Design framework and optimization of portable biomedical waste decomposition systems using ANN and MOPSO

Sep 30, 2026

Upload by Riley

Biomedical waste incineration requires accurate prediction of energy demand and efficiency because the waste composition is heterogeneous. This work combines material and energy balance calculations with DOE, ANOVA, artificial neural network (ANN) modeling, and multi-objective particle swarm optimization (MOPSO) to develop a portable decomposition-focused design and optimization framework. MOPSO is integrated to optimize incineration operating conditions, achieving near-perfect ANN prediction accuracy (R² > 0.9999). Results identify cellulose, tissue, and moisture as key drivers, with auxiliary LPG demand reduced and efficiency slightly improved under Pareto-optimal conditions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Biomedical waste decomposition background

Risks of unmanaged biomedical waste

Need for decentralized portable treatment

Limitations of existing systems

Integrated modeling and optimization framework

Material and energy balance with DOE and ANOVA

ANN surrogate modeling

MOPSO multi-objective optimization

Key findings and optimization results

[www. nature.com/scientificreports](www. nature.com/scientificreports) OPEN Design framework and optimization of portable biomedical waste decomposition systems using ANN and MOPSO Naresh N. Bhaiswar1,2, Sushant S. Satputaley3, Sandeep M. Kadam3,4, P. Dinesha5 & Sooraj Mohan5􀀍 Biomedical waste (BMW) incineration requires accurate prediction of energy demand and efficiency due to its heterogeneous composition. In this study, material and energy balance calculations were combined with design of experiments (DOE), analysis of variance (ANOVA), artificial neural network (ANN) modeling, and multi-objective particle swarm optimization (MOPSO). The novelty of the work presents the integration of metaheuristic optimization (MOPSO) into the biomedical waste incineration process. Results showed cellulose content as the most significant determinant of auxiliary energy requirement, with higher cellulose reducing LPG demand, while tissue and moisture exerted secondary but measurable effects. Efficiency ranged between 95.5 and 95.6%, with efficiency decreasing at higher moisture levels. The ANN model achieved near-perfect prediction accuracy (R² > 0.9999), enabling robust surrogate-based optimization. MOPSO analysis identified Pareto-optimal operating conditions where auxiliary energy demand reduced from 99.7 MJ/h to 97.2 MJ/h while efficiency improved from 95.52% to 95.60%. Under optimal waste composition identified by the ANNMOPSO hybrid, auxiliary LPG consumption reduced from 33.8 to 27.4 kg/h, indicating strong potential for energy savings within the studied domain. Keywords BMW, Energy optimization, Machine learning, Sustainable incineration, Climate action Safe management of biomedical waste (BMW) is increasingly recognised as a global challenge, directly linked to the United Nations Sustainable Development Goals (SDGs)1, particularly SDG 3 (Good Health and Well-being), SDG 6 (Clean Water and Sanitation), SDG 11 (Sustainable Cities and Communities), and SDG 12 (Responsible Consumption and Production) . Effective BMW treatment is critical to protecting human health, reducing infection risk, and ensuring environmental sustainability. The rapid expansion of healthcare facilities, rural healthcare outreach, population growth, and pandemic responses have significantly increased BMW generation worldwide2. Biomedical or clinical waste includes used needles and syringes, contaminated dressings, pharmaceuticals, body fluids, and laboratory disposables. Unmanaged BMW poses a severe threat to public health and the environment. Healthcare staff, waste handlers, and the community are vulnerable to infection from pathogens, while unregulated landfilling and open burning release toxic compounds, contaminate soil and water, and contribute to the spread of antibiotic-resistant bacteria3. The risks are even greater in low-resource and rural areas, where the absence of waste treatment infrastructure prevents safe management4. Centralised BMW treatment facilities are often scarce or unavailable in rural and remote regions, disaster zones, and temporary healthcare facilities such as mobile hospitals and field camps5. Conventional methods such as large-scale incinerators and autoclaves require stable infrastructure, electricity supply, and skilled personnel, which are typically lacking in these contexts6. As a result, there is a growing demand for decentralised, effective, and safe BMW treatment solutions that are adaptable to resource-limited conditions. Portable decomposition 1Post Graduate Teaching Departments (PGTD) of Electronics & Computer Science, Rashtrasant Tukadoji Maharaj Nagpur University, Nagpur 440033, Maharashtra, India. 2Department of Mechanical Engineering, Priyadarshini College of Engineering, Nagpur 440019, Maharashtra, India. 3Department of Mechanical Engineering, St. Vincent Pallotti College of Engineering & Technology, Nagpur, Maharashtra, India. 4Thermax Limited, Pune, Maharashtra, India. 5Department of Mechanical

FAQs

How does the study predict energy demand and efficiency for biomedical waste incineration?

It combines material and energy balance calculations with DOE, ANOVA, ANN modeling, and MOPSO-based multi-objective optimization to model and optimize performance based on waste composition.

Which waste components most influence auxiliary energy demand?

Cellulose is identified as the most significant determinant of auxiliary energy requirement, while tissue and moisture have secondary but measurable effects.

What optimization outcome does the ANN-MOPSO approach achieve?

The hybrid analysis finds Pareto-optimal operating conditions that reduce auxiliary energy demand and improve efficiency, with auxiliary LPG consumption decreasing under the optimal composition identified by the hybrid method.

Sep 30, 2026

Upload by Riley