Method and system for dynamic environmental monitoring

Abstract

Regulations and standards are acquired and analysed 310 to determine the assumptions 320 behind them and the associated environmental parameters 330 within the building space. These parameters are use

Description

TECHNICAL FIELD

[0001] The present invention relates to advanced environmental monitoring systems for buildings, and more particularly to systems and methods for dynamically converting static regulatory standards into real-time adaptive sensorbased solutions that utilize Internet of Things (loT) technology for comprehensive monitoring and automated management of indoor environmental conditions. BACKGROUND ART

[0002] Building regulations worldwide, such as Part F (Ventilation) of the UK Building Regulations 2010, establish minimum standards for indoor air quality, ventilation rates, and environmental conditions in residential and commercial buildings. These regulations typically rely on static, standardized tables and design assumptions that presume consistent usage patterns, occupancy levels, and environmental conditions throughout a building's operational life.

[0003] Traditional building ventilation and environmental control systems are designed to meet these static regulatory requirements at the design phase. For example, Part F specifies minimum ventilation rates based on floor area and room type, assuming average occupancy and usage patterns. However, these assumptions often misalign with actual occupancy patterns, usage behaviours, and dynamic environmental conditions that occur during real-world building operation.

[0004] This misalignment creates several significant problems. First, poor air quality management can result when ventilation systems operate at fixed rates regardless of actual occupancy or pollutant generation. Second, the risk of damp and mould formation increases when humidity levels are not monitored and controlled in real-time, particularly in bathrooms, kitchens, and bedrooms where moisture generation varies significantly throughout the day. Third, energy is wasted when ventilation systems operate at maximum capacity during periods of low or no occupancy. Fourth, and most critically, buildings may experience unsafe conditions that comply with design-time regulations but nevertheless pose health and safety risks to occupants.

[0005] Existing prior art systems have attempted to address some of these limitations, but each suffers from significant drawbacks:

[0006] US Patent Application 2016 / 0147506 Al discloses a generic loT platform for environmental monitoring using temperature, humidity, and pressure sensors. However, this system does not perform multi-parameter correlation analysis to assess health and safety risks, nor does it translate regulatory standards into dynamic operational thresholds. The system is designed primarily for data collection rather than proactive risk assessment and regulatory compliance.

[0007] US Patent 8,731,724 B2 describes an automated fault detection and diagnostics system for building management systems (BMS). While this system monitors equipment performance and energy consumption, it focuses on mechanical faults and energy efficiency rather than occupant health and safety. The system does not monitor humidity-temperature correlations for mould risk, nor does it assess compliance with ventilation regulations such as Part F.

[0008] US Patent Application 2015 / 0100167 Al discloses a smart-home control system that integrates hazard detectors (smoke and carbon monoxide) with HVAC systems. While this system responds to acute hazards, it does not monitor for chronic environmental risks such as mould formation, nor does it use multiparameter environmental data to infer occupancy patterns, activities, or equipment malfunctions.

[0009] US Patent Application 2009 / 0125283 Al describes a method for automatically determining compliance with building regulations using Building Information Models (BIM). This system performs static, design-phase compliance checking rather than continuous operational monitoring. It cannot detect real-time unsafe conditions that arise during building occupancy, nor can it adapt to actual usage patterns that differ from design assumptions.

[0010] Academic research has explored the use of temperature, humidity, CO2, and other parameters for occupancy detection, primarily for energy management purposes. For example, Candanedo and Feldheim (2016) achieved high accuracy in occupancy detection using statistical learning models applied to environmental sensor data. However, these approaches focus narrowly on occupancy presence / absence for HVAC scheduling and energy savings, rather than on health and safety risk assessment or regulatory compliance.

[0011] None of the prior art systems address the fundamental problem of translating static regulatory standards into dynamic, real-time monitoring thresholds that can detect unsafe conditions as they arise during building operation. Furthermore, no existing systems perform multi-parameter correlation analysis to identify complex risk scenarios such as mould formation (requiring both elevated humidity and specific temperature ranges) or fire detection (requiring rapid CO2 rise combined with temperature increase).

[0012] The Building Safety Act 2022 in the UK has increased the emphasis on ongoing compliance and safety monitoring in buildings, particularly in residential settings. This regulatory shift creates a need for systems that can continuously monitor and document compliance with environmental standards, maintain tamperproof audit trails, and provide early warning of conditions that may lead to health and safety risks.

[0013] There is therefore a need for an improved environmental monitoring system that can dynamically translate static regulatory standards into real-time monitoring thresholds, perform multi-parameter correlation analysis to detect complex risk scenarios, infer occupancy patterns and activities from environmental data, and maintain secure, compliant records of environmental conditions and system responses. SUMMARY OF THE INVENTION

[0014] It is an object of the present invention to provide an improved method and system for dynamic environmental monitoring that addresses one or more of the problems identified above, or that at least provides a useful alternative.

[0015] According to a first aspect of the invention, there is provided a method for dynamic environmental monitoring in a building, the method comprising: (a) analysing one or more static regulatory standards to identify environmental parameters and associated regulatory assumptions; (b) translating said static regulatory standards into dynamic sensor thresholds for real-time monitoring, wherein said dynamic sensor thresholds include at least temperature thresholds, humidity thresholds, and carbon dioxide (CO2) thresholds; [c] deploying a plurality of loT-enabled sensors throughout said building, wherein said sensors are configured to continuously monitor temperature, humidity, and CO2 levels in real-time; (d) receiving sensor data from said plurality of loT-enabled sensors; (e) analysing said sensor data using multi-parameter correlation to determine environmental status and detect risk conditions; and (f) generating alerts or automated responses when said sensor data exceeds said dynamic sensor thresholds or indicates a risk condition.

[0016] In some embodiments, said multi-parameter correlation includes analysing combinations of temperature and humidity to determine mould formation risk.

[0017] In some embodiments, said multi-parameter correlation includes analysing patterns of CO2, temperature, and humidity to infer at least one of: occupancy status, occupant activity, and equipment operational status.

[0018] In some embodiments, said multi-parameter correlation includes analysing rapid increases in CO2 combined with temperature increases to detect combustion events.

[0019] In some embodiments, said static regulatory standards comprise Part F of the UK Building Regulations, and wherein said method translates ventilation rate requirements and air quality assumptions into said dynamic sensor thresholds.

[0020] In some embodiments, said dynamic sensor thresholds include multiple alert levels comprising at least an early warning threshold and a danger alert threshold for each monitored parameter.

[0021] In some embodiments, for bedrooms, said temperature thresholds include an early warning threshold below 18°C and a danger alert threshold below 17°C, and said humidity thresholds include an early warning threshold above 60% relative humidity (RH) and a danger alert threshold above 65% RH.

[0022] In some embodiments, for living rooms, said CO2 thresholds include an early warning threshold above 800 ppm and a danger alert threshold above 900 ppm.

[0023] In some embodiments, for kitchens, said CO2 thresholds include an early warning threshold above 1000 ppm and a danger alert threshold above 1200 ppm.

[0024] In some embodiments, said automated responses include at least one of: operating ventilation equipment, operating heating equipment, operating dehumidification equipment, activating alarms, and sending notifications to users or monitoring services.

[0025] In some embodiments, said method further comprises recording said sensor data and said automated responses in a blockchain network to provide a tamperproof audit trail.

[0026] In some embodiments, said blockchain network is configured to comply with General Data Protection Regulation (GDPR) requirements.

[0027] In some embodiments, said method further comprises communicating said sensor data to a centralized control system via loT communication protocols.

