Find out how bow-ties and AI will improve your safety

In this blog, we will explore how bow-tie diagrams and AI-powered computer vision can be used together to improve safety in your workplace.

What are bow-tie diagrams?

Bow-tie diagrams are widely used to improve safety in high-hazard industries, but they can provide a better understanding of how to prevent harm in any industry. 

In particular, if you are looking for insights on ways to use new technology – such as AI-powered computer vision (CV) – to reduce risk, the bow tie method could be the tool you need. To illustrate this, we’ll use a 5 step example from a warehouse. 

Step 1:  Identify the hazardous event

Your incident records and hazard analysis will help you to identify warehouse hazards. 

Imagine you’ve had several incidents where forklift trucks (FLTs) have hit racking, causing objects to become unstable, fall, or nearly fall, with or without injuries. 

Define this hazardous event in the center of the bow tie (the yellow circle in our example).

Step 2: Enumerate the hazards

For the event you’ve described, list all the hazards you can think of related to that event. Don’t worry about whether a single hazard or a combination leads to the event. 

In the orange section of our bow tie, we’ve listed hazardous activities that might contribute to an FLT hitting the racking – driving too fast, using the wrong route, or a pedestrian causing the FLT to maneuver too close to the racking to avoid a collision.

Step 3: List the outcomes

Exclude highly improbable outcomes – for example, unless you are storing flammable items, it is unlikely that a falling box will cause a fire. However, you should include a range of possible outcomes. 

For example, consider an object falling off the shelf when no one is around, leading to financial losses, or a load falling in front of a vehicle and causing it to swerve or brake. 

You should also include outcomes where a falling object directly injures a worker. These are described in the red section of the bow tie. 

Step 4: Evaluate the barriers

There are two types of barriers: things that stop the hazardous event and those that limit its impact.

If a fire was the central event, controlling ignition sources and combustible materials would be on the left (the blue area), and fire alarms, emergency lighting, and evacuation procedures would be on the right (the green zone). 

Recovery measures may not stop the hazardous event, but they do reduce the severity of the outcome. 

Preventing forklift hazards with barriers

Barriers that prevent an FLT from hitting the racking could include speed limits enforced by vehicle controls, training, observation, signage, and separation of routes for vehicles and pedestrians. 

These safety barriers block the progression from hazard to hazardous event. Once an FLT has hit the racking, your key barriers might be reporting and inspecting the damage, as well as correcting any stacking problems. This is shown in the green part of the bowtie diagrams.

Step 5: Assess the barriers 

Controlling risk requires multiple lines of defense. Speed delimiters may fail or be disabled, preferred routes can become blocked, and people make wrong decisions. 

People might forget to report a hazardous event. Traditional approaches offer limited options – vehicles can be inspected more often, and workers can be reminded of the importance of reporting. 

But Computer vision (CV) allows you to add extra lines of defense. If you are familiar with Reason’s Swiss Cheese model, this is like adding an extra slice of cheese with fewer holes. 

The bow-tie model helps identify additional controls on either side of the hazardous event – what can we do to prevent the FLT from hitting the racking, and if that occurs, how can we effectively recover from and mitigate any harmful outcomes?

Adding extra defense layers with computer vision

When adding AI safety technology like Computer Vision as an extra defense layer, it enhances safety protocols by allowing real-time workplace safety monitoring.

• Prevention

With computer vision safety, you can detect when FLTs travel too quickly, when they are in the wrong location, and even when they travel the wrong way along a route. 

It also detects pedestrians using a vehicle-only route. This capability to monitor and measure these hazardous activities improves your chance of risk detection and preventing hazardous events.

• Mitigation

Rather than relying on individual drivers to report collisions with racking, CV can detect close proximity events and feed short video clips to a manager for risk assessment. 

If it has, the manager can arrange for an inspection of the racking and address any stacking issues if necessary.

Redefining safety with bow-tie analysis and Protex AI

Bowtie diagrams serve as effective tools for improving safety. They illustrate the sequence of hazards, prevention, event, recovery, and outcomes. You can review existing barriers and identify opportunities to use new warehouse safety solutions, such as computer vision, to minimize risk.

Protex AI uses computer vision to analyze real-time video feeds and detect potential safety hazards before they occur. This proactive approach alerts employees to potential dangers and helps prevent accidents and injuries. 

Our software provides detailed reports that enable businesses to identify trends and take proactive steps to improve safety. Watch our demo video and discover how Protex AI can help your business.

‍