Automated Building Element Positioning via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual planning of complex systems like fire detector, sprinkler, and wireless radio networks in buildings is inefficient, often resulting in suboptimal designs and increased costs due to assumptions about element density rather than precise calculations.
Innovation Solution
A computer-implemented method using machine learning to determine optimal element positions and arrangements within a space, considering predetermined technical rules, to achieve the largest possible total work area with the fewest elements, thereby simplifying and cost-effectively designing these systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual planning with experienced engineers is used, then system design quality can be maintained, but planning time and complexity increase significantly
Solution Approach 1:
The patent replaces manual mechanical planning processes with an automated computer-implemented method. The system uses algorithms to automatically determine optimal element positions, calculate work areas, and generate positioning plans, substituting human engineers' manual calculations and decision-making with automated computational processes that are both faster and equally precise.
Solution Approach 2:
The system enables self-service planning where the computer automatically performs all planning tasks without requiring experienced engineers. The automated method independently determines element positions, calculates coverage areas, evaluates positioning rules, and generates complete positioning plans, making the planning process self-sufficient and eliminating dependency on manual expert intervention.
2Productivity
If automated positioning methods are used, then planning speed increases, but determining work areas and verifying arrangements becomes complex
Solution Approach 1:
The patent segments the verification process into distinct automated computational steps: calculating individual element work areas, aggregating total coverage area, checking positioning rules, and evaluating arrangement quality. This segmentation transforms a complex verification task into manageable, automated sub-tasks that can be processed systematically by the computer without increasing overall complexity.
Solution Approach 2:
The system replaces complex manual verification processes with automated computational verification. The computer automatically performs geometric calculations, checks positioning constraints, and validates arrangement quality metrics, substituting what would otherwise be complex manual verification tasks with straightforward automated computations.
3Device complexity
If average element density assumptions are used, then planning process is simplified, but system design optimality is compromised
Solution Approach 1:
The patent replaces assumption-based planning with calculation-based planning. Instead of using average element density assumptions, the system automatically calculates the precise number and positions of elements needed based on actual space geometry, element work areas, and positioning rules, providing optimal designs without requiring complex manual optimization processes.
Solution Approach 2:
The system dynamically adjusts element positioning parameters to achieve optimal coverage. Rather than fixing element density as an average value, the method calculates and adjusts the number and positions of elements based on specific space characteristics, element performance parameters, and coverage requirements, enabling optimal design adaptation to each unique situation.
Data Source
AI summary
A computer-implemented method for positioning technical elements in a space, wherein the elements each have an element work area, where the method includes a) providing the geometry of the space via a space model, b) determining a set of possible element positions for positioning elements from the space model taking into account predetermined positioning rules for the space, c) ascertaining the number of elements for the space via a model based on machine learning, d) determining a set of element arrangements with permutations for elements at each possible element position, and e) determining the element arrangement with the smallest ratio of the number of elements for the space and the total element work area from the ascertained set of element arrangements.