Learn how our customers leverage Sight Machine to improve their manufacturing productivity
Sight Machine integrates with data from all your existing technology, like historians and MES, so you don’t need to worry about standardizing software to start gaining productivity improvements immediately.
Sight Machine is purpose-built for manufacturing professionals: operators, process engineers, continuous improvement leaders, and plant managers. The platform equips each with data superpowers, driving real-time continuous improvement.
Toros Tarim is the leading manufacturer of fertilizer for Turkey and neighboring regions. This large scale process requires a huge industrial chemical complex with each step in the production pathway (sulfur acid to phosphoric acid to ammonium diphospate for example) being dependent upon the former. Downtimes are extremely costly, with potential to impact all areas, including the on-site co-generated electricity whose surplus also bolsters the Turkish electrical grid. Toros approached Sight Machine as part of their digital transformation and lean journey with the clear expectation to start at building a contextualized data platform of all their data, facilitating an holistic view of their process network, before moving to data visibility and automated dashboarding of reports and key performance indicators (KPIs).
The next part of the journey is now underway as Sight machine and Toros partner to use their data platform to explore advanced analytics such as predictive and AI, process optimization (including for sustainability and emissions management), and maximizing plant reliability / minimizing asset downtime. This project was implemented entirely remotely during the COVID-19 pandemic and was possible because of the unique way Sight Machine is able to rapidly ingest and use automated tool sets to transform and contextualize tens of thousands of data fields in parallel.
Carbon Revolution is as innovative and disruptive as a technology can be. They fabricate carbon fibre wheels (rims) that are both lighter and stronger than current aluminum constructions. While these concepts started with sales to niche manufacturers such as Ferrari, they are now becoming commonplace options on more mainstream manufacturers. As production ramps up and concomitantly unit cost drops these will undoubtedly become the new normal over time, just as aluminum rims did to steel decades before. Carbon Revolution is using Sight Machine to provide an end-to-end view of its fabrication process in real time. For this fast paced company, instant access to data is paramount as it rapidly grows. Track and trace of a wheel to understand weaknesses in quality and fabrication techniques needs expedited root cause analysis.
Sight Machine provides end-to-end visibility by automating all of the data collection, cleaning, aligning, and joining, even for out of order records. This frees up engineers to be refining their processes for growth and not using their valuable time hand-prepping data for hypothesis testing. With all of their data at their finger tips Carbon Revolution aims to retain their agility and speed as they scale and be at the forefront of using their digital data.
Data was isolated in disparate systems, making it difficult to perform data-driven analyses of quality and performance problems.
Sight Machine integrated quality data, process, and sensor data from the production line enabling regular visibility, problem-solving, and data-driven Continuous Improvement across a network of plants
This dairy producer used Sight Machine to optimize yield in fermentation and separation processes by analyzing the processes, providing alerts as to optimal times to run and stop the processes, and automating recommendations for the decisions holistically across multiple assets.
Sight Machine enabled end-to-end traceability of each batch and modeled optimal times for critical processes so as to increase both yield from the processes and throughput.
The platform allowed the manufacturer to increase output by optimizing production for the entire line vs individual processes.
Corrugated paper plant had trouble knowing which specific process parameters drove up scrap and customer claims. In addition, plant wanted to know when and which SKUs resulted in driving peak energy consumption.
Sight Machine integrated process data, energy data, quality data and customer claims data to provide integrated models that were then utilized to run advanced analytics including AI/ML algorithms.
AI/ML yielded insight within 2 weeks about causes of quality issues that had previously eluded company data scientists. Similarly, connections between process variation and energy use and defects and process variation represented new insight into mission-critical questions.
This manufacturer had extremely tight control over each process step. But with more than 90 steps, subtle interaction effects between each step were challenging to see.
Sight Machine provided a way to associate quality data throughout the entire process as well as trace parts and perform multivariate analysis. This enabled them to analyze variation impacts on quality throughout the entire production process.
Within the first months, the company achieved a significant reduction in scrap related to quality problems. They use Sight Machine as a single source of truth to understand quality and process data across 90 different operations.
Asian Paints had capacity constraints in highly automated regional batch chemical plants. They could not solve for global constraints in a complex batching system of 100s of individual assets with their current data.
Sight Machine continuously streamed and contextualized data from different sources at both a system and asset level. This enabled instant visualization of individual assets with the line as a system to balance utilization and identify key bottlenecks.
Reduced cycle time by 7% at first factory. This was achieved in two months and driven by operators using Sight Machine in company-sponsored hackathons to diagnose and solve problems. The improvement in cycle time represented a $7M increase in throughput. Additional outcomes are being driven across the network of factories now.
OEM body assembly involves 100s of robots, where intermittently a catastrophic failure would create costly line downtime. Operators had a manual system for maintenance, which was difficult to keep operationally supported, and were seeking a predictive analytic for robot downtime.
