Loan Form

Total Productive Maintenance is a useful approach using which you can streamline your asset maintenance activities and enable the machine operators along with the maintenance teams to be equally responsible and carry out regular checks and precautions to avoid major breakdowns or downtime of the assets in the manufacturing plant. The concepts of TPM and how it helps in asset management are explained in detail in the following article: Drive Total Productive Maintenance with Digitalization Though TPM provides the approach of streamlining and continuous improvement of asset maintenance activities, you can actually make the processes more automated and intelligent infusing AI and ML technologies into it. Let’s take the example of the asset maintenance process, where three key personas are involved as below: Asset Reliability Engineer: Needs to understand the performance of the asset and take proactive decisions to maintain it minimizing the downtime Asset Maintenance Planner: Need to plan the maintenance activities and schedule with the relevant maintenance technicians Asset Maintenance Technician: Performs the maintenance on the machine replacing spare parts or carrying out regular maintenance activities. Personas & Key Activities for Asset Maintenance Process Intelligent Use Cases for Asset Reliability Engineer The Asset Reliability Engineer needs to monitor the asset and detect any issues proactively to avoid major breakdowns and ensure the reliability of the asset. To aid the asset reliability engineer, some of the key enablers can be continuous asset condition monitoring and predictive analytics for asset health and performance. To enable these, the asset performance data from its PLC and sensors need to be collected and analyzed after contextualizing it. Depending on the asset type it may be different parameters such as vibration, temperature, power consumption, etc.  The approach to collect and contextualize the asset parametric data is explained in the following article along with how modern architectural concepts such as Unified Namespace can be leveraged for the same: Leveraging Unified Namespace for Asset Management. After collection, storage, and contextualization, the feature set or the parameters applicable for specific analysis need to be determined from the data. Based on that, the condition rules and the predictive models need to be determined to be used to fit the data and provide the relevant predictions.  It also involves training the model with historical data sets which need to be collected and stored for model training. This might be an iterative process to build or select the right model or algorithm.     The predictions can be on the anomaly of the data to determine any potential issue based on the operational parameters of the assets or remaining useful life prediction to determine when the asset breakdown may happen next. Once the insights based on the conditions and prediction start coming in, the maintenance process to create the maintenance notification and alert the asset reliability engineer is triggered automatically. The Reliability Engineer can do the root-cause analysis based on the data that are already collected for the machine performance and initiate early and preventive maintenance to avoid larger breakdown issues. While doing the root-cause analysis he can get the information related to the earlier failure and maintenance of that specific machine in a concise format as insight and recommendations. If a maintenance need is determined by the root-cause analysis the maintenance work order is created to carry out the maintenance work. Thus using the predictive and condition-based analysis of machine performance data, the asset reliability engineer’s activities are automated and made more intelligent to take proactive action even before a breakdown issue happens to a machine. Intelligent Use Cases for Maintenance Planner The Maintenance Planner gets all the different work orders, scheduled maintenance plans and maintenance requests for different machines for the work area or plant he is responsible for. Based on the different work orders and the maintenance technicians available at a specific shift or day, the maintenance planner has to effectively plan the maintenance schedules to optimize the work and schedule. The planning and scheduling is a tedious process that needs to consider different factors such as technicians’ skills, availability, spare parts, etc. Optimization algorithms can be used make to an optimized plan considering the available resources. Based on the input data and the trained machine learning algorithm, the Maintenance Planner can view the maintenance schedules as proposed by the optimization model and can make changes if needed. For each of the maintenance tasks, the maintenance technicians are proposed by the algorithm and the planner can either accept the proposal or change as needed. Additionally, the maintenance planner can also view the Failure Mode and Effect Analysis (FMEA) to understand the types of failure of the specific assets and their effects to determine its criticality which can be also a factor considered for the planning. Intelligent Use Cases for Maintenance Technician Once the maintenance process gets triggered based on the prediction of asset health, the work order is created and assigned to the maintenance technician. The maintenance technician on getting the task based on the work order goes to the machine to carry out the maintenance activity. However, the maintenance technician may need to refer to SOPs and manuals for the equipment and processes he/she may work on. It isn’t easy to check large documents during the actual maintenance work at the field or at the equipment location. To solve this problem, a GenAI-based intelligent chatbot can be used to consume different types of