In recent years, industrial enterprises have seen a rise in emerging technologies and digital
tools that offer impressive improvements to worksites, yet 60% of an industrial worker’s day is characterized as “non-productive” time, the skills gap continues to widen as 75 million youth are underemployed or without work, and thirteen workers are killed every single day on industrial sites across the United States. At contextere, we believe that the combination of artificial intelligence and human ingenuity is the key to improving productivity, decreasing operational costs and saving lives.
The industrial worker is traditionally viewed as either the recipient of top-down decisions and pre-defined work optimizations or is considered irrelevant to the process. Neither case considers their vital involvement and expertise in the minute-to-minute decisions that are made in the operation, maintenance and inspection of complex equipment and assets.
I am focussed on changing that dynamic. The platform we offer begins with the assumption that all information the industrial worker needs to conduct their jobs effectively should be assembled and delivered in real-time based on personal context. We integrate to the existing enterprise data and Industrial IoT sensor feeds to correlate the appropriate selection of information based on the worker’s context, skills and competencies, and proximity to equipment plus historical results.
Based on the information available, our technology will understand the worker’s context, determine what they need to do next, curatethe available information relevant to their situational context, and send insights appropriate to their competency and mobile devices. As they conduct and respond to the dynamic work instructions, we capture any relevant performance of in-situ data for integration into the back-end enterprise environment for analytical, verification, and compliance purposes.
Over time, as individual competencies change through repeated actions, as productivity increases, or enterprise analytics provide additional inputs, the application of machine-learning algorithms automatically adjusts the work instructions received by the worker to optimize their actions. From the industrial worker’s point of view, he or she can go to any location and be consistently delivered an individually tailored, dynamic instruction of what to do next.
Transforming the industrial world
The typical industrial enterprise has a range of IT solutions in place, supported by various levels of connectivity and analytics, at headquarters and the edge. Centrally, you find enterprise-resource planning, product lifecycle management, and enterprise-asset-management products that accumulate data in centralized databases upon which analysis and ‘what-if’ simulation processes are applied in order to develop performance-optimization strategies. In addition, as greater numbers of smart sensors are installed on legacy field-based machines, more investment is being applied to the analysis of the data produced by those sensors to automate micro-optimizations that may increase efficiency or extend equipment life.
The human at the edge can now receive similar benefits and value. We take a human-centric approach to micro-optimization through the generation of minimalist instruction sets, known as Microforms, which are templated from fundamental activities that might be conducted in the three primary operational use cases below:
- Complex equipment utilization—Operation, maintenance, and repair of complex remote-equipment assets to maximize utilization and efficiency.
- Skilled workforce development—On-the-job guidance and mentoring to increase individual and collective competency while optimizing classroom-based pre-training.
- Hazard avoidance and emergency response—Shared awareness and emergency guidance to individuals and concurrent work teams to increase individual and collective safety.
The curation process that generates these Microforms assembles information relevant to the work instruction and formats, delivers, and presents this information in a way most effective for the specific device that is in use by the worker at that moment.
Just as in-car navigational guidance replaced paper maps, we create a trusted relationship with the end user because the guidance provided is accurate, relevant and reliable. The machine-learning intelligence and prediction algorithms within our platform are the critical elements that build this relationship. The Microform generator ensures delivery of the instructions to the worker and inspires in them the confidence that they will get the information they need—when they need it—to be more productive and more safe.
