Piezo-Actuated Enhanced Nucleate Boiling: from Saturated to Controlled Flash Regimes In Two-Phase Direct-To-Chip Cooling for AI Superchips and Data Centers
Amitabh Narain, Hardik Bhutka, Ranjeeth Naik, Nirgun Mohite, Yagel BelikoffAbstract
Two-phase direct-to-chip cooling is emerging as an important thermal management pathway for the rapidly increasing thermal design powers of modern AI superchips while maintaining data center energy efficiency. This paper presents a combined passive-active approach that transitions high-performance saturated nucleate boiling to a stabilized controlled flash-nucleate boiling regime using low-power piezoelectric actuation.
Experiments on microstructured copper cold plates with dielectric fluids establish baseline nucleate boiling performance in partial flow-boiling configurations typical of direct-to-chip flow loops. These results quantify cold-plate behavior and indicate that physics-guided modifications to both microstructures and flow-loop design can substantially increase heat-transfer coefficients and critical heat flux.
Activation of megahertz piezo actuators with low-frequency modulation near anti-resonance generates small micro-vibrations that modify nucleating bubble dynamics and trigger a rapid transition to controlled flash boiling. The transition alters boiling through microlayer heating, acoustic streaming, and a short-duration increase in interfacial mass transfer, producing transient heat extraction of 200-400 joules from the heated surface. Three-dimensional transient conduction simulations predict chip-level temperature reductions of about 15-20 degrees Celsius for low-thermal-inertia test vehicles and future chip implementations.
Baseline experiments show nucleate boiling heat transfer with critical heat flux near 50-60 watts per square centimeter. The proposed architecture integrates optimized microstructures, refined flow control, and piezo actuation to stabilize flash boiling, enabling lower junction temperatures, improved chip reliability, and more energy-efficient next-generation AI data centers.