Method and system for realtime monitoring and forecasting of fouling of air preheater equipment

Patent metadata

Field	Value
Publication number	US-12044400-B2
Application number	US-202017753779-A
Country	US
Kind code	B2
Filing date	Oct 9, 2020
Priority date	Oct 9, 2019
Publication date	Jul 23, 2024
Grant date	Jul 23, 2024

Abstract

This disclosure relates generally to a method and system for real time monitoring and forecasting of fouling of an air preheater (APH) in a thermal power plant. The system is deploying a digital replica or digital twin that works in tandem with the real APH of the thermal power plant. The system receives real-time data from one or more sources and provides real-time soft sensing of intrinsic parameters as well as that of health, fouling related parameters of APH. The system is also configured to diagnose the current class of fouling regime and the reasons behind a specific class of fouling regime of the APH. The system is also configured to be used as advisory system that alerts and recommends corrective actions in terms of either APH parameters or parameters controlled through other equipment such as selective catalytic reduction or boiler or changes in operation or design.

First claim

We claim:

1. A processor implemented method for real time monitoring and forecasting of fouling of an air preheater (APH) in a thermal power plant, the method comprising:
receiving, via a user interface, a plurality of data related to the thermal power plant from one or more sources;
preprocessing, via one or more hardware processors, the received plurality of data;
monitoring, via the one or more hardware processors, the air preheater using a plurality of monitoring models, the plurality of monitoring models is configured to soft-sense a set of fouling parameters, wherein the set of fouling parameters comprises:
a temperature profile of flue gas, air streams and regenerative packing of the APH,
a quantity and a location of the fouling material deposition in one or more layers of the APH, and
a fouling index and a pressure profile in each of the one or more layers of the APH, wherein the fouling index and the pressure profile indicate fouling condition of the APH;
diagnosing, via the one or more hardware processors, using a diagnostic model, a current fouling regime in the APH using the preprocessed plurality of data and the soft sensed fouling parameters, wherein the diagnosis provides:
classification of current fouling regime of APH, and
one or more influencing parameters of current fouling regime;
forecasting, via the one or more hardware processors, using a forecasting model, the fouling condition for a forecast horizon, wherein the forecast is obtained through:
estimating one or more influencing parameters for an estimation horizon using the received plurality of data,
forecasting the fouling index for each of the one or more layers of APH for the selected forecast horizon using the estimated one or more influencing parameters and the classified fouling regime, and
forecasting the fouling conditions comprising of pressure drop for the selected forecast horizon using the estimated one or more influencing parameters and the forecasted fouling index for each layer;
estimating, via the one or more hardware processors, a minimum time to outage of the APH based on the forecasted fouling conditions and the classified fouling regime;
providing, via the one or more hardware processors, an alert to a user if the estimated minimum time to plant outage is less than a predefined threshold; and
recommending via the one or more hardware processors, a plurality of corrective actions to minimize the losses and avoid the plant outage based on forecasted fouling conditions and classified fouling regime.

2. The method according to claim 1 , wherein the plurality of data related to the thermal power plant comprises:
real-time operation data from a plurality of sensors for the APH and upstream and downstream equipment,
ambient conditions data from internal or external sources,
fuel and materials property, usage and inventory data,
design specifications data for the APH and the thermal power plant; and
maintenance history and scheduling data.

3. The method according to claim 1 , the one or more sources comprises of distributed control system (DCS), historian, laboratory information management system (LIMS), databases, advanced sensors, external sources, manual input and other digital systems in plant.

4. The method according to claim 1 , wherein the preprocessing comprises one or more of:
checking erroneous data in the plurality of data,
removing outliers in the plurality of data,
imputing new values in place of missing values,
merging and synchronizing plant data from multiple sources,
synchronizing the plurality of data with the past data, and
transforming the plurality of data into different shape, size and frequency based on the APH design specifications, forecasting horizon and the available plant data.

5. The method according to claim 1 , wherein the estimation horizon and the forecast horizon are selected by a user or set automatically.

6. The method according to claim 1 , wherein the provided alert is one of a short-term alert or a long-term alert, wherein
the short-term alert is generated when one of the plurality of fouling conditions is crossing a predefined threshold before a predefined set period, and
the long-term alert is generated when one of the plurality of fouling conditions is crossing the predefined threshold after the predefined set period.

7. The method according to claim 1 , wherein corrective actions comprise of:
a short-term recommendation of operation and maintenance suggestions comprising modifying operation settings of the APH or upstream/downstream equipment, modifying soot-blowing parameters and cleaning of the APH, and
a long-terms recommendation of operation and maintenance suggestions comprising alternate usage of fuels, relaxed pollutant norms and modification of equipment.

8. The method according to claim 1 , wherein the forecasting is performed after every predefined time interval.

9. The method according to claim 1 , wherein the fouling regimes are classified into one of under normal fouling, abnormal fouling and severe fouling regimes.

10. The method according to claim 1 , further comprising providing a notification to the user about the identified one or more causes of the current fouling condition.

11. The method according to claim 1 , further comprising displaying on a display device:
the real-time predicted fouling material deposition and location;
the real-time temperature profile of gas/air/metal, real-time pressure profile and real-time fouling index of each layer of APH
the real-time classification of current fouling regime
the real time forecasted results of fouling index and pressure drop for each of the layers of APH, and
the real-time recommendations.

12. The method according to claim 1 further comprising re-calibrating the plurality of models periodically based on the plant data accumulated in the database and the plurality of model tuning parameters stored in the database.

13. A system for real time monitoring and forecasting of fouling of an air preheater (APH) in a thermal power plant, the system comprises:
an input/output interface for receiving a plurality of data related to the thermal power plant from one or more sources;
one or more hardware processors;
a memory in communication with the one or more hardware processors, wherein the one or more first hardware processors are configured to execute programmed instructions stored in the one or more first memories, to:
preprocess the received plurality of data;
monitor the air preheater using a plurality of monitoring models, the plurality of monitoring models is configured to soft-sense a set of fouling parameters, wherein the set of fouling parameters comprises:
a temperature profile of flue gas, air streams and regenerative packing of the APH,
a quantity and a location of the fouling material deposition in one or more layers of the APH, and
a fouling index and a pressure profile in each of the one or more layers of the APH, wherein the fouling index and the pressure profile indicate fouling condition of the APH;
diagnosis using a diagnostic model, a current fouling regime in the APH using the preprocessed plurality of data and the soft sensed fouling parameters, wherein the diagnosis provides:
classification of current fouling regime of APH, and
one or more influencing parameters of current fouling regime;
forecast using a forecasting model, the fouling condition for a forecast horizon, wherein the forecast is obtained through:
estimating one or more influencing parameters for an estimation horizon using the received plurality of data,
forecasting the fouling index for each of the one or more la

Assignees

• Tata Consultancy Services Ltd

Inventors

• Deodhar Anirudh
• Jadhav Vishal
• Gupta Ashit
• Ramanujam Muralikrishnan
• Runkana Venkataramana
• Patil Mukul
• Dhanda Charan Theja
• Subramaniam Dhandapani
• Jain Lalith Roshanlal
• Diraviam Andrew Joel Thomson
• Malhotra Pankaj
• Parameswran Sai Prasad

Classifications

• G05B23/0221

  Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods · CPC title

• G05B13/048

  using a predictor · CPC title

• F28G15/003

  Control arrangements · CPC title

• F23N3/002

  using electronic means (F23N3/02 - F23N3/08 take precedence) · CPC title

• F23L15/04

  Arrangements of recuperators · CPC title