Technology and best practices to turn our middle managers into data citizens.

Perfect low-code platforms to capture more relevant data and improve efficiency.

Objectives:

• To help establish fully interconnected and digitised smart factories
• Data to be extracted from legacy machining data/throughput
• Data within legacy machines/systems can integrate with external condition monitoring systems into one complete dashboard

Desired Outcomes:

• Key users are management and shop-floor personnel.
• One current method to obtain data from legacy machines is to introduce sensors in a non-invasive way to extract data for visualisation and analysis.
• However, there are still crucial data of these legacy machines or data from their Manufacturing Execution system that are still not retrievable.
• The limitation to the add-on sensors is that they cannot generate data to the needs of business owners fully.

Current Limitations:

• Costly and unjustifiable to replace existing legacy machines/systems (e.g. CNC/laser cutting).
• Lack of standard IoT communication protocols like MQTT and OPC UA.
• External sensors can only fulfil a partial wish list of business owners – mainly on reducing downtime and saving wastage costs.
• Crucial data like cutting speed, machine uptime, and throughput are also needed for OEE.

Objectives:

• The purpose of i4.0 implementation is to increase productivity or promote process transparency.
• To convince and attract the decision-makers / top management.
• Provide a cost-benefit analysis in this i4.0 transformation process to address and educate the benefits of i4.0 implementation and that it should be of high priority.
• Lower the cost of implementing new technologies.

Desired Outcomes:

• The reasons for the reluctance to bring operations to the Internet/Cloud are often security and cost.
• There is currently no one-size-fits-all solution that can be easily applied to companies for a large scale internal review to produce the cost-benefit report for consideration to move operations to the Internet/Cloud.
• There is also no ability to effectively visualise these benefits and present data coherently to address cost and security concerns. 

Current Limitations:

• i4.0 implementation can consist of various technologies/services, which can be costly overall.
• Despite the time and effort spent, the solution proposed may not yield positive results or be up to the business owner’s expectations.
• No ability to effectively visualise benefits – business owners cannot gauge the results / ROI.
• Difficult for a large-scale internal review to produce a cost-benefit report.

Objectives:

• Automate tasks assignment and prioritisation based on technical requirements and technicians’ profiles.
• Optimise execution with a grouping of tasks to improve efficiency.
• Predict the demand vs supply and forecast the overtime planning.
• Identify the technical competency gap among technicians.

Desired Outcomes:

• Over 34 technicians with different skillsets for operation and engineering tasks are complex and vary widely, from logistical units collection to equipment setup.
• To have a one-stop solution platform between managers, engineers and technicians.
• Interactive solution on a mobile device for technicians to receive notifications and report efficiently.
• If the execution of tasks can be on auto-pilot mode and optimised continuously driven by data analytics, this would significantly improve work efficiency.

Current Limitations:

• Engineers need to manually book the necessary resources, including equipment and technicians’ availability.
• Independent systems are used to check and book different resources, e.g. equipment booking, technician scheduling, engineering samples, etc.
• Manual and tedious effort on engineers to communicate, cross-check, and set priorities with managers and teammates.

Objectives:

• Establish integration tools for data extraction, transformation and loading.
• Develop AI data processing platforms.
• Scalable for operations implementation.
• Enable domain experts to perform data analytics independently.

Desired Outcomes:

• Focus on predictive maintenance for automated material handling equipment.
• To package prototypes into a suite of recommended platforms and tools. 
• Develop AI algorithms related to the project scope. 
• AI SMART Discovery: Demonstrate capability for prototype analytics for the layman.

Current Limitations:

• Problem centric data analysis: Engineers must analyse a voluminous amount of data for actionable insights through various data sources (OEE, yield, product data & recipes, machine alarms, etc.).
• High effort, time and subject matter knowledge are required for effective cause and effect analysis.

Objective:

• Improve vehicle build quality using vision systems, AI & Machine Learning algorithms.

Desired Outcomes:

• Delivery of visually defect-free vehicle to the customer.
• Inspection of fit and finish, painting defects, missing parts and mismatch of parts as per checklist.
• Quantifying in terms of AQI score as per the provided standard.
• Statistical analytics using the obtained data and escalation in case of deviations as defined.
• The system needs to be capable of connecting defects to the stage where the defect is happening and sending alerts/escalations.
• The system should be able to give results immediately after inspection, clearly indicating the zones and places where visual defects need to be corrected.
• The system needs to interact with the ERP system to understand the variant of the vehicle to inspect. 

Current Limitations:

• Skilled men are deployed in the line to inspect the finished vehicle and give dispatch clearance on every shift.
• Inspection needs to be done within the cycle time of <20 seconds on a moving conveyor.
• Inspection is subjective, and perception varies between inspectors and between shifts too.
• Data is manually recorded and not in a form for consumption or analysis.
• Data is entered manually in SAP.
• Occasionally, errors escape to the next stage due to monotony in the inspection.
• More information on existing system constraints:
• Type A and Type B errors – disagreement between man and machine
• Unable to cover all checkpoints (220) in < 20 seconds.
• A vehicle needs to be loaded in a particular orientation to get better images for giving ok and not ok decisions – loading difficulty to an operator to be avoided.
• Difficulty in getting repeatability in results due to allowed variations in fabricated parts.
• The camera cannot clearly differentiate minor dust particles (>1.5 mm) and colour shade differences.
• Some defects will come once in a while, and it is challenging to teach the system frequently.

A platform to synchronise different transportation, yard & warehousing systems to optimise resources & unlock efficiency with speed.

Solutions that consider customer demands that may change rapidly (such as delivery destination, delivery window) to improve logistics efficiency.

Objective:

• To improve the transfer efficiency of robot painting.

Desired Outcomes:

• To improve efficiency by 30% through optimisation of the robot programme and spray parameters using vision system based AI/ML logic:
• The vision system fitted on the robot scans the painting jig and captures the image of the parts to be painted.
• Robot path to be generated using AI/ML algorithm based on the image data captured by the vision system.

Current Limitations:

• Two-wheeler parts are painted using a robot painting process, with the parts moving on a conveyor.
• Robot programme and spray parameters are developed by trial and error process based on the shape of the parts to be painted.
• It is an iterative process of modifying robot parameters and checking the paint film built on the parts after baking.
• This results in lower paint transfer efficiency – paint transfer efficiency is the ratio of paint deposited on the part to the total paint sprayed.
• Transfer efficiency for parts is measured by weight method, i.e. weight of the paint on the component to the total paint sprayed from the robot gun.
• The above process is highly skill-oriented (a skilled robot programmer is needed)
• Wide variety of parts to be painted in a single paint plant.
• Robot programmes cannot be optimised for each type of part, as it is a manual process of creating the robot programme.
• Trials and verification are time-consuming as paint thickness can be checked only after parts are baked in the oven.
• High skill requirement for engineers carrying out robot teaching for the painting process.