0630-In-depth analysis of artificial intelligence

「Deep Learning」

Machine Learning Advanced Service

"Deep Learning" advanced machine learning service

In-depth physical examination to understand the health status of old solar power plants

Shengqi cooperated with an Israeli artificial intelligence software company to launch the "Deep Learning" advanced machine learning service. Just install the Pixel View monitoring system, you can apply for an upgrade and use the existing power plant data for data analysis. Through the extremely complex algorithm, Interpret all index data of solar energy and analyze the reasons for the decline in power generation efficiency, deeply study the power generation behavior of power plants in the past year, and analyze 20 reasons for the decline in power generation indicators:

In-depth physical examination to understand the health status of old solar power plants

Major Analysis Items

Wire loss and connector breakage

Inverter wakes up late

MPPT/Converter Efficiency

Efficiency measurement of the tracking system

Including: Converter Clipping, Data Collection Integrity, Voltage and Frequency Deviation, Module Temperature Coefficient Abnormal, MPPT/Inverter Efficiency Abnormal, MPPT Accuracy, Disconnected Serial, Inverter Conversion Efficiency Poor, Inverter Failure or Due to factors such as getting up late, environmental sensor failures, etc., a quantifiable renovation and maintenance plan is proposed, and preventive abnormal maintenance and corrective measures are carried out, which can increase the average power generation of old power plants by 3-8% and reduce O&M costs by 10-12%.

Major Analysis Items

Wire loss and connector breakage

Inverter wakes up late

MPPT/Converter Efficiency

Efficiency measurement of the tracking system

frequency deviation	Converter data integrity	Inverter wakes up late
Abnormal temperature coefficient	Converter Clipping	Converter failure
Device disconnection	Voltage deviation	Abnormal power factor
Solar Meter Data Integrity	Tandem power generation performance	Abnormal temperature alarm
Environmental sensor failure	Tandem Generation Data Integrity	Converter/AC meter power generation ratio
Environmental Sensor Data Consistency	MPPT exception	Transformer is inefficient
Solar module clean/dirty	Converter efficiency below specification	Transformer temperature is abnormal
Vegetation needs pruning	The relative efficiency of the converter is abnormal

frequency deviation	Converter data integrity	Inverter wakes up late
Abnormal temperature coefficient	Converter Clipping	Converter failure
Device disconnection	Voltage deviation	Abnormal power factor
Solar Meter Data Integrity	Tandem power generation performance	Abnormal temperature alarm
Environmental sensor failure	Tandem Generation Data Integrity	Converter/AC meter power generation ratio
Environmental Sensor Data Consistency	MPPT exception	Transformer is inefficient
Solar module clean/dirty	Converter efficiency below specification	Transformer temperature is abnormal
Vegetation needs pruning	The relative efficiency of the converter is abnormal