documents for the machines and processes as those are available and provide concise answers for any natural-language-based questions that the maintenance technician may ask. This is enabled by a RAG-based GenAI model which can consume unstructured data as documents and tokenize them to provide relevant and contextual information based on natural language queries. The documents fed to the GenAI model may have detailed descriptions of the equipment and process, but the answers provided based on specific questions can be very specific with steps to follow as a field technician. Thus the maintenance technician can quickly get the information needed during the work and need not have to search in large documents for relevant information. Conclusion Machine Learning models for Predictive Analytics, anomaly detection and planning optimization, as well as GenAI-based natural-language chatbot can transform the asset maintenance process infusing intelligence and automation and making the process faster and better. The below diagram shows the different use cases for Intelligent TPM. Intelligent TPM Use Cases If you want to know more about how you can utilize the intelligent and AI-based functionalities for your manufacturing and maintenance operations check out Incture Cherrywork Intelligent Maintenance & Operations (IMO) solution, which provides a platform for Total Productive Maintenance integrated with your SAP S/4HANA, enabling real-time asset monitoring, condition monitoring and predictive analytics, GenAI Chatbot and easy integration with business processes and systems. Cherrywork Industry 4.0 suite of digital applications have digital twins that enable organizations to optimize asset operations by providing real-time insights, predictive capabilities, and simulation capabilities. They help improve asset performance, reduce maintenance costs, enhance safety, and support data-driven decision-making throughout the asset lifecycle Read about Industry 4.0 Portfolio https://youtu.be/9kS6lFj_ygo Would you like to do the same for your organization? If yes, then reach out to us at talk2us@cherrywork.com

Assets refer to machines and physical objects, which are important aspects of the manufacturing industry mostly used in factories to carry out production activities. Often these assets consist of complex machinery and its operation and performance depend on several factors, which need to be monitored and may be adjusted as needed. Also, the assets need maintenance activities to fix problems, replace spare parts, or do periodic checks and servicing. Usually, asset maintenance can be done using two different approaches broadly as below: –          Reactive Maintenance:  Initiate and execute maintenance when an issue is identified on the machine to fix the same with or without replacing spare parts as needed. This results in unplanned downtimes and major breakdown issues. –          Proactive Maintenance:  Periodically check and execute maintenance activities on the machine to ensure the machine is performing optimally. This helps in minimizing downtimes and breakdowns.   Approaches for Improving Asset Management Though proactive maintenance is advisable, certain breakdown or reactive maintenance might be still needed for unforeseen issues. In both the maintenance approaches mentioned above, the monitoring of equipment conditions and its operating parameters and tracking performance is one of the key aspects, that help in understanding the issues that the equipment might be having, so that some action can be taken proactively. The monitoring of the asset condition to determine issues that may need maintenance can be of the following approaches: – Condition-Based Maintenance: In this approach certain parameters that can indicate the condition of the asset are monitored continuously to determine if there is a maintenance need. This is enabled by developing certain business rules based on the machine parameters that are being monitored, and when the rule is satisfied based on the parameter values recorded, a maintenance action is triggered. The rule when satisfied indicates that there is some potential problem with the machine that needs to be fixed. – Predictive Maintenance: In this approach, the asset parameter values are processed through machine learning models which are pre-trained with historical data for machine failure and anomaly. The machine learning models by analyzing the parameter values determine the pattern and probability of failure or anomaly in the data which indicates a potential issue in the machine, that may happen in the future. In both the above approaches the operational data from machines need to be fetched in real-time and analyzed to determine the condition of the asset. Below are some of the key aspects that need to be considered to determine the parameters to monitor and how to get its values in real time: ·         Define the critical data collection points and parameters needed from each machine. ·         Validate the parameters based on PLC model, PLC make, PLC port availability, and connection protocol supported by the machine. ·         Assess the sensors needed in the machine/PLC to get the relevant parameters. ·         Assess installation feasibility for sensor mounting on the machine and outage time window for installation of the sensor. ·         Implement sensors at each machine to capture the process parameters. ·         Implement Plant Gateway with MQTT/OPC support to all sensor tags for read and write back (if needed).   