Converter valve internal cooling system dissolved oxygen strong correlation factor analysis method and device

Abstract

The invention provides a converter valve internal cooling system dissolved oxygen strong correlation factor analysis method and a converter valve internal cooling system dissolved oxygen strong correlation factor analysis device, and belongs to the technical field of converter valve cooling. Parameters of cooling water temperature, cooling water conductivity, cooling water flow and exposure time of internal cooling water in air are acquired by utilizing a control variable method, and meanwhile, an internal cooling water oxygen content parameter at a corresponding moment is acquired; and establishing a regression model by using a least square support vector machine to confirm the internal cooling water oxygen content strong correlation factor. The method can quickly and accurately confirm the strong correlation factors of the oxygen content of the internal cooling water, and has important significance for protecting equipment and improving the production safety and efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of converter valve cooling, and in particular relates to a method and device for analyzing a strongly correlated factor of dissolved oxygen in a converter valve inner cooling system. Background Art

[0002] Each valve group in a DC converter station is equipped with an independent valve cooling system, consisting of internal and external cooling systems. The internal cooling system directly cools the converter valves, preventing overheating and potentially damaging components such as thyristors and accelerating aging. The internal cooling system piping within the valve towers used to cool the converter valves is equipped with a number of platinum electrodes to clamp the potential of the internal cooling water circuit and suppress the electrolytic current. Higher dissolved oxygen levels in the internal cooling water increase the likelihood of platinum electrodes scaling, severely impacting their electrical conductivity and posing a significant threat to the stable operation of the converter valves. After valve tower maintenance, internal cooling system repairs, and cooling water drainage, the dissolved oxygen content in the cooling water is typically around 2000 ppb, far exceeding the State Grid industry standard of no more than 200 ppb. Therefore, during valve tower maintenance, internal cooling system repairs, and cooling water drainage, dissolved oxygen removal from the cooling system is necessary.

[0003] Currently, all converter stations in China that use the Gaolan and Xuji Jingrui valve cooling systems lack truly fast and safe nitrogen deoxygenation capabilities. Nitrogen deoxygenation requires significant amounts of high-purity nitrogen and considerable time. During natural operation, nitrogen replacement of dissolved oxygen typically requires over 40 days to reduce the dissolved oxygen level in the cooling water to below 200 ppb. During valve tower maintenance, internal water cooling system repairs, and cooling water draining, despite the use of sealed containers, significant amounts of oxygen still enter the cooling water, causing the dissolved oxygen content to exceed the standard. Numerous factors influence the dissolved oxygen content in converter station cooling systems: cooling water temperature, cooling water conductivity, cooling water flow rate, and the time the cooling water is exposed to air. However, no relevant domestic research has identified any key, strongly correlated factors. Summary of the Invention

[0004] Aiming at the uncertainty of the strong correlation factor of dissolved oxygen content in cooling water of current converter valve internal cooling system, a method for analyzing the strong correlation factor of dissolved oxygen in converter valve internal cooling system and a device for implementing the method are provided.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for analyzing a strongly correlated factor of dissolved oxygen in a converter valve internal cooling system comprises the following steps: Step 1: Collect the various change factors and oxygen content parameters of the internal cooling water during operation, where the change factors include cooling water temperature, cooling water conductivity, cooling water flow rate and internal cooling water exposure time in the air; Step 2: Use the least squares support vector machine to build a regression model for the data collected in step 1 to confirm the strong correlation factors.

[0006] Furthermore, the parameter collection method is to fix three of the change factor parameters in sequence, continuously change and collect the fourth change factor parameter, and simultaneously collect the internal cooling water oxygen content parameter at the same time.

[0007] Furthermore, the abnormal values of the acquisition parameters are subjected to a two-out-of-three mechanism.

[0008] Furthermore, when a regression model is established based on the collected parameters using the least squares support vector machine to confirm the strong correlation factors, let: , in, is a set of linearly independent functions selected in advance, is the undetermined coefficient , the fitting criterion is to make and distance The sum of squares is the smallest, which is called the least squares criterion; set up is a pair of observations, which in this embodiment are the oxygen content of the inner cooling water at consecutive time points and the current moment, and Satisfies the following theoretical function: , in is a parameter to be determined; To find the function Parameters The optimal estimate of , for a given m groups (usually m>n) of observations , solve the objective function: , The parameter with the minimum value ; For unconstrained optimization problems, the general form of the least squares method is: , in It is called the residual function.