[0028] According to a second aspect of the invention, there is provided a system for dynamic environmental monitoring in a building, the system comprising: (a) a plurality of loT-enabled sensors deployed throughout said building, each sensor being configured to measure at least one of temperature, humidity, and CO2 levels; (b) a communication network configured to transmit sensor data from said plurality of sensors; (c) a processing unit configured to: (i) receive said sensor data from said plurality of sensors; (ii) compare said sensor data against dynamic sensor thresholds derived from static regulatory standards; (hi) perform multi-parameter correlation analysis on said sensor data to determine environmental status and detect risk conditions; (iv) generate alerts when said sensor data exceeds said dynamic sensor thresholds or indicates a risk condition; and (d) a control interface configured to initiate automated responses to detected risk conditions.

[0029] In some embodiments, said processing unit is further configured to analyse combinations of temperature and humidity to determine mould formation risk.

[0030] In some embodiments, said processing unit is further configured to analyse patterns of CO2, temperature, and humidity to infer at least one of: occupancy status, occupant activity, and equipment operational status.

[0031] In some embodiments, said processing unit is further configured to identify cooking activity based on rising humidity, and rising temperature in a kitchen space.

[0032] In some embodiments, said processing unit is further configured to identify gas cooking activity based on rising CO2 levels in a kitchen space.

[0033] In some embodiments, said processing unit is further configured to identify extraction fan failure by identifying elevated CO2 or humidity levels during inferred cooking activity.

[0034] In some embodiments, said processing unit is further configured to detect combustion events by analysing rapid increases in CO2 combined with temperature increases.

[0035] In some embodiments, said system further comprises environmental control devices operatively connected to said control interface, said environmental control devices including at least one of: ventilation fans, heating devices, dehumidifiers, air conditioning units, automated window openers, and vent openers.

[0036] In some embodiments, said system further comprises a blockchain network interface configured to record said sensor data and system responses in a distributed ledger.

[0037] In some embodiments, said plurality of loT-enabled sensors includes sensor sets positioned in bedrooms, living rooms, kitchens, and bathrooms, each sensor set comprising at least a temperature sensor, a humidity sensor, and a CO2 sensor.

[0038] In some embodiments, said dynamic sensor thresholds include room-specific thresholds tailored to expected usage patterns and regulatory requirements for each room type.

[0039] According to a third aspect of the invention, there is provided a non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform the method of the first aspect.

[0040] According to a fourth aspect of the invention, there is provided a method for detecting unsafe environmental conditions in a building, the method comprising: (a) monitoring temperature, humidity, and CO2 levels in real-time using a plurality of sensors; (b) detecting mould formation risk by identifying conditions where humidity exceeds a first threshold and temperature is within a mould-conducive range; (c) detecting potential combustion events by identifying rapid increases in CO2 levels combined with temperature increases; and [d] generating alerts or automated responses upon detection of said unsafe environmental conditions.

[0041] The invention may also broadly consist in the parts, elements, steps, examples and / or features referred to or indicated in the specification individually or collectively in any and all combinations of two or more said parts, elements, steps, examples and / or features. In particular, one or more features in any of the embodiments described herein may be combined with one or more features from any other embodiment(s) described herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Preferred embodiments of the invention will be described by way of example only and with reference to the drawings, in which:

[0043] FIG. 1 is a block diagram showing an overview of the dynamic environmental monitoring system according to one embodiment of the invention;

[0044] FIG. 2 is a schematic diagram showing sensor deployment throughout a residential building according to one embodiment;

[0045] FIG. 3 is a flow diagram illustrating the method for translating static regulatory standards into dynamic sensor thresholds;

[0046] FIG. 4 is a flow diagram illustrating multi-parameter correlation analysis for mould risk detection;

[0047] FIG. 5 is a flow diagram illustrating multi-parameter correlation analysis for occupancy and activity inference;

[0048] FIG. 6 is a flow diagram illustrating multi-parameter correlation analysis for combustion event detection;

[0049] FIG. 7 is a block diagram showing the integration of sensors with environmental control devices and blockchain network;

[0050] FIG. 8 is a graph showing temperature and humidity zones with mould risk regions according to one embodiment;

[0051] FIG. 9 is a graph showing CO2 concentration patterns for different occupancy and activity scenarios; and

[0052] FIG. 10 is a block diagram showing the data flow from sensors through processing to automated responses and blockchain recording. DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS Overview of the System

[0053] Referring to FIG. 1, the dynamic environmental monitoring system 100 comprises a plurality of loT-enabled sensors 110 deployed within a building, a communication network 120 for transmitting sensor data, a central processing unit 130 configured to analyse sensor data and determine environmental status, a control interface 140 for initiating automated responses, environmental control devices 150 (such as ventilation fans, heating systems, and dehumidifiers), a user interface 160 for displaying alerts and system status, and optionally a blockchain network interface 170 for maintaining tamper-proof records of environmental data and system actions.

[0054] The sensors 110 continuously monitor environmental parameters including temperature, humidity (relative humidity, RH), and carbon dioxide (CO2) concentration. The sensor data is transmitted via communication network 120, which may utilize wireless protocols such as Wi-Fi, Zigbee, Z-Wave, LoRaWAN, or other suitable loT communication standards. The central processing unit 130 receives the sensor data and performs real-time analysis, including comparison against dynamic thresholds and multi-parameter correlation analysis to detect risk conditions.

[0055] When risk conditions are detected, the system generates alerts via user interface 160 and / or initiates automated responses via control interface 140. Automated responses may include operating ventilation equipment to increase air exchange rates, activating heating systems to raise temperature, operating dehumidifiers to reduce humidity, or any combination thereof. All sensor data and system actions are optionally recorded in blockchain network 170 to provide a verifiable, tamper-proof audit trail for regulatory compliance purposes. Sensor Deployment Architecture

[0056] Referring to FIG. 2, in a typical residential building application, loT-enabled sensors are strategically deployed in key rooms where environmental monitoring is critical for health, safety, and regulatory compliance. Each room type has specific monitoring requirements based on expected usage patterns and regulatory standards.

[0057] In bedrooms 210, sensor sets monitor temperature and humidity to detect conditions conducive to mould growth and to ensure comfortable sleeping conditions. Bedrooms are particularly susceptible to mould due to moisture released during respiration and limited ventilation during sleeping hours. The system monitors for temperature below 18°C (which increases condensation risk) and humidity above 60% RH (which promotes mould growth).

[0058] In living rooms 220, sensor sets monitor temperature, humidity, and CO2 to assess air quality and occupancy. Living rooms typically have variable occupancy throughout the day, and CO2 levels provide a reliable indicator of occupancy density and ventilation effectiveness. The system monitors CO2 levels with an early warning threshold at 800 ppm and a danger threshold at 900 ppm, consistent with indoor air quality guidelines.

[0059] In kitchens 230, sensor sets monitor all three parameters (temperature, humidity, CO2) due to the complex environmental dynamics during cooking activities. Cooking generates significant moisture (steam from boiling water, humidity from food preparation), heat, and combustion byproducts if gas cooking appliances are used. The system monitors CO2 with higher thresholds (early warning at 1000 ppm, danger at 1200 ppm) to account for expected CO2 generation from gas appliances while still detecting ventilation failures or unsafe conditions.

[0060] In bathrooms 240, sensor sets primarily monitor temperature and humidity to manage moisture from bathing and showering activities. Bathrooms are high-risk areas for mould formation due to frequent, intense moisture generation. The system monitors humidity levels and can trigger extraction fans when humidity exceeds thresholds.

[0061] Additional sensors may be deployed in hallways, utility rooms, or other spaces depending on building layout and specific monitoring requirements. The system architecture is scalable and can accommodate any number of sensors across any building type.