Sight Machine automated the operational maintenance alerting and built a predictive maintenance solution that led to increased effectiveness of maintenance scheduling.
Sight Machine enabled the manufacturer to monitor anomalies in torque sensor data and detect patterns correlated to failures enabling the servicing of robots likely to experience failure reducing manual inspection 90%.
The facility was not able to efficiently utilize its raw material causing higher scrap and rework.
Process and Quality data was leveraged to run correlation analysis and perform setpoint enhancements.
Projected savings of $2.5mm per year at the first plant served, resulting from better Raw Material Utilization improvement across 4 lines.
Steam usage had been high on a paper machine coming up from an outage with no identified root cause.
Variance analysis and correlation analysis identified a single valve that was found to not be 100% open. Root cause was found and corrective action was taken for a valve cut back.
This single insight and the corresponding best practice developed from it – one of dozens generated annually – yields millions per year at the enterprise level in steam savings and increases in production rate.
As part of the initial steps in a conversion from manual to automated processes and a parallel shift in costing processes with contract manufacturers, this manufacturer sought real-time visibility across a wide network of plants.
Sight Machine implemented across multiple contract manufacturer plants, and enabled previously unattainable visibility and asset management.
This manufacturer confirmed that in just the first year, visibility alone into assets was worth 2x program cost.
Despite having data in many forms, it was not possible to identify causes of scrap.
Sight Machine identified the causes of defects by analyzing voluminous process data.
Small adjustments in materials temperature resulted in 18% reduction in scrap.
High-speed medical device line had more than a thousand alarms per shift, but could not identify alarm sources and the root cause of micro-downtimes and process variations.
Sight Machine contextualized and continuously streamed data from 12 different data sources to enable an AI application that identified causes of micro-stops across a 300-yard long automated line.
Sight Machine’s platform enabled the site to make real-time decisions. Site engineers and operators used results from the AI application to prioritize problem-solving efforts. The site reduced scrap by more than 50%.
Using traditional quality procedures, in-line quality issues in die casting and machining processes were impossible to resolve across 3 plants. Serialization varied from plant to plant, and data could not be combined.
Sight Machine integrated process and part data from multiple sources and facilities to empirically represent and analyze the entire production process with a single Data Foundation. This enabled traceability and provided an analytical foundation across processes.
The OEM was able to identify the root cause and reduce rejects by 25%.
Medical device plants depend on CNC machines and downtime is costly. Variations in operator practices make standardization difficult.
Sight Machine modeled the production line, consisting of many different CNC machining operations. Analysis on modeled data provided insight to improve uptime by 30%.
Large reduction in downtime alleviated planning and scheduling constraints.
High material waste, cost and low productivity due to lack of process instability in the extrusion production process.
Sight Machine integrated PLC, MES and in-line test data to identify causes of process variability. The platform’s statistical process control analysis was used to proactively monitor output.
After implementing SightMachine this company saw a 25% reduction in scrap plus better planning and scheduling capabilities.
The lag between the causes of quality issues in a furnace and the emergence and detection of faults in glass 3 days later, makes it difficult for glass producers to manage yield and results in glass being returned to the furnace at every glass company. This results in increased energy use when glass has to be re-melted to remove defects.
By continuously analyzing 45 furnace parameters, Sight Machine predicted increases in fault density up to three days in advance with an extremely high degree of accuracy.
The furnace analytic predicted 78% of all defects from the entire process.
Manufacturer was looking to improve quality and efficiency of a new, highly automated line.
Sight Machine contextualized real-time data to identify cycle time variability during setup. Visibility application provided a view of defect types and sensor readings by machine to identify opportunities for efficiencies.
Productivity and efficiency nearly doubled as Sight Machine enabled rapid improvement.
The company used Sight Machine to balance Takt time across high-speed, automated production lines. Sight Machine enabled a substantial improvement in yield.
Sight Machine enabled the client to accurately capture and continuously visualize Takt time at every station on multiple lines, thereby identifying bottlenecks that arose from slight miscalculations in the machine set up.
For a maker of construction mining and forestry equipment, weld integrity is of paramount importance. This manufacturer’s welding process experienced multiple unplanned stoppages.
Sight Machine provided a scalable solution to aggregate, store, analyze, and visualize data from hundreds of robot welding machines. This allowed concise data blending, visualization, access, and product evaluation.
Visibility into metrics, including availability, downtime reasons, and key performance indicator, E, where E = weld deposit (kg) / cycle time (hr). Analyzed 60K cycles across the fleet of robot welders to gain correlated insight into the cause to accelerate corrective actions, reducing downtime and bottlenecks.
Identified insights to reduce downtime events resulting in 16% throughput improvement.