Intelligent or Smart?
Published on : Thursday 06-04-2023
Does not matter actually, if at the end of the day, humans are relieved of some work, says PV Sivaram.
Anand has been talking to his seniors at his college. They have told him that most of what he learns about sensors at college is already out of date. He will have to learn everything the hard way, by trial and error, by experimentation. That leaves him a little unsettled. It is a common picture – students imagine the workplace to have strange and novel systems and gadgets which neither they, nor their faculty is aware of. I said to myself, this sort of thinking can only lead to indigestion and insomnia. I must bring him out of this. So I prepared a small lecture on modern sensor systems.
Over the change of millennium, a lot many things have happened to sensors, I told Anand. Many changes are caused by technologies not directly related to instrumentation and measurement. The origin of these changes is due to the following – 1) CPUs are becoming smaller; 2) CPUs are becoming faster; and 3) Wireless connectivity is increasingly available. Combination of these three makes sensors more intelligent.
What is the basic function of a sensor? A sensor should – well, sense a physical quantity like temperature, pressure, flow, current, and scale it in some way and relay it to a central point. The scaling traditionally was 0-20 mA. The corresponding physical values for top of scale and bottom of scale were available in the central point. The basic sensors became smart or intelligent or both.
Is a smart sensor not the same as an intelligent sensor? The two terms are used interchangeably so that people get confused. If they are not the same, then how are they different? Is there any universally accepted definition? Anand is full of questions. I take a deep breath, and say these are somewhat marketing terms and hence lack a precise definition.
An intelligent sensor appears to be nearly the same as a smart sensor. In literature one can find that the intelligent sensor device is one with a capability to perform a self-check on its calibration.
But I will give you a lay definition. We can attempt to distinguish these two classes in different ways – by their structure and components, and by their functionality.
A smart sensor is a normal or basic sensor with added capability to store a defined number of measurement samples, and transmit in digital format on request or at defined cycle. Some more capabilities are auto calibration, plausibility checks, periodic self-diagnosis, and annunciation of faults. There is a list of such features, and every sensor termed as a smart sensor will have some or other of these features.
An intelligent sensor is the sensor that has one or several intelligent functions. The ‘intelligent sensor’ is a self-validating sensor that produces an estimation of measurement value, measurement uncertainty and a discrete valued flag indicating how the measurement value and uncertainty have been calculated. Such a sensor is also called self-diagnosing, self-validating, or self-calibrating.
In modern understanding, a sensor is packaged with the conversion unit like ADC and also a transmission unit. The transmission can be on a two wire configuration where all sensors are connected in a star fashion to the central CPU. To improve ruggedness of communication, a bus architecture is preferred, which needs more intelligence at the sensor level. Having a bus system gives scope for more functions like on-the-fly calibration and check, better error reporting and so on.
Almost like a slogan is the call for Sensor to the cloud. It appears useful in the case of consumer space that appliances and devices might communicate to the cloud. One can think of personal wearables in this context communicating for example health parameters to the cloud. But in Industrial Manufacturing, much data is obtained as a by-product of automation of processes and machines. So anyway the data would be need at the local control level, before getting parked in the cloud. Therefore we are thinking of having data buffering at sensor level.
Anand pops the inevitable question – what of AI? Yes Anand, even if you are a specialist in instrumentation, you will still have an opportunity to work with AI. After all, sensors provide data. And when you are working with data what makes more sense than analysing this data? Therefore future sensors will not just tell what the status of the variable is, but can also provide a guess about what it is going to become.
Will such a sensor be called smart or intelligent? Does not matter actually, if at the end of the day, humans are relieved of some work.
PV Sivaram, Evangelist for Digital Transformation and Industrial Automation, is mentor and member of steering committee at C4i4. He retired as the Non-Executive Chairman of B&R Industrial Automation and earlier the Managing Director. He is a past President of the Automation Industries Association (AIA). After his graduation in Electronics Engineering from IIT-Madras in 1976, Sivaram began his career at BARC. He shifted to Siemens Ltd and has considerable experience in Distributed Systems, SCADA, DCS, and microcontroller applications.
Sivaram believes strongly that digitalisation and adoption of the technology and practices of Industry4.0 is essential for MSME of India. He works to bring these concepts clearer to the people for whom it is important. He believes SAMARTH UDYOG is nearer to the needs of India, and we must strike our own path to Digital Transformation. Foremost task ahead is to prepare people for living in a digital world. He is convinced that the new technologies need to be explored and driven into shop floor applications by young people. We need a set of people to work as Digital Champions in every organisation.