The above approach will fetch the parameter data from machines directly through the PLC connected to it or through the sensors. Moreover, for some machines, the parameter data may be already collected and stored in a Plant Data Historian or MES from where it can be fetched. The asset parameter data should be processed by business rules or machine learning algorithms to determine the condition of the asset and accordingly determine and trigger the maintenance action. Unified Namespace for Simplifying Asset Management For asset management, you may also need to monitor the condition of the assets based on their operating parameters as well as KPIs to understand the performance of the assets. In a typical factory you may have multiple assets and many of those are related to each other semantically. Also, you need to monitor the condition of the assets based on different parameters and KPIs, the data for which may be coming from different data sources such as PLC, Historian, MES, ERP, etc as mentioned earlier. For monitoring and processing the data for the different assets, you need to have a semantic model to define the relationship and hierarchy of the assets and the gateway to process and monitor the data and the KPIs through a single platform. Having different systems in the landscape with heterogenous data sources it is always a challenge to achieve this, and we end up developing the monitoring and data processing in silos. Unified Namespace is a new concept that helps to simplify asset monitoring and data processing for further analytics and action. Unified Namespace entails two important aspects as below: –          Enables a semantic model of the asset structure across the plant and can be across plants in the organization. –          Provides an easy interface to receive and collect data from heterogeneous data sources for specific assets and semantically links them in the asset hierarchy model.   So Unified Namespace is a semantic model of the asset hierarchy that can contextually link its data and KPIs coming from different data sources and systems and provide a unified view of the asset structure to monitor its performance and operational parameters. Unified Namespace should use MQTT (Message Queue Transport Telemetry) as the protocol to exchange messages with the source and target systems or data sources, as it is a generic messaging protocol specially designed for IoT communications. Most of the data sources for the asset parameter and performance data may be PLC, SCADA, Historian, or legacy IoT devices which should be able to communicate using MQTT protocol either directly or through plant gateways, which collect the data from multiple PLCs, SCADA and can send the data as a single source. Enterprise and execution systems such as ERP, MRP, WMS, MES, etc can also publish the messages for different information such as current order, inventory, yield, etc. using the MQTT messages for the specific node or asset. The Unified Namespace can be set up using an MQTT broker such as HiveMQ, Eclipse Mosquitto or Advanced Event Mesh in SAP BTP which can receive and send messages using MQTT protocol. You need to define the MQTT topics to send the messages from the data sources based on the hierarchy of the assets. You can design the asset hierarchy using a simple model such as Site-> Area -> Line -> Machine -> Cell. So the topic to receive the data that are relevant at the site or plant level for plant code 1000 will be /UNS/1000 and the topic for the areas under it will be UNS/1000/Area1/, UNS/1000/Area2, UNS/1000/Area3, etc. Similarly, to send the message for a production line Line1 under Area1 will be UNS/1000/Area1/Line1 and to the machine1 under it will be UNS/1000/Area1/Line1/Machine1, and so on. Unified Namespace or UNS is a simple event fabric or mesh that is edge-driven and provides the single point of truth and visibility across your entire asset hierarchy and plant. Unified Namespace as a Single Data and Event Fabric for Asset Monitoring and Analytics This not only provides the ability to monitor the asset performance and operational data but also enables easy integration across different systems avoiding point-to-point integration. Different subscribers can subscribe to the topics for specific assets and can get the data in real time when published to them. Then that data can be processed and the processed data or the KPIs can be published back again to the same topic as a different parameter. E.g. the SCADA may publish the machine counter, stoppage, and rejection data based on which the OEE can be calculated by the MES system that subscribed to it, or the remaining useful life (RUL) of the asset can be predicted by a predictive analytics system by getting the operational parameters of the asset from its PLCs. The Unified Namespace can be also treated as a digital twin for all assets across the hierarchy which can display its parameters and operational data in near real-time.    Conclusion Unified Namespace as explained above simplifies the data collection, monitoring, and data processing for assets helping in improving and automating the asset maintenance activities by aggregating data from different sources and contextually linking them.   If you want to know more about how you can utilize Unified Namespace for your manufacturing and maintenance operations check out Incture Cherrywork Intelligent Maintenance & Operations (IMO) solution, which provides a platform to realize Unified Namespace integrated with your SAP S/4HANA, enabling real-time asset monitoring, condition monitoring and predictive analytics and easy integration with business processes and systems. Cherrywork Industry 4.0 suite of digital applications have digital twins that enable organizations to optimize asset operations by providing real-time insights, predictive capabilities, and simulation capabilities. They help improve asset performance, reduce maintenance costs, enhance safety, and support data-driven decision-making throughout the asset lifecycle Read about Industry 4.0 Portfolio https://youtu.be/9kS6lFj_ygo Would you like to do the same for your organization? If yes, then reach out to us at talk2us@cherrywork.com