[0009] Furthermore, by comparing the slope values of the fitted graphs of the change of the oxygen content of the inner cold water with time when one of the four change factors was changed one by one obtained by establishing the regression model, it was confirmed that the dissolved oxygen in the inner cold water had a strong correlation factor.

[0010] A device for analyzing dissolved oxygen-related factors in a converter valve internal cooling system, comprising: The data acquisition module is used to obtain real-time data of four change factors and dissolved oxygen content during internal cooling water operation; The data processing module is used to obtain the time-varying trend of the dissolved oxygen content in the inner cold water when only the values of different single change factors are changed through the least squares method, and to find the strong correlation factors affecting the dissolved oxygen in the inner cold water by comparing the corresponding trends of different change factors.

[0011] Compared with the prior art, the present invention has the following beneficial effects: 1) Compared with the traditional single-factor analysis method, the efficiency is greatly improved, and the accuracy of identifying strongly correlated factors is high; 2) It can capture nonlinear interaction effects (such as the multiplicative effect of temperature-flow coupling on dissolved oxygen); 3) Establish a dynamic map of the influence weights of each factor (with a time resolution of minutes); 4) Provide guidance on optimizing cooling system operating parameters to reduce the rate of dissolved oxygen exceeding the standard and provide support for early warning of faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a flow chart of a method for analyzing dissolved oxygen-related factors in a converter valve internal cooling system according to a first embodiment of the present invention; Figure 2 This is a structural diagram of a correlation factor parameter acquisition and monitoring simulation platform according to a first embodiment of the present invention; Figure 3 This is a structural diagram of a device for analyzing dissolved oxygen-related factors in a converter valve internal cooling system according to a second embodiment of the present invention. DETAILED DESCRIPTION

[0013] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention. Example 1

[0014] The method for analyzing the strongly correlated factors of dissolved oxygen in the converter valve internal cooling system includes the following steps: 1) Collect various change factors and oxygen content parameters during internal cooling water operation.

[0015] See Figure 1 and Figure 2 Factors influencing dissolved oxygen in the converter station cooling system include cooling water temperature, cooling water conductivity, cooling water flow rate, and the time the internal cooling water is exposed to air. Pipeline pressure and flow rate are directly proportional. By varying the value of any one of these four parameters while keeping the remaining three constant, multiple sets of experimental data with continuously controlled variables can be obtained.

[0016] Multiple sensors are used for synchronous data collection, and the sampling frequency of each sensor is 1Hz. A two-out-of-three mechanism is applied to the abnormal values of the data collected by the sensors.

[0017] 2) Based on the collected parameters, a regression model was established using the least squares support vector machine to confirm the strong correlation factors.

[0018] The least squares method is a mathematical tool that is widely used in many fields of data processing, such as error estimation, uncertainty, system identification, prediction, and forecasting. It is a mathematical optimization technique. It finds the best function matching the data by minimizing the sum of squares of errors. The least squares method can be used to easily obtain unknown data and minimize the sum of squares of errors between the obtained data and the actual data. The least squares method is the most commonly used method to solve curve fitting problems. Its basic idea is: let

[0019] in, is a set of linearly independent functions selected in advance, is the undetermined coefficient , the fitting criterion is to make and distance The sum of squares is minimized, which is called the least squares criterion.

[0020] set up is a pair of observations, which in this embodiment are the oxygen content of the inner cooling water at consecutive time points and the current moment, and Satisfies the following theoretical function:

[0021] in To be determined parameters.

[0022] To find the function Parameters The optimal estimate of , for a given m groups (usually m>n) of observations , solve the objective function:

[0023] The parameter with the minimum value .

[0024] For unconstrained optimization problems, the general form of the least squares method is:

[0025] in It is called the residual function.

