Revolutionize elevator and solenoid valve maintenance with artificial intelligence at the Edge. Detect failures before they occur and operate and optimize your equipment, processes, and operations in real-time and locally, enabling efficient operation and optimizing the performance of your equipment.
Our advanced sensors collect real-time data on vibrations, temperature, pressure, and other critical parameters.
Edgemant is trained in the Field protocols used in industry and buildings. OPC-UA, Mqtt, Modbus, Profibus, KNX, Bacnet
Artificial intelligence processes data locally, detecting patterns and anomalies before they turn into failures.
You receive proactive alerts and specific recommendations to optimize maintenance and avoid unscheduled downtime.
The system can take corrective actions autonomously, adjusting parameters to maintain optimal and safe operation.
Fewer emergency repairs and better use of technical resources.
Data never leaves the local environment, ensuring total security and regulatory compliance.
Works with an integrated battery, no need for an electrical connection. Ideal for secure and versatile installations.
Compatible with existing equipment. Just add sensors, without modifying your infrastructure.
Access constantly updated information to make fast and accurate decisions.
Monitor the status of your equipment, detecting any anomaly in real time.
Local data processing for maximum speed and privacy, without depending on remote connections.
AI on the Edge analyzes real-time sensor data, detecting subtle deviations in the system before failures occur.
The model constantly adapts thanks to new data, surpassing static systems that do not evolve.
Advanced algorithms that learn from operating patterns to improve the accuracy of predictions.
Statistical and AI models that anticipate failures up to 30 days in advance.
Thanks to CNN neural networks, the system accurately distinguishes anomalous sounds and images, avoiding unnecessary interventions and improving operational efficiency.
Native read and write with the main protocols on the market for transparent integration.
RTU & TCP
DP & Industrial Ethernet
Unified Architecture
Publish/Subscribe
Building Automation
Lighting Control
98% reduction in elevator failures
Implementation in 12 critical elevators, improving the safety of patients and medical staff.
Savings of $150,000 annually in maintenance
Monitoring of 8 elevators and 24 solenoid valves, optimizing the flow of visitors.
99.9% uptime
System implemented in 6 high-speed elevators, ensuring business productivity.
"EdgeMant Conauti completely transformed our maintenance. Now we can anticipate problems before they affect our patients."
"The accuracy of the predictions is incredible. We have reduced our maintenance costs by 60%."
"Edge AI technology gives us the confidence that our systems will always operate optimally."
Visual, auditivo, de temperatura y vibraciones en componentes críticos. Prevención de fallas mediante Deep Learning discriminativo y generativo local.
Control predictivo de flujo, presión y temperatura para optimizar el rendimiento de sistemas hidráulicos.
Real-time overview of the status of all monitored equipment with alerts and key metrics.
Use of TinyML Sensors that integrate sensors, cameras, and microphones into Deep Learning models, all locally.
Planning and tracking of maintenance tasks with integration of calendars and resources.
| Benefit Dimension | Traditional Reactive Maintenance | Planned Preventive Maintenance | Predictive Maintenance with EdgeMant Conauti |
|---|---|---|---|
| Maintenance Cost | Low initial cost (no planning). High, unpredictable, and recurring repair costs. | Regular planning and execution costs. Low to moderate initial investment. Often unnecessary spending on labor and parts. | Initial investment in sensors and technology. Drastically reduced operating costs (10-40% savings). |
| Downtime Cost | Very high. Causes unplanned and prolonged downtime. Loss of productivity (up to $50K/hour). | Medium Low. Allows for planned downtime. However, it does not prevent unforeseen failures. | Very low. Reduces unplanned downtime by up to 50%. Repairs are scheduled at the most optimal times. |
| Asset Lifespan and Value | Low. Lack of maintenance accelerates wear and shortens the asset's life. | Moderate to High. Scheduled maintenance extends the equipment's lifespan (20-30% more). | Very high. Premature wear is prevented, extending the asset's lifespan (up to 60% more). |
| Productivity and Efficiency | Very low. Performance decreases before a failure. Failures affect production and product quality. | Moderate. Avoids most unexpected stops and maintains acceptable performance. | Very high. Increases labor productivity (5-20%) and improves OEE (5-15%). |
| Safety and Occupational Risk | Very high. Sudden failures endanger workers and can cause catastrophic accidents. | Low. Regular inspections and maintenance reduce the risk of accidents. | Very low. The ability to predict failures eliminates most safety risks before they occur. |
| Inventory and Parts Cost | High. A spare parts inventory is required for emergency and unscheduled repairs. | Moderate. It is based on statistical planning that often requires a safety stock. | Low. Allows for just-in-time inventory management and parts acquisition. |
| Planning Level | None. No prior planning required. | High. Based on a schedule or usage, with predefined task lists. | Very high. Maintenance is scheduled based on real-time data and failure prediction. |
| Required Technology | None. It is based on manual response. | CMMS software to manage work orders and calendars in the cloud with internet. | IoT sensors, Edge computing, data platforms, AI, and Machine Learning all local without internet. |
| Return on Investment (ROI) | Negativo. El "ahorro" inicial se pierde rápidamente en costos ocultos y perdidas de productividad. | Moderate. It generates savings, but with the cost of inefficiency and premature interventions. | Very high and measurable. It can generate a 10x ROI, with returns in a matter of months. |
This product monitors the real-time status of elevators and solenoid valves, detecting anomalies before failures occur. It uses local sensors and Edge AI processing to act without depending on the cloud.
Yes. All processing is done locally, which means that the data is not sent to external servers. This protects user privacy and complies with industrial security regulations.
Totally. The system is designed to operate autonomously, even in environments without connectivity. Ideal for critical installations or areas with limited access.
No. The system is modular and plug-and-play. It adapts easily to existing elevator and solenoid valve infrastructures, with minimal technical intervention.
It reduces maintenance costs, extends the useful life of the equipment, and avoids losses from unexpected stops. In addition, it minimizes energy use by optimizing operating cycles.
Join the leading companies that already trust EdgeMant Conauti to optimize their operations and reduce costs.