Multi-objective Particle Swarm Optimization Research Articles

Variable-Length Multiobjective Social Class Optimization for Trust-Aware Data Gathering in Wireless Sensor Networks

Data gathering in wireless sensor networks (WSNs) is vital for deploying and enabling WSNs with the Internet of Things (IoTs). In various applications, the network is deployed in a large-scale area, which affects the efficiency of the data collection, and the network is subject to multiple attacks that impact the reliability of the collected data. Hence, data collection should consider trust in sources and routing nodes. This makes trust an additional optimization objective of the data gathering in addition to energy consumption, traveling time, and cost. Joint optimization of the goals requires conducting multiobjective optimization. This article proposes a modified social class multiobjective particle swarm optimization (SC-MOPSO) method. The modified SC-MOPSO method is featured by application-dependent operators named interclass operators. In addition, it includes solution generation, adding and deleting rendezvous points, and moving to the upper and lower class. Considering that SC-MOPSO provides a set of nondominated solutions as a Pareto front, we employed one of the multicriteria decision-making (MCDM) methods, i.e., simple additive sum (SAW), for selecting one of the solutions from the Pareto front. The results show that both SC-MOPSO and SAW are superior in terms of domination. The set coverage of SC-MOPSO is 0.06 dominant over NSGA-II compared with only a mastery of 0.04 of NSGA-II over SC-MOPSO. At the same time, it showed competitive performance with NSGA-III.

Bread staling prediction with a multiobjective particle swarm optimization-based bread constitutive modeling method.

Aiming at the complex and cumbersome problems of current bread staling detection technology, a food constitutive modeling method based on the multiobjective particle swarm optimization (MOPSO) was proposed, which can quickly and efficiently identify the creep test parameters for bread, and predict the viscoelastic parameters of bread staling using the analyzed viscoelastic parameters, resulting in convenient and efficient detection of bread staling. Firstly, airflow-laser detection technology was used to carry out rapid, efficient, and non-destructive bread rheological tests to obtain bread creep test data. The MOPSO based on the Pareto set was then used to identify the generalized Kelvin model, and the discrimination accuracy was evaluated by using the inversion results established by the viscoelastic parameters, which resulted in efficient discrimination of creep test data of starch-based products represented by bread. Finally, using extreme learning machine regression (ELM), a prediction model between the analysis results and the moisture content of bread staling was established, and the prediction effect of the analysis results on bread staling was verified. The experimental results show that, when compared to finite element analysis (FEA) and non-linear regression (NLR) to identify creep parameters, the MOPSO overcomes the shortcomings of easy falling into the local optimal solution, is easy to implement, has strong global search ability, and is suitable for the analysis of high-dimensional viscoelastic models of complex foods. The correlation coefficient (R) of the prediction set established by the 12-membered viscoelastic parameters in the prediction model established by multi-element viscoelastic parameters and bread moisture content was 0.847, and the root mean square error (RMSE) was 0.021. This demonstrated that, when combined with MOPSO, airflow-laser detection technology could effectively identify the viscoelastic parameters of bread and establish a method suitable for monitoring bread staling in industrial production. The results of this study provide a reference for the identification of viscoelastic parameters of complex foods and to detect bread staling quickly and efficiently.

A MOPSO-based spectrum modification method for shallow surface electromagnetic detection transmitting scheme

In shallow surface electromagnetic detection, the conventional transmitting schemes, such as square wave and pseudo-random binary sequence (PRBS) wave schemes, have fixed spectrum configurations, which limits the detection efficiency and accuracy for specific targets. To solve this problem, a novel transmitting scheme based on multi-objective particle swarm optimization (MOPSO) algorithm is proposed. This method allows flexible spectrum modification by optimizing the switching time sequence of the transmitting current with multiple objectives required for detection. The principle of the MOPSO-based spectrum modification method is analyzed. Combined with detection requirements, two optimization schemes are provided with the objectives of matching the desired spectrum and maximizing the transmission energy of detection frequencies. Finally, comparative simulations and laboratory experiments are carried out to verify the feasibility of the novel transmitting scheme. The proposed scheme offers more reasonable configuration of main frequency distribution and spectral energy allocation, which contributes to improving detection efficiency and accuracy.

