In the context of accelerated transformation and upgrading of
the non-ferrous metal industry, lead and zinc smelting, as a
typical high-energy consumption and high-pollution process
industry, is experiencing a subversive change from “experience-driven” to
“data intelligence”. The traditional smelting mode relies on manual
experience to adjust process parameters, facing high energy
consumption (comprehensive energy consumption of >1800kWh
per ton of zinc), large fluctuations in the metal recovery rate
(lead recovery rate of 88%-92%), and excessive emissions
(SO₂ concentration fluctuations of ±15%) and other pain points,
resulting in direct economic losses of more than 2.5 billion U.S.
dollars per year. With the deep integration of artificial intelligence
technology and smelting process, the new generation of intelligent
control system has improved process stability to 99.7%, reduced
energy consumption by 18%, and cut heavy metal emissions
by 90% through the technology closed loop of real-time
perception-autonomous decision-making-dynamic
optimization, which has pushed lead and zinc smelting into
a new era of “accurate and intelligent smelting”.
First, the traditional manual control of
the four major dilemmas
Lagging regulation of process parameters
Relying on manual inspection (2 hours/times) and offline
assay (delayed 4-6 hours), the lag rate of key parameters
(melt temperature, oxygen potential, slag type) adjustment
reaches 78%.
Experience inheritance barrier
Operators need 5-8 years training cycle, the lead yield
fluctuation controlled by different shifts is up to 3.5
percentage points, the talent disconnection leads to
the decline of process stability.
Multi-variable coupling out of control
The non-linear interaction of 20+ parameters, such as sinter
block composition, wind-oxygen ratio, coke rate, etc., makes
it difficult to realize global optimization manually, and
triggers 3-5 major fluctuations in working conditions every year.
Passive response to environmental control
Flue gas SO₂ concentration relies on end-to-end management,
the disposal delay of sudden emission peak exceeding the
standard is more than 30 minutes, and the environmental
protection fine accounts for 12% of the production cost.
Second, the technological breakthrough: AI
control system of three-layer architecture innovation
1. All-dimensional perception network
Real-time monitoring of melt status: 1400+ intelligent sensors are
deployed in sintering machine, blast furnace and electrolyzer to
collect 40 types of parameters such as temperature (accuracy ±0.5℃),
pressure, composition (XRF online analyzer, 0.1s/time), etc.
Multi-source data fusion engine: integrating DCS, MES, LIMS system
data flow, building an industrial Internet of Things platform that
processes 200,000 data points per second.
2. Intelligent decision-making core
Digital twin dynamic modeling: build a 3D smelting process
simulation system based on Computational Fluid Dynamics
(CFD) and Discrete Element Method (DEM), with a prediction
accuracy of 95%.
Multi-objective optimization algorithm: Deep Reinforcement
Learning (DRL) is used to balance the objectives of metal
recovery rate, energy consumption, and emissions, and
300+ sets of optimization parameter schemes are
automatically generated every day.
3. Autonomous execution system
Intelligent valve group response time <50ms, realizing
precise control of blast air volume (adjustment precision
0.1m³/min) and oxygen concentration (±0.3%).
Adaptive control system can re-optimize the dosage ratio
within 10 seconds when the composition of raw materials
fluctuates, which guarantees the stability of the process.
Application Scenario: Intelligent Reconstruction of the
Whole Smelting Process
1. Intelligent control of sintering process
Recognize the porosity of sintered blocks through machine
vision (detection speed of 200 blocks/minute), and
dynamically adjust the thickness of the material layer
and ignition temperature.
AI model predicts the sintering end time (error <2
minutes), which increases the sintering capacity by
15% and reduces the powder return rate by 40%.
2. Blast furnace melting optimization
Real-time monitoring of oxygen potential distribution
in the furnace, intelligent adjustment of oxygen-rich
concentration (27%-33%), stabilizing the lead yield
above 94.5%.
Melt temperature control accuracy is improved from
±25℃ to ±5℃, and coke consumption is reduced by 12%.
3. Electrolytic refining upgrade
Based on the current efficiency digital twin model,
dynamically optimize the pole pitch (adjustment
precision 0.1mm) and electrolyte composition (Zn²+
concentration control ±2g/L).
Uniformity of cathode zinc thickness increased to
98%, DC power consumption reduced to below 2900kWh/t.
4. Environmental protection control forward
Predictive emission control system warns of SO₂
concentration abnormality 10 minutes in advance,
and adjusts the operating parameters of desulfurization
tower in a linked manner.
Arsenic, cadmium and other heavy metals emissions
concentration fluctuations compressed to ± 5%, the
annual emission reduction of 800 tons of hazardous wastes
IV. Benefit verification: value leap of
intelligent manufacturing
Economic breakthrough: Reduction of zinc processing costs by
230 yuan per ton, annual output of 300,000 tons of smelters
with an annual profit increase of more than 60 million yuan.
Quality leap: 0# zinc grade rate increased from 88% to 99%,
meeting GB/T 470-2022 high-end zinc ingot standard.
Energy consumption innovation: comprehensive energy
consumption dropped to 1500kWh/t zinc, reducing
standard coal consumption by 42,000 tons per year.
Safety upgrading: major process accidents decreased
to 0.05/year, saving 18% on insurance costs.
Green transformation: sulfur dioxide emission concentration
stabilized at <80mg/m³, heavy metal removal rate of
wastewater exceeded 99.9%
V. Future picture: AI-driven new ecology
of smelting industry
Autonomous evolution system
Construct AI model with migration learning capability, and
complete independent development of smelting process for
new ore types within 3 months.
Cross-process collaborative optimization
Open up the data chain of the whole process of sintering-smelting-refining
to maximize the efficiency of global resources.
Quantum Computing Empowerment
Applying quantum neural network to process trillions of parameter
combinations, the speed of solving complex smelting optimization
problems is increased by 1,000 times.
Industrial meta-universe fusion
Create virtual smelting digital twins to support process engineers
in immersive interactive optimization.
Conclusion
The paradigm shift from manual to AI not only solves the century-long
control challenges in the lead and zinc smelting industry, but also
redefines the competitiveness standards of the non-ferrous metals
industry. This change has achieved a synergistic leap in quality,
efficiency, and environmental protection by digitizing process knowledge,
intelligentizing the decision-making process, and automating the
execution system. With the deep penetration of 5G, edge computing,
knowledge map and other technologies, the AI control system will
continue to evolve and push lead and zinc smelting towards the ultimate
goal of “zero human intervention, zero quality defects and zero pollution
emission”, providing core support for the construction of the global green
metal supply chain.