Like in many industries, we are undergoing a data revolution in the mining, metals and materials (MMM) sector. Historically, MMM decision-making was based on amalgamating raw data across disparate data sources and sites. This typically required manual data collection, cleansing and contextualization using spreadsheets to make sense of process information. These exercises were cumbersome, time-consuming and error-prone. Adding to the challenge, these analyses were often difficult to curate for accuracy, leaving multi-million-dollar decisions at risk.
Due to limited subject matter expert (SME) time and the complexity of manually gathering, cleaning, stitching together and organizing data, MMM teams often steered clear of these critical analyses. And the experienced engineers and analysts responsible for these types of tasks are only becoming scarcer.
To address these challenges, the MMM industries are adopting automated solutions to connect, cleanse and analyze time series data from multiple sources. Advanced analytics solutions provide these capabilities, connecting live data from these disparate sources in a single platform, bridging process data in near-real time and enabling SMEs — engineers, operations managers, analysts, data scientists and more — to quickly derive operational insights with full contextualization. By deploying these sorts of solutions across their enterprises, MMM companies are accelerating their critical corporate initiatives and achieving faster business outcomes.
Cross-industry challenges
Before the MMM industries can fully transition to a culture focused on leveraging operational data and advanced analytics, they must address existing challenges, including SME time available. Engineers across these industries are accustomed to reactive firefighting, which reduces the time available for innovation and process optimization. In the words of Johanness Sikström, senior development engineer at Boliden, “Having time to focus on the right problem” is rare. When personnel do get time to focus on these efforts, the spreadsheets and other antiquated tools used for data analysis hamper progress and dampen morale. Additionally, retaining experts in the current job market is more challenging than ever before. As highly skilled employees retire or leave roles they held for many years, companies are searching for seamless ways to scale process knowledge and maintain productivity. Furthermore, recruiting new talent is difficult because these industries are competing with tech-focused businesses also looking to hire graduates with the unique data and analytics skills required to fuel digital transformation in the process manufacturing space.
Mining environments must carry out lean operations around the clock, often with only a small group of experienced engineers to solve complicated issues with minimal capital investment. Also tasked with leading process optimization efforts, like improving recovery yield despite being hit with lower ore grades, the engineers in charge can only do so much, making it impossible to scale operations beyond certain limits. Fortunately for the MMM industries, advanced analytics solutions, such as Seeq, are automating many of the steps required for process optimization and creating operational insights. These solutions connect the raw data from multiple sources, then cleanse it into optimal formats for analysis and insight generation. These tools also include many user-friendly tools, but the most significant benefit for most organizations is the time saved for their experts, both increasing time to spend on process optimization and improving the on-the-job experience.
Leveraging advanced analytics applications
From very basic to highly complex analyses, MMM operations can leverage advanced analytics solutions to transform raw data into meaningful insights. Combining automated functions with point-and-click interfaces for descriptive, diagnostic, predictive and prescriptive analytics, these tools empower users to perform and easily recognize the impact of analyses, identify errors and successes, and model and innovate their operations.
Advanced analytics solutions also empower organizations to maximize the effectiveness of SMEs, whether working together at a single site or in different locations throughout the enterprise, like a remote monitoring center supporting a site in South America. These solutions incorporate intuitive tools for reporting and sharing insights, facilitating team collaboration and knowledge-sharing among employees at a site, in different countries and even across continents.
Automated analyses are frequently set up to predict common failure modes among particular types of assets, for example, when tensioning a conveyor belt network. Leveraging the collaboration tools included with the software, these insights can then be communicated across multiple sites and used to train new personnel, preventing significant downtime and costs.
Implementing advanced process control in an ore grinding operation
Ore grinding is the most energy-intensive step in mining processes, up to 50% of the total energy consumed in some mills. It is also designed to be the bottleneck for the operation, so any improvements to this step are felt in full force at the output stage. As corporate initiatives increasingly focus on sustainability, mining organizations are looking for new opportunities to maximize energy use with long, sustained periods of high production.
