Industrial IoT: Challenges in PoC to Production Implementation at Scale
It's no secret IoT evangelists are frustrated these days. Not too many PoC are going to production level deployment. While extracting solid value proposition is one issue, the other big issue that is hurting production level IoT deployment is how to manage software, firmware and connectivity of so many sensors and systems? The technology world does not have any precedent of such scale and complexity that needs to be managed within a meager budget to meet ROI.
Several studies and analyses have revealed that the success factor on this IoT journey, much depends on the foresight in careful selection of the infrastructure (tools) to design and support a robust and reliable system. Together with trusted data source(s) and controlled and strong analytics, there should also be tools for predictive and preventative maintenance, reduction of downtime, assurance on quality and real time risk management. However, not many PoCs progress to a feasible production system, as the proponents fail to see the big picture. There is a tendency to connect few sensors and devices and use the raw data to show some useful analytics. The availability of Azure IoT PaaS cloud or AWS helps create a secured and connected IoT. It may be a good beginning but lack of foresight in the application and thus, selection of supporting tools or infrastructure, invariably result in challenges which become difficult to overcome in later stages.
One notable challenge is scalability of the product or system. Limitations become apparent as the number of sensors and devices exceed, (say > 250) in the IoT system. Connectivity becomes a major issue as every device has to be brought up to same firmware/ middleware version. The challenges and limitations compound as edge computing has become the norm of the day. One has to update the algorithms in the device as well, using Over the Top Architecture (OTA).
Then management of the Application Program Interface (API) for any device, any cloud service needs to be monitored and managed as increasing connections potentially give rise to hundreds and thousands of end point possibilities resulting in failure. This requires a robust and automated management system for API and log using a “Watch Dog” tool.
Much is dependent on the quality, reliability and availability of the data silo for proper value creation to any system or end user. Stake holders would be required to trust the data quality and the compatibility of the data sets. If sensors are the main data source, then with increasing numbers of sensors, the management of calibration and recalibration of the sensors becomes a major task. Sensor data is useless without assured calibration. IoT system has to manage and control the life cycle of the sensors and their calibration throughout the lifecycle of the sensor in order to produce trust-worthy data.
Intensive edge computing and analytics system need assurance on quality, connectivity and reliability. These analytics and algorithms then need simulated or emulated failure/alarm data for testing and ascertain that they work well in distributed computing environment.
Azure and AWS IoT PaaS cloud architects are aware of all of the above-mentioned issues. But in their attempt to address these issues they have succeeded only to a limited extent. For example, every IoT PaaS cloud offers connectivity management. But often, that is not enough because in reality IoT system connectivity can be a mix of many connections. A competent connectivity manager must track all the connectivity levels with their Tx/Rx level, connectivity logs and must be able to build a Machine Learning based model for connectivity diagnosis and API management as well. The end result, automation and machine learning will not only be applicable to IoT application, the whole IoT infrastructure has to be managed by automation and machine learning too.
Why MachineSense:
MachineSense is a disruptive technology company with strong roots in the machinery and manufacturing sector. Our affordable technology is focused on predictive maintenance and analytics for industrial machinery, components and infrastructure systems including pumps, compressors and electrical supply.
MachineSense uses flexible deployment models, proven diagnostic instruments, sophisticated software, and unmatched analytical expertise to deliver sustainable, scalable, and cost-effective condition-based maintenance and monitoring programs. The company’s offerings enable customers to implement comprehensive predictive maintenance and monitoring programs that ensure asset availability, maximize productivity, and reduce total maintenance expenditure.
The following figure(s) 1 and 2 show the basic features and architecture of the system. To note: MachineSense uses sub-sampling techniques for sensor sampling and inductive edge for increased batch size. This results in the Artificial Intelligence (AI) AutoML to run inside the machine.
Figure 1
Figure 2
Machinesense Production system developed all of these internal tools needed as barriers for the challenges stated above. They are called necessary and critical IIoT plugins, (see figure 3 below) and now MachineSense is making them available for any IoT company that is attempting to migrate from PoC to a robust and scalable automated production level system.
Figure 3
As evident in the figure 3 above, the six necessary and critical plug-ins around the Crystal Ball (main AI analytics tool) will ascertain a robust and trustworthy infrastructure. Incorporating such infrastructure, will enable a promising IoT concept to successfully mature to a production level. MachineSense, in pursuit of promoting service as opposed to product, offer free consultation and would welcome any discussion with IoT proponents with the commitment of offering partnership in this venture. Call us at +1-443-457-1165 or email us at info@machinesense.com to start a conversation with our experts.
