Optimization of building placement on irregularly shaped land plots using artificial intelligence methods

Layout Optimization of Irregular Construction Sites Based on SLP and Improved NSGA-II

Previous studies on construction site layout often simplified the site as a rectangle, with little consideration of adaptability to complex terrain and multiple functional constraints. An optimization method was developed for irregular construction sites, based on Systematic Layout Planning (SLP) and an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II), to address the limited adaptability of traditional methods in multi-objective and multi-constraint scenarios. A mathematical model for site layout was constructed using a rasterization method, with transportation time, transportation cost, and noise level as the optimization objectives. High-quality initial populations were generated by quantifying logistics and non-logistics relationships using the SLP method. The NSGA-II algorithm was enhanced with an adaptive penalty function, two-point crossover encoding, dynamically adjusted crossover and mutation probabilities, and a population restart mechanism. This improved its global search efficiency and convergence performance in complex solution spaces. Case validation results indicate that SLP-INSGA-II outperforms NSGA-II and SLP-NSGA-II while maintaining comparable performance to INSGA-II on some indicators. Without degrading overall optimization performance, incorporating SLP-based engineering priors can enhance search guidance, leading to layout solutions that are both feasible and engineering-interpretable. This study provides a modeling and solution approach for layout optimization in irregular construction sites.

Improved SA algorithm for masonry layout optimization of building infill walls

This paper proposes a hybrid optimization algorithm that fuses multiple methods to address the weak global exploration ability, frequent local optima, and poor engineering adaptability in masonry layout optimization of building infill walls. The method builds a multilayer cooperative framework. It first uses the Genetic Algorithm to create a diverse population. It then applies Simulated Annealing to perform probabilistic jumping optimization. After that, it introduces sparse A search to verify topological feasibility. It finally relies on a cooperative mechanism of Adaptive Whale Optimization and iterative local search to explore the solution space in depth. Experiments on the simultaneous localization and mapping–building information modeling coupled dataset and the building information modeling component multimodal dataset show that the algorithm reaches a standard block utilization rate of 98.76 percent. It also keeps the cutting loss rate as low as 2.79%and achieves a peak stagger-joint compliance rate of 97.11%. In irregular wall scenarios, it reduces cost by up to 33.87%. The results show that this algorithm improves the optimization quality and engineering applicability of masonry layout and provides reliable technical support for precise construction and efficient material use of building infill walls.

A Review of Stope Layout Optimization Algorithms: Linking Resource Efficiency, Circular Mining, and Sustainable Production

Stress-Relief Annealing: Polynomial-Time Simulation-Free Layout Optimization for Automated Warehouses

We study the problem of optimizing physical layouts for automated warehouses, where hundreds to thousands of robots are coordinated to transport packages. Previous works have shown that optimizing the warehouse layout (e.g., the physical location of the storage shelves) significantly improves throughput. However, state-of-the-art layout optimization approaches are based on evolutionary optimization methods, which treat the entire warehouse as a black box and rely on random mutation to search for high-quality layouts. While the optimization outcomes are promising, these methods require a massive number of simulations to evaluate candidate solutions, making them sample-inefficient. In this paper, we present Stress-Relief Annealing (SRA), a polynomial-time simulation-free layout optimization algorithm. SRA turns the task demand into a per-vertex \emph{stress field} that predicts where traffic will concentrate in the warehouse; the field's peak provably caps the throughput. Our experimental results show that (1) SRA improves both the throughput and the scalability of a human-designed warehouse, roughly doubling the number of robots it can sustain, (2) it matches or exceeds the throughput of the evolutionary baselines while taking only $19$ minutes on one CPU core, against their $25{,}000$ simulations and $25$ hours on a $64$-core machine, and (3) the gain generalizes across different Multi-Agent Path Finding algorithms, non-uniform task demands, and a warehouse with doubled dimensions.

Social Spider Optimization for Preliminary Earthwork-Balanced Highway Alignment Design

This study proposes a metaheuristic-based route optimization framework that balances earthworks in highway design by referencing a constant-slope “zero polygon.” The aim is to distribute excavation and embankment volumes evenly between fixed endpoints. The positions of Point of Intersection nodes and curve radii are optimized using the Social Spider Optimization (SSO) algorithm, guided by an objective function that minimizes the weighted signed distances between the route and the zero polygon while enforcing geometric constraints such as minimum curve radius, tangent length, and alignment continuity through penalty terms. Applications on two terrains with varying slopes demonstrate that the calibrated model substantially improves the cut–fill balance compared with both manual and pre-calibration solutions: the absolute difference between excavation and embankment volumes decreased from thousands to hundreds of cubic meters, and the cut–fill ratio fell below 0.1 in representative cases. Coupling a swarm-intelligence search with an interpretable geometric reference line, the framework offers a reproducible decision-support tool for preliminary corridor design. It enhances transparency and reduces reliance on trial-and-error practice. It targets preliminary, open-terrain corridor selection under a constant longitudinal slope without vertical curves, and does not yet incorporate land-use, environmental, or geotechnical constraints.

A new algorithm for finding optimal solutions of transportation problems

This paper presents a computational refinement of classical optimality procedures for solving Transportation Problems (TPs). Rather than altering the underlying linear programming formulation, the method introduces a structured loop-enumeration strategy within the transportation simplex framework. Specifically, admissible improvement loops are generated from the current basis (occupied cells) and constrained to include exactly one nonbasic (unoccupied) cell, reducing redundant loop exploration. A formal analysis establishes feasibility preservation, strict descent when an improving loop exists, finite termination, and equivalence with classical optimality conditions via reduced costs. Computational experiments on benchmark problems from literature compare the new method with the Stepping–Stone and MODI methods. To evaluate computational efficiency, all computational experiments were conducted using MATLAB R2022b on a computer equipped with an Intel Core i7 processor (3.20 GHz), 16 GB RAM, running Windows 10 (64-bit), Execution time was measured using MATLAB’s built-in timing functions. Each method was run five times per dataset, and the average CPU execution time (in seconds) was recorded to ensure consistency. Results show that the new approach yields optimal solutions identical to classical methods and achieves comparable or improved performance on average runtime, with clearer benefits on medium-to-large instances where loop redundancy is more pronounced. For small instances, differences are minor and may vary due to implementation overhead. The findings position the method as a practical, verifiable computational refinement for efficient loop selection in transportation simplex implementations.