Despite the pressure of carbon emissions and clean energy, coal remains the economic backbone of many developing countries due to its abundant resources and widespread distribution. The stable supply of coal is also vital for the global economy and remains irreplaceable in the future global energy structure. China has been a major contributor to annual coal output, accounting for nearly 50% worldwide since 2014. However, despite implementing intelligent coal mining technology, China’s coal mining industry still employs over 1.5 million underground miners, posing significant safety risks associated with underground mining operations. Therefore, the introduction of coal mining robots in underground mines is an urgently needed scientific and technological solution for upgrading China’s and even the world’s coal energy industry. The working face needs a shearer, hydraulic support, a scraper conveyor, and other equipment for coordination. The deep integration of intelligent technology with factors such as “humans, machines, the environment, and management” in the workplace is the core content of intelligent coal mines. This paper puts forward an advanced framework for robot technology systems in coal mining, including single robots, robotized equipment, robot crowds, and unmanned systems. The framework clarifies the common key technologies of coal mining robot research and development and the cross-integration with new technologies such as 5G, the industrial internet, big data, artificial intelligence, and digital twins to improve the autonomous and intelligent application of coal mining robots. By establishing a scientific and complete standard system for coal mining robots, we aim to achieve the customized research and development and standardized production of various types of robot. A specific analysis is conducted on the research progress of common key technologies such as the explosion-proof design, mechanical system innovation, power drive, intelligent sensing, positioning and navigation, and underground communication of coal mining robots. The current research and application status of various types of coal mining robots in China are summarized. A new direction for future coal mining robot research and development is proposed. Robotic mining systems should be promoted to enhance the overall intelligence level and efficiency of mining equipment. To develop human–machine environment-integrated robots to improve the autonomy and collaboration level of coal mining robots, the digital twinning of the entire mine robot system should be accelerated; the normalized operation level of coal mine robots should be improved; research on coal mining robots, shield support robots, and transportation robots should be performed; intelligence should be achieved in fully mechanized mining faces; and equipment shield support for fully mechanized mining faces should be provided. The practical process of implementing coal mining robotization is summarized in this paper, and the technical and engineering feasibility of the coal mining machine population is verified.

Fully mechanized mining face production involves complex geological conditions; mining pressure; gas, water, fire and other mining environments. The working face needs a shearer, hydraulic support, a scraper conveyor and other equipment for coordination. The deep integration of intelligent technology with factors such as "humans, machines, the environment, and management" in the workplace is the core content of intelligent coal mines. This paper puts forward an advanced framework for coal mining robot technology systems, including single robots, robotized equipment, robot clusters and unmanned systems. The framework clarifies the common key technologies of coal mining robot research and development and cross-integration with new technologies such as 5G, the industrial internet, big data, artificial intelligence, and digital twins to improve the autonomous and intelligent application of coal mining robots. By establishing a scientific and complete standard system for coal mining robots, we aim to achieve customized research and development and standardized production of various types of robots. A specific analysis was conducted on the research progress of common key technologies such as explosion-proof design, mechanical system innovation, power drive, intelligent sensing, positioning and navigation, and underground communication of coal mining robots. The current research and application status of various types of coal mining robots in China are summarized. A new direction for future coal mine robot research and development is proposed. Moreover, robotic mining systems should be promoted to enhance the overall intelligence level and mining efficiency of mining equipment. To develop human‒machine environment-integrated robots to improve the autonomy and collaboration level of coal mining robots. The digital twinning of the entire mine robot system should be accelerated, the normalized operation level of coal mine robots should be improved, research on coal mining robots, support robots, and transportation robots should be carried out, intelligence should be achieved in fully mechanized mining faces, and equipment support for fewer and unmanned fully mechanized mining faces should be provided. The practical process of implementing coal mining robotization has been summarized, and the technical and engineering feasibility of the coal mining machine population has been verified.

High-speed and conventional laser cladding technologies were used to prepare Fe-based alloy cladding layers on the surface of 45 steel, compare and analyze the microstructure, microhardness, and phase structure of the two cladding layers, and study and analyze the morphology of the molten pool under the two cladding technologies, as well as the mechanism of evolution of the microstructure of the molten pool during the solidification process. The results show that, compared with the conventional laser melting coating, the grain size of the high-speed laser melting coating is finer, and the cooling rate at the top for conventional laser melting is 5.72 × 10³ K/s, and the cooling rate for high-speed laser melting is 3.53 × 10⁵ K/s. The microhardness of the high-speed laser melting coating has been significantly improved, and the solidification rates at the top for the two types of laser melting are the highest, namely 5.84 mm/s and 24.7 mm/s; the molten pool in conventional laser melting is usually larger and deeper, presenting a wide and deep shape, whereas the high-speed laser molten pool is usually shallower and narrower, with a flatter shape, presenting a comet trail, and the fast-cooling and fast-heating effects of high-speed laser melting are more significant.

Accurate measurement of dynamic coal gangue size directly affects the grasping strategy of the coal gangue sorting robot, but there is still a lack of fast and effective measurement methods. To target this problem, a dynamic coal gangue size measurement method combining image coordinate-pixel calibration and Canny edge detection is proposed. Firstly, a dynamic coal gangue image acquisition system is built, and the actual size of the coal gangue is obtained by three-dimensional scanning reconstruction as a comparison benchmark. Then, through image coordinate measurement, pixel benchmark setting, and coordinate-actual size conversion model construction, combined with gray-scale conversion, Gaussian filtering, and Canny edge detection instead of traditional binarization processing, the accurate extraction of coal gangue image contour is realized. On this basis, non-maximum suppression, double threshold lag selection and morphological operation are introduced to optimize the edge detection effect, and the shadow removal technology is combined to further improve the measurement accuracy. Finally, dynamic measurement experiments are carried out under seven different working conditions to compare the measurement accuracy and stability before and after optimization. The results show that the average measurement accuracy of the optimized method is more than 98%, the measurement error is less than 1.2 mm, and the single frame processing time is about 6 ms, which meets the real-time sorting requirements. This research provides an effective technical scheme for the size measurement of dynamic irregular objects.