Cold end optimization system based on DCS
By designing DCS-based data acquisition and intelligent diagnostic models in the cold-end optimization system, the problem of inapplicability of the optimization results caused by the dependence of the DCS system on communication network is solved, and more efficient cold-end system operation and prediction accuracy are achieved.
Patent Information
- Application Number
- CN202411912795.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-24
- Publication Date
- 2025-04-15
AI Technical Summary
In the application of DCS systems in the field of cold-end optimization, due to their high dependence on communication networks, they are susceptible to network failures or instability, which leads to the optimization results not applicable to the current equipment operation status.
A cold-end optimization system based on DCS is designed to obtain cold-end data in real time through the DCS data acquisition end, and add instantaneous timestamps to the offline data processing end to form an instantaneous data set. The system has built-in intelligent diagnostic model based on VAR model, performs trend prediction and verification, and generates cold-end diagnostic results and optimization strategies.
It improves the operating efficiency and prediction accuracy of the cold-end system, reduces dependence on the communication network, and avoids affecting the operation of the entire control system due to network failure or instability.
Smart Images
Figure BDA0005206149660000051 
Figure BDA0005206149660000052 
Figure BDA0005206149660000053
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power plant cold end intelligence, and in particular to a DCS-based cold end optimization system. Background Art
[0002] The cold end system is an important part of the generator set, including the low-pressure cylinder body and its heat recovery steam extraction system, exhaust port and condenser system, circulating water system, sealing system and vacuum system, cooling tower system and other subsystems. The core purpose of this system is to convert the exhaust gas of the steam turbine into condensed water, so that the power generation process can heat the water into steam again to achieve continuous power generation. The operating quality of the cold end system is directly related to the vacuum degree of the generator set, and the vacuum degree or back pressure of the steam turbine of a large generator set has a significant impact on its energy consumption level and economy. Research data shows that when the back pressure exceeds the critical back pressure, the coal consumption of power generation will increase by 2-3g / KWh for every 1KPa increase in back pressure. Therefore, the operating goal of the cold end system is to strive to achieve the best vacuum degree or the lowest back pressure under certain circulating water system power consumption conditions.
[0003] DCS (distributed control system) has certain applications in the field of industrial cold end. Due to its distributed structure, the communication of DCS system has become an issue that cannot be ignored, which may affect the overall performance and stability of the system. Since the DCS system is highly dependent on the communication network, network failure or network instability may affect the operation of the entire optimization system, resulting in the optimization results being unsuitable for the current equipment operation status. Summary of the invention
[0004] The present invention is intended to provide a DCS-based cold end optimization system, which optimizes the operation of the cold end by collecting and analyzing the DCS-based cold end data.
[0005] To achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a DCS-based cold end optimization system, including a DCS data acquisition end and an offline data processing end, wherein the DCS data acquisition end acquires cold end data including cold end historical data and cold end real-time data; the data acquisition end is connected to the offline data processing end; the offline data processing end adds an instantaneous timestamp to the cold end real-time data to obtain an instantaneous data set; the offline data processing end inputs the instantaneous data set into a built-in intelligent diagnosis model, and outputs a cold end diagnosis result including an instantaneous timestamp.
[0006] Preferably, as an improvement, the intelligent diagnosis model built into the offline data processing end is based on a VAR model, and an instantaneous data set is input. The intelligent diagnosis model performs trend prediction on the cold end working condition to obtain a prediction result.
[0007] Preferably, as an improvement, the offline data processing end verifies the prediction results, and the verification is to compare the deviation of the prediction results with the corresponding instantaneous data set; the cold end data includes the rotation speed of the enhanced heat exchange device, the inlet and outlet water temperatures of the condenser, and the real-time flow rate of the circulating water.
[0008] Preferably, as an improvement, the offline data processing end forms a mapping relationship between the prediction result and the instantaneous data set of the cold end, and uses the instantaneous data set of the cold end to perform machine learning on the intelligent diagnosis model.
[0009] Preferably, as an improvement, the cold end diagnosis result output by the offline data processing end includes a verification prediction result, which is a prediction result obtained by the offline data processing through the cold end historical data and the cold end real-time data.