[0026] By comparing the slope values of the fitted graphs of the change of internal cold water oxygen content with time when one of the four change factors is changed one by one, the strong correlation factor affecting the dissolved oxygen in internal cold water is confirmed. Example 2

[0027] See Figure 3 This embodiment provides a device for analyzing factors strongly correlated with dissolved oxygen in converter valve cooling systems. This embodiment is applicable to analyzing factors strongly correlated with dissolved oxygen in converter valve cooling systems. The device can be implemented using software and / or hardware and integrated into any device that provides analysis of factors strongly correlated with dissolved oxygen in converter valve cooling systems. The device features adjustable cooling water temperature (-20-80°C), cooling water flow rate (0.5-5 m³ / h), cooling water conductivity (0.1-500 μS / cm), and cooling water exposure time to air (±0.5 second accuracy).

[0028] Among them, the data acquisition module is used to obtain real-time data of four change factors and dissolved oxygen content during the operation of internal cooling water; The data processing module is used to obtain the time-varying trend of the dissolved oxygen content in the inner cold water when only the values of different single change factors are changed through the least squares method, and to find the strong correlation factors affecting the dissolved oxygen in the inner cold water by comparing the corresponding trends of different change factors.

[0029] The above-mentioned product can execute the method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0030] Finally, it should be noted that the above embodiments are only preferred embodiments of the present invention and are only used to illustrate the technical solution of the present invention rather than to limit it. Any modifications, improvements, other modifications or equivalent replacements made to the technical solution of the present invention by ordinary technicians in this field, as long as they do not depart from the spirit and scope of the technical solution of the present invention, should be included in the scope of protection of the present invention.

Claims

1. A method for analyzing strongly correlated factors of dissolved oxygen in a converter valve internal cooling system, characterized in that: The steps include: Step 1: Collect the various change factors and oxygen content parameters of the internal cooling water during operation, where the change factors include cooling water temperature, cooling water conductivity, cooling water flow rate and internal cooling water exposure time in the air; Step 2: Use the least squares support vector machine to build a regression model for the data collected in step 1 to confirm the strong correlation factors.

2. The method for analyzing dissolved oxygen-related factors in a converter valve internal cooling system according to claim 1, characterized in that: The parameter collection method is to fix three of the change factor parameters in turn, continuously change the fourth change factor parameter and collect them, and at the same time collect the internal cooling water oxygen content parameter at the same time.

3. The method for analyzing dissolved oxygen-related factors in a converter valve internal cooling system according to claim 1, characterized in that: The abnormal values of the acquisition parameters are subjected to a two-out-of-three mechanism.

4. The method for analyzing dissolved oxygen-related factors in a converter valve internal cooling system according to claim 1, characterized in that: When establishing a regression model based on the collected parameters using the least squares support vector machine to confirm the strong correlation factors, let: ,in, is a set of linearly independent functions selected in advance, is the undetermined coefficient , the fitting criterion is to make and distance The sum of squares is the smallest, which is called the least squares criterion; set up is a pair of observations, which in this embodiment are the oxygen content of the inner cooling water at consecutive time points and the current moment, and Satisfies the following theoretical function: ,in is a parameter to be determined; To find the function Parameters The optimal estimate of , for a given m groups (usually m>n) of observations , solve the objective function: , taking the minimum parameter ; For unconstrained optimization problems, the general form of the least squares method is: ,in It is called the residual function.

5. The method for analyzing dissolved oxygen-related factors in a converter valve internal cooling system according to claim 4, characterized in that: By comparing the slope values of the fitted graphs of the change of the oxygen content of the inner cold water with time when one of the four change factors is changed one by one obtained by establishing the regression model, the strong correlation factor affecting the dissolved oxygen in the inner cold water is confirmed.

6. A device for analyzing dissolved oxygen-related factors in a converter valve internal cooling system, characterized in that: include: The data acquisition module is used to obtain real-time data of four change factors and dissolved oxygen content during internal cooling water operation; The data processing module is used to obtain the time-varying trend of the dissolved oxygen content in the inner cold water when only the values of different single change factors are changed through the least squares method, and to find the strong correlation factors affecting the dissolved oxygen in the inner cold water by comparing the corresponding trends of different change factors.

Images