[0062] Each sensor set preferably comprises a multi-parameter sensor module capable of measuring temperature (with accuracy of ±0.5°C or better), relative humidity (with accuracy of ±3% RH or better), and CO2 concentration (with accuracy of ±50 ppm or better). Alternatively, separate individual sensors for each parameter may be used. Sensors are preferably wireless and battery-powered or powered by low-voltage wiring to facilitate installation in existing buildings without extensive retrofitting. Translation of Static Regulatory Standards into Dynamic Thresholds

[0063] Referring to FIG. 3, the method for translating static regulatory standards into dynamic sensor thresholds begins at step 310 with analysis of the relevant regulatory standard, such as Part F of the UK Building Regulations. Part F specifies minimum ventilation rates based on room type and floor area, expressed in litres per second (1 / s) or air changes per hour (ACH). For example, Part F requires minimum ventilation rates of 30 1 / s for a kitchen hood extracting to the outside, 13 1 / s for kitchens for continuous mechanical extract ventilation, 15 1 / s for bathrooms with intermittentextraction fans, or 8 litres per second (29 m3 per hour) for bathrooms with continuous mechanical extract ventilation.

[0064] At step 320, the underlying assumptions and objectives of these ventilation requirements are identified. The fundamental objective of Part F is to maintain acceptable indoor air quality by limiting the accumulation of pollutants, moisture, and CO2. The specified ventilation rates are calculated based on assumptions about typical pollutant generation rates, occupancy patterns, and acceptable pollutant concentrations.

[0065] At step 330, these assumptions are reverse-engineered to determine the target environmental conditions that the ventilation requirements are intended to achieve. For example, the 8 1 / s bathroom continuous ventilation requirement is designed to remove moisture sufficiently to prevent humidity from remaining elevated for extended periods. By analysing the moisture generation rate during showering (approximately 200-300 grams per shower) and the target humidity level (below 60% RH for mould prevention), the system can calculate the equivalent real-time humidity threshold.

[0066] At step 340, dynamic sensor thresholds are established based on these target conditions. Rather than simply ensuring that the ventilation system meets the design specification (e.g., 8 1 / s), the system monitors whether the actual environmental conditions meet the underlying objectives (e.g., humidity below 60% RH). This approach accounts for variables that static regulations cannot address, such as variations in bathroom size, shower duration, outdoor humidity, and ventilation system performance degradation over time.

[0067] At step 350, multiple threshold levels are established for each parameter to provide graduated alerts and responses. An "early warning" threshold triggers when conditions are trending toward unsafe levels but have not yet reached dangerous levels. A "danger alert" threshold triggers when conditions pose an immediate health or safety risk. This graduated approach allows for proactive intervention before conditions become hazardous.

[0068] For example, for bedroom humidity, the early warning threshold is set at 60% RH (based on research showing increased mould growth rates above this level) and the danger threshold is set at 65% RH (representing sustained conditions that will likely result in visible mould within weeks). For bedroom temperature, the early warning threshold is set at 18°C (the minimum temperature recommended for sleeping spaces) and the danger threshold is set at 17°C (below which condensation risk increases significantly on cold surfaces).

[0069] At step 360, these thresholds are programmed into the central processing unit 130, where they are used for real-time comparison against incoming sensor data. The thresholds may be room-specific to account for different regulatory requirements and usage patterns for different room types. Multi-Parameter Correlation for Mould Risk Detection

[0070] Referring to FIG. 4, one of the key innovations of the present invention is the use of multi-parameter correlation analysis to detect complex risk conditions that cannot be identified by monitoring individual parameters in isolation. Mould formation risk is a prime example of such a complex condition.

[0071] Mould growth requires three conditions: moisture (typically above 60% RH), suitable temperature (typically 5-35°C, with optimal growth at 20-30°C), and organic substrate (present in building materials and furnishings). While traditional systems might simply monitor humidity, the present invention recognizes that mould risk depends on the combination of humidity and temperature.

[0072] At step 410, the system continuously receives temperature and humidity data from sensors in each monitored room. At step 420, the system determines whether humidity exceeds the early warning threshold (e.g., 60% RH). If not, the system continues monitoring at step 410. If humidity does exceed the threshold, the system proceeds to step 430.

[0073] At step 430, the system evaluates whether temperature is within the mould-conducive range. If temperature is below 5°C or above 35°C, mould growth is unlikely even with elevated humidity, and the system may generate a lower-priority alert or simply continue monitoring. If temperature is within the range of 5-3 5°C, particularly within the optimal range of 20-30°C, the system proceeds to step 440.

[0074] At step 440, the system calculates a mould risk score based on the combination of temperature and humidity. The mould risk score may be calculated using established models such as the Viitanen mould growth model (A mathematical model of mould growth on wooden material, Wood Science and Technology, December 1999) or similar empirical relationships between temperature, humidity, substrate properties, and mould growth rate. Higher temperatures (within the optimal range) combined with higher humidity result in higher mould risk scores.

[0075] At step 450, if the mould risk score exceeds a threshold value, the system generates an alert and / or initiates automated responses. Automated responses may include activating ventilation fans to increase air exchange and reduce humidity, activating dehumidifiers to directly remove moisture from the air, or increasing heating (if appropriate) to raise temperature above the mould-conducive range.

[0076] Referring to FIG. 8, a graphical representation shows temperature on the x-axis and humidity on the y-axis, with regions color-coded by mould risk. The safe zone 810 represents combinations of temperature and humidity where mould risk is low. The elevated risk zone 820 represents conditions where mould growth may occur over extended periods (weeks to months). The high-risk zone 830 represents conditions where visible mould is likely to develop within days to weeks. The danger zone 840 represents conditions where rapid mould growth is occurring.

[0077] This multi-parameter approach provides significantly earlier warning of mould risk compared to systems that monitor humidity alone. For example, 70% RH at 10°C poses much lower mould risk than 70% RH at 25°C, yet a humidity-only system would treat these situations identically. The present invention recognizes this distinction and provides more accurate risk assessment and more effective responses.

[0078] Furthermore, by monitoring these conditions continuously in real-time, the system can detect unsafe conditions that would not be prevented by design-time compliance with building regulations. For example, a building may fully comply with Part F ventilation requirements, but if occupants keep windows closed and generate high moisture levels, mould-conducive conditions can still develop. The present system detects these conditions as they occur and takes corrective action, rather than relying on design assumptions about occupant behaviour. Multi-Parameter Correlation for Occupancy and Activity Inference

[0079] Referring to FIG. 5, another innovative aspect of the present invention is the use of environmental parameter patterns to infer occupancy status and occupant activities. This capability enables the system to understand the context of environmental changes and to differentiate between normal, expected conditions and abnormal, potentially unsafe conditions.

[0080] At step 510, the system continuously receives temperature, humidity, and CO2 data from sensors throughout the building. At step 520, the system analyses CO2 patterns over time. Human respiration generates approximately 200-300ml of CO2 per minute per person at rest, and significantly more during physical activity. In a typical bedroom (3m x 4m x 2.4m = 28.8 m3), a single sleeping occupant will cause C02to rise from background levels (approximately 400-450ppm outdoor air) to 800-1000 ppm over several hours with the door closed and minimal ventilation.

[0081] At step 530, the system determines whether a rising CO2 pattern is detected. A gradual, steady rise in CO2 indicates human occupancy and respiration. The rate of rise provides information about the number of occupants and their activity level. If rising CO2 is detected, the system infers that the space is occupied at step 540.