[0010] Preferably, as an improvement, the offline data processing end verifies the cold end historical data in the intelligent diagnosis model, and generates a cold end verification instruction and a cold end verification optimization strategy.
[0011] Preferably, as an improvement, the offline data processing end inputs the cold end optimization instructions and the cold end verification optimization strategy into the intelligent diagnosis model, and establishes a correspondence between the verification data of each cold end device and the cold end optimization instructions and the cold end verification optimization strategy.
[0012] Preferably, as an improvement, the prediction result at time t+1 is a prediction value calculated by using the instantaneous data sets at time t and time t-1.
[0013] Preferably, as an improvement, the instantaneous data set at time t+1 is used to remove abnormal points in the instantaneous data sets at time t and time t-1.
[0014] Preferably, as an improvement, the instantaneous data set at time t+1 is used to correct the abnormal points in the instantaneous data sets at time t and time t-1.
[0015] The principle and advantages of this solution are: the cold end optimization system obtains cold end data in real time through the DCS data acquisition end, and adds instantaneous timestamps to these data at the offline data processing end to form an instantaneous data set. This ensures the timeliness and accuracy of the data and provides a reliable foundation for subsequent intelligent diagnosis. The system has a built-in intelligent diagnosis model based on the VAR model, which can use the instantaneous data set to predict the trend of the cold end working conditions. This prediction capability helps to discover potential problems in advance, thereby optimizing the cold end operation strategy. The system verifies the prediction results and ensures the accuracy of the prediction by comparing the deviation between the prediction results and the actual instantaneous data set. At the same time, for the abnormal points found, the system can use the instantaneous data set at the subsequent moment to eliminate or correct them, further improving the reliability of the data and the accuracy of the model. The system forms a mapping relationship between the prediction results and the instantaneous data set of the cold end, and uses these data to perform machine learning on the intelligent diagnosis model. This continuous learning process enables the model to continuously adapt to changes in cold end working conditions and improve the accuracy and efficiency of diagnosis. The system not only provides cold end diagnosis results, but also generates cold end verification instructions and optimization strategies based on cold end historical data and real-time data, which helps to achieve comprehensive optimization of cold end operation. By using the instantaneous data set at the subsequent moment to eliminate or correct the abnormal points in the previous data, the system effectively handles the noise and abnormal values in the data and improves the quality and reliability of the data.
[0016] In summary, the DCS-based cold-end optimization system not only improves the accuracy of prediction through technical means such as real-time data acquisition, intelligent diagnosis and prediction, verification and correction, machine learning optimization, and comprehensive optimization strategies, but also continuously optimizes model performance through verification mechanisms and machine learning, thereby reducing dependence on communication networks and avoiding network failures or instability that affect the operation of the entire control system. DETAILED DESCRIPTION
[0017] The following is further described in detail through specific implementation methods:
[0018] The specific implementation steps are as follows: a DCS-based cold end optimization system, including a DCS data acquisition terminal and an offline data processing terminal, wherein the DCS data acquisition terminal acquires cold end data including cold end historical data and cold end real-time data; the data acquisition terminal is connected to the offline data processing terminal; the offline data processing terminal adds an instantaneous timestamp to the cold end real-time data to obtain an instantaneous data set; the offline data processing terminal inputs the instantaneous data set into a built-in intelligent diagnosis model, and outputs a cold end diagnosis result including an instantaneous timestamp.
[0019] Responsible for obtaining cold end data in real time, including cold end historical data and cold end real-time data. These data cover key parameters such as the speed of the enhanced heat exchange device, the inlet and outlet water temperature of the condenser, and the real-time flow rate of circulating water, providing a comprehensive and accurate information basis for subsequent cold end operating condition analysis.
[0020] Offline data processing terminal: connected to the DCS data acquisition terminal, receiving and processing real-time data. The processing process includes adding instantaneous timestamps to the cold end real-time data to form an instantaneous data set for subsequent accurate time series analysis. The offline data processing terminal has a built-in intelligent diagnosis model based on the VAR model. The model can use the instantaneous data set to predict the trend of the cold end working condition, discover potential problems in advance, and provide decision support for operators.
