The intelligent transformation of coal mines is an inevitable choice to promote the green transformation of energy and to achieve safety and efficiency in the industry. Exploring the path of its efficient construction is the key to realizing the construction of intelligent coal mines in China. To analyze the configuration paths for the efficient construction of intelligent coal mines, 17 typical coal-producing provinces in China were used as the research object of a fuzzy set qualitative comparative analysis (fsQCA), and five conditional variables, namely research funds, technical talent, government importance degree, national demonstration, and basic resource support, were selected from four levels (technology, organization, environment, and resources) based on relevant national data from 2019–2021, and multiple configurations as well as multiple driving paths for the construction of intelligent coal mines were discussed. We found that there are three configuration paths that will enable the construction of intelligent coal mines: a technology-driven path under the government’s supervision, a path jointly driven by three-prongs, and a policy-driven path under the resource priority. The critical importance of the government is the common factor among the three driving modes. These research results can provide useful construction ideas for the construction of intelligent coal mines in different regions and enable provincial governments to carry out strategic combination actions according to local conditions to contribute to the efficient construction of intelligent coal mines and the green transformation of energy across the country.

Intelligent mines require much more mental effort from visual display terminal (VDT) operators. Long periods of mental effort can easily result in operator fatigue, which further increases the possibility of operation error. Therefore, research into how brain fatigue affects the sustained attention of VDT operators in intelligent mines is important. The research methods were as follows: (1) Recruit 17 intelligent mine VDT operators as subjects. Select objective physiological indicators, such as reaction time, error rate, task duration, flicker fusion frequency, heart rate, electrodermal activity, and blink frequency, and combine these with the subjective Karolinska Sleepiness Scale to build a comprehensive brain fatigue evaluation system. (2) According to the fatigue-inducing experiment requirements, subjects are required to carry out mathematical operations in accordance with the rules during the presentation time, determine whether the results of the operations fall within the [7, 13] interval, and continue for 120 min to induce brain fatigue. (3) Perform the standard stimulus button response experiment of the sustained attention to response task, before and after brain fatigue, and compare each result. The results show that: (1) When the standard stimulus appeared in the EEG experiment, the amplitude of the early N100 component before and after brain fatigue was significantly different. When the bias stimulus appeared, the average amplitudes of the P200 component and the late positive component, before and after brain fatigue, were significantly different, suggesting that the brain fatigue of VDT workers in coal mines would reduce sustained attention; (2) After the 120 min of the continuous operation task, the subjects showed obvious brain fatigue. The objective brain fatigue was followed by an increase in reaction time, an increase in error rate, a decrease in flicker fusion frequency, an increase in heart rate, an increase in electrodermal current, an increase in the number of blinks, and a larger pupil diameter, and both the subjective and objective data indicated more significant changes in the subjects’ brain fatigue at the 45th and 90th min. The results of the study could provide insight into the reduction in operational efficiency and safety of VDT operators in intelligent mines due to brain fatigue and further enrich the research in the area of brain fatigue in VDT operations.

To explore the influence of the construction and presentation frames of visualization information for safety (VIS) on people’s situation awareness (SA), we designed a three-level user interface (UI) of VIS based on the three-stage SA theory, including perception (SA1), comprehension (SA2), and projection (SA3). Then, 166 subjects were recruited and divided into three groups to participate in the experiment, in which SA was measured by the situation-present-assessment method (SPAM) and situation-awareness-rating technique (SART), and eye-movement data were recorded. The results show that the level−3 UI design could effectively improve the subjects’ SA levels. Although the increase in VIS displayed caused by the higher UI level led to a decrease in the perception-stage score of SA, the level−3 UI fully considered the three stages of human information processing, and helped improve the SA of the subjects; the overall SA score measured using the SART method was not significant, but the result was consistent with the SPAM. There was a framing effect on the presentation of VIS, and subjects perceived different degrees of risk under different presentation frames; that is, less risk under the positive frame, more risk under the negative frame, and a higher level of SA under the positive frame compared with the negative frame. To some extent, the nearest-neighbor-index (NNI) algorithm could be utilized to quantify subjects’ eye-tracking fixation mode. While the frames were guided by the high-level interface and the positive presentation frame, the distribution of the subjects’ gaze points was more discrete; they could grasp the relevant information more comprehensively and had a relatively high level of SA. To some extent, this study can provide a reference for the design and optimization of the VIS presentation interface.

