Molten Salt Thermal Energy Storage System State Prediction Dataset

#temporal state prediction #state change detection #change event recognition #anomaly assessment #CSP plant operations #molten salt storage management #charge and discharge scheduling #equipment condition monitoring

Records: 4060
Size: 0.3GB
Format: JSON
Provider: MOBIUSI INC
Updated: v1.02026-11-04

AI Analysis & Value Prop

Designed for concentrated solar power applications, the JSON time-series samples record operating conditions and key measurements, including temperature, level, and flow, for molten salt tanks, heat exchangers, pumps, and valves. They include comparisons between consecutive states, change events, and future storage-state labels, covering operating patterns such as charging, discharging, state holding, mode switching, equipment start-up or shutdown, and abnormal changes. The data supports storage-state prediction, operational change analysis, and anomaly assessment, and is suitable for domain-specific model fine-tuning and evaluation.

Overview

Dataset Insights

Preview

Sample Examples

sample.json

{}

Schema

Technical Specifications

Field	Type	Description
file_name	string	File name
change_events	array	Lists events identified from consecutive state comparisons, such as charging, discharging, mode switching, equipment start-up or shutdown, and abnormal changes.
current_state	object	Records the molten salt thermal energy storage system's operating state and key measurements at the current sampling time.
previous_state	object	Records the system's operating state and key measurements at the previous sampling time for comparison with the current state.
sample_context	object	Records original time-series information, such as the sample collection time and time interval.
anomaly_assessment	object	Provides an anomaly assessment based on measurements, changes between consecutive states, and equipment operating logic.
state_change_comparison	object	Contains changes in key variables and the overall direction of change, calculated by comparing the current and previous states.
future_storage_state_label	object	Provides a label for the future storage operating state inferred from current and previous states and identified change events.

Trust

Compliance Statement

Authorization Type

Proprietary - Commercial AI Training License (No Redistribution)

Commercial Use

Requires exclusive subscription or authorization contract (monthly or per-invocation charging)

Privacy and Anonymization

No PII, no real company names, simulated scenarios follow industry standards

Compliance System

Compliant with China's Data Security Law / EU GDPR / supports enterprise data access logs

FAQ

Frequently Asked Questions

What does the dataset contain?: The JSON time-series samples include sampling context, current and previous system states, state-change comparisons, change events, future storage-state labels, and anomaly assessments.

Which operating states can the data support predicting?: The data supports future storage-state prediction and analysis of charging, discharging, state holding, mode switching, equipment start-up or shutdown, and abnormal changes. Refer to the specific data version for exact label values and measurement fields.

How can I access the data, and what are the licensing terms?: Refer to the product page for available samples, delivery format, access options, and license terms. Before use, confirm the permitted use cases, redistribution restrictions, and commercial-use conditions.

Which applications is this dataset suited for?: It is suited to CSP plant operations analysis, molten salt storage management, charge and discharge scheduling, and equipment condition monitoring. It can also support fine-tuning and testing models for temporal state prediction, change event recognition, and anomaly assessment.

Can't find the data you need?

Post a request and let data providers reach out to you.

Get this Dataset

High-quality data, ready for your next AI breakthrough.

Cite this Work

@dataset{Mobiusi2026,
  title={Molten Salt Thermal Energy Storage System State Prediction Dataset},
  author={MOBIUSI INC},
  year={2026},
  url={https://www.mobiusi.com/datasets/39b1d97fbded76a6f70a9605555df0d9?dataset_task_cate_id=11},
  urldate={2026-10-28},
  keywords={molten salt storage dataset,CSP data,thermal storage state prediction,molten salt time series,charge discharge recognition,equipment condition monitoring,state change detection,CSP model fine-tuning},
  version={1.0}
}

Using this in research? Please cite us.

placeholder

Scene

Domain

Modality

Task