PlugAIn allows the monitoring of data coming from any IoT sensor network
PlugAIn can acquire data from any IoT sensor network. The data of the sensors to be monitored can be easily managed by the platform administrator.
PlugAIn offers several algorithms to enable descriptive and predictive analysis and the models produced are made understandable to decision makers through “AI explanation” techniques.
Through several information acquisition plug-ins, PlugAIn insert data into a big data lake that support data analytics available through web monitoring dashboards in real time.
PlugAIn provides mechanisms to support operational and strategic decisions, optimizing response times and operational efficiency.
Industrial use cases
PlugAIn è utilizzato in diversi contesti applicativi, sia nel contesto del manufacturing, sia nelle smart cities.
PlugAIn is used in various application scenarios, both in manufacturing and in smart cities sectors.
The management of failures and breakages, when not properly managed, leads to higher costs, due to plant shutdowns, as well as the need, at times, to replace the entire machinery subject to maintenance.
Likewise, the implementation of “preventive” maintenance policies leads to unnecessary costs and inefficiencies due to the replacement of components that are still functional, without avoiding sudden breakdowns of subsystems at the end of their life.
It is therefore necessary to be able to implement maintenance policies that allow timely intervention on components with a low residual life, in order to minimize downtime and maximize the effectiveness of the interventions.
– Acquisire e storicizzare grandi quantità di dati provenienti da sensori IoT
– Monitorare gli impianti oggetto di analisi tramite cruscotti operazionali ed analisi multidimensionali OLAP
– Individuare comportamenti anomali degli impianti tramite tecniche di outlier detection
– Prevedere situazioni di guasto, valutando la vita residua utile dei singoli componenti e sotto-sistemi
– Fornire spiegazioni sui guasti predetti e conseguentemente guidare le operazioni di manutenzione
– Storage of large amounts of data from IoT sensors
– Plants monitoring through operational dashboards and OLAP
– Identification of anomalous behaviors of the plants through outlier detection techniques
– Failure prediction, evaluating the residual useful life of the individual components and subsystems
– Explanations on the aforementioned failures and consequently guide maintenance operations
– Savings in maintenance / repair costs
– Optimization of maintenance processes
– On-premise and cloud platform
– Failure prediction models can be run “on board” (edge computing)
Water consumption monitoring
Water losses due to faults on the pipe or theft of water mean that it is necessary to purchase the lost water from third parties (wholesalers), often requiring lifting before being put into the network, with high energy expenditure, so that water losses translate into economic losses.
Furthermore, the lack of meters installed for users, without which it is not possible to correctly account and invoice water consumption, causes, together with the high levels of arrears, an economic and financial imbalance of management.
The lack of meters also has the effect of amplifying the problem of water losses (especially the “apparent” ones, i.e. the volume of water distributed but not invoiced), encouraging waste.
– Acquisire in tempo reale i valori dei consumi idrici, con riferimento alle utenze (commerciali e domestiche)
– Monitorare il flusso d’acqua nelle condotte della rete idrica, tramite sensori che consentono di misurare il flusso entrante ed uscente
– Calcolare il “Bilancio idrico”, individuando la presenza di perdite “patologiche” dovute a rotture o furti d’acqua
– Individuare scenari anomali di consumo da parte delle utenze, dovute a probabili perdite
– Real-time water consumption monitoring, with reference to users (commercial and domestic)
– Monitoring the flow of water in the pipelines of the water network, using sensors that allow you to measure the incoming and outgoing flow
– “Water balance” evaluation, identifying the presence of “pathological” losses due to breakage or theft of water
– Identification of anomalous consumption scenarios by users, due to probable losses
– Cost savings due to water losses
– Improvement of service and citizen satisfaction
– Minimization of downtime on the network
Industrial Quality Control
The quality checks of large quantities of products made with industrial processes is difficult and expensive, because it requires the use of specialized personnel and cannot be performed on the entire production, but only on a sample basis.
This problem becomes even more evident in the case of products that require the assembly of numerous components, which must be positioned correctly to ensure the assembled system works in the way it was designed.
The verification of the coherence between the project and the finished product can be carried out in an exhaustive way only through automatic agents able to visually analyse the objects with the same logic of a man but obtaining a smart quality control.
– Automatic analysis of images of industrial products
– Identification of the basic components and the position in which they are mounted
– Verification of the absence of components necessary for the final product
– Verification of compliance of finished products with respect to the project
– Automatic Quality Inspection
– Comprehensive batch analysis
– Verification of compliance with the project to be implemented
In manufacturing and in the logistics sector, the formulation of work shifts is a complex task, since shifts depend on forecasts on the arrival times of goods and on various constraints, both contractual and extra-contractual.
The use of simple tools, such as excel sheets, makes work less efficient, because it is based on the dexterity and experience of the planners and does not allow you to systematically verify that the constraints of scheduling work shifts are respected.
Therefore, simple tools are needed which, using the same reasoning mechanisms as humans, allow the production of admissible solutions to the planning problem in a very short time, while still allowing the operator to manually modify the calculated shifts.
– Allocation needs management
– Automatic calculation of work shifts, in compliance with contractual and non-contractual constraints
– Allows planners to manually change calculated shifts
– Quick implementation of staff allocation on single, daily, weekly and monthly shifts
– Reduction of calculation times
– Greater control over compliance with contractual and non-contractual obligations
– Flexibility of the system and possibility to customize it