigate the noise interference，and improve the feature extraction ability of the model.Secondly，to trade-off the accuracy and real-time performance of the open-pit obstacle detection model，the Neck end of the model was reconstructed，and the lightweight convolutional techniques GSConv and VoV-GSCSP modules were used to reduce the complexity of the computation and network structure，and realize a higher computational cost-effectiveness of the detector.Finally，for the situation that there is a large gap between the quality of data in the open-pit mining area，especially at night when there is insufficient light，and low-quality data will affect the ability of the model to learn features in training，the loss function was optimized to solve the problem of the bounding box regression equilibrium between the samples of different qualities，to improve the ability of the model to generalize and accelerate the convergence.The experimental results show that the improved algorithm in this paper reduces the computational GFLOPs of the model by about 8.5% and the number of parametric params by about 3% while maintaining the real-time performance，and improves the mean Average Precision（mAP） of the YOLOv8n by 1.8% and 2.6% in daytime and nighttime scenarios，respectively，and realizes obstacle recognition at different scales in daytime and nighttime scenes.

During deep tunnelling using drill-and-blast method，excavation damaged zone （EDZ） is inevitably induced in surrounding rocks due to the coupled impacts of blast loading and dynamic initial stress unloading and thus affect the structure stability.Therefore，it is very important to predict EDZ depth before roadways excavation.Relying on the field measurements of EDZ in several underground mines as the research object，300 data samples were collected.Four mainstream hyperparametric optimization algorithms，i.e.，genetic algorithm （GA），gray wolf optimization algorithm（GWO），particle swarm optimization algorithm（PSO），and salp swarm algorithm （SSA），were used to optimize the XGBoost algorithm and to construct four hybrid models for EDZ prediction.Comparative analysis of predictive model performance was conducted in terms of R²，RMSE，MAE and MAPE，along with a sensitivity analysis of the influencing parameters.Finally，the optimal PSO-XGBoost model was applied to a transportation roadway in an underground mine for engineering validation.The results show that the GA-XGBoost，GWO-XGBoost，PSO-XGBoost，and SSA-XGBoost models achieve the best predictive performance with swarm sizes of 90，70，60 and 100，respectively.Among them，the PSO-XGBoost model demonstrates the best predictive performance with correlation coefficients of 0.9244 and 0.8787 in the training and testing sets，respectively.Moreover，compared to bench models（XGBoost，RF，SVM and LightGBM），both the prediction accuracy and stability of the optimized models are improved.The tunnel diameter（TD） and rock mass geological strength index（GSI） have the most significant influence on the loosened zone thickness，along with a noticeable impact from the vertical principal stress.The application results of the optimized XGBoost model in practical engineering show that the error between the measured value and the predicted value is within 10%，indicating that the PO-XGBoost is of significance for engineering application.

At present，traditional evaluations of green mine construction mostly use a direct scoring method to evaluate the effectiveness of green mine construction.This method ignores the relationship between evaluation indexes and fails to fully consider the input-output efficiency of mining enterprises.This paper selected 24 specific indicators from four aspects of resource utilization，environmental protection，enterprise society，and technological economy to build an evaluation index system for the effectiveness of green mine construction in the gold industry.In addition，the input-output efficiency evaluation index system of green mine construction in gold industry was constructed by optimizing and screening efficiency index from input-output aspect.The interval analytic hierarchy process（IAHP） and entropy weight method（EWM） were used to obtain the subjective and objective combined weights of evaluation indicators，and the TOPSIS method was combined to build the green mine construction effect evaluation model for the gold industry.The input-output efficiency evaluation of green mine construction in the gold industry was analyzed by using the BCC model of DEA method.On the basis of effect and efficiency measurement，the efficiency-effect evaluation matrix was designed to facilitate the analysis of the degree of green mine construction and the benefits of gold mining enterprises.It helps to judge whether gold mining enterprises take efficiency into account during the process of green mine construction，and the results reflect the actual overall construction situation of gold mining enterprises.Through the case analysis of ten gold mining enterprises of the same type in Shaanxi Province，the results show that the effectiveness and efficiency of the ten gold mining enterprises are fluctuating and rising.The overall construction situation is good，and the input-output efficiency is superior to the construction’s effect.Among the ten gold mining enterprises，except for M2 and M9，the green mine construction of the other mining enterprises has reached a high status.The four mining enterprises，M1，M4，M5 and M6，have given consideration to the effect and efficiency，and the other mining enterprises should pay attention to the development of both in the future construction.The index system constructed in this paper considers the characteristics of green mine construction in the gold industry，and the economic and quantitative indicators improve the accuracy of the evaluation results.The effect-efficiency evaluation model strengthens the connection between indicators，and can evaluate and analyze the overall situation of green mine construction in gold mining enterprises.It provides a scientific basis for the improvement of gold mining enterprises.

