Weather normalisation is a process that adjusts actual energy consumption or peak outcomes to what a building would have used under average conditions. The weather in a given year may be much hotter or colder than your buildings normal climate; weather-normalised energy accounts for this difference.

Acutro deploys a data abstraction layer in order to reduce a particular body of data to a simplified representation of the whole. Abstraction, in general, is the process of removing characteristics from multiple sources of data and condensing it to a set of essential elements that are user-friendly to the relevant stakeholders.

The Asset Validation data is typically a condition survey report produced by a stakeholder across the property ecosystem that captures the entire asset register, including key data values like asset group, system group, manufacturer, model, serial number, install date, location, human survey condition, maintenance schedule information, forecasted lifecycle costs etc.

Indoor Air Quality is the air quality within and around buildings and structures. IAQ is known to affect the health, comfort, and well-being of building occupants. IAQ is evaluated through collection of air samples, monitoring human exposure to pollutants, analysis of building surfaces, and computer modelling of air flow inside buildings. IAQ is part of indoor environmental quality (IEQ), along with other factors that exert an influence on physical and psychological aspects of life indoors (e.g., lighting, visual quality, acoustics, and thermal comfort).

Predictive maintenance (PdM) is a technique that uses data analysis tools and techniques to detect anomalies in your operation and possible defects in equipment and processes so you can fix them before they result in failure. Ideally, predictive maintenance allows the maintenance frequency to be as low as possible to prevent unplanned reactive maintenance, without incurring costs associated with doing too much preventive maintenance.

The internet of things, or IoT, is a system of interrelated computing devices, mechanical and digital machines, objects, animals or people that are provided with unique identifiers (UIDs) and the ability to transfer data over a network without requiring human-to-human or human-to-computer interaction.

A data source may be the initial location where data is born or where physical information is first digitized, however even the most refined data may serve as a source, as long as another process accesses and utilises it. Concretely, a data source may be a database, a flat file, live measurements from physical devices, scraped web data, or any of the myriad static and streaming data services which abound across the internet.

Telemetry is the automatic recording and transmission of data from remote or inaccessible sources to an IT system in a different location for monitoring and analysis. Generally, telemetry works through sensors at the remote source which measures physical (such as precipitation, pressure or temperature) or electrical (power draw) data. This is converted to electrical voltages that are combined with timing data. They form a data stream that is transmitted over a wireless medium, wired or a combination of both.

A building management system (BMS) is a control system that can be used to monitor and manage the mechanical, electrical and electromechanical services in a facility. Such services can include power, heating, ventilation, air-conditioning, physical access control, pumping stations, elevators and lights. The data monitored on the BMS is largely telemetry and binary values capturing the operating profile of all critical assets across the base build infrastructure of the property.

Long Short-Term Memory (LSTM) is a type of recurrent neural network (RNN) architecture that is designed to capture and predict patterns in sequential data. The data streaming from the BMS systems and IoT sensors is relatively simple but the patterns and subtle variances from the individual data points builds a comprehensive picture into asset operation performance and the indicative signs of degradation or potential failure. The LSTM approach allows the platform to indicate potential issues before they would be identified with traditional engineering.

A Support Vector Machine (SVM) approach added another mechanism through which these ‘outlier’ events could be identified through novelty detection. It is an adapted model which involves identifying instances that significantly differ from the majority of data points in a dataset. This is also known as one-class classification or one-class SVM. The goal is to build a model that can accurately identify instances that are unusual or novel compared to the majority of the data. These novel instances might represent anomalies, outliers, or rare events. In the example discussed this would look for the difference in airflow on a smaller time period not a degradation but more of a big bang critical event or failure. The outcome of the combination of approaches now allows alerts and interventions to be driven from almost any scenario presented in the data which would have an impact on the end client.

As part of the IoE architecture; an alert is triggered from the IoE rules-engine providing a notification to the specified user group with a specified message that will require action on the Platform. Alerts can be received by email, SMS, Text-to-speech, or API.

The annual timings allocated to the asset ID against the adopted maintenance standard.

Historical and forecasted Meteorological data pertaining to the atmosphere, such as wind, temperature, air density, visibility, precipitation levels and current weather condition.

A core component on the IoE Platform that allows you to define rules and then apply those rules to data. The rules that are defined and stored can trigger alert notifications to the specified user group with a specified message that will require action on the Platform.

This page component on the IoE pre-aggregates all asset records and their associated telemetry values against a time series data base allowing the user to visualise, plot, overlay, interrogate, trend, share and export data.

This is providing a dynamic score as a % that renders a RAG status indicator every 7 days from AI models applied against the dataset which is considering data from multiple sources (primarily telemetry points from BMS, IoT, and meteorological sources) in relation to that asset’s operating profile against its baseline. To provide an Asset Health score, the AI model requires at least over 5 telemetry points across at least two data sources to provide the foundation of an asset health score. The more datapoints and sources factored into the AI model, the more accurate the Asset Health score will be. The Asset Health AI scores will the workflows on maintenance activities relating to suppression of tasks or acceleration of tasks - ultimately a more dynamic, data-led maintenance model.

With respect to maintenance, an asset is any piece of equipment, property, or other physical item used in a facility's operations.

The execution of opting not to perform an upcoming PPM task in the calendar based on the Asset Health AI score powered by the Acutro IoE Platform.

A gentleman from New York discovered what he calls an “oversight” on the part of 99.9% of all marketers that allows him to get otherwise paid-for advertising at Google as well as all other search engines that allow sponsored ads.

Defined on Acutro IoE as a manual intervention task mapped against any asset / system / building for a specific use case. Must be approved or declined by an administrator user to be logged and performed.

Planned preventative maintenance (PPM), also commonly referred to as planned maintenance or scheduled maintenance, is essentially a scheduled maintenance routine for the assets across an estate. Tasks are scheduled ahead of time, while assets are still in functioning order.