Monixo provides a complete, efficient and reliable solution to effectively anticipate failures. Thanks to continuous data acquisition and analysis, Monixo beyond alerting teams in case of fault detection, ensures anticipating these. Monixo allows acting in time in order to avoid the cumbersome and costly failures, but never too early to avoid the expense and unnecessary downtimes.
Monixo offers the ability to integrate existing acquisition systems and instrumentation devices (existing sensors) at the user's place.
As well for the provision of data and analysis results: in addition to its website and mobile applications, Monixo easily integrates with existing maintenance management systems (GMAO or ERP).
This will add proven and critical value to proactive maintenance, but especially not to complicate or disrupt the processes and habits of end users by leveraging the existing.
From manufacturing SMEs to industrial groups with numerous and sometimes geographically distributed assets, Monixo responds to needs and technical requirements (types of connectivity, sensors/relevant data to be collected, security...). Analysis of the data flows in real time by the learning processor allows their immediate processing, which gives the processor the ability to analyze mass data with high performance, combining processing speed and reliability of forecasts.
The modular architecture (standalone components, one vis-a-vis the other ones) ensures the solution a rapid deployment (within a few minutes) and the ease of use (plug-and-play). Battery optimization, analysis algorithms and data collection, types and network topologies... All this complexity is fully integrated into the solution in order to provide a simple, transparent interfacing between the service technician and supervised assets. In addition to the usability and intuitiveness of these applications, Monixo allows users to access the data as directly as possible.
Monixo is an ecosystem dedicated to connected and proactive maintenance, the one of the factory 4.0 . The architecture meets the requirements of security and confidentiality, which are subject to maintenance 4.0 systems, and also to the requirements for interoperability. Indeed, the modular and standardized design of its components offers them great autonomy vis-a-vis each other and allows them to interface easily with other existing systems (sensors, CMMS). Its API also provides to the solution additional integration flexibility.
Wireless acquisition, high-precision and two-way, communicating on a high speed network, medium-range, low-consumption, but also on long-range networks (LoRaWAN) systems for geographically distributed assets
In charge of the provision and storage of data, it interfaces third party's systems through its APIs
Guarantor of automatic data analysis and prediction with the patterns of extraction
The acquired data and analysis are made available on the Monixo platform via the web and mobile applications
Monixo fits many sectors of the industry, respecting the specificities and constraints of each business. The solution is deployed in the energy, transportation, or manufacturing industries where it provides adequate answers to predictive maintenance needs.
At the heart of the digital transformation of the industry, Monixo adds its contribution to the plant 4.0 construction by increasing machinery's availability and reduced downtime after failures or planned interventions. Indeed, for conditional maintenance, some planned interventions will not take place as they are unnecessary. Predictive maintenance ensures the late cumbersome, lengthy and costly recurrent failures that are replaced by short curative interventions programmed during slack period or off-production periods.
Monixo provides real-time tracking of vehicles (cars, trucks, tractors...) not for the sole purpose of geolocating, but especially to ensure their proper functioning and their optimal use. Data analysis diagnostics and DTC error code (Data Trouble Code) generated by vehicles followed by Monixo allows them to be tracked beyond the speed or the used fuel to automatically identify abnormal operating scenarios allowing to accurately anticipate failures that could affect vehicle fleets and, by extension, the supply and distribution network companies.
From production to distribution via the transportation, electrical networks are plagued by recurrent failures. Despite this relative fragility, these networks have advantages from an analytical point of view without almost equivalent compared to other application areas: the existence of reporting and historical (sometimes going back decades ago) failures; representing a treasure trove for data mining in particular in the post-analysis fault's characterization stage. Moreover, the shift towards smart grids undertaken by major players in the field provides an important data stream and rich in useful information for preventive maintenance. Monixo is once again at the heart of these innovations. Proof is, if required, in 2015 the solution is winner of the ERDF Big Data for predictive maintenance contest.
Monixo ensures the establishment of a semi-supervised model allowing anticipating failures by learning (based on partially modelled patterns) beyond the conditional analysis of the state of infrastructure. From lifts to the frame of a building through the ventilation systems, Monixo supports the collection of data and key parameters (vibration, temperature, ultrasound) in order to feed the learning processor that transmits forecasts and the more specific recommendations, with a maximum entropy to ensure the optimal infrastructure status including possible failures that can have serious or even catastrophic consequences.
Monixo was designed on the assumption that all industrial assets have signs, visible or not, of degradation announcing the failure. Connected sensors allow to measure degradation. The measured data is made available and stored in the cloud, where the learning processor performs its analysis. The result of this analysis is available on the platform with two purposes: continuous monitoring of optimal thresholds of operation, more commonly known as conditional maintenance, and anticipating failures through continuous analysis of the state of assets, predictive maintenance To this comprehensive approach to predictive maintenance, we named it CAP approach. The example below is an illustration of this approach applied to a pellet press of one of our agribusiness customers.
Within seconds, monitors are set up on the machine to be supervised on the basis of a detailed instrumentation plan previously defined. In the case of this press, instrumentation relates to bearings and drums (engine at 1500 rev/min). The monitor is fixed by its magnetic base in this use case.
From the start of the monitor, measurements are collected and instantly available on the platform. On each one of the instrumented subcomponents, the relevant measurements are acquired in order to have a continuous monitoring of the degradation of the press: vibration (global level and FFT), infrared temperature, ultrasound, the current intensity (via an amperometric sensor in the cabinet)...
Once acquired, the data is analysed by integrating the thresholds defined by the maintenance operators from the platform or those defined by the existing standards on the machine in question (conditional maintenance). Alerts are then sent as a function of the selected stroke.
Monitors bi-directionality allows on measures such as the vibration of acquiring spectra, which are automatically analysed and interpreted with detailed monitoring of the evolution of detected anomalies. These analysis, as well as the historical data, are available and can be exported in several formats (XML, CSV, or PDF).
Monixo, through its automatic learning processor follows several failures signatures on the machines in order to automatically extract reliable failures scenarios. The analysis of these patterns allows to detect and track failure at the first known signs of abnormality.
Gradually, prediction gets refined; characterization of failures corresponding to it becomes more formal. The concerned measures, as well as the type of characterized upstream failures allow then to act in a targeted way and to optimize actions and resources: act early enough to avoid cumbersome and costly failures, but never too early to avoid the expenses and unnecessary downtimes