Optimize your production process using cutting edge technology
Zyfra AI optimizes industrial processes using Deep Learning and numerical optimization methods. By applying cutting edge data science combined with industrial expertise, we provide end-to-end solutions for optimizing production speed, quality, and costs.
Zyfra develops industrial digitalization technologies, invests in the corresponding products, and improves the Industrial Internet of Things and Artificial Intelligence environment. Machinery, metallurgy, mining, oil & gas, and chemical enterprises represent the Company's key fields of interest.
The solution is designed to optimize the area of pipes heat treatment. Moreover, it's built on models that describe the quality of pipes (mechanical test results) depending on the task, heat treatment mode and historical observations.
The solution takes into account the equipment possibilities and limitations. Recommended modes can be applied automatically or after validation by a person.
A feature of the solution is to take into account all the details of the process specific to a particular production:
- chemical composition of the specific melt; - furnace condition; - inaccuracies of sensors and temperature settings; - cooling water temperatures.
Possible effects from the solution implementation:
- increase in output to 6% per year; - defect level decrease.
Electrical submersible pump (ESP) unit developed by ZYFRA is designed to enhance the upstream oil extraction efficiency. The solution's efficiency is found as a result of operational decisions, - an increase in the oil production rate of each oil well by 1.5%. This allows increase extraction productivity excluding any additional capital investments.
ESP unit is equipped with artificial intelligence in order to give certain recommendations basing on historic Big Data analysis.
Software unit recommends such a mode of operation of the well, which provides the maximum oil flow rate for a certain period of time and provides a stable mode of operation for the same period. The solution is designed to maximize the flow rate of each well. The solution analyzes the current frequency, gauged oil flow rate, periods of intermittent mode of pump operation and other operating parameters.
Dashboards and other analysis instruments are also provided including current and planned mode, operation parameters visualization etc.
BOF Zyfra AI:
The product purpose is to reduce the amount (and cost) of ferroalloys per melting and simultaneously align product's chemical components with heat report. Ferroalloys are added into Basic Oxygen Furnace (BOF) during melting and this operation is one of the most expensive. This product is connected to the operating system and basing on the raw materials, current status of melting and heat report it gives recommendations according to the available ferroalloys. The product is fitted with adapters for connection with any SCADA (operating system) and can be configured to adopt GUI with customer's requirements. In case if the historical data (six month or more) from BOF SCADA system is available, the product can be put into operation during a month. Otherwise, trial operation is needed up to six months period.
EAF Zyfra AI:
The product is a part of Steel Melting Engine (SME), but can be used standalone. EAF Zyfra AI is designated to reduce melting time and power costs per melting and to align semi product's chemical components with technical requirements. The product is fitter with the adapters for connection with any SCADA and can be configured to adopt GUI with customer's requirements. In case if the historical data (six month or more) from EAF SCADA system is available. the product can be put into operation during a month. Otherwise, trial operation is needed up to six months period. The product has two main operating modes of: recommendation or fully automated control.
LF Zyfra AI:
The product is a part of Steel Melting Engine (SME), but can be used standalone. LF Zyfra AI is designated to reduce melting time, power costs per melting, amount of ferroalloys per melting and to align semi product's chemical components with technical requirements. Ferroalloys are added into Laddle Furnace (LF) during melting and this operation is one of the most expensive. The product is fitted with the adapters for connection with any SCADA and can be configured to adopt GUI with customer's requirements. In case if the historical data (six month or more) from LF SCADA system is available, the product can be put into operation during a month. Otherwise, trial operation is needed up to six months period.
CCM Zyfra AI:
The product is part a of Steel Melting Engine (SME), but can be used standalone. CCM Zyfra AI is designated to predict failures main units of CCM (continues casting machine) to avoid outage during casting and to align product's features with technical requirements. CCM stops are one of the main reasons of productivity and quality reduction, the cost of slabs increase. Based on prediction, CCM operator can change operating mode or use routine break for maintenance critical units. The is fitted with the adapters for connection with any SCADA and can be configured to adopt GUI with customer's requirements. In case if the historical data (six month or more) from CCM SCADA system is available, the product can be put into operation during a month. Otherwise, trial operation is needed up to six months period.
Harness the power of Computer Vision to collect data from your non-connected machines and industrial equipment
Zyfra Eye is a Computer Vision and Deep Learning powered solution which processes raw video footage of the dashboards of non-connected industrial machines and other industrial equipment, recognizes meters readings and controls positions, converts them to the structured data and transfers to SCADA or IoT platform.
It comes as a server software for video feed processing or as a hardware solution, combining industrial camera and video recognition unit.
Zyfra Eye has a convenient UI, walking you through the installation and setup process.
Zyfra Eye allows you to monitor your unconnected industrial equipment for a fraction of price of the traditional machine data collection installation.
Well maintenance logistics
Today, there is a trend in Oil&Gas industry of permanent production cost growth. Management are trying to take measures such as internal logistics optimization to retard it.
Zyfra has developed a unique well maintenance scheduling solution that allows to overcome random work/service orders allocation, scheduling process decentralization, orders/services prioritization strategy absence.
Solution software implementation assures maximum of overall asset oil flow rate by means of decreasing maintenance downtime, vehicle routing time and distance taking into account limited transportation, spare parts and equipment resources
Architecture of the solution provides unprecedented adaptability in order to suit changing conditions, constrains and inputs. User interface allows to adjust optimization model operation parameters and constrains such as services costs, routes availability and configuration, season constrains, service team specialization, equipment and spare parts availability, list of available transportation resources, prioritization rules without programming.
Dashboards and other analysis instruments are also provided including schedules, current and planned work completion status, utilization rates visualization etc.
IIoT/AI Platform (Data lake)
Most of industrial data is stored in separate systems. Application services are usually provided by different data sources and are oriented on different users with their own data structure. Platform provides connectivity to different industrial (such as OPC DA/UA, Modbus, MQTT) and non industrial data sources. The platform is oriented on raw stream data flow and provides stream calculations.
It has NoSQL database and object model which makes possible to store large amounts of data in a structured way. Any external applications can be easily integrated with IIoT Platform via REST API. It is a new step to crosscutting approach in production plant management and its usage is an easy way to implement new solutions.
Digital Advisor is a recommender system that helps to optimize a discrete or continuous production process.
Zyfra is happy to share the experience of organizing data monetization in large companies.
Digital Advisor uses AI to analyze the process data:
- input data for raw materials, current job; - current values of monitored parameters; - historical process results (product quality).
Optimization of the process takes into account the economic assessment of the cost of raw materials, energy and value added from additional production volumes. In some cases, a physical or chemical process model is used to ensure the required accuracy of the models.
Recommendations can be issued to the operator for approval or be applied automatically depending on the process and the customer's requirements.
Zyfra is happy to share the experience of organizing data monetization in large companies. Our services include:
- conducting a workshop to identify and prioritize tasks; - business analysis of tasks; - data monetization methodology.
- introduction to monetization; - AI application in your industry; - description of data management and monetization methodology; - brainstorming together with our experts and representatives of the production, collecting 100-300 ideas; - express assessment, ranking and selection of ideas.
The business analysis of specific ideas results are:
- business setting; - data quality analysis and feasibility; - cost and effect evaluation; - MVP description.
Data monetization methodology describes the processes:
- regular collection of ideas; - portfolio management of data monetization initiatives; - initiative analysis framework, effect evaluation; - data quality management; - metadata management; - integrated process of managing data monetization.
Learn more about our solutions, products and services
We will get back to you ASAP
Feel free to write and call us. We really love to communicate with our clients.