[0082] At step 550, the system analyses humidity and temperature patterns in combination with CO2 data to infer specific activities. Different activities have characteristic environmental signatures:

[0083] Cooking activity in a kitchen is characterized by rising humidity (from steam and moisture in food), rising temperature (from oven / stove operation), and potentially rising CO2 (if gas appliances are used). The magnitude and rate of change of these parameters can indicate the type and intensity of cooking. For example, boiling water produces rapid humidity increase with moderate temperature increase, while oven baking produces significant temperature increase with minimal humidity change.

[0084] Showering / bathing in a bathroom is characterized by rapid, dramatic humidity increase (potentially from 40% RH to 80-95% RH within minutes), moderate temperature increase (from steam), and minimal or no CO2 change (unless the bathroom is occupied for an extended period with poor ventilation).

[0085] Sleeping occupancy in a bedroom is characterized by gradual CO2 increase over several hours, slight humidity increase (from respiration), and stable or decreasing temperature (depending on heating system operation and outdoor temperature).

[0086] At step 560, based on the inferred activity, the system can generate activityspecific alerts or responses. For example, if cooking activity is inferred in a kitchen, the system expects to see rising humidity and temperature, and can allow these changes within expected ranges without generating false alarms. However, if humidity rises excessively (above danger thresholds) or CO2 rises rapidly to dangerous levels, the system can infer that the extraction fan is not operating properly or that ventilation is insufficient.

[0087] At step 570, the system can also use activity inference to detect equipment malfunctions. For example, if cooking activity is inferred (based on temperature and humidity patterns) but CO2 is not rising as expected with a gas stove, this may indicate that the extraction fan is working effectively. Conversely, if CO2 rises above expected levels during cooking, this indicates that extraction is inadequate. If cooking is inferred but there is no change in environmental parameters over time, this may indicate sensor malfunction.

[0088] Referring to FIG. 9, a graphical representation shows CO2 concentration over time with different patterns for various scenarios. Pattern 910 shows background CO2 levels with no occupancy. Pattern 920 shows gradual rise from single-occupant sleeping (bedroom at night). Pattern 930 shows steeper rise from multiple occupants in a living room. Pattern 940 shows sharp rise from cooking with gas appliances. Pattern 950 shows very rapid rise indicating potential combustion event (fire).

[0089] This activity inference capability provides several advantages. First, it enables context-aware alerting that reduces false alarms by distinguishing between normal, expected environmental changes and abnormal conditions. Second, it enables detection of equipment malfunctions such as extraction fan failures that would not be detected by systems that only monitor absolute parameter levels. Third, it provides valuable data about building usage patterns that can inform energy management, maintenance scheduling, and verification of regulatory compliance overtime. Multi-Parameter Correlation for Combustion Event Detection

[0090] Referring to FIG. 6, another critical safety feature of the present invention is the ability to detect potential fire or combustion events by analysing patterns of CO2 and temperature changes. This provides an early warning capability that complements traditional smoke detectors.

[0091] At step 610, the system continuously monitors CO2 and temperature data from all sensors. At step 620, the system calculates the rate of change (derivative) of CO2 concentration. Normal CO2 increases from respiration or cooking are gradual, typically on the order of 50-100 ppm per hour. Combustion events, by contrast, produce very rapid CO2 increases, potentially on the order of hundreds of ppm per minute.

[0092] At step 630, the system determines whether the rate of CO2 increase exceeds a threshold indicative of combustion. If so, the system proceeds to step 640 to evaluate temperature data. At step 640, the system determines whether temperature is also increasing rapidly. Combustion produces heat, so a genuine fire event will show both rapid CO2 increase and temperature increase.

[0093] This combination of parameters reduces false alarms compared to monitoring either parameter alone. For example, a space heater or oven might produce rapid temperature increase without abnormal CO2 increase. Conversely, a large group of people entering a small room might cause relatively rapid CO2 increase without significant temperature increase. By requiring both conditions, the system improves detection accuracy.

[0094] At step 650, if both rapid CO2 increase and temperature increase are detected, the system generates a high-priority combustion alert. At step 660, the system may initiate emergency responses such as activating audible / visual alarms, sending emergency notifications to occupants and monitoring services, shutting down HVAC systems to prevent smoke circulation, and / or automatically contacting emergency services.

[0095] This combustion detection capability provides earlier warning than traditional smoke detectors in some scenarios, particularly for smouldering fires that produce CO2 and heat before producing detectable smoke. The capability also provides redundant safety detection, improving overall fire safety in the building. Integration with Environmental Control Devices

[0096] Referring to FIG. 7, the system 100 is configured to integrate with various environmental control devices 150 to provide automated responses to detected conditions. The control interface 140 communicates with these devices via wired or wireless control signals, using appropriate protocols such as relay switching, 0-10V analogue control, DALI (Digital Addressable Lighting Interface), BACnet (Building Automation and Control networks), Modbus, or other suitable building automation protocols.

[0097] Environmental control devices may include extraction fans 710 (for bathrooms, kitchens, and other spaces requiring moisture removal or ventilation), supply fans 720 (for mechanical ventilation with heat recovery systems), heating devices 730 (such as radiators, underfloor heating, or forced-air heating systems), dehumidifiers 740 (for targeted moisture removal), air conditioning units 750 (for cooling and dehumidification), and window actuators 760 (for automated opening of windows for natural ventilation).

[0098] When the system detects conditions requiring intervention, it determines the appropriate response based on the specific condition detected, the room type, the available control devices, and user preferences. For example, if elevated humidity is detected in a bathroom during showering activity, the system may activate the bathroom extraction fan 710 at high speed and maintain operation until humidity drops below the early warning threshold. If elevated humidity is detected in a bedroom during sleeping hours, the system may avoid activating loud extraction fans and instead provide a low-priority alert to the user.

[0099] The system preferably implements graduated responses corresponding to the early warning and danger alert threshold levels. When an early warning threshold is exceeded, the system may implement a gentle, automatic correction (such as activating ventilation at moderate speed) without alerting the user. When a danger alert threshold is exceeded, the system implements more aggressive responses (such as maximum ventilation, dehumidifier activation, and user notification).

[0100] For safety-critical detections such as potential combustion events, the system implements immediate, comprehensive responses including all available alarms and notifications, regardless of time of day or user preferences. Blockchain Integration for Data Integrity and Compliance

[0101] Referring again to FIG. 7, the system optionally includes blockchain network interface 170 for recording environmental data and system actions in a distributed ledger 780. This provides several important benefits for regulatory compliance, data integrity, and dispute resolution.

[0102] The Building Safety Act 2022 in the UK and similar legislation in other jurisdictions increasingly require building owners and managers to maintain verifiable records of building safety systems operation and compliance. Traditional database systems are vulnerable to tampering, where records could be altered or deleted to conceal non-compliance or system failures. Blockchain technology provides a tamper-proof audit trail where each record is cryptographically linked to previous records, making unauthorized modification detectable.

[0103] The blockchain network 780 maybe implemented as a private / permissioned blockchain where only authorized entities (such as the building owner, system operator, and regulatory authorities) can read records, or as a public blockchain with privacy-preserving techniques for sensitive data. The blockchain interface 170 records timestamped entries including sensor readings, detected conditions, alerts generated, automated responses initiated, and manual interventions by users.

[0104] For GDPR compliance, the system implements appropriate data protection measures. Personal data (such as occupancy patterns that could reveal when residents are present or absent) is either anonymized before recording, encrypted with keys held by data subjects, or stored off-chain with only cryptographic hashes recorded on-chain. The system implements data minimization principles, recording only the minimum necessary data for compliance and safety purposes.

[0105] Data subjects (building occupants) are provided with appropriate access to their data and can exercise rights including data access, correction, and deletion in accordance with GDPR requirements. The immutability of blockchain records is balanced against data subject rights through mechanisms such as off-chain storage of personal data with on-chain pointers that can be invalidated when deletion is required.

