top of page

Industries We Work With

Our current focus is Oil and Gas, Chemicals, Energy, and Manufacturing. We have global presence as our product is already taken up by industry leaders. However, our technology can be applied to any industry, where time-series data is collected continuously or periodically.


Oil and Gas

The oil and gas industry, which is facing a growing number of challenges with profitability, has an opportunity to increase the bottom line with cutting edge, early risk detection technologies. Unplanned shutdowns and incidents cost oil production units, refineries and gas plants huge monetary losses every year, in the form of lost revenue opportunity, higher insurance costs, fines, regulatory scrutiny and diminished customer satisfaction. Even the abnormal process situations that do not result in incidents still negatively impact the bottom line significantly by leading to poor product quality, schedule delays, increased equipment wear and other significant costs. Studies by ASM Consortium indicate that the inability of the automated control system and operating personnel to control abnormal situations has an economic impact of at least $20 billion annually in the US alone.

Near-Miss Management technology keeps oil and gas operations informed of changes in their risk levels, positioning them to anticipate an abnormal situation or shutdown with warnings often days and weeks before humans and alarms, far in advance of what current technology can provide. By analyzing the entire spectrum of process data from a plant, our software is able to detect implicit leading indicators of potential risks before they become explicit (observable) issues, thereby facilitating early preventive actions and predictive maintenance. Our patented methodology identifies those conditions where the legacy systems or data search assistance tools may be missing the increasing likelihood of a process failure, by detecting what we call hidden near-misses™. Ultimately, the leading indicators help operating teams embed proactive risk management culture into their daily workflow and achieve increased on-stream efficiency and capacity utilization – without increasing risks.



No one is more aware than the chemical industry of the unintended consequences of unplanned production disruptions that often lead to incidents. According to Occupational Safety and Health Administration (OSHA), there are about 300 high-consequence incidents every year in the US chemical industry alone that cause injuries, deaths or are greater than $500,000 worth of damage [1]. From the potential loss of life, bodily harm, multi-year contaminations to litigations, insurance claims and diminished corporate image, mitigating risks could not command a higher priority these days. Even lesser incident prevention has been recognized as an operational priority to be targeted, since the smallest of unplanned shutdowns can cost from the tens of thousands to millions.

The technology to accurately predict process risks in a timely enough fashion to enable mitigation has only recently become available. Advancements in artificial intelligence, autonomous systems and machine learning have finally matured to a point where industry can extract the answers they need from the reams of data to which they’ve had access. What has been of particular interest to the industry, is the cohesive benefits of this technology, since the same early detection that mitigates risk also increases productivity and optimizes operations, leading to extended life of process and equipment.

At Near-Miss Management, we help chemical companies develop a peripheral risk vision by identifying the changing risk dynamics of their processes and the drivers behind each change. By dynamically ripping through the entire spectrum of process data, our software systems identify process risks at their initiation stage, typically days and weeks before humans and alarms. By analyzing the operating conditions holistically and frequently, our methodology identifies unexpected changes and events in the process conditions that can eventually lead to observable near-misses, incidents or accidents. For example, whether a process operation or an equipment is heading towards a risky region can be more accurately understood by looking at the timeline of leading indicators – what we have termed hidden near-misses™ – that signal the system is approaching a critical point. These early data insights help operating teams resolve issues while they are still non-threatening, enabling them to avoid any major issues, thereby achieving increased bottom lines and insurance standings.

Source: [1] OSHA, Data and Statistics.



There are numerous electricity production options these days – nuclear, fossil fuels, hydro, wind, solar, geothermal and biomass. With increasing energy demands and available competing options, the most important priority for any power plant is to maximize its reliability, while ensuring its safety. Reliable plants ensure uninterrupted power supply in our homes, communities and businesses, which maintains public and political confidence in the energy industry.

However, outages and incidents are not uncommon in the power industry. Statistics on loss history show that mechanical and electrical failure of equipment and components is the main driver for losses and prolonged unplanned outages in power plants. While the age of the equipment has an important bearing on failures, so does poor maintenance procedures. Often there are warning signs, such as excessive vibration, that indicate the equipment is not working properly or is under stress. Unfortunately, these signs are often missed or not recognized before a major problem occurs [1].

With the new advancements in early risk detection techniques and data analytics, effective risk management can help prevent unplanned outages and incidents at power plants and ensure increased reliability. Our cost-effective solutions are designed to assist all types of power plants seeking better risk detection and management. Our technology provides leading indicators to operating teams by indicating those instances where potential failure conditions are generated but are hidden and therefore go undetected. These hidden patterns can help detect when risk levels are beginning to change and what their drivers are. For example, while alarms or static models may miss the change in the turbine or compressor patterns, our dynamic risk detection technology flags engineers about slow yet unexpected operating changes, enabling them to resolve issues at their earliest stages.

Source: [1] Johnson P., “Keeping power plants online with risk management,” Utility Week, February 2011.



Industrial incidents and unplanned downtime are a serious challenge for the manufacturing industry, leading to decreased profitability, on-stream efficiency, and employee well-being. The resulting reputation risks and under delivered customer needs can lead to a significant long-term impact on the bottom line and longevity of the company, especially when such production disruptions occur unexpectedly. Although most of the traditional manufacturers are still struggling to reduce the firefighting nature of their maintenance tasks (breakdown maintenance), some companies have successfully adopted the preventive maintenance program in their factories. However, the latter often results in an unnecessary loss of productivity either because maintenance is performed when the process is still functioning at an acceptable level, or because unpredicted breakdowns occur before scheduled maintenance operations are performed. In contemporary markets, it becomes increasingly important to predict and prevent failures based on current and past behavior [1], thus ensuring its maintenance scheduling is optimized.

With the new data acquisition and storage capabilities, a typical manufacturing plant now tracks thousands of variables, generating millions of data points every day. Measurements are available on the smallest movements of parameters. However, recent studies report that only a small percent of this data (typically less than 5%) is used in any type of risk calculations today. Current process risk management has centered mostly around Six Sigma or lean management principles. The elements of hidden near-miss analysis and early risk detection, which, in most cases, are not effectively integrated into these management methods, are particularly critical as near-misses hidden in the processes provide true leading indicators. Today’s plants have the opportunity to harness their big data with cutting edge technologies and to anticipate problems as they are beginning to form. Near-Miss Management’s patented technology helps achieve this goal as our software systems deliver earliest insights on potential problems, obtained by analyzing from the entire volume of process data. With easy integration of our solutions into existing workflow, manufacturing facilities can stay focused on early resolution of operating issues and maintain consistent high efficiency and reliability of their operations.

Source: [1] Qiu H. and Lee J., “Near-zero downtime: Overview and trends,” Reliable Plant, June 2007.

bottom of page