Building automation has gone through many different periods. There was the” initial “medieval period” back in 1883, when Warren Johnson, a school teacher from Milwaukee invented a thermostat that could indicate that more coal was needed in the furnace, thus the first building automation apparatus and obviously, Warren Johnson went on to found Johnson Controls.
There was a large and growing need for automation for industry and buildings; ventilation, air conditioning, hot water, steam, processes and a need for full automation control systems.
The initial automation market used compressed air to run or power the equipment. Pneumatic systems were somewhat inefficient, but were used for a long time; the “Middle Ages” of building automation. Pneumatic controls were around close to a century; engineers were still removing them in the 1970’s and 1980’s.
The development and introduction of Direct Digital Controls (DDC) happen in a time when information technology was growing and used extensively. DDC automation was the beginning of the “Modern Ages” of building automation and provided the development of building management systems (BMS) which turned out to be the primary management system for building operations. It allowed facility staff to monitor the building’s mechanical and electrical equipment such as ventilation, lighting, power systems, fire systems, and security systems. Over time the controllers became much more sophisticated, and all major building automation companies manufactured and marketed DDC.
Building automation, building operations, and related controls are likely to be quite different in the near future. Automation will be less about wrenches and screwdrivers and more about a whole new vocabulary that will include artificial intelligence, robotic process automation, open edge software, self-managing systems, self-organizing networks, self-optimization systems and self-learning systems. While the industry has embraced analytics and to some extent data mining, the newer concepts for the building industry will take some time to understand and absorb for typical building owners and facility engineers. In time, however, facility staff will see that self-learning systems can be just “another tool in the tool belt”; providing key information for the issues facility engineers are addressing.
To move to higher levels of building automation, systems need to be smarter, innovative, and sophisticated. Where for example the systems can automatically configure and integrate new equipment or devices without the need for a technician to manually configure the equipment; where the system can optimize itself and self-heal; and it will not only identify faults or failures but compensate and re-configure the system to minimize any impact on the system.
The new main concepts are:
Artificial intelligence (AI)
The idea of AI is that machines can accurately mimic intelligence. Yes, machines and computer systems can perform tasks that would normally require human intelligence. Underlining AI is massive data sets. The machines can “learn” and “solve problems” and have a “cognitive function” somewhat like humans. Statistical methods are used, and systems can understand human speech, identify visual perception, decision-making, and translation between languages.
Self-learning, self-management machines, and automation are expected to be the next generation network management systems. Self-learning Machines can learn without being programmed. The systems learn by analyzing the data sets and can make predictions, assessments and even decisions without human intervention. Self-Management technologies are expected to be the next generation of network management systems.
Robotic process automation (RPA) is the use of software with artificial intelligence (AI) and machine learning capabilities to handle high-volume, repeatable tasks that previously required a human to perform, such as clerical work. RPA uses the application of technology that allows configuring computer software or a “robot” to capture and interpret existing applications for processing a transaction, manipulating data, triggering responses and communicating with other systems. It is a form of clerical process automation technology based on the notion of software robots or artificial intelligence (AI)
Machine learning focuses on the development of computer programs that can teach themselves to grow and change when additional new data is available. The process of machine learning is like that of data mining. Both systems search through data to look for patterns. However, instead of extracting data for human comprehension — as is the case in data mining applications — machine learning uses that data to detect patterns in data and adjust program actions accordingly.
Examples of Self-Learning Machines
Self-Driving Cars – Part of the mechanisms that allow cars to drive by themselves use image processing. A Machine Learning algorithm learns where the edge of the road is if there’s a stop sign or a car approaching by when examining at each frame taken by a video camera. The primary sensors for driverless cars are related to location identification. Driverless cars can detect surroundings using a variety of techniques such as radar, lidar, GPS, odometry, and computer vision.
Facebook And Machine Algorithms – Facebook set out to redefine machine learning platforms from the ground up, and to put state-of-the-art algorithms in AI and ML. a “like” in Facebook, the algorithm automatically detects that your face or the face of your friends appear in a photo. Basically, a Machine Learning algorithm learns from the photos you manually tag. Machine learning is essential to Facebook. It helps people at Facebook develop machine learning algorithms that rank feeds, ads and search results and vision algorithms can “read” images and videos to the blind and display over two billion translated stories every day, speech recognition systems automatically caption the videos that play in your news feed, and Facebook creates visual experiences such as turning panorama photos.
Reliable Controls Traffic Patterns – To predict traffic patterns at a busy intersection you can run it through a Traffic Patterns machine learning algorithm with data about past traffic patterns and, if it has successfully “learned,” it will then do better at predicting future traffic patterns.
Distributed Antenna Systems – DAS systems can deploy a Self-Organizing Network (SON). The network can automatically configure and integrate new equipment into the wireless network; something like “plug and play.” The DAS network discovers new components in a system without the need for a technician to manually configure the equipment. The SON can also automatically optimize the wireless network. It analyzes based on data from the system itself. An example of self-optimization is the automatic switch-off a percentage of base stations during the night hours which would then reconfigure to cover a larger area or a significant increase in usage. Finally, the network can self-heal and can identify faults or failures in the network such as failing base stations and automatically compensates and reconfigures the wireless network to minimize the impact.
Machines and systems “learn” via computers,” and the computers learn by managing and analyzing data. The computers are smart enough to recognize patterns, and then predict data and develop algorithms, assessments or “conclusions.” Learning machines are part of the larger “artificial intelligence.” Machine learning is employed in a range of computing tasks where designing and programming explicit algorithms are not feasible. Machine learning is closely associated with computational statistics, mathematical optimization, data analytics, and data mining.
Within the field of data analytics, machine learning, is a method which is used to devise complex models and algorithms that lend themselves to prediction. In commercial use, this is known as predictive analytics. These analytical models allow researchers, data scientists, engineers, and analysts to “produce reliable, repeatable decisions and results” and develop new “hidden insights” through machine learning from relationships and trends.
This level of building automation is not illusory. We will see the first steps of heightened automation and innovation in a range of companies creating new automation systems and new analytic tools which will incorporate IT tenants and platforms. You can also see it in technology companies increased interest in buildings, energy, life safety, and analytics. Enhanced automation is the vehicle to eventually get to the nirvana of providing optimum performance of the building.