Reliability Enhancement on Distribution System Using Modified Multi-Objective Particle Swarm Optimization Technique

This research paper introduces an innovative approach for optimizing the placement of fault indicators (FIs) within electric distribution systems. The primary focus is on addressing how the presence of existing protection and control devices affects the time it takes to restore service to customers in the event of a fault. Unlike conventional FI placement methods, this extended approach considers the uncertainties associated with automatic switching and introduces a novel technical objective function known as the Customers' Average Restoration Time Index (CARTI). To tackle the complex task of multi-objective optimization, a solution approach has been devised, with the goal of simultaneously minimizing both economic and technical objectives. This methodology harnesses a Multi-Objective Particle Swarm Optimization (MOPSO) algorithm and incorporates a Modified Particle Swarm Optimization technique to select the most suitable solution from the set of Pareto optimal solutions generated. The proposed method's effectiveness is demonstrated through its application in two scenarios: firstly, in the context of bus number four within the Roy Billinton test system (RBTS4), and secondly, in a practical real-life distribution network. The study assesses technical objectives, specifically the System Average Interruption Duration Index (SAIDI) and CARTI, providing insights into the method's practical utility and its capacity to enhance FI placement for improved distribution system performance.

The optimisation of the location of front distribution centre: A spatio-temporal joint perspective

Front Distribution Centre (FDC) is a new terminal warehouse which is closer to customers, with its location selection being crucial for e-commerce and customer time satisfaction. We introduce in this paper a joint distribution function of demand based on time and space, which constructs two spatio-time models: spatio-time clustering model and spatio-time optimisation model. A staged clustering algorithm is designed to obtain the candidate FDCs, and an intelligent algorithm based on NSGA-Ⅱ (Non-dominated Sorting Genetic Algorithm II) is applied to determine the final FDCs, in which the location selection problem is formulated as a bi-objective programming model to minimise total costs and maximise customer time satisfaction. Our results indicate that the model considering spatio-temporal joint attribute of demand performs better than the traditional spatial model. Furthermore, when compared with the k-means clustering algorithm, Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) and its improved algorithm Multi-Objective Evolutionary Algorithm based on the Adaptive Neighborhood Adjustment strategy (MOEA/D-ANA), Multi-Objective Particle Swarm Optimisation” (MOPSO) and its enhancing algorithm Competitive Multi-Objective Particle Swarm Optimiser (CMOPSO), the solving method based on staged clustering and NSGA-II absolutely performs more stable and can get a greater number of pareto-optimal solutions with higher qualities. Especially when compared with K-means clustering algorithms, it can reduce total costs by up to 38.84% and improve customer time satisfaction by up to 36.22%.

Dynamic cyclic kitting part-feeding scheduling for mixed-model assembly line by a hybrid quantum-behaved particle swarm optimization