[0021] For example, suppose that in the cold end system of a power plant, real-time data such as the speed of the enhanced heat exchange device and the inlet and outlet water temperature of the condenser are obtained through the DCS data acquisition terminal. After the offline data processing terminal inputs this data into the VAR model, the model predicts that in the next few hours, due to the increase in ambient temperature, the condenser inlet water temperature may increase significantly, thereby affecting the operating efficiency of the unit. Based on this, the operating personnel can adjust the cooling water flow in advance or take other measures to cope with the upcoming high temperature challenges.
[0022] Verification mechanism: The offline data processing end verifies the prediction results and evaluates the accuracy of the prediction by comparing the deviation between the prediction results and the corresponding instantaneous data set. This process helps to timely discover and correct deviations in the model and improve the reliability of the prediction.
[0023] In the above example, suppose the model predicts that the condenser inlet water temperature will rise by 5°C in the next two hours, but the actual monitored data shows that it has only risen by 3°C. The offline data processing end records this deviation and may trigger adjustments or optimizations to the model to improve the accuracy of subsequent predictions.
[0024] The offline data processing end maps the prediction results to the instantaneous data set of the cold end, and uses this data to perform machine learning on the intelligent diagnosis model. This process enables the model to continuously learn and adapt to changes in the cold end operating conditions, improving the accuracy and efficiency of diagnosis. As the power plant's operating time increases, the operating conditions of the cold end system may change for various reasons. Through continuous machine learning optimization, it can gradually adapt to these changes and improve the ability to predict future operating conditions. If the power plant has modified or upgraded the cooling tower, the model will be able to automatically adjust its prediction algorithm to more accurately reflect the characteristics of the new operating conditions.
[0025] After verifying the cold end historical data in the intelligent diagnosis model, the system can generate cold end verification instructions and cold end verification optimization strategies. These strategies provide improvement suggestions for the specific operating conditions of each cold end device, which helps to reduce energy consumption and improve operating efficiency. Based on an in-depth analysis of historical data, the system may find that a circulating water pump has low operating efficiency under specific operating conditions. Therefore, in the cold end optimization instructions, it is recommended to adjust the operating parameters of the water pump or consider replacing a more efficient water pump model. At the same time, by establishing a correspondence between the verification data of each cold end device and the optimization instructions, the system can ensure that these optimization measures are effectively implemented and monitored.
[0026] The DCS-based cold-end optimization system achieves comprehensive monitoring and optimization of cold-end operating conditions by integrating functional modules such as real-time data acquisition, intelligent diagnosis and prediction, and machine learning optimization. These optimization improvements not only improve the prediction accuracy and operating efficiency of the system, but also provide strong support for energy conservation, emission reduction, cost reduction and efficiency improvement in industrial fields such as power plants.
[0027] The prediction result at time t+1 is the prediction value calculated by the instantaneous data set at time t and time t-1. The instantaneous data set at time t+1 is used to remove the abnormal points in the instantaneous data set at time t and time t-1. The instantaneous data set at time t+1 is used to correct the abnormal points in the instantaneous data set at time t and time t-1.
[0028] For example, to obtain the cold end real-time data, the following cold end real-time data is obtained at a certain moment:
[0029] Circulating water real-time flow rate: 1500m 3 / h;
[0030] Speed data of enhanced heat exchange device: 3000rpm.
[0031] The data transmission end sends the above cold end real-time data to offline data processing. After receiving the data, the offline data processing adds an instantaneous timestamp to each data (assuming it is 2024-12-12T16:20:00Z) to obtain the instantaneous data set:
[0032]
[0033] Generate cold end diagnosis results: Offline data processing inputs the instantaneous data set into the intelligent diagnosis model based on the VAR model. The model predicts the trend of the cold end working condition. Assuming that the prediction result is that the real-time flow rate of circulating water will rise to 1550m in the next 10 minutes, the cold end working condition will be predicted. 3 / h, the speed of the enhanced heat exchanger will remain unchanged. Offline data processing outputs the prediction results together with the instantaneous timestamp (assuming it is 2024-12-12T16:20:00Z) to form the cold end diagnosis results:
[0034]
[0035] Verify the prediction results: Offline data processing verifies the prediction results, that is, compares the prediction results with the corresponding instantaneous data set. Assume that offline data processing uses historical instantaneous data sets (that is, previously collected and timestamped data) to verify the accuracy of the model. For example, offline data processing may find that the prediction error rate of the model under similar working conditions in the past is within 5%, so the current prediction result is considered reliable.
