Aiming at the problems of low recovery rate of tailings resources and poor adaptability to dynamic working conditions, this paper proposes a reinforcement learning (RL) optimization method driven by Industrial Internet of Things (IIoT). By deploying a multi-source sensor network for real-time sensing of ore grade, flow rate and equipment status, a digital twin collaborative framework is constructed; a multi-intelligent body depth deterministic policy gradient (MADDPG) algorithm is innovatively designed to realize dynamic decision-making for agent addition and equipment control. Based on the open data set validation, the system recovery rate is increased to 92.3%, and the energy consumption per ton of ore is reduced by 18.7%, which significantly optimizes the dynamic resource recovery efficiency. The method provides key technical support for the green transformation of the mining industry.
Hudson-EdwardsKAKempDTorres-CruzLA, et al.Tailings storage facilities, failures and disaster risk. Nat Rev Earth Environ2024; 5: 612–630.
2.
BendaouiaAQassimiSBoussettaA, et al.Hybrid features extraction for the online mineral grades determination in the flotation froth using Deep Learning. Eng Appl Artif Intell2024; 129: 107680.
3.
InghelsDDullaertWAghezzafEH, et al.Towards optimal trade-offs between material and energy recovery for green waste. Waste Manag2019; 93: 100–111.
4.
BurchellJLe RouxJDCraigIK. Nonlinear model predictive control for improved water recovery and throughput stability for tailings reprocessing. Control Eng Pract2023; 131: 105385.
5.
ZvarivadzaTOnifadeMDayo-OluponaO, et al.On the impact of Industrial Internet of Things (IIoT)-mining sector perspectives. Int J Min Reclamat Environ2024; 38: 771–809.
6.
OforiPO'BrienGFirthB, et al.The use of tri-block copolymer surfactants as promoters to improve flotation recovery of poorly floating coal components. Int J Coal Prep Util2012; 32: 103–119.
7.
KimTYGouldTBennetS, et al.The role of critical minerals in clean energy transitions. International Energy Agency, 2021, pp. 70–71.
8.
NcongwaneMSBroadhurstJPetersenJ. Assessment of the potential carbon footprint of engineered processes for the mineral carbonation of PGM tailings. Int J Greenh Gas Control2018; 77: 70–81.
9.
BrooksLGaustadGGesingA, et al.Ferrous and non-ferrous recycling: challenges and potential technology solutions. Waste Manag2019; 85: 519–528.
10.
TsengMLWongWPSohKL. An overview of the substance of resource, conservation and recycling. Resour Conserv Recycl2018; 136: 367–375.
11.
HigashitaniKMakinoHMatsusakaS. Powder technology handbook. Chemical Rubber Company Press, 2019, pp. 45–52.
12.
KhajehzadehNHaavistoOKoresaarL. On-stream mineral identification of tailing slurries of an iron ore concentrator using data fusion of LIBS, reflectance spectroscopy and XRF measurement techniques. Miner Eng2017; 113: 83–94.
13.
MuñizRNuñoFDíazJ, et al.Real-time monitoring solution with vibration analysis for industry 4.0 ventilation systems. J Supercomput2023; 79: 6203–6227.
14.
KanellopoulosDSharmaVK. Dynamic load balancing techniques in the IoT: a review. Symmetry2022; 14: 2554.
15.
NazirF. Enhancing big data processing with a hybrid cloud-edge framework: addressing latency, privacy, and scalability challenges in real-time analytics. IJASSA2022; 1: 16–22.
16.
LiangFYuWLiuX, et al.Toward deep Q-network-based resource allocation in industrial Internet of Things. IEEE Internet Things J2021; 9: 9138–9150.
17.
WangPShenYLiR, et al.Multisensor information-based adaptive control method for cutting head speed of roadheader. Proc IME C J Mech Eng Sci2021; 235: 1941–1955.
18.
SuttonRSBartoAG. Reinforcement learning: an introduction. MIT press Cambridge, 1998.
19.
MarinescuADusparicIClarkeS. Prediction-based multi-agent reinforcement learning in inherently non-stationary environments. ACM Trans Autonom Adapt Syst2017; 12: 1–23.
20.
RaeiszadehMEbrahimzadehAGlithoRH, et al.Real-time adaptive anomaly detection in industrial IoT environments. IEEE Trans Netw Serv Manage2024; 21(2): 1254–1272.
21.
LoweRWuYITamarA, et al.Multi-agent actor-critic for mixed cooperative-competitive environments. Adv Neural Inf Process Syst2017; 30: 1–15.
22.
SaxenaDSinghAK. A self-healing and fault-tolerant cloud-based digital twin processing management model. IEEE Trans Ind Inf2025; 21(3): 1980–1992.
23.
HuangBDiYJinC, et al.Review of data-driven prognostics and health management techniques: lessions learned from PHM data challenge competitions. MFPT2017; 1: 1–17.
24.
SummariesMC. Mineral commodity summaries. US Geological Survey, 2021, p. 200.
25.
PeeLGPanSL. Climate-intelligent cities and resilient urbanisation: challenges and opportunities for information research. Int J Inf Manag2022; 63: 102446.
26.
SoniAKMuthrejaILYerpudeRR. Principles and practice in mining engineering. Chemical Rubber Company Press, 2023, p. 480.
27.
BouffardSC. Benefits of process control systems in mineral processing grinding circuits. Miner Eng2015; 79: 139–142.
28.
HafizAMHassaballahMAlqahtaniA, et al.Reinforcement learning with an ensemble of binary action deep Q-networks. Comput Syst Sci Eng2023; 46(3): 2587–2602.
ShaerIShamiA. WrapperRL: reinforcement learning agent for feature selection in high-dimensional industrial data. IEEE Access2024; 12: 12345–12360.
31.
VasconcelosWWKollingbaumMJNormanTJ. Normative conflict resolution in multi-agent systems. Auton Agent Multi Agent Syst2009; 19: 124–152.
32.
LuMZhaoY. Mineral resource extraction and environmental sustainability for green recovery. Resour Policy2024; 90: 104616.
33.
LiRZhouZChenX, et al.Resource price-aware offloading for edge-cloud collaboration: a two-timescale online control approach. IEEE Trans Cloud Comput2019; 10: 648–661.
34.
OrmacheaOVillazónATercerosI. Analysis of mining ore concentrates with a low cost portable LIBS system. Investigación & Desarrollo2018; 18: 81–90.
35.
YangHHuangCWangL, et al.An improved encoder–decoder network for ore image segmentation. IEEE Sens J2020; 21: 11469–11475.
36.
ZhangWYangDWuW, et al.Optimizing federated learning in distributed industrial IoT: a multi-agent approach. IEEE J Sel Area Commun2021; 39: 3688–3703.