PurposeThe purpose of this paper is to cut down energy consumption and eliminate production waste on mixed-model assembly lines. Therefore, a supermarket integrated dynamic cyclic kitting system with the application of electric vehicles (EVs) is introduced. The system resorts to just-in-time (JIT) and segmented sub-line assignment strategies, with the objectives of minimizing line-side inventory and energy consumption.Design/methodology/approachHybrid opposition-based learning and variable neighborhood search (HOVMQPSO), a multi-objective meta-heuristics algorithm based on quantum particle swarm optimization is proposed, which hybridizes opposition-based learning methodology as well as a variable neighborhood search mechanism. Such algorithm extends the search space and is capable of obtaining more high-quality solutions.FindingsComputational experiments demonstrated the outstanding performance of HOVQMPSO in solving the proposed part-feeding problem over the two benchmark algorithms non-dominated sorting genetic algorithm-II and quantum-behaved multi-objective particle swarm optimization. Additionally, using modified real-life assembly data, case studies are carried out, which imply HOVQMPSO of having good stability and great competitiveness in scheduling problems.Research limitations/implicationsThe feeding problem is based on static settings in a stable manufacturing system with determined material requirements, without considering the occurrence of uncertain incidents. Current study contributes to assembly line feeding with EV assignment and could be modified to allow cooperation between EVs.Originality/valueThe dynamic cyclic kitting problem with sub-line assignment applying EVs and supermarkets is solved by an innovative HOVMQPSO, providing both novel part-feeding strategy and effective intelligent algorithm for industrial engineering.

A Two-Level Fuzzy Multi-Objective Design of ATO Driving Commands for Energy-Efficient Operation of Metropolitan Railway Lines

Policies for reducing CO2 and other GHG emissions have motivated an increase in electrification in metropolitan areas, mandating reductions in energy consumption. Metro systems are keystone contributors to the sustainability of cities; they can reduce the energy consumption of cities through the use of the economic driving parameters in their onboard automatic train operation systems (ATO) and through the strategic design of efficient timetables. This paper proposes a two-level optimization method to design efficient, comfortable, and robust driving commands to be programmed in all the interstations of a metro line. This method aims to increase the sustainability of metro operations by producing efficient timetables with economic driving for each interstation while considering comfort restrictions and train mass uncertainty. First, in the eco-driving level, an optimal Pareto front between every pair of successive stations is obtained using a multi-objective particle swarm optimization algorithm with fuzzy parameters (F-MOPSO). This front contains optimized speed profiles for different running times considering train mass variations. The global problem is stated as a multi-objective combinatorial problem, and a fuzzy greedy randomized adaptive search procedure (F-GRASP) is used to perform an intelligent search for the optimal timetables. Thus, a global front of interstation driving commands is computed for the whole line, showing the minimum energy consumption for different travel times. This method is analyzed in a case study with real data from a Spanish metro line. The results are compared with the minimum running time timetable and a typical timetable design procedure. The proposed algorithms achieve a 24% reduction in energy consumption in comparison to the fastest driving commands timetable, representing a 4% increase in energy savings over the uniform timetable design.

Incorporating the best sizing and a new energy management approach into the fuel cell hybrid electric vehicle design

Under the banner of sustainable transportation, fuel cell hybrid electric vehicles (FC-HEVs) have become a matter of fascination in today's ever-growing need to save fossil fuels and reduce greenhouse gas emissions, addressing the 3Es challenges (efficiency, economy, and environment). However, one of the most pressing issues at the moment is determining how to incorporate the optimal sizing and energy management strategy (EMS) into FC-HEVs. In this regard, this article presents an integrated approach for optimal sizing as well as a new energy strategy for the design of FC-HEVs. To minimize the decision variables, including operating cost, fuel consumption, and component weight, an in-house optimization MATLAB code with a Multi-Objective Particle Swarm Optimization algorithm was developed. Four energy cases were tested under ARTEMIS and NEDC driving cycles for simulation, and their influence on the key decision variables was also investigated. The results show that using a battery pack with a supercapacitor reduces fuel consumption by 19% and 30.3% in both driving cycles, while decreasing the maximum output power of the fuel cell. It should be noted that hybrid energy sources have the potential to improve vehicle performance.

