The increasing frequency of health crises, pandemics, and constraints on medical equipment supply has highlighted the growing need to design robust and resilient healthcare networks. Under such conditions, decisions concerning the location of healthcare centers, patient allocation, capacity planning, and medical equipment procurement under uncertainty have become major challenges for healthcare systems. This study develops a multi-objective mixed-integer linear programming model for the robust location–allocation of temporary healthcare centers with service-oriented resilience considerations. The proposed model integrates facility location, service allocation, capacity planning, and medical equipment procurement decisions under demand uncertainty and medical equipment supply constraints. To address uncertainty, a robust optimization approach based on the Mulvey framework is employed, which accounts for both expected cost minimization and the stability of system performance across different scenarios. In addition, a service-shortage control constraint and a shortage penalty are incorporated to strengthen the service-oriented resilience of the network.The proposed model includes two objective functions: minimizing the total robust cost and minimizing the patient accessibility index. The model was solved using the ε-constraint method in GAMS with the HiGHS solver. For computational evaluation, in addition to an illustrative example, 15 test instances in three sizes—small, medium, and large—were examined. The proposed model was also compared with a deterministic expected-value model and a scenario-based model without the robustness term. The decisions generated by the three models were evaluated through a total of 750 out-of-sample assessments. The Pareto-front analysis showed that, at the compromise solution, a 7.44% increase in robust cost improved the accessibility index by 18.80%. Moreover, the out-of-sample results indicated that, compared with the deterministic model, the proposed model reduced the mean and worst observed costs by 56.12% and 83.90%, respectively, while maintaining full demand coverage, compared with 96.93% coverage under the deterministic model. The findings indicate that scenario-based planning and robustness control can strengthen the service-oriented resilience of healthcare networks by reducing service shortages and maintaining demand coverage.