The Swedish metals and mining giant Boliden leverages Seeq to determine ways to increase these sustained periods of high production. The company began by running a simulation model of its grinding process to benchmark current operations against a new control model to identify scenarios that would increase production.
Next, the team used the advanced analytics solution to look at historical data for both the absolute power utilization and the relative power distribution utilization to calculate the available power. Using the solution to complete the calculation not only saved Boliden significant time, but it also empowered the company to visualize the calculations, motivating team members to buy into the idea of implementing a new control regime (Figure 1).
Using the benchmark and baseline calculations from Seeq, the team decided the next step was implementing a revamped advanced process control model for the grinding circuit. However, before evaluating the new control, the team took advantage of the advanced analytics solution’s capabilities to improve, refine and add nuance to the analysis, including setting up conditions to determine and correct load limitations for a more accurate evaluation (Figure 2).
Monitoring and evaluating the new control regime within the advanced analytics solution, the data revealed a 15% increase in long, sustained periods of high production.
Adapting to volatile markets by benchmarking assets
Speed of transformation in the market, for instance, adapting assets to changing business drivers, is crucial for operational development and maintaining a competitive advantage. Following a currency devaluation — and consequently, profit losses — in the Egyptian market, a global manufacturer of glass products began exploring new markets to sell in and assess quality across regional sites to ensure equivalency throughout its operations.
Historically, these studies would have required months to perform due to the need to analyze data from numerous pieces of equipment throughout the region while accounting for local currency differences. Using Seeq, however, the company was able to accelerate the analysis and calculate a benchmark with regional counterparts in a matter of days, avoiding the need to stagnate in a single market and sell at a loss. By connecting to all data sources throughout regional locations, the team of SMEs identified defect rate gaps, and analyzing past trends, they pinpointed optimal performance periods in the plant’s history. After establishing a high-performance operating envelope and a process improvement plan, the company was able to maintain low defect levels. (Figure 3).
As a result, the company achieved a 60% reduction in defect rates and quickly began shipping into new markets. It took less than a month for the team to complete the analysis, launch the process improvement plan and begin shipping the product to the new markets, saving months in the go-to-market due to inevitable downtime and profit losses if left to antiquated analysis techniques.
Predicting power export commitment
When a new local government regulation required facilities to report predicted daily power exports, carbon black additive manufacturer Birla Carbon sought a method for predicting its power export commitment. The changing dynamics of daily production and consumption made this a difficult task, with multiple lines producing different product grades at any given time, using different feedstocks of varying quality, and not all equipment continually running at scale.
To avoid revenue loss from either under or over-committing to an export, the company leveraged Seeq to create a machine learning model to predict the daily power export from the facility. By connecting all data sources in the advanced analytics solution, the company could visualize the effects of the entire facility’s power generation and consumption and accurately predict — within a 2% margin of error — the power export for the next day (Figure 4).
As a result, Birla Carbon eliminated cost penalties due to short supply and increased revenue with accurate predictions of their power export.
Empowering operational agility with advanced analytics solutions
With the diminishing quantities of MMM SMEs and the large demands placed on their backs, the only way to sustain process optimization is to apply automated solutions to carry the brunt of data analysis and insight generation. Left to antiquated manual procedures, there is simply not enough time left over for SMEs to implement critical process improvements.
However, modern advanced analytics solutions provide not only the tools to review and assess automated analyses, but also the means to share insights throughout the entire enterprise. Leveraging this sort of software is a commitment to cross-disciplinary collaboration and knowledge sharing.
Solutions like Seeq automate data analysis tasks, predicting common failure modes and facilitating insight sharing throughout multiple sites to reduce downtime and operational costs. This automation also saves SMEs time, enabling the MMM industries to better-leverage operational data, automate analyses, optimize processes and make data-driven decisions to improve efficiency, productivity and competitiveness.
Mariana Sandin has more than 15 years of experience in enterprise industrial software and analytics, and she leads the mining, metals and materials practice at Seeq. Mariana has an MBA from the University of St. Thomas in Houston, TX, and a BS in Chemical Engineering from Nuevo Leon, Mexico. She also has several certifications from TAPPI and IIMCh.
Seeq Corporation
