Efficient biogas production significantly impacts greenhouse gas (GHG) emissions and carbon sequestration by reducing emissions and enhancing carbon storage. Nonetheless, the consistency and optimization of biogas production are hindered by fluctuations in key input variables, namely, pH, moisture content, organic loading rate (OLR), and temperature, which significantly impact the quality of agricultural waste biomass and biogas production. Any fluctuations in these variables can affect biogas productivity. This study aims to provide valuable optimization parameters for maximum biogas production using rice straw and cow dung as agricultural waste biomass for biogas input materials. Therefore, machine learning techniques such as multilayer perceptron feedforward neural networks with a particle swarm optimization (PSO) combination generate optimal values for each variable for maximum biogas production. This study uses three variants of the training function for neural networks, namely gradient descent with momentum and adaptive learning rate, gradient descent with momentum, and gradient descent with adaptive learning rate. The findings reveal that, under an optimum pH value of 6.0000, a humidity of 62.3176%, an OLR of 67.6823 kg.m³/day, and a temperature of 37.0482 °C, biogas production has the potential to increase to 2.91 m³/day with a high accuracy testing value of R² = 0.90. These methods in use accurately predict the optimal parameters, with a maximum deviation of 8.48% from experimentally derived values and mean square error (MSE) of 0.0051243. This study emphasizes the benefits of using multilayer perceptron feedforward neural networks and particle swarm optimization to optimize operational parameters and accurately predict biogas production.

The utilization of biogas contributes significantly to the reduction of greenhouse gas emissions and diminishes the dependency on traditional fossil fuels. Nonetheless, the consistency and optimization of electricity generation through a biogas generator are hindered by fluctuations in key input variables, namely biogas input pressure, methane (CH ₄ ) content, and the flow rate of biogas. Hence, the optimization of these influential input parameters is crucial for enhancing the power output of the electricity generator. The primary objective of this study was to refine the input parameters to maximize the electrical power output generated by the biogas electricity generator. The data collected from the monitoring system were analyzed using an artificial intelligence (AI) model, specifically an Artificial Neural Network (ANN). This study introduces an enhanced ANN model that incorporates an Adaptive Backpropagation Algorithm to ensure best practices in modelling optimization. Furthermore, the utilization of Particle Swarm Optimization (PSO) aids in determining the optimal values for each variable affecting the output power of the electric generator. The configuration of the multilayer perceptron model, combined with the Adaptive Backpropagation Algorithm and PSO, establishes the fundamental framework for the proposed advancements. The findings reveal that under the optimal conditions of biogas input pressure at 34.36 kPa, CH4 content at 90%, and biogas flow rate at 0.22 l/s, the output power of the electric generator can achieve levels of up to 1.42 kW, with a notably high accuracy testing value of 0.98513. This study highlights the potential benefits of employing adaptive neural network models and optimization methodologies to determine the appropriate operational parameters and accurately predict the output power of a biogas-fueled electric generator.

Biogas is a renewable energy potential to be developed in Indonesia. It is based on the increase in the number of household-scale biogas reactor. But the number of biogas reactors currently installed is still not equipped with biogas purification system integrated with the biogas storage tank system. Storage of purified biogas on the tube is required to extend the range of the use of biogas in some areas that have been using biogas as an alternative energy source. Storage tank systems require control systems in a storage tube that could biogas storage mechanism accordance with the maximum capacity of the tube used. This system uses a sensor components MPX5700AP and Arduino microcontroller, LCD display to display pressure readings, and solenoid valve as an actuator. The working principle of this pressure control system that is used to read the sensor value changes of pressure in the biogas storage tank A and B to be sent to the Arduino and a subsequently processed data accordance specified set point. Charging conducted alternately pressurized biogas through a method ON / OFF Valve Selenoid 1,2,3 and 4 on each biogas storage tanks. At the testing that was done we got the result response of pressure control system against time on pressure sensors P2 and P3 value rise time (tr) = 15 s, settling time (ts) = 12 s, whereas for pressure sensors P3 obtained values rise time ( tr) = 14 s, settling time (ts) = 12 s. The test results are static characteristics sensor hysteresis error of 0.00078% and 0.90%.

Biogas, an eco-friendly energy source, significantly reduces greenhouse gas emissions by converting organic waste or biomass into methane. However, the quality of biogas, primarily determined by methane content and pressure variables, directly impacts its efficiency and safety. This study, which aims to design a pressure control system and monitor methane gas levels in a biogas reactor using a PID Controller with Particle Swarm Optimization (PSO), provides crucial insights into improving biogas production efficiency and safety. Tests were conducted on a fixed dome-type biogas reactor in the East Java region, Indonesia. The PSO-based PID tuning was compared with two other PID tuning methods: Trial-error and Ziegler-Nichols (ZN). Data on pressure values and biogas flow rates from the biogas reactor were collected, and system modeling was carried out to produce a system transfer function. The PSO algorithm was developed to optimize PID control parameters. The results of this research demonstrate that the PID tuning method using PSO produces a stable state error value of 1.40%, rise time of 0.09 s, settling time of 2.1 s, maximum overshoot of 0.986404, and ITAE of 0.0010801. The implementation of PID-PSO can significantly enhance PID control performance in rise time, settling time, maximum overshoot, and ITAE compared to Trial-Error and ZN, while the stable state error value in PID-PSO tuning is higher than tuning using Trial-Error and ZN.

An integral aspect of sustainable agriculture involves the implementation of a meticulously planned waste management infrastructure. One strategy to achieve this objective is the utilization of agricultural waste, specifically in the form of biomass, to generate sustainable energy such as biogas. This study aims to provide valuable prediction model for biogas production with many variables which is influenced. The study identifies four variables, namely pH, moisture content, Organic Loading Rate (OLR) and temperature which significantly impact on the biogas production, especially in Indonesia. Any fluctuations in these variables can affect biogas productivity. Therefore, machine learning techniques such as adaptive backpropagation neural network is used to modeling for predition of biogas production. The configuration of the multilayer perceptron model, combined with the Backpropagation Algorithm, establishes the fundamental framework for the proposed advancements. This study explores three different types of training algorithms in the backpropagation neural network, specifically Adaptive Learning Rate, Levenberg-Marquardt, and Resilient Backpropagation. The Resilient Backpropagation approach exhibited exceptional effectiveness, as evidenced by a correlation coefficient of 0.9411 for training and 0.90423 for testing. The best results obtained for Mean Squared Error (MSE) and Mean Absolute Error (MAE) were 0.0038 and 0.0316, respectively. The Standard Deviation was computed to be 0.0615. This study highlights the potential benefits of employing Resilient Backpropagation Neural Network alghoritm to determine the appropriate operational parameters and accurately predict the biogas production