Carbon emission allowance allocation based on a bi-level multi-objective model in maritime shipping

To mitigate carbon emissions from maritime shipping, this study investigates the strategies and performance of allocating carbon emission allowances (CEAs) with the cap-and-trade mechanism among shipping companies. Using a bi-level model solved by the multi-objective particle swarm optimization algorithm based on Pareto solution set, the interactions between decisions of the government and shipping companies are well characterized. The results of the benchmark scenario indicate that all shipping companies’ optimal carbon emissions decrease annually during the planning period, and a larger company usually exhibits a better emission reduction performance. However, economic benefits of shipping companies and the society display an annually declining trend due to additional carbon emission reduction costs. The sensitivity analysis demonstrates that the decreasing carbon prices lead to more emissions, while the optimal total carbon emissions decrease as carbon reduction costs increase. These findings create implications for multiple stakeholders to formulate their own carbon emissions mitigation strategies under the cap-and-trade mechanism.

Harris Hawks Optimization-Based Clustering Algorithm for Vehicular Ad-Hoc Networks

Vehicular ad-hoc network (VANET) is highly dynamic due to the high speed and sparse distribution of vehicles on the road. This creates major challenges (e.g., network fragmentation, packet routing) for the researchers to enable robust, reliable, and scalable communication, especially in a highly dense network. Clustering in VANET is one of the remedies to address the scalability issue. However, it is observed in the literature, that existing clustering techniques produce a high number of clusters for the vehicular environment. Consequently, it increases the consumption of scarce resources in a wireless network. Furthermore, it also increases the communication overhead as well as the number of hops for data routing. As a result communication latency also increases and the reliability of communication protocol decreases. So it is highly desirable to find out the optimal clusters for a given vehicular environment. As finding optimal clusters is a multi-objective combinatorial optimization problem, therefore by employing nature-inspired meta-heuristic algorithms we can optimize the multi-objective problem. To this end, we proposed a novel clustering algorithm based on the Harris Hawks Optimization (HHO) algorithm for VANET (HHOCNET). HHO algorithm is a nature-inspired meta-heuristic algorithm inspired by the foraging maneuver of hawks called surprise pounce. The proposed framework imitates the cooperative foraging maneuver of hawks (i.e., surprise pounce for creating optimized vehicular clusters). The stochastic operators of the HHO algorithm and proper maintenance of the equilibrium state between the operations of exploration and exploitation enable the proposed algorithm to escape from the local optima and provide a globally optimal solution (i.e., the optimal number of vehicular clusters). Simulations are performed in MATLAB and the results are compared with the state-of-art schemes (i.e., Gray Wolf optimization-based clustering algorithm (GWOCNET), Multi-objective Particle Swarm Optimization (MO, PSO), and Comprehensive Learning Particle Swarm Optimization (CLPSO)) using different performance metrics. The results demonstrate that the proposed approach is an effective approach for clustering in VANET and outer performs the other benchmark algorithms in terms of optimizing the multi-objective clustering problem. HHOCNET algorithm selects 36.04% of nodes as cluster heads while the existing state-of-the-art schemes are providing 50.42%, 56.7%, and 60.89% for GWOCNET, CLPSO, and Multi-objective Particle Swarm Optimization (MOPSO). The proposed HHOCNET algorithm enhances the performance of the vehicular network by up to 15%. Consequently, it increases network efficiency by reducing the consumption of the required wireless resources. It also reduces the number of hops for packet routing. Hence it achieves a minimum end-to-end communication latency.

Availability-Oriented Maintenance Strategy of Key Equipment in Automated Production Line Considering Performance Degradation

Long-term manufacturing would bring performance degradation of key equipment in automated production lines (APLs), leading to operating unbalance and inefficiency. The existing maintenance strategies can generate maintenance schemes, but they generally ignore performance degradation that can further influence the production process. To efficiently generate maintenance schemes with maximized availability and minimized cost, an availability-oriented maintenance strategy considering performance degradation is proposed based on a synchronized hybrid optimization algorithm (SHEA) in this study. Firstly, the performance degradation of key equipment in APLs is analyzed based on the Weibull distribution, and the availability of the equipment is analyzed considering performance degradation. Secondly, a maintenance model for the key equipment in APLs is established, and a SHEA based on multi-objective particle swarm optimization (MOPSO) and squirrel search algorithm (SSA) is proposed to optimize the maintenance model with higher efficiency. Finally, the effectiveness and superiority of the proposed method are verified by citing a practical APL of the engine cylinder head as an example in the case study.