The digitization of the instrument control system in monitoring operations makes the problem of the operator’s situational awareness failure more prominent. In order to better prevent this occurrence, this paper explores the failure of situational awareness from the perspective of cognitive function. The subjects were randomly divided into two groups: a working memory training group and a control group. Working memory measurements and coal mining machine monitoring simulation system operation tasks were performed before and after training, and the task performance, situational awareness scale, and EEG index data were recorded. The results showed that, after the training, there was a significant improvement in the task performance of the monitoring operation and the scores of the situational awareness scale, and there were different degrees of activation in the θ, α₂, and β₁ frequency bands. It was demonstrated that working memory training could help to improve the rapid reaction and decision-making abilities of operators in complex or emergency situations, thus preventing the failure of situational awareness. This study provides a new direction for research on the prevention of situational awareness failure.

The intelligent development of coal mines is a crucial way to achieve the safe, efficient, green, and low-carbon transformation of the coal industry and to reach the “double carbon” target, which is related to the life and health of miners, the stable development of enterprises and the national energy reform. As directly affected subjects, the cooperative attitudes of miners in different emotional states have a significant impact on the smooth implementation of intelligent coal mine renovation projects. Hence, we combined the RDEU theory and game theory, constructed a three-party evolutionary game model of the small and medium-sized energy enterprises (SMEE), the government, and the miner, considered the influence of the strategies made by the miner on the equilibrium strategy choices of other game subjects in the intelligent coal mine construction under the rational and irrational emotional states of the miner, and finally used MATLAB 2021 to simulate and analyze the impact of the evolution of the gaming system from 3 key elements: initial participation rate, construction costs, and government support. The study found the following: (1) The government will insist on actively promoting intelligent coal mine construction regardless of the miner’s emotional state. (2) Both moderate pessimism and optimism will, to a certain extent, give a positive impetus to the development of intelligent coal mine construction. (3) The miner’s emotions have a greater impact on SMEE than on the government’s strategic behavior. (4) Excessive construction costs or low government support will make SMEE may reduce the enthusiasm of SMEE to carry out an intelligent construction of coal mines. Accordingly, corresponding suggestions and countermeasures are put forward, aiming to provide targeted and practical ideas for the efficient construction of intelligent coal mines in China, thereby accelerating the green and low-carbon transformation of energy.

Under the context of non-dyadic human–machine interaction in intelligent coal mines, this study investigates the impact of different dyadic collaboration modes on Team Situation Awareness (TSA). Based on a simulated coal mine monitoring task, the experiment compares four working modes—Individual Operation, Supervised Operation, Cooperative Operation, and Divided-task Operation—across tasks of varying complexity. TSA was assessed using both objective (SAGAT) and subjective (SART) measures, alongside parallel evaluations of task performance and workload (NASA-TLX). The results demonstrate that, compared to Individual or Supervised Operation, both Cooperative and Divided-task Operation significantly enhance TSA and task performance. Cooperative Operation improves information integration and comprehension, while Divided-task Operation enhances response efficiency by enabling focused attention on role-specific demands. Moreover, dyadic collaboration reduces cognitive workload, with the task-sharing mode showing the lowest cognitive and temporal demands. The findings indicate that clear task structuring and real-time information exchange can alleviate cognitive bottlenecks and promote accurate environmental perception. Theoretically, this study extends the application of non-dyadic interaction theory to intelligent coal mine scenarios and empirically validates a “Collaboration Mode–TSA–Performance” model. Practically, it provides design implications for adaptive collaboration frameworks in high-risk, high-complexity industrial systems, highlighting the value of dynamic role allocation in optimizing cognitive resource utilization and enhancing operational safety.