[0106] The blockchain audit trail provides valuable evidence in various scenarios. If a building experiences mould infestation, the blockchain records can demonstrate whether the monitoring system was operating properly, whether unsafe conditions were detected, whether appropriate alerts were generated, and whether automated or manual interventions were taken. This protects building owners from spurious claims while also ensuring accountability if the system was not maintained or if warnings were ignored.

[0107] Similarly, if questions arise about compliance with building regulations or the Building Safety Act, the blockchain records provide verifiable evidence of continuous monitoring and compliance with environmental standards. This is particularly valuable for demonstrating that the building met regulatory requirements not just at the design phase but throughout its operational life. Room-Specific Threshold Examples

[0108] The following examples illustrate specific threshold configurations for different room types according to preferred embodiments:

[0109] Bedroom Monitoring: Bedrooms are monitored primarily for temperature and humidity to ensure comfortable sleeping conditions and prevent mould formation. The system implements the following thresholds: Temperature Early Warning: <18°C (triggers low-priority alert, may suggest increasing heating) Temperature Danger Alert: <17°C (triggers high-priority alert, may automatically increase heating if control is available) Humidity Early Warning: >60% RH (triggers alert, activates gentle ventilation if available) Humidity Danger Alert: >65% RH (triggers urgent alert, activates maximum ventilation and / or dehumidification)

[0110] The 18°C lower limit is based on WHO recommendations for bedroom temperature and UK Housing Health and Safety Rating System (HHSRS) guidance. Below this temperature, condensation risk increases on cold surfaces (windows, external walls), particularly when combined with elevated humidity from respiration during sleep.

[0111] The humidity thresholds are based on research showing that mould growth accelerates significantly above 60% RH when combined with suitable temperatures. During an 8-hour sleep period, a single occupant can increase bedroom humidity by 5-10% RH through respiration if ventilation is minimal. The system accounts for this expected rise and alerts if humidity exceeds safe levels.

[0112] Living Room Monitoring: Living rooms are monitored for temperature, humidity, and CO2 to ensure air quality during the typically high occupancy periods. The system implements: Temperature Early Warning: <18°C or >22°C (triggers alert for comfort) Temperature Danger Alert: <17°C or >23°C (triggers urgent alert) CO2 Early Warning: >800 ppm (indicates ventilation maybe insufficient for current occupancy) CO2 Danger Alert: >900 ppm (indicates poor air quality requiring immediate ventilation increase) Humidity Early Warning: >60% RH Humidity Danger Alert: >65% RH

[0113] The CO2 thresholds are calibrated based on Part F assumptions about acceptable indoor air quality. Part F's specified ventilation rates are intended to maintain CO2 below approximately 1000 ppm under typical occupancy. However, research shows cognitive performance impacts and occupant discomfort at levels above 800 ppm, so the system uses more stringent thresholds to ensure optimal conditions.

[0114] Living rooms typically have variable occupancy throughout the day. The system's CO2 monitoring detects when occupancy exceeds the level that fixed ventilation can accommodate, triggering increased ventilation only when needed rather than continuously over-ventilating (which wastes energy) or underventilating (which degrades air quality).

[0115] Kitchen Monitoring: Kitchens are monitored for all three parameters due to the complex environmental dynamics during cooking. The system implements: Temperature Early Warning: >25°C (may indicate cooking activity or inadequate ventilation) Temperature Danger Alert: >30°C (indicates excessive heat buildup) Humidity Early Warning: >65% RH (indicates moisture generation from cooking) Humidity Danger Alert: >70% RH (indicates inadequate extraction during moisture-generating cooking) CO2 Early Warning: >1000 ppm (indicates possible inadequate extraction with gas appliances) CO2 Danger Alert: >1200 ppm (indicates dangerous combustion byproduct accumulation)

[0116] The higher CO2 thresholds for kitchens (compared to living rooms) account for the expected CO2 generation from gas cooking appliances. However, these levels still require effective extraction. Part F requires continuous extract ventilation of 13 1 / s for kitchens during cooking, specifically to remove combustion products and moisture.

[0117] The system's real-time monitoring verifies that extraction is actually achieving its intended effect (reducing CO2 and humidity) rather than simply verifying that the extraction fan is switched on. This addresses the common problem of extraction systems that are inadequately sized, improperly installed, or degraded in performance overtime.

[0118] Bathroom Monitoring: Bathrooms are monitored primarily for humidity and temperature to manage moisture from bathing activities. The system implements: Temperature Early Warning: <18°C (increases condensation risk) Temperature Danger Alert: <16°C (high condensation risk) Humidity Early Warning: >70% RH (expected during / immediately after showering) Humidity Danger Alert: >80% RH for >30 minutes (indicates inadequate extraction) Humidity Persistence Alert: >60% RH for >2 hours after bathing activity (indicates insufficient ventilation)

[0119] Bathrooms present unique monitoring challenges because very high humidity (80-95% RH) is normal and expected during and immediately after showering. The system differentiates between acceptable temporary humidity elevation and problematic sustained humidity by implementing time-based thresholds.

[0120] The system infers bathing activity from rapid humidity rise and maintains extraction until humidity returns to safe levels (<60% RH). If humidity remains elevated for extended periods, this indicates that extraction capacity is insufficient or that the extraction fan is not operating, and the system generates alerts and may increase extraction speed or duration. Operational Examples Example 1: Mould Risk Detection and Prevention

[0121] A bedroom in a residential building is monitored by a sensor set measuring temperature and humidity. During winter months, outdoor temperatures are cold (5°C) and the bedroom heating maintains indoor temperature at 19°C. A single occupant sleeps in the room from 23:00 to 07:00 (8 hours) with the bedroom door closed and minimal ventilation.

[0122] At 23:00, initial conditions are: temperature 19°C, humidity 45% RH. Over the 8-hour sleep period, the occupant's respiration adds approximately 200g of moisture to the room air. Given the room volume of 30 m3 and temperature of 19°C, this increases humidity to approximately 58% RH by 07:00.

[0123] The system monitors these conditions continuously. The humidity remains below the 60% RH early warning threshold, so no alerts are generated. This represents normal, safe operation.

[0124] However, suppose the room temperature drops to 16°C (due to heating system failure or thermostat setting). At 16°C, the same 200g of moisture addition increases humidity to approximately 65% RH due to reduced moisture-holding capacity of cooler air. At 06:00, the system detects that humidity has exceeded 60% RH (early warning) and temperature is below 18°C (early warning). The multiparameter correlation analysis calculates a mould risk score indicating elevated risk.

[0125] The system generates an alert to the occupant: "Bedroom conditions are conducive to mould growth. Temperature is low (16°C) and humidity is elevated (65% RH). Recommended actions: increase heating and improve ventilation." If the system has control capability, it may automatically increase heating setpoint to 19°C and activate gentle ventilation.

[0126] By 07:00, the occupant opens windows for natural ventilation, and temperature increases to 18°C through increased heating. Humidity drops to 55% RH. The system records that the mould-conducive conditions existed for approximately 3 hours and normal conditions were restored. This event is recorded in the blockchain ledger for compliance documentation.

[0127] This example demonstrates how the system detects a complex risk condition (mould risk depending on both temperature and humidity) that would not trigger alarms in a simple humidity-only monitoring system, and how it provides actionable guidance to prevent mould formation. Example 2: Kitchen Extraction Failure Detection

[0128] A kitchen in a residential building is equipped with a gas cooker and a continuous extraction fan rated at 13 1 / s as required by Part F. The kitchen is monitored by sensors measuring temperature, humidity, and CO2.