[0036] Forming a mapping relationship and performing machine learning: Through offline data processing verification, a mapping relationship is formed between the prediction results and the instantaneous data set at the cold end. Offline data processing can use these instantaneous data sets with timestamps for continuous machine learning of the intelligent diagnosis model to optimize the model's prediction performance. For example, offline data processing uses algorithms such as gradient descent to adjust model parameters to minimize prediction errors.
[0037] The instantaneous data set includes Y1 at time point t: real-time flow of circulating water; Y2: heat load of condenser; and Y3: efficiency of cooling tower.
[0038] The intelligent diagnosis model is:
[0039]
[0040] Among them, c1, c2, c3 are constant terms, ij, k are lag term coefficients, and it is the error term.
[0041] The prediction result at time t+1 is the prediction value calculated by the instantaneous data set at time t and time t-1.
[0042] The instantaneous data set at time t+1 is used to remove abnormal points in the instantaneous data sets at time t and time t-1.
[0043] The instantaneous data set at time t+1 is used to correct the abnormal points in the instantaneous data sets at time t and time t-1.
[0044] For example, there is the following time series data, which records the instantaneous data sets at time points t, t-1, and t+1, including Y1: real-time flow rate of circulating water (unit: m 3 / h), Y2: condenser heat load (unit: MW), Y3: cooling tower efficiency (unit: %).
[0045]
[0046] Outlier Detection
[0047] Determine the value of Y1 (real-time flow of circulating water) at time point t, 1500m 3 / h is an abnormally high value. Similarly, we can detect whether there are abnormal points in other variables and other time points.
[0048] Outlier removal
[0049] If you choose to remove this outlier, you can delete the Y1 value at time t from the data set, or fill in the missing value. Here, just delete the value directly.
[0050] The dataset after removing outliers may look like this:
[0051]
[0052] In practical applications, directly deleting data points may not be the best choice because it will reduce the sample size of the data set. A better approach may be outlier correction.
[0053] If we choose to correct this outlier, we can use the data at time t+1 to help us find a more reasonable value to replace it. We can assume that the value of Y1 changes smoothly between adjacent time points and use linear interpolation or other more complex interpolation methods to estimate the value of Y1 at time t.
[0054] The dataset after correcting the outliers using linear interpolation might look like this:
[0055]
[0056] Here, we use (1200m 3 / h+1300m 3 / h) / 2=1250m 3 / h as the corrected value of Y1 at time t, but in order to keep it close to the original outlier value (and still be a "corrected" value), it is rounded to 1350m 3 / h.
[0057] Through the above process, we can see how to use the instantaneous data set at time t+1 to detect, remove and correct the outliers in the data sets at time t and time t-1. In practical applications, these steps need to be adjusted according to the characteristics of the data and the objectives of the analysis.
[0058] The cold end optimization system obtains cold end data in real time through the DCS data acquisition end, and adds instantaneous timestamps to these data at the offline data processing end to form an instantaneous data set. This ensures the timeliness and accuracy of the data, and provides a reliable foundation for subsequent intelligent diagnosis. The system has a built-in intelligent diagnosis model based on the VAR model, which can use the instantaneous data set to predict the trend of the cold end working conditions. This prediction capability helps to discover potential problems in advance, thereby optimizing the cold end operation strategy. The system verifies the prediction results and ensures the accuracy of the prediction by comparing the deviation between the prediction results and the actual instantaneous data set. At the same time, for the abnormal points found, the system can use the instantaneous data set at the subsequent moment to eliminate or correct them, further improving the reliability of the data and the accuracy of the model. The system forms a mapping relationship between the prediction results and the instantaneous data set of the cold end, and uses these data to perform machine learning on the intelligent diagnosis model. This continuous learning process enables the model to continuously adapt to changes in the cold end working conditions and improve the accuracy and efficiency of diagnosis. The system not only provides cold end diagnosis results, but also generates cold end verification instructions and optimization strategies based on the cold end historical data and real-time data, which helps to achieve comprehensive optimization of cold end operation. By using the instantaneous data set at a subsequent moment to eliminate or correct abnormal points in the previous data, the system effectively handles the noise and outliers in the data and improves the quality and reliability of the data.