Optimal interdigitated electrode sensor design for biosensors using multi-objective particle-swarm optimization

<p>Interdigitated electrodes (IDEs) are commonly employed in biological cellular characterization techniques such as electrical cell-substrate impedance sensing (ECIS). Because of its simple production technique and low cost, interdigitated electrode sensor design is critical for practical impedance spectroscopy in the medical and pharmaceutical domains. The equivalent circuit of an IDE was modeled in this paper, it consisted of three primary components: double layer capacitance, C<sub>dl</sub>, solution capacitance, C<sub>Sol</sub>, and solution resistance, R<sub>Sol</sub>. One of the challenging optimization challenges is the geometric optimization of the interdigital electrode structure of a sensor. We employ metaheuristic techniques to identify the best answer to problems of this kind. multi-objective optimization of the IDE using multi-objective particle swarm optimization (MOPSO) was achieved to maximize the sensitivity of the electrode and minimize the Cut-off frequency. The optimal geometrical parameters determined during optimization are used to build the electrical equivalent circuit. The amplitude and phase of the impedance versus frequency analysis were calculated using EC-LAB® software, and the corresponding conductivity was determined.</p>

Optimal Dispatching Method of Urban Comprehensive Energy System Based on Multi-energy Complementarity

Considering the complexity of the multi-microgrid system and the diversity of internally distributed power sources, it is challenging for the centralized control scheduling mode to deal with new microgrid systems. Hierarchical management and distributed control strategy can adapt to the power grid management system. In this paper, considering the source-load uncertainty of multi-energy complementary power grid operation, the influence of the multi-energy output distribution model on the supply-demand balance of power grid regulation is constructed, and the probability balance model of power grid regulation capacity is built. To minimize the cost of cooperative operation between multi-energy microgrids and energy storage power stations and maximize the flexibility of regulation, the multi-objective particle swarm optimization (PSO) algorithm is used to constrain the deterministic equivalence of the regulation power probability balance constraint. The effectiveness of the proposed model in describing uncertain factors, reducing operating costs, and improving the regulation capacity of multi-energy microgrids and energy storage power stations is verified through an example analysis.

Multi-Objective Based Generation Expansion Planning for Utility Power System of Tamil Nadu State Considering Recuperation of Older Power Plants

Generation Expansion Planning (GEP) is a problem that comprises multiple contradictory features while planning to construct new generating units. It must be solved by considering cost, reliability and environmental emission. Hence the mathematical representations have been developed to be accurate, and to improve the understanding of the multifaceted and contradictory aspects of the GEP problem. In this study, the Multi-Objective Comprehensive Learning Particle Swarm Optimization (MOCLPSO) algorithm is implemented for solving Multi-Objective GEP (MOGEP) problem. The objectives such as minimization of overall cost, decrement of the pollutant emission and enhancement of reliability have been considered by considering the constraints. The real-world MOGEP problem has been solved for seven-year (from the year 2020 to 2027) and fourteen-year (from the year 2020 to 2034) planning span for the utility power system of Tamil Nadu state, India. The problem is solved for four different cases with the consideration of retirement and recuperation of the older generating units. coal, gas, oil, nuclear, hydel, wind, Solar-photovoltaic (SPV) and biomass power plants were considered in this planning study. The results establish the competence of MOCLPSO to produce well-spread Pareto optimal non-dominated solutions of the MOGEP problem.

