Over the last few years, we have been told that data is the key to Smart, Industry 4.0 manufacturing. We have each allocated resources creating various data exchanges between machines and solutions, building in most cases, a rather dank looking lake of data, so, now what? Many manufacturing operations have been facing the pain, without yet, the gain. What were we not told? What do we need to do in order to use all of this precious data?
Happiness is gained where expectations have been aligned with reality. In many cases, the real expectation of what comes after data collection was never really explained, leaving many in the position of being driven purely by their own expectations, based on snazzy, graphic-laden demonstrations by solution providers, keen to draw customers in. The reality in most cases however, is that a great deal of work is necessary to create value from that data, which does not represent a sustainable model. There is a history of countless brilliant industrial engineering projects, that initially make a massive difference to the operation, but after time, once the problem appears solved, drift into obscurity, as the resources to sustain them lose priority to other matters. The sustainability of solutions, the automation of problem avoidance, is paramount, which should be the decisive factor when considering digital solutions. The assurance of this is achieved in three key stages:
- 1: Connectivity
- 2: Ontology
- 3: Action
Connectivity was just the start, and let’s take a moment to confirm where we are. IIoT-based connectivity is essential, as it is designed to exchange data from one to many, and from many to one. It is imperative that IIoT data has a clear, defined meaning. Data represents a known condition or defines an event that has been experienced. Though several legacy standards, such as OPC-UA and MT Connect, and hundreds of propriety methods exist, the IPC Connected Factory Exchange (CFX) standard uniquely exchanges IIoT data in a true plug and play environment, with a fully comprehensive defined language. This is a sustainable example, as new equipment can be seamlessly integrated into the operation, without any change to information-based solutions, meaning zero costs of deployment, no delays, no need for middleware etc. Connectivity with defined language is essential in order to get successfully and sustainably to the second stage.
Ontology is a data model populated by software algorithms that connect data-points derived from IIoT messages. As equipment knows only what happens in the context of its own instance, the IIoT-based MES platform uses built-in ontology to create the context of the data-points in many different ways, including for example, to confirm and enforce correct product routing; to control production appropriately when a quality risk is detected; to identify opportunities for optimization of the production flow; orchestrate Lean material management; or simply provide dashboards and alerts that bring the Smart holistic view of manufacturing to the attention of those who then take actions. Rules within algorithms that form the ontology of a solution also need to be sustainable, based on the standard data model from stage 1, such that any change of factory configuration, customer or product type, will not require re-work of the software, or worse, cause ineffective decisions to be made whilst no-one is the wiser.
Actions taken as a result of data analysis are both automated and interactive. Many decisions, such as the timing, selection and delivery of materials, the monitoring of potential defect triggers etc., become completely automated and trusted, whilst opportunities based on complex conditions are shown in live reports for the human ontology to process. As time goes on, more and more of these decisions become automated. Either way, all decisions are based on holistic data, set into the context of the whole operation, such that decisions are made with complete visibility of the current status, and extrapolation to expose consequences, beneficial and otherwise. Sustainability of data and ontology brings trust in these decisions, true data-driven manufacturing.
To learn more about these three stages of Industry 4.0 digitalization, and how Aegis FactoryLogix achieves sustainability for data-driven manufacturing, please read our white-paper, “From Connectivity To Context”, powering data-driven industrial transformation in your factory.