With the booming development of big data and Internet of Things technology，traditional mines have developed to smart mines and intelligent mines，and unmanned technology has been gradually applied to mining areas.In order to solve the problem that the rockfall detection of unstructured road in open-pit mine area has complex environment，large difference in rockfall size and similar color between rockfall and unstructured road surface，a rockfall detection model of mining road based on weighted bidirectional feature fusion was proposed.First，the SimAM attention mechanism is added to the backbone network，this attention mechanism is different from the previous channel attention mechanism and spatial attention mechanism，it can effectively eliminate the interference of the background environment without adding additional parameters，so that the model can focus more on the target characteristics of rockfall.Second，the weighted bidirectional feature pyramid（BiFPN）structure was used to realize multi-scale feature fusion in the neck.Since the PANet structure in the YOLOv5s network model only adds or splice the characteristics of the pyramid structure in the melting process，the bidirectional feature weighting was combined with the bidirectional feature of the weight and adaptive adjustment to ensure that the network model attaches proper importance to the rock ebaissees different sizes and different levels and realizes the addition between the low-level position information and high-level semantic information for multiple cross-layer weighted feature fusion，thus enhancing the feature extracion ability of the model for rockfall of different sizes.Finally，the lightweight convolution GSConv module was introduced into the col，which can be used to process function cards at this time，not only reducing redundant information，but also avoiding compression.The GSConv lightweight convolution module is based on deep separable convolution（DSC），ordinary convolution（SC） and channel shuffle operation，which improves the detection speed of the model by effectively reducing the complexity of the model.The experimental results show that the average detection accuracy of this algorithm reaches 92.8%.and the detection speed reaches 63.1FPS.Compared with the current fastest R-CNN，YOLOv4-tiny，YOLOv7 and YOLOv5s algorithms，the average detection accuracy is increased by 17.0，13.6，3.4 and 2.5 percentiles，and the detection speed is increased by 32.2，1.4，14.6 and 2.6 FPS，respectively.Moreover，the model size of the algorithm is only 12.9 MB，which is easy to deploy on mobile devices.Therefore，the algorithm can realize the real-time and accurate detection of unstructured road rockfall in mining area，and ensure the safe driving of unmanned mining card.

The “cloud-edge-terminal” system of smart mines under the mode of industrial internet of things（IIoT） has become the focus of development of mining enterprises.At present，the digitalization and intelligence at the “cloud” and “end” levels have began to take shape.However，the construction at the “edge” level，namely the edge layer，is relatively weak，which restricts the production efficiency of smart mines.Therefore，the concept of “mine-edge intelligence” were proposed，which was defined as an edge intelligence technology system specifically designed for mining production environments，with multi-dimensional characteristics in geography，network and technology.The key technologies include data fusion，information communication and edge security.Data fusion not only integrates data from different sources，but also solves the issue of equipment compatibility.The equipment in the mining environment comes from various vendors，utilizing different communication protocols and data formats.It is very important to establish a data fusion platform that can handle heterogeneous data and ensure compatibility among devices.This necessitates the conversion of data formats，so that the data in the system circulation，coupled with data cleaning，processing，and analysis.The information and communication capacities focus on establishing an efficient and reliable communication network in the mining environment.This includes the adoption of advanced communication technologies and network architectures to optimize network configuration and management，and ensure rapid and secure data transmission between the “cloud”，“edge” and “end”.The edge security technology focuses on protecting edge layer devices and data，including encryption，authentication，and access control methods to enhance security.Moreover，it is necessary to emphasize the deep integration of mining technology with intelligent technology.This includes process reshaping driven by software requirements，as well as innovations in process decision-making，network architecture and environmental sensing.In summary，as the core of the smart mine’s edge layer，“mine-edge intelligence”needs to strengthen data fusion，information communication and edge security technology.Future development should focus on the deep integration of mining technology and intelligent technology to enhance production efficiency and safety.