Multi-objective particle swarm optimization applied to a solar-geothermal system for electricity and hydrogen production; Utilization of zeotropic mixtures for performance improvement

Renewable energy sources such as solar, wind, and geothermal energy have become increasingly popular due to their environmental benefits and long-term sustainability. This study proposes an innovative integration of a solar system and a geothermal system to optimize the performance of a geothermal power plant. The geothermal system is coupled with a solar system, which utilizes a direct and storage system to increase the efficiency of solar energy utilization and minimize energy loss. To recover waste heat, an electrolyzer is used in a triple-flash geothermal system that operates at high feed geofluid temperatures, producing hydrogen as a byproduct. The organic Rankine cycle with a zeotropic mixture working fluid is employed to generate additional power. After considering eight candidate working fluids, Butene/R123 is selected. The designed system exhibits an impressive 10.83 MW net power, 9.87 kg/h hydrogen, 18.86% energetic efficiency, 29.45% exergetic efficiency, and 4.88 years payback period with a 29.72 M$ net present value. Additionally, two energy-economic and exergy-economic scenarios are evaluated to determine the optimum state. The energy-economic scenario has a lower payback period, whereas the exergy-economic scenario offers greater profitability over the system's lifetime.

Demand response scheduling based on blockchain considering the priority of high load energy enterprises

In order to improve the consumption capacity of wind power plants and deal with the problems of high cost, high risk and low efficiency in traditional demand response, this paper proposes a new optimal scheduling strategy of demand response based on blockchain and the priority of high-capacity enterprises. Based on the analysis of different high-energy load types, the load response dispatching priority and hierarchical electricity price strategy are first put forward. Then the transaction framework of load aggregator, wind power, high-energy enterprise based on blockchain is constructed. Furthermore, the optimization model of load aggregator participating in dispatching is established, which is optimized by multi-objective particle swarm optimization (MOPSO) algorithm. Finally, through the simulation of a certain day in a certain area, the income of aggregators and the cost of wind power plants participating in this dispatching transaction before and after adopting this demand response dispatching scheme are analyzed and compared. It is verified that the demand response scheduling scheme proposed in this paper can effectively guarantee the revenue of load aggregators and improve the wind power consumption level.

A multi-objective cooperative particle swarm optimization based on hybrid dimensions for ship pipe route design

Pipe route design has an important influence on ship performance. The main objective is to generate pipe routes satisfying complicated constraints in 3D space. The design process includes two parts: mathematical modeling and automatic optimization algorithm, where facility simplifying is an essential part of the mathematical modeling. However, previous studies mainly focused on pipe layout algorithms based on single objective optimization, and facility simplifying need to rely on artificial assistance. Nowadays, the optimization algorithm which can give several feasible solutions for designers, and the implementation of automatic pipe route design receive much attention. Therefore, this paper presents a multi-objective cooperative particle swarm optimization based on hybrid dimensions (HDMCPSO) for ship pipe route design (SPRD), which adopts multi-particle dimensions strategy and cooperative update mechanism via representative of each subswarm based on multi-objective particle swarm optimization (MOPSO). The framework can solve the two separate NP-hard problems of facility simplifying and pipe layout compatibly, and obtain high-quality Pareto solutions. To fully evaluate the effectiveness of HDMCPSO, the pipe length, bend number and assembly are optimized as the objectives, and a real piping system of ship engine room is used to compare different methods reported in the literature. The results show that HDMCPSO has generality which can simplify different facilities models and obtain better engineering pipe layout solutions.

Cascade reservoirs operation rules derivation using integrated decision-making method and combinatorial evolution network

