Background to the problem

The availability of industrial assets is a critical factor in ensuring the continuity of waste management operations, the quality of the service provided, worker safety and the environmental performance of the facilities.

Waste treatment and recovery operations rely on a wide range of equipment and infrastructure, including transport systems, sorting equipment, processing machinery, energy recovery equipment, electromechanical systems and logistics assets. Unexpected failure of this equipment can lead to operational disruptions, high repair costs, loss of productivity and increased risks to safety, quality and the environment.

Advances in industrial IoT technologies, connectivity and advanced data analytics now make it possible to continuously monitor the condition of equipment and identify early signs of deterioration before failures occur. These capabilities create opportunities to move away from reactive or purely preventive maintenance models towards maintenance based on the actual condition of assets and supported by data.

Overview of the current context

Amarsul and Valorsul are urban waste management companies which, together, process around 154,000 tonnes of waste per year and serve approximately 2.44 million inhabitants across Greater Lisbon, the Western Region and the Setúbal Peninsula. 

Their activities include:

• Waste collection and transport;
• Sorting and recycling centres;
• Treatment of organic waste (food waste);
• Waste-to-energy plant;
• Bottom ash treatment;
• Sanitary landfills;
• Transfer stations;
• Ecocenters (collection centre for other types of household waste);
• Industrial maintenance operations;
• Environmental monitoring.

The companies operate a wide range of industrial and logistical assets, the availability of which directly influences treatment capacity, operational efficiency, operating costs and compliance with environmental and public service objectives.

The challenge

We are seeking solutions in industrial IoT, asset monitoring and advanced data analytics that will enable us to implement predictive maintenance and condition-based maintenance strategies for critical equipment.

These solutions should transform operational data into actionable insights, enabling maintenance teams to anticipate failures, identify patterns of deterioration, optimise resources and make more informed decisions throughout the assets’ lifecycle.

Proposals may make use of:

• Industrial sensors;
• IoT and Industrial IoT (IIoT);
• Edge computing;
• Artificial intelligence and machine learning;
• Digitalisation of maintenance;
• Online monitoring systems;
• Predictive models;
• Advanced data analysis;
• Integration with automation and maintenance management systems.

The aim is to find solutions capable of generating value by utilising existing infrastructure wherever possible and minimising complex interventions or disproportionate investment.

Expected results and objectives

The solutions presented should contribute to one or more of the following objectives:

• Early detection of signs of equipment failure or deterioration;
• Reduction in unplanned downtime;
• Increased availability and reliability of assets;
• Improved planning of maintenance interventions;
• Reduction in maintenance costs over the life cycle;
• Optimisation of spare parts management;
• Extension of equipment service life;
• Improvement of operational safety;
• Reduction of risks associated with critical failures;
• Support for decision-making regarding asset replacement or investment;
• Greater efficiency in the use of maintenance resources.

Non-exhaustive list of topics that may be covered

• Vibration sensors;
• Temperature sensors;
• Acoustic and ultrasonic monitoring;
• Monitoring of electrical variables;
• Monitoring of motors, gearboxes and bearings;
• Monitoring of hydraulic and pneumatic systems;
• Monitoring of conveyor belts and rotating equipment;
• Early fault detection systems;
• Failure prediction models;
• Scoring and asset health assessment systems;
• Equipment performance and condition dashboards;
• Integration with CMMS/EAM systems;
• Intelligent maintenance planning tools;
• Root cause analysis;
• Digital twins for maintenance and operational optimisation.

Requirements to be met when presenting the solution

The proposal must demonstrate:

• The ability to integrate with existing industrial facilities;
• Scalability for different types of assets;
• Robustness in demanding industrial environments;
• High quality and reliability of the data collected;
• Compatibility with existing automation and maintenance systems;
• Clearly defined implementation requirements;
• Ease of installation and operation;
• A model for calculating expected benefits;
• An approach to industrial cybersecurity;
• Operational resilience and service continuity.

Solutions must allow for the development of pilot schemes in a real-world operational environment and provide objective indicators for evaluating the results achieved.

Why take part?

This challenge offers the opportunity to develop and validate predictive maintenance solutions within a complex and demanding industrial context, involving a wide variety of equipment and processes.

We are looking for technologies that will increase the reliability of assets, reduce costs, improve operational efficiency and accelerate the digital transformation of waste management operations.

Solutions with proven potential may be scaled up to multiple Valorsul sites and, in the future, to other companies within the EGF Group.