Promoting the digital transformation of resource-based enterprises is an effective path to crack the development dilemma of enterprises and achieve high-quality development.Due to the significant differences in resource-based enterprises’ resource endowments and transformation capabilities，the degree of digital transformation also shows significant differences.So，what combination of influencing factors can effectively promote the digital transformation of resource-based enterprises？What are the differentiated transformation paths that different resource-based enterprises should follow？At the same time，the digital transformation of resource-based enterprises is a complex systemic project，and previous studies are limited in exploring it only from a single dimension.This paper took resource-based enterprises in China as the research object，from the perspective of “pressure-capacity-drive”，it refined into six antecedent conditions：market competition，growth capability，resource integration capability，innovation capability，enterprise size and financial support.Using NCA and fsQCA methods，it analyzed the relationship between the six antecedent conditions and the NCA and fsQCA methods were used to analyze the complex causal relationships between the six antecedent conditions and the digital transformation of resource-based enterprises.The study found that：The digital transformation of resource-based enterprises is not driven by a single condition，but it is the result of the synergy of multiple conditions.There are three types of groupings that generate high-level digital transformation，namely，the innovation capability-driven type that responds to pressure，the government-led type under pressure and the comprehensive-driven type，mainly by SMEs.There are two types of groupings that generate non-high-level digital transformation，namely，the settled type and the type with both weak innovation capability and drive.And market competition plays a key role in the digital transformation of resource-based enterprises.The results of the study reveal the interaction between various factors in the digital transformation of different resource-based enterprises，which can provide theoretical guidance and path references for resource-based enterprises to realise digital transformation.

Roadway is the main engineering for the development，production and transportation of underground metal mines.The stability of surrounding rock of underground roadway will directly affect the safety production of the mine.The structural analysis of roadway rock mass was carried out to obtain the spatial characteristics of the surrounding rock structural plane，so as to analyze the characteristics and instability of blocks cutted by structural plane，and identify the dangerous area of roadway block instability，so as to provide a good guarantee for roadway safety.The information acquisition of rock mass structural plane includes the measurement of occurrence，trace length，spacing and opening degree.At present，there are mainly full manual identification，semi-manual identification and automatic identification methods to carry out rock mass structural plane identification.Different methods have different effects on the identification accuracy of rock mass structural plane，but it is generally difficult to accurately distinguish the surrounding rock defects and structural plane of underground roadways，and the accuracy of the identified structural plane data is poor.Therefore，it is very necessary to develop a safe and accurate rock mass structural plane measurement and identification technology to provide accurate data support for the accurate deconstruction and stability analysis of roadway structural plane.In order to strengthen the high quality and high precision identification and optimization of the structural point cloud data of the surrounding rock of underground roadway，the research on the measurement and identification of the structural plane of underground roadway rock mass was carried out based on 3D laser scanning technology.In this paper，the structural plane identification method based on point cloud data was summarized，and three-dimensional laser scanning and structural plane information extraction were carried out in the 910 m midsection transportation roadway of Maoping lead-zinc mine，Luozehe Town，Yilang County，Yunnan Province.Finally，the field manual measurement and manual identification，semi-automatic identifi-cation and manual identification were compared and verified and analyzed.The results show that in the underground mine roadway，when the combination of manual identification and semi-automatic identification was used to identify the rock mass structural plane of the roadway，the obtained structural plane data is more accurate and comprehensive.Due to the advantages of high precision and convenience of 3D laser scanning，the combination of “manual+semi-automatic”identification method has great further optimization in the measurement and identification of rock mass structural plane of underground roadway.It provides a new idea for the identification of tunnel structural plane information and the extraction of geometric features，and provides an efficient and accurate measurement method for the identification of tunnel structural plane.