[0129] At 18:00, the occupant begins cooking dinner. Initial conditions are: temperature 20°C, humidity 45% RH, CO2 450 ppm. The occupant uses the gas cooker (generating CO2) and boils water (generating steam / humidity).

[0130] Under normal operation with the extraction fan working properly: By 18:15, temperature increases to 23°C, humidity increases to 55% RH, CO2 increases to 650 ppm By 18:30, with extraction fan removing moisture and CO2, levels stabilize: temperature 24°C, humidity 58% RH,CO2 700 ppm By 19:00 (cooking complete, extraction fan continues), conditions return toward normal: temperature 22°C, humidity 50% RH, CO2 500 ppm

[0131] The system recognizes this pattern as normal cooking activity with effective extraction. No alerts are generated.

[0132] However, suppose the extraction fan fails to operate (due to mechanical failure, electrical issue, or occupant forgetting to switch it on): By 18:15, temperature increases to 23°C, humidity increases to 62% RH, CO2 increases to 850 ppm (higher than with extraction) By 18:30, without extraction, accumulation continues: temperature 25°C, humidity 68% RH (exceeds early warning), CO2 1050 ppm (exceeds early warning) The system recognizes cooking activity pattern but detects that CO2 and humidity are not being controlled effectively

[0133] At 18:30, the system generates an alert: "Kitchen ventilation may be inadequate. CO2 and humidity are elevated during cooking. Please verify extraction fan is operating." If the system has control capability over the extraction fan, it attempts to activate the fan. If the fan is already supposed to be on (per control signals), the system infers a mechanical failure and escalates the alert.

[0134] If conditions continue to worsen, reaching CO2 1200 ppm (danger threshold), the system generates an urgent alert: "DANGER: Kitchen air quality is poor. CO2 has reached unsafe levels. Immediately stop using gas appliances and ventilate the space."

[0135] This example demonstrates howthe system uses multi-parameter correlation and activity inference to detect equipment malfunctions that would not be detected by design-time compliance verification. A building may have a compliant extraction system installed, but if it fails or is not used, unsafe conditions can develop. The present system detects these conditions in real-time and prompts corrective action. Example 3: Combustion Event Detection

[0136] A living room in a residential building is monitored by sensors measuring temperature, humidity, and CO2. At 14:00 on a winter afternoon, an electrical fault in a power outlet causes a fire to begin smouldering inside a wall cavity.

[0137] Initial conditions: temperature 20°C, CO2 450 ppm. The smouldering fire produces heat and combustion products (CO2, CO) but minimal visible smoke initially.

[0138] Timeline of detection: 14:05: Temperature increases to 21°C (gradual), CO2 increases to 480 ppm. Rate of change is within normal fluctuation ranges. No alert. 14:10: Temperature 22°C, CO2 520 ppm. Rates of change increasing but still below combustion thresholds. 14:12: Temperature 23°C, CO2 580 ppm. System calculates rate of change: temperature increasing at 0.5°C / minute, CO2 increasing at 30 ppm / minute. 14:14: Temperature 25°C, CO2 680 ppm. Rates continue to accelerate: temperature l°C / minute, CO2 50 ppm / minute. 14:15: Temperature 27°C, CO2 780 ppm. System detects both rapid temperature increase AND rapid CO2 increase, meeting combustion event criteria.

[0139] At 14:15, the system generates a combustion alert: "POTENTIAL FIRE DETECTED. Rapid temperature and CO2 increase detected in living room. Evacuate immediately and call emergency services." The system activates audible / visual alarms throughout the building and sends emergency notifications to registered contacts.

[0140] In this scenario, the system provides approximately 10-15 minutes advance warning before the fire produces visible smoke or flames. This early detection could be life-saving, particularly if the fire occurs during sleeping hours when occupants might not notice smoke immediately.

[0141] A traditional smoke detector would not activate until the fire produces sufficient smoke, which might not occur until the fire transitions from smouldering to flaming combustion. The CO2 and temperature monitoring provides an additional, independent detection mechanism that can detect some fire scenarios earlier than smoke detection alone. Example 4: Occupancy Pattern Analysis for Energy Optimization

[0142] A residential building is monitored by the system for several months, collecting continuous data on temperature, humidity, and CO2 across all rooms. The system analyses this data to learn typical occupancy patterns.

[0143] The system determines that: Bedrooms show elevated CO2 and humidity from 23:00 to 07:00 (sleeping hours) on weekdays Living room shows elevated CO2 from 18:00 to 22:00 on weekdays (evening occupancy) Kitchen shows cooking-related patterns at 07:00-08:00 and 18:00-19:00 On weekends, patterns shift with later wake times and more variable daytime occupancy

[0144] Using this learned occupancy data, the system can optimize HVAC operation: Reduce heating in bedrooms during daytime hours when unoccupied Pre-heat living spaces before expected occupancy periods Ensure extraction systems are ready to operate at typical cooking times Reduce ventilation rates during confirmed unoccupied periods

[0145] The system can also detect anomalies that may indicate security concerns or health issues: If normal bedroom occupancy pattern (rising CO2 at night) is absent, this may indicate the occupant is away from home (relevant for security) or did not return home as expected (potential welfare concern for elderly occupants) If typical daily activity patterns cease (no cooking activities, no movement between rooms), this may indicate a health emergency

[0146] This example demonstrates how the environmental monitoring data provides value beyond immediate safety alerts, enabling energy optimization, security awareness, and potential welfare monitoring applications. Alternative Embodiments

[0147] While the detailed description above focuses on residential buildings and UK Building Regulations Part F, the inventive concept applies broadly to other building types and regulatory frameworks.

[0148] In commercial office buildings, the system may monitor open-plan office areas, meeting rooms, and restrooms using similar principles but with different threshold values reflecting higher occupancy densities and different regulatory requirements. CO2 monitoring in meeting rooms is particularly valuable given the high occupancy density and importance of maintaining cognitive performance during meetings.

[0149] In educational buildings, classrooms may be monitored with particular emphasis on CO2 levels, which research has shown significantly impact student concentration and learning outcomes. The system may adjust ventilation rates in real-time based on actual classroom occupancy rather than using fixed ventilation rates based on maximum design occupancy.

[0150] In healthcare facilities, patient rooms, operating theatres, and other clinical spaces require stringent environmental control. The system may implement more restrictive thresholds and may integrate with medical gas monitoring systems.

[0151] In industrial facilities, the system may monitor for process-specific parameters in addition to or instead of the parameters described above. For example, food processing facilities may monitor temperature and humidity for food safety compliance, while manufacturing facilities may monitor for specific airborne contaminants.

[0152] The regulatory standards translated into dynamic thresholds may include standards other than Part F, such as: ASHRAE Standard 62.1 (Ventilation for Acceptable Indoor Air Quality) used in the United States and many other countries Part L (Conservation of fuel and power) thresholds for energy efficiency The Building Safety Act 2022 safety requirements WELL Building Standard health and wellness criteria Local regulations specific to particular jurisdictions

[0153] The blockchain implementation may use various distributed ledger technologies including Ethereum, Hyperledger Fabric, Corda, or other suitable platforms. The choice of platform depends on requirements for public vs. private deployment, transaction throughput, energy efficiency, and integration with existing systems.

[0154] The sensor technology may include various sensor types and communication protocols. Temperature sensors may include thermocouples, thermistors, resistance temperature detectors (RTDs), or infrared sensors. Humidity sensors may include capacitive, resistive, or thermal conductivity types. CO2 sensors may include non-dispersive infrared (NDIR) sensors, photoacoustic sensors, or electrochemical sensors. Communication protocols may include Wi-Fi, Bluetooth, Zigbee, Z-Wave, Thread, Matter, LoRaWAN, or proprietary protocols.