[0059] In summary, the DCS-based cold-end optimization system not only improves the accuracy of prediction through technical means such as real-time data acquisition, intelligent diagnosis and prediction, verification and correction, machine learning optimization, and comprehensive optimization strategies, but also continuously optimizes model performance through verification mechanisms and machine learning, thereby reducing dependence on communication networks and avoiding network failures or instability that affect the operation of the entire control system.
[0060] The above is only an embodiment of the present invention, and the common knowledge such as the known specific technical schemes and / or characteristics in the scheme is not described in detail here. It should be pointed out that for those skilled in the art, several variations and improvements can be made without departing from the technical scheme of the present invention. In the present invention, unless otherwise clearly specified and limited, the terms "install", "connect", "connect", "fix" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal connection of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The scope of protection claimed in this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.
Claims
1. A DCS-based cold end optimization system, characterized by: It includes a DCS data acquisition terminal and an offline data processing terminal, wherein the DCS data acquisition terminal acquires cold end data including cold end historical data and cold end real-time data; The data acquisition end is connected to the offline data processing end; the offline data processing end adds an instantaneous timestamp to the cold end real-time data to obtain an instantaneous data set; the offline data processing end inputs the instantaneous data set into a built-in intelligent diagnosis model and outputs a cold end diagnosis result including an instantaneous timestamp.
2. The DCS-based cold end optimization system according to claim 1, characterized in that: The intelligent diagnosis model built into the offline data processing end is based on the VAR model. The instantaneous data set is input, and the intelligent diagnosis model performs trend prediction on the cold end working condition to obtain a prediction result.
3. The cold end optimization system based on DCS according to claim 1, characterized in that: The offline data processing end verifies the prediction results, and the verification is to compare the deviation of the prediction results with the corresponding instantaneous data set; the cold end data includes the rotation speed of the enhanced heat exchange device, the inlet and outlet water temperatures of the condenser, and the real-time flow rate of the circulating water.
4. The DCS-based cold end optimization system according to claim 3, characterized in that: The offline data processing end maps the prediction results with the instantaneous data set of the cold end, and uses the instantaneous data set of the cold end to perform machine learning on the intelligent diagnosis model.
5. The cold end optimization system based on DCS according to claim 1, characterized in that: The cold end diagnosis results output by the offline data processing end include verification prediction results, which are the prediction results obtained by offline data processing through cold end historical data and cold end real-time data.
6. The cold end optimization system based on DCS according to claim 1, characterized in that: The offline data processing end verifies the cold end historical data in the intelligent diagnosis model, and generates a cold end verification instruction and a cold end verification optimization strategy.
7. The cold end optimization system based on DCS according to claim 6, characterized in that: The offline data processing end inputs the cold end optimization instruction and the cold end verification optimization strategy into the intelligent diagnosis model, and establishes the corresponding relationship between the verification data of each cold end device and the cold end optimization instruction and the cold end verification optimization strategy.
8. The DCS-based cold end optimization system according to claim 7, characterized in that: The prediction result at time t+1 is the prediction value calculated by the instantaneous data set at time t and time t-1.
9. The DCS-based cold end optimization system according to claim 1, characterized in that: The instantaneous data set at time t+1 is used to remove abnormal points in the instantaneous data sets at time t and time t-1.
10. The DCS-based cold end optimization system according to claim 2, characterized in that: The instantaneous data set at time t+1 is used to correct the abnormal points in the instantaneous data sets at time t and time t-1.