With the rapid development of digital economy in the world，how to realize the rapid optimal allocation of underground mine production equipment has become the key to the continuous advancement and in-depth application of digital mine.In view of the characteristics of underground mines such as limited space，limited equipment resources，and large production tasks，an optimization model was constructed for production planning of the follow-up filling mining method in the open pit using pre-controlled roof medium-and deep-hole and sublevel open-stopping and subsequent filling method.The model aims at minimizing the interval time between adjacent processes and the total production time，and the above issue is solved using genetic algorithms.The genetic algorithms used for solving the problem include traditional genetic algorithms and optimized genetic algorithms.Taking the actual data of a copper mine test stope in Zambia as an example，it can be seen from the iterative results that all genetic algorithms can solve the model，and the optimized genetic algorithm converges faster than the ordinary genetic algorithm.The genetic algorithm accelerated by heuristic algorithm has the fastest convergence speed.Therefore，the heuristic genetic algorithm is used to solve the multi-objective optimization model and the results are visualized.After analyzing the solution results，it is found that the average utilization rate of equipment is only 49.16%，and the utilization rate of some equipment is low，so the number of equipment is optimized.After the number of equipment was optimized and solved again，the average utilization rate of mine equipment increased to 64.8%，basically meeting the requirements of the mine.In terms of production，the daily average ore output is 3 631.19 t/d，which meets the mining demand and effectively shorts the operation time interval to ensure the requirements of mining safety.In addition，copper and cobalt sunrise ore grade fluctuation is small，easy to concentrate.Therefore，the algorithm and model can quickly and effectively solve the problem of multi-equipment coordination in a copper mine in Zambia，improve production efficiency and safe mining.

As a typical process industry，the mining of underground metal mines depends on the smooth operation of the ore transportation link，and the unmanned mine truck bears an indispensable and important responsibility in the ore transportation link，so the intelligent scheduling and management of the unmanned mine truck is the key to ensure the smooth production of the mine.There are few studies on the scheduling and management of unmanned mine trucks，and it is difficult to meet the new requirements brought by the increasing degree of unmanned mine trucks.Based on the analysis of the current situation of cluster intelligent scheduling strategy，scheduling business flow，and data integration system for unmanned mining trucks in a certain underground mine in Gansu province，an integrated system platform for intelligent decision-making，automatic scheduling，and process control serving unmanned mining trucks scheduling was proposed.In response to the transformation of unmanned mining trucks scheduling mode and two traffic control challenges，corresponding intelligent scheduling strategies were designed，and the overall architecture was designed.Some functional modules were designed，including scheduling console，real-time monitoring，scheduling visualization，and production management.The system platform has been successfully applied to the mine through the intelligent transformation of the mine truck，the construction of the intelligent dispatching system，and the development of the system.The application results show that the existing traffic control problems have been solved and the dispatching efficiency has been improved by 7.18% with the help of the intelligent dispatching system with the core of vehicle end scheduling algorithm，single-lane collision avoidance algorithm and merging truck algorithm.It provides a centralized and unified management and use platform for data，breaks the information island，and greatly improves the data utilization rate.Through vocational work split and process drive，the scheduling modular management is realized.The successful application of the platform has innovated the dispatching mode，supplemented the research in relevant fields，provides an important reference for the intelligent transformation of underground mines，and also provides reference experience for the development of cluster dispatching management system platform across equipment categories and production areas.