The role of data analysis in workplace safety

Responding is Eric Whitley, director of smart manufacturing, L2L, Salt Lake City.

Organizations use data from connected worker platforms to monitor employee behavior, as well as to track equipment use patterns and productivity, the impacts of multiple work schedules, safety compliance among employees, and proper use of personal protective equipment.

Access to long-term data enables organizations to identify different work trends and the ways these affect workplace safety. For example, sensor-enabled PPE can be used to track worker motion in a facility. This data can be used to identify repetitive tasks that increase a worker’s risk of musculoskeletal injuries.

Additionally, organizations can identify patterns, trends and anomalies indicating potential hazards and risks. Such information is vital for establishing continuous safety awareness and identifying suitable preventive measures.

Data analysis is essentially a simplified method for organizations to manage the information collected from different equipment and employees. Historical data can be used to create models for predicting future safety risks based on present work patterns.

The analysis also establishes a relationship between events and workplace incidents or injuries. Predictive analytics is beneficial for assessing risk factors. It predicts the possibility of incidents, helps in identifying relevant mitigation measures and can be used to establish data-driven safety programs.

Additionally, when establishing data-driven maintenance strategies, it’s essential to maximize operational efficiency and the safety of machinery. Predictive algorithms rely on maintenance history and sensor information to detect the slightest anomalies that can cause irreversible equipment damage and increase the probability of workplace incidents. Predictive analytics ensures these defects are rectified in time, before they cause safety risks.

Data analysis can enhance the real-time monitoring of connected workers in different locations of a facility. Supervisors monitor the data from wearable devices and condition-monitoring sensors to identify anomalies such as temperature or humidity spikes and drops. They can also identify unsafe work behavior, poor work posture or psychological signals indicating worker fatigue.

Supervisors can use this data to alert workers about potential work injuries or incidents.

Organizations can respond faster and more accurately to safety incidents such as chemical spills or fires – the supervisors know where each employee is stationed and have data on their overall wellness.

Analyzing real-time equipment performance data can unearth underlying machine defects that could affect the safety of operators and the environment negatively. The organization can effectively initiate planned equipment downtime to rectify the defects and avert incidents or injuries.

Data analysis from a connected worker platform ensures organizations identify the underlying causes of various safety incidents in a facility.

The organization can effectively identify the factors or operations contributing to a safety problem by analyzing sensor data, digital work records and the accuracy of multiple safety checklists.

Organizations can interpret the data to verify if a safety incident is the result of machinery defects, wrong work procedures, worker fatigue or external factors hazardous for workers.

For instance, they can find the cause of fall incidents in a facility by analyzing various datasets – indicating the worker’s position during the fall, their posture and their movement when the fall occurred.

The organization can conclude whether the fall was caused by unsafe worker behavior or faulty PPE, and then develop safety protocols to ensure similar incidents never happen.

Editor's note: This article represents the independent views of the author and should not be considered a National Safety Council endorsement.