How AI Improves Warehouse Performance and Alleviates Supply Chain Disruptions

Delivering greater performance improvements in warehouses using artificial intelligence (AI) and machine learning (ML) will make supply chains more resilient and allow them to recover from disruptions faster. Unfortunately, the severity and frequency of supply chain disruptions are increasing, with McKinsey noting that on average companies experience a disruption from one to two months every 3.7 years.

Over a decade, the financial impact of supply chain disruptions in the consumer goods sector can equal 30% of one year’s earnings before interest, taxes, depreciation and amortization (EBITDA). However, Fortune 500 companies with resilient supply chains achieved a 7% premium on their share price and market capitalization.

Resilient supply chains are the shock absorbers that keep e-commerce, retail, supermarkets and mail and parcel companies running despite the accelerating pace of disruptions. Hardening supply chains to make them more resilient pays off.

Closing gaps in the warehouse strengthens supply chains

Unexpected delays and undiscovered warehouse errors cost the most to fix and wreak havoc in supply chains. Warehouse managers, planners and freight forwarders rely on decades-old processes based on Microsoft Excel spreadsheets. But with increasing costs, speed and severity of disruptions, warehouses cannot respond quickly enough with these manual systems. As a result, “Operations managers spend hours collecting data and manually entering it into Excel spreadsheets, wasting valuable time managing and optimizing warehouse operations,” said Akash Jain, Honeywell Connected Enterprise General Manager for connected warehouse, to VentureBeat.

Warehouse accuracy and performance continues to decline as decisions made on the warehouse floor that affect margins, costs and revenue are often not reached on the top floor. Senior executives need to understand how split-second decisions about orders to ship affect inventory costs and total inventory value. Runaway inflation makes inventory valuation one of the most expensive risks to manage today.

Stress-testing supply chains often expose the largest and costliest gaps in warehouse performance down to the asset level. Asset Performance Management (APM) should be a core part of managing a warehouse so that costs, risks and used machines can be optimized with real-time data.

To ensure warehouses sustain disruptions and continue to operate, the managers who run them require a continuous flow of near real-time data from supervised ML algorithms to optimize the many constraints of their operations. “Many distribution companies were completely taken by surprise when demand for e-commerce soared at the start of the pandemic. Many had multiple shifts to meet demand, and had little to no time to maintain machines and warehouse assets so they wouldn’t break down,” Jain told VentureBeat.

How AI is filling the gaps in warehouses

The more vulnerable supply chains become, the more important it is to find and plug the gaps in the warehouse. By using supervised ML algorithms and convolutional neural networks, it is possible to use the real-time data streams generated from warehouses to determine where gaps are. However, it has proved elusive to determine the magnitude of these gaps, their impact on day-to-day warehouse operations, and their financial impact on a business.

Cloud based business performance management (EPM) platforms are taking up that challenge. They combine APM with location management applications to determine how warehouse locations are performing against plan, enabling managers to identify and resolve bottlenecks before impacting performance. Leading EPM providers rely on APIs to integrate with current and legacy warehouse management systems, distinguishing themselves in functional area and vertical market. Oracle, SAP, IBM, Anaplan, OneStream Software and Honeywell Connected Warehouse offer EPM platforms today.

Among the many approaches adopted by enterprise software vendors today, Honeywell’s Connected Warehouse platform strategy and use of AI and machine learning are noteworthy. It leads the EPM platform market by using advanced ML techniques and constraint modeling to identify warehouse and logistics bottlenecks.

AI and ML are the foundation of Honeywell’s Forge platform and product portfolio. The company employs more than 150 AI and data science experts who focus on the Honeywell Forge roadmap, future innovations and new patent opportunities.

All of these AI and ML investments translate into continuous improvement in providing real-time insights and contextual intelligence that improve warehouse and supply chain performance. The goal is to provide distribution companies with a real-time record-keeping system that they can use to identify gaps in warehouse performance and better manage machines and assets, Jain said.

Honeywell’s Connected Warehouse uses ML to analyze real-time data and make recommendations based on constraints, while monitoring machines to see how to optimize their performance. The dashboard below combines real-time updates for outbound activities, tracking current progress on packed and shipped boxes against the plan.

Real-time data, analyzed with analytics and ML algorithms, keeps the dashboard current. Constraint-based ML algorithms also calculate planned performance in real time and are used to track asset downtime. Besides, Honeywell recently introduced and APM that predicts when warehouse machines need preventive maintenance and updates.

Anticipate more supply chain disruptions

Supply chain stress testing should start in the warehouse, where small process improvements on a large scale can make a difference to keep distribution centers and networks running efficiently. What was missing is a 360-degree view of warehouse performance, which can identify how fast bottlenecks are growing and their financial impact. By combining AI, ML, and real-time OT and IT data, cloud-based EPM platforms are addressing this challenge.

It is a certainty that more supply chain disruptions are on the way. By using AI and machine learning to optimize warehouse operations, those shocks can be cushioned. AI and ML-based warehouse management is a necessity today for high-speed distribution companies, including e-commerce, retail, grocery, and postal and parcel services, to reduce the impact of supply chain disruptions.