[0155] The system may integrate with existing building management systems (BMS), home automation systems, or standalone controllers. Integration maybe achieved through standard protocols (BACnet, Modbus, MQTT, etc.) or through custom integration layers.

[0156] The user interface may be implemented as a web application, mobile application (iOS, Android), desktop application, or integrated into existing building management interfaces. The interface may provide real-time dashboards showing current conditions, historical trend graphs, alert logs, and system status information.

[0157] Machine learning algorithms may optionally be incorporated to improve threshold accuracy over time, predict conditions before they occur, or optimize automated responses based on learned occupant preferences and building characteristics. However, the fundamental inventive concept does not require machine learning and provides significant benefits through the rules-based approach described. Advantages and Benefits

[0158] The present invention provides numerous advantages over existing environmental monitoring and building management systems:

[0159] Real-time compliance verification: Unlike traditional building regulations that verify compliance only at the design and construction phase, the present system continuously verifies that environmental conditions meet regulatory objectives throughout building operation. This addresses the reality that buildings are dynamic systems where conditions change based on occupancy, weather, equipment performance, and maintenance status.

[0160] Early warning of health and safety risks: The multi-parameter correlation analysis detects complex risk conditions such as mould formation risk, inadequate ventilation, and potential fire scenarios before they pose immediate danger. This provides opportunity for preventive action rather than reactive response after damage or injury has occurred.

[0161] Adaptation to actual usage patterns: Static regulatory standards assume typical usage patterns, but real buildings are used in diverse ways. The present system adapts to actual conditions, providing appropriate responses whether occupancy is higher or lower than design assumptions, whether cooking is intensive or minimal, whether occupants prefer windows open or closed, etc.

[0162] Equipment performance monitoring: The system detects when extraction fans, ventilation systems, or other equipment fail to achieve their intended effect, even if the equipment appears to be operating. This addresses the common problem of compliant-at-installation systems that degrade over time due to duct blockage, filter clogging, fan wear, or other issues.

[0163] Energy efficiency: By adjusting ventilation and environmental control in response to actual conditions rather than running continuously at maximum capacity, the system can significantly reduce energy consumption while maintaining or improving air quality and comfort.

[0164] Data integrity and accountability: The blockchain integration provides tamper-proof records of environmental conditions and system responses, supporting regulatory compliance verification, insurance claims assessment, and dispute resolution.

[0165] Privacy and data protection: Unlike camera-based occupancy detection or location tracking systems, environmental parameter monitoring respects occupant privacy while still providing valuable information about occupancy patterns and activities.

[0166] Scalability and adaptability: The system architecture scales from single-room monitoring to large multi-building deployments. The threshold configuration system allows easy adaptation to different regulatory frameworks, building types, and specific requirements.

[0167] Integration capability: The system integrates with existing HVAC equipment, building management systems, and home automation platforms, allowing retrofit installation in existing buildings without requiring complete system replacement.

[0168] False alarm reduction: The multi-parameter correlation approach reduces false alarms by considering context. For example, high humidity during showering is recognized as normal rather than immediately triggering mould risk alerts.

[0169] Actionable guidance: Rather than simply indicating that a problem exists, the system provides specific, actionable recommendations for corrective action and can implement automated responses when appropriate.

[0170] While the present invention has been described with reference to specific embodiments and examples, it will be appreciated that modifications and variations are possible without departing from the scope of the invention as defined in the appended claims.

[0171] The invention may be embodied in many different forms and should not be construed as limited to the specific embodiments described. Rather, these embodiments are provided to illustrate the principles of the invention and its practical applications, thereby enabling others skilled in the art to understand and practice the invention in various forms and with various modifications suited to particular uses.

[0172] Features described in relation to one embodiment may be combined with features from other embodiments where technically feasible. The invention encompasses all combinations and sub-combinations of features disclosed herein.

[0173] Ranges of values disclosed herein include all values within those ranges, including endpoints. References to "approximately," "about," or similar terms in relation to numerical values should be interpreted as including values within ±10% of the stated value unless otherwise specified.

[0174] The term "comprising" as used herein does not exclude the presence of additional elements or steps beyond those explicitly listed. Claims using "comprising" should be interpreted as open-ended unless context clearly requires otherwise.

[0175] References to loT, sensors, blockchain, and other technologies encompass current implementations and future developments in those technology areas that perform equivalent functions.

[0176] The methods described herein may be performed in different orders unless a specific sequence is required by technical necessity. Steps may be performed concurrently where technically feasible.

[0177] Computer-implemented aspects of the invention maybe embodied in software, firmware, hardware, or combinations thereof. Storage media may include any non-transitory computer-readable medium including magnetic, optical, solidstate, or other storage technologies.

