Client: Leading Industrial & Automotive Battery Manufacturer
Industry: Automotive
Segment: Asset Performance Analytics
Solution: Predictive Analytics
Technology: .NET, SQL Server, SAP Integration
About the Client
The client is an India based technology leader and one of the largest manufacturers of lead-acid batteries for both industrial and automotive applications in the Indian storage battery industry.
The client manufactures and supplies automotive batteries under OE relationships to Ford India, Honda, Hyundai, Mahindra & Mahindra, Maruti Suzuki, Ashok Leyland, and Tata Motors, Honda Motorcycles & Scooters India Private Ltd, Royal Enfield, Bajaj Auto Ltd among others. They are also the leading private label supplier for prominent brands in India.
Business Challenge
The client is a strong believer in environmental causes and tries to harness renewable energy in order to offset its manufacturing carbon footprint. To this extent, the client had installed Solar PV panels on the roofs of its manufacturing plans to augment the power needs of the manufacturing facility.
The client faced challenges in managing the Solar PV plant on a day to day basis. Breakdowns and maintenance activities were performed in an ad-hoc manner since there was no analytics around equipment failure rates. Sometimes, parts of the Solar PV plant were shut down while waiting for replacement parts to arrive.
Another challenge was around predictability in the quantity of power that the Solar PV plant could deliver on a day to day basis. At the same time, the client had to commit to purchase a fixed amount of power from its utility provider. This meant that the client had to commit to purchase more power than necessary to account for the risk or unpredictability in output from the Solar PV plant.
The client was looking for a solution provider with expertise to understand the unique challenges they faced. After evaluating several solution providers, the client chose AiMetric’s LARA predictive analytics platform for its next-gen features as well as highly modular build that allowed for a high degree of customization.
Solution
AiMetric implemented its innovative LARA predictive analytics platform for the client. The platform enabled the client with inputs and intelligence around the following:
- Prediction of solar energy output based on weather parameters for the week
- Predicted data is used in the overall planning of import/export of energy
The predicted energy output helped the client better manage and plan plant connected load so that continuous operations are planned and maintained. The LARA platform integrates with 3rd party weather information providers to collect weather data for the week and based on the same can calculate the predicted plant output.
The platform provided a set of intuitive and user-friendly dashboards that were updated in real time. The intelligence and information provided in the dashboards helped operations personnel take decisions that helped in minimizing downtime and operating cost.
Here is an architectural diagram of the solution implemented for the client.
Capacity vs Generation
The LARA platform provided Inverter wise Capacity Vs Generation reports that helped identify low performing inverters and take corrective action plans. Inverter performance reports could be generated daily/ weekly / monthly / yearly.
Expected vs Actual Power Generation
LARA’s integrations with 3rd party weather forecast providers as well as AI & ML-enabled algorithms helped predict Plantwise Expected Vs Actual generation based on weather (irradiation, rainfall) data and provided a high-level understanding of the impact of irradiance on plan generation.
Plant-wise Performance Comparisons
Data from multiple plants could be imported into the platform to identify the impact of various factors on the plant performance, such as:
- Radiation at the site
- Losses in the PV system
- Temp and climatic conditions
- Inverter efficiency
- Module degradation
Downtime and Maintenance
The platform used custom rules, algorithms and historical data to predict equipment failure and downtime requirements. This helped the client proactively service the equipment and keep the needed parts in inventory. Features included:
- Downtime report on the level of String, SMB, Inverter
- Identify the losses on each level of plant
- Enable root cause analysis
- OEM services can be monitored to take corrective actions
Technology
Database: MS SQL server 2005
MES application: Microsoft.NET
PLC: LSIS make
ERP system: SAP
Benefits
- 20% Reduced downtime and increased OEE
- 30% cost savings through better Solar PV power predictions
- 15% Reduced labor cost from physical monitoring of the rooftop solar PV plant
- Better cash management through the intelligent stocking of right maintenance parts at the right time