Implicit reservoir operation rules map known reservoir conditions to discharge flow or water level decisions to guide reservoir operation. Existing data-driven operation rule extraction models are influenced by both features and hyperparameters, and lack subjective-objective coordination, hindering the formulation of reasonable water energy utilization strategies. To improve the comprehensive benefits of cascade reservoirs, this study proposes a novel multi-objective cascade reservoir operation rule derivation framework. First, a multi-objective optimal operation model for cascade reservoirs (MOOMCR) considering power generation, environment, and navigation is constructed and solved using a Speed-constrained Multi-objective Particle Swarm Optimization algorithm (SMPSO). The relationships among the requirements were explained using a four-dimensional Pareto front visualization analysis. Then, an Integrated Decision-making Method based on Multilevel Subspace Domination (IDMSD) is proposed to circumvent the subjective defects of single decision-making models and reliably select the optimal scheme with the most significant comprehensive benefits from all typical years. Finally, a feature-hyperparameter combination optimization technique based on the differential evolutionary algorithm (FHCC-DE/best/1) is proposed, which exhibits its strength in the identification of key influencing factors on the optimal discharge flow from the IDMSD. The method was embedded in a deep learning model to construct a Combinatorial Evolution Network (CEN) to extract the implicit reservoir operation rules from the optimal IDMSD schemes for the MOOMCR. The results show that the RMSE of the CEN simulating the optimal discharge flow is improved by 5.98%, 28.03%, and 27.89% for the XLD reservoir and by 11.01%, 1.66%, and 60.98% for the XJB reservoir, respectively, over the best results of all benchmark models. Meanwhile, the operation simulation results confirmed that the CEN outperforms conventional reservoir scheduling, with advanced multi-objective comprehensive effects. This suggests that multimethod integrated decision-making and deep learning evolution optimization can help improve the accuracy, generalization, and reliability of implicit reservoir operation rules.

A blockchain-based evaluation approach to analyse customer satisfaction using AI techniques

Due to technological advancements and consumer demands, online shopping creates new features and adapts to new standards. A robust customer satisfaction prediction model concerning trust and privacy platforms can encourage an organization to make better decisions about its service and quality. This study presented an approach to predict consumer satisfaction using the blockchain-based framework combining the Multi-Dimensional Naive Bayes-K Nearest Neighbor (MDNB-KNN) and the Multi-Objective Logistic Particle Swarm Optimization Algorithm (MOL-PSOA). A regression model is employed to quantify the impact of various production factors on customer satisfaction. The proposed method yields better levels of measurement for customer satisfaction (98%), accuracy (95%), necessary time (60%), precision (95%), and recall (95%) compared to existing studies. Measuring consumer satisfaction with a trustworthy platform facilitates to development of the conceptual and practical distinctions influencing customers' purchasing decisions.

Novel Intelligent System Based on Automated Machine Learning for Multiobjective Prediction and Early Warning Guidance of Biogas Performance in Industrial-Scale Garage Dry Fermentation

Industrial-scale garage dry fermentation systems are extremely nonlinear, and traditional machine learning algorithms have low prediction accuracy. Therefore, this study presents a novel intelligent system that employs two automated machine learning (AutoML) algorithms (AutoGluon and H2O) for biogas performance prediction and Shapley additive explanation (SHAP) for interpretable analysis, along with multiobjective particle swarm optimization (MOPSO) for early warning guidance of industrial-scale garage dry fermentation. The stacked ensemble models generated by AutoGluon have the highest prediction accuracy for digester and percolate tank biogas performances. Based on the interpretable analysis, the optimal parameter combinations for the digester and percolate tank were determined in order to maximize biogas production and CH4 content. The optimal conditions for the digester involve maintaining a temperature range of 35–38 °C, implementing a daily spray time of approximately 10 min and a pressure of 1000 Pa, and utilizing a feedstock with high total solids content. Additionally, the percolate tank should be maintained at a temperature range of 35–38 °C, with a liquid level of 1500 mm, a pH range of 8.0–8.1, and a total inorganic carbon concentration greater than 13.8 g/L. The software developed based on the intelligent system was successfully validated in production for prediction and early warning, and MOPSO-recommended guidance was provided. In conclusion, the novel intelligent system described in this study could accurately predict biogas performance in industrial-scale garage dry fermentation and guide operating condition optimization, paving the way for the next generation of intelligent industrial systems.