Claims

The invention claimed is:Claim 1. A method for dynamic environmental monitoring in a building, the method comprising:(a) analysing one or more static regulatory standards to identify environmental parameters and associated regulatory assumptions;(b) translating said static regulatory standards into dynamic sensor thresholds for real-time monitoring, wherein said dynamic sensor thresholds include at least temperature thresholds, humidity thresholds, and carbon dioxide (CO2) thresholds;(c) deploying a plurality of loT-enabled sensors within said building, wherein said sensors are configured to continuously monitor temperature, humidity, and CO2 levels in real-time;(d) receiving sensor data from said plurality of loT-enabled sensors;(e) analysing said sensor data using multi-parameter correlation to determine environmental status and detect risk conditions; and(f) generating alerts or automated responses when said sensor data exceeds said dynamic sensor thresholds or indicates a risk condition.Claim 2. The method of claim 1, wherein said multi-parameter correlation includes analysing combinations of temperature and humidity to determine mould formation risk.Claim 3. The method of claim 2, wherein determining mould formation risk comprises: (a) detecting humidity levels exceeding a first threshold value; (b) determining whether temperature is within a mould-conducive range; (c) calculating a mould risk score based on the combination of temperature and humidity; and (d) generating an alert when said mould risk score exceeds a threshold value.Claim 4. The method of claim 1, wherein said multi-parameter correlation includes analysing patterns of CO2, temperature, and humidity to infer at least one of: occupancy status, occupant activity, and equipment operational status.Claim 5. The method of claim 4, wherein inferring occupant activity comprises identifying cooking activity based on rising humidity, rising temperature, and rising CO2 levels in a kitchen space.Claim 6. The method of claim 4, wherein determining equipment operational status comprises detecting extraction fan failure by identifying elevated CO2 or humidity levels during inferred cooking activity.Claim 7. The method of claim 1, wherein said multi-parameter correlation includes analysing rapid increases in CO2 combined with temperature increases to detect combustion events.Claim 8. The method of claim 7, wherein detecting combustion events comprises: (a) calculating a rate of change of CO2 concentration; (b) determining whether said rate of change exceeds a combustion threshold; (c) determining whether temperature is increasing simultaneously; and (d) generating a combustion alert when both rapid CO2 increase and temperature increase are detected.Claim 9. The method of claim 1, wherein said static regulatory standards comprise Part F of the UK Building Regulations, and wherein said method translates ventilation rate requirements and air quality assumptions into said dynamic sensor thresholds.Claim 10. The method of claim 1, wherein said dynamic sensor thresholds include multiple alert levels comprising at least an early warning threshold and a danger alert threshold for each monitored parameter.Claim 11. The method of claim 10, wherein for bedrooms, said temperature thresholds include an early warning threshold below 18°C and a danger alert threshold below 17°C, and said humidity thresholds include an early warning threshold above 60% relative humidity (RH) and a danger alert threshold above 65% RH.Claim 12. The method of claim 10, wherein for living rooms, said CO2 thresholds include an early warning threshold above 800 ppm and a danger alert threshold above 900 ppm.Claim 13. The method of claim 10, wherein for kitchens, said CO2 thresholds include an early warning threshold above 1000 ppm and a danger alert threshold above 1200 ppm.Claim 14. The method of claim 1, wherein said automated responses include at least one of: operating ventilation equipment, operating heating equipment, operating dehumidification equipment, activating alarms, and sending notifications to users or monitoring services.Claim 15. The method of claim 1, further comprising recording said sensor data and said automated responses in a blockchain network to provide a tamper-proof audit trail.Claim 16. The method of claim 15, wherein said blockchain network is configured to comply with General Data Protection Regulation (GDPR) requirements by at least one of: anonymizing personal data, encrypting personal data, and storing personal data off-chain with cryptographic references on-chain.Claim 17. The method of claim 1, wherein step (b) comprises: (i) identifying underlying objectives of said static regulatory standards; (ii) determining target environmental conditions that said regulatory standards are intended to achieve; (hi) reverse-engineering said target environmental conditions to establish real-time monitoring thresholds; and (iv) establishing multiple threshold levels including early warning and danger alert levels.Claim 18. The method of claim 1, wherein said plurality of loT-enabled sensors are deployed in room-specific configurations, with different dynamic sensor thresholds applied to different room types based on expected usage patterns and regulatory requirements.Claim 19. The method of claim 1, further comprising learning typical occupancy patterns from historical sensor data and optimizing environmental control based on learned patterns.Claim 20. The method of claim 1, wherein said method provides real-time operational compliance monitoring that detects unsafe conditions arising during building occupancy that static design-time regulatory compliance would not prevent.Claim 21. A system for dynamic environmental monitoring in a building, the system comprising: (a) a plurality of loT-enabled sensors deployed within said building, each sensor being configured to measure at least one of temperature, humidity, and CO2 levels; (b) a communication network configured to transmit sensor data from said plurality of sensors; (c) a processing unit configured to: (i) receive said sensor data from said plurality of sensors; (ii) compare said sensor data against dynamic sensor thresholds derived from static regulatory standards; (hi) perform multiparameter correlation analysis on said sensor data to determine environmental status and detect risk conditions; (iv) generate alerts when said sensor data exceeds said dynamic sensor thresholds or indicates a risk condition; and (d) a control interface configured to initiate automated responses to detected risk conditions.Claim 22. The system of claim 21, wherein said processing unit is further configured to analyse combinations of temperature and humidity to determine mould formation risk by calculating a mould risk score based on both parameters.Claim 23. The system of claim 21, wherein said processing unit is further configured to analyse patterns of CO2, temperature, and humidity to infer at least one of: occupancy status, occupant activity, and equipment operational status.Claim 24. The system of claim 23, wherein said processing unit is further configured to identify cooking activity based on rising humidity, and rising temperature in a kitchen space.Claim 25. The system of claim 24, wherein said processing unit is further configured to identify gas cooking activity based on rising CO2 levels in a kitchen space.Claim 26. The system of claim 24 or 2 5, wherein said processing unit is further configured to identify extraction fan failure by identifying elevated CO2 or humidity levels during inferred cooking activity.Claim 27. The system of claim 21, wherein said processing unit is further configured to detect combustion events by analysing rapid increases in CO2 combined with temperature increases.Claim 28. The system of claim 21, further comprising environmental control devices operatively connected to said control interface, said environmental control devices including at least one of: ventilation fans, heating devices, dehumidifiers, and air conditioning units.Claim 29. The system of claim 21, further comprising a blockchain network interface configured to record said sensor data and system responses in a distributed ledger to provide a tamper-proof audit trail.Claim 30. The system of claim 21, wherein said plurality of loT-enabled sensors includes sensor sets positioned in bedrooms, living rooms, kitchens, and bathrooms, each sensor set comprising at least a temperature sensor, a humidity sensor, and a CO2 sensor.Claim 31. The system of claim 21, wherein said dynamic sensor thresholds include room-specific thresholds tailored to expected usage patterns and regulatory requirements for each room type, including for bedrooms: temperature early warning threshold below 18°C, temperature danger threshold below 17°C, humidity early warning threshold above 60% RH, and humidity danger threshold above 65% RH;Claim 32 The system of claim 21, wherein said dynamic sensor thresholds include room-specific thresholds tailored to expected usage patterns and regulatory requirements for each room type, including for living rooms: CO2 early warning threshold above 800 ppm and CO2 danger threshold above 900 ppmClaim 33 The system of claim 21, wherein said dynamic sensor thresholds include room-specific thresholds tailored to expected usage patterns and regulatory requirements for each room type, including for kitchens: CO2 early warning threshold above 1000 ppm and CO2 danger threshold above 1200 ppm.Claim 34. The system of claim 21, wherein said processing unit implements graduated responses corresponding to early warning thresholds and danger alert thresholds, with more aggressive automated responses triggered by danger alert threshold exceedances.Claim 35. The system of claim 21, wherein said system is configured to detectunsafe conditions that arise during building operation despite design-time compliance with building regulations, by continuously monitoring actual environmental conditions.Claim 36. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform a method for dynamic environmental monitoring, the method comprising: (a) receiving sensor data from a plurality of loT-enabled sensors measuring temperature, humidity, and CO2 levels in a building; (b) comparing said sensor data against dynamic sensor thresholds derived from static regulatory standards; (c) performing multiparameter correlation analysis on said sensor data to detect at least one of: mould formation risk based on temperature and humidity combinations, occupancy patterns based on CO2 patterns, cooking activity based on temperature, humidity and CO2 patterns, and combustion events based on rapid CO2 and temperature increases; and (d) generating alerts or initiating automated responses when risk conditions are detected.Claim 37. A method for detecting unsafe environmental conditions in a building, the method comprising: (a) monitoring temperature, humidity, and CO2 levels in realtime using a plurality of sensors in multiple rooms of said building; (b) detecting mould formation risk by identifying conditions where humidity exceeds 60% RH and temperature is within a range of 5°C to 35°C; (c) detecting potential combustion events by identifying rapid increases in CO2 levels exceeding 100 ppm per minute combined with temperature increases exceeding 0.5°C per minute; (d) detecting equipment malfunction by identifying elevated humidity or CO2 during inferred cooking activity; and (e) generating alerts or automated responses upon detection of said unsafe environmental conditions.Claim 38. The method of claim 32, wherein said method detects unsafe conditions that static building regulations based on design assumptions would not prevent, by continuously monitoring actual environmental conditions during building operation.Claim 39. The method of claim 32, further comprising recording detected conditions and system responses in a blockchain network to provide verifiable compliance records.Claim 40. A method for translating static regulatory ventilation standards into dynamic real-time monitoring thresholds, the method comprising: (a) analysing a static regulatory standard specifying minimum ventilation rates for building spaces; (b) identifying underlying assumptions about pollutant generation rates, occupancy levels, and acceptable pollutant concentrations; (c) calculating target environmental conditions that said ventilation rates are intended to achieve under said assumptions; (d) establishing dynamic sensor thresholds for temperature, humidity, and CO2 that correspond to said target environmental conditions; (e) deploying sensors to monitor actual environmental conditions against said dynamic sensor thresholds; and (f) determining compliance with regulatory objectives based on measured conditions.Claim 41. The method of claim 35, wherein said static regulatory standard comprises Part F of the UK Building Regulations specifying ventilation rates in litres per second, and wherein said dynamic sensor thresholds include CO2 thresholds of 800-900 ppm for living spaces and 1000-1200 ppm for kitchens.A

Images