Machine Learning BMS for TPH Compliance and Occupant Comfort

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Building management systems (BMS) face challenges in maintaining optimal temperature, pressure, and humidity (TPH) levels in buildings, particularly in healthcare facilities, where compliance with standards like ASHRAE is crucial, while ensuring occupant comfort and energy efficiency.

Innovation Solution

A BMS that incorporates machine learning algorithms to analyze TPH sensor data, detect faults, generate work orders, and adjust HVAC equipment, providing customizable dashboards for different user profiles and integrating scheduling requests to maintain compliance and comfort.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional BMS controls are used to maintain TPH levels, then basic compliance can be achieved, but energy efficiency and occupant comfort are compromised

Engineering Contradiction:

ImproveTPH complianceVSAvoidenergy efficiency

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system continuously monitors TPH parameters and uses machine learning models to predict future deviations from compliance thresholds. This predictive feedback mechanism allows the system to take preventive actions before violations occur, optimizing energy usage while ensuring compliance. The feedback loop includes real-time sensor data collection, ML-based prediction, and automated control adjustments.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The machine learning engine autonomously analyzes sensor data, detects faults, generates work orders, and adjusts HVAC settings without requiring constant human intervention. The system self-optimizes TPH control strategies by learning from historical data and adapting to changing building conditions, thereby improving energy efficiency while maintaining compliance reliability.

Inventive Principle:

Principle #25Self-service

2Reliability

If traditional BMS controls are used to maintain TPH levels, then basic compliance can be achieved, but occupant comfort is compromised

Engineering Contradiction:

ImproveTPH complianceVSAvoidoccupant comfort

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system implements zone-specific TPH control strategies tailored to different building areas and occupancy patterns. Machine learning models analyze local conditions in each zone independently, allowing customized comfort optimization for different spaces while maintaining overall compliance. This localized approach enables the system to address specific comfort issues without affecting the entire building.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system dynamically adjusts TPH setpoints and control parameters based on real-time occupancy data, weather conditions, and learned occupancy patterns. This dynamic adaptation allows the system to optimize comfort for current occupant needs while maintaining compliance, rather than relying on static control strategies that cannot respond to changing conditions.

Inventive Principle:

Principle #15Dynamics

3Use of energy by moving object

If machine learning algorithms are implemented to optimize TPH control, then energy efficiency and comfort improve, but system complexity increases

Engineering Contradiction:

Improveenergy efficiencyVSAvoidsystem complexity

Core Design Contradiction:

Use of energy by moving objectVSDevice complexity

Solution Approach 1:

The system architecture is divided into distinct modular components: sensor data collection modules, machine learning engine modules, fault detection modules, work order generation modules, and HVAC control modules. This segmentation allows each component to be developed, tested, and maintained independently, reducing overall system complexity despite the advanced functionality provided by machine learning algorithms.

Inventive Principle:

Principle #1Segmentation

4Reliability

If real-time TPH monitoring and fault detection are implemented, then compliance reliability improves, but measurement and detection difficulty increases

Engineering Contradiction:

Improvecompliance monitoringVSAvoidfault detection accuracy

Core Design Contradiction:

ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The machine learning engine serves as an intermediary layer between raw sensor data and compliance determination. It processes and interprets complex sensor readings, applying learned patterns to accurately detect faults and predict compliance violations. This intermediary processing simplifies the detection task by transforming raw data into meaningful insights about system health and compliance status.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20210080139A1User experience system for improving compliance of temperature, pressure, and humidity

Publication Date: 2021.03.18 TYCO FIRE & SECURITY GMBH

AI summary

A building management system (BMS) for heating, ventilation, or air conditioning (HVAC) parameters in a building. The BMS includes one or more processing circuits including one or more memory devices coupled to one or more processors. The one or more processors query a training data storage and receive training data, institute a policy with a machine learning engine and train the policy using the training data, receive temperature, pressure, and humidity (TPH) sensor data from one or more sensors, determine a fault based on the TPH sensor data, provide the TPH sensor data and the fault to the policy of the machine learning engine and output a corrective action to resolve the fault, and generate a work order for a user based on the TPH sensor data, the determined fault and the corrective action.