Thyristor junction temperature prediction and evaluation method and system

Abstract

The invention discloses a thyristor junction temperature prediction evaluation method and system, and relates to the technical field of thyristor junction temperature prediction, and the method comprises the steps: obtaining a to-be-predicted parameter, and carrying out the data preprocessing of the to-be-predicted parameter, the to-be-predicted parameter comprising first prediction data and second prediction data; summarizing a first junction temperature prediction model according to the first prediction data, and inputting the first prediction data into the trained first junction temperature prediction model to obtain a first junction temperature prediction result; summarizing a second junction temperature prediction model according to the second prediction data, and inputting the second prediction data into the trained second junction temperature prediction model to obtain a second junction temperature prediction result; and fusing the first junction temperature prediction result and the second junction temperature prediction result to obtain a final junction temperature prediction result, and completing thyristor junction temperature prediction. Real-time prediction is combined with the current working state, the failure rate caused by the fact that overheating of the thyristor is not found is reduced, prediction is carried out through historical data and load changes, and the comprehensiveness of the prediction result is improved.

Description

Technical Field

[0001] The invention relates to the technical field of thyristor junction temperature prediction, and in particular to a thyristor junction temperature prediction and evaluation method and system. Background Art

[0002] The junction temperature of semiconductor switching devices such as thyristors during operation will directly affect the performance and life of the devices. Long-term high-temperature operation will lead to reduced performance of thyristors. For example, excessive leakage current will cause the thyristor to lose its blocking ability, resulting in uncontrolled misconduction, which will have an adverse effect on the operation of the converter valve, thereby shortening the service life of the thyristor. Under extreme conditions such as short circuits and lightning strikes in the power grid, the thyristor heats up sharply due to overloaded current in the system. The heat cannot be completely dissipated in a short time, resulting in excessively high internal junction temperature of the thyristor, and thermal breakdown and failure of the thyristor.

[0003] Therefore, there is an urgent need for a method that can quickly predict the junction temperature of the thyristor so that timely measures can be taken to prevent the internal junction temperature of the thyristor from being too high. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a thyristor junction temperature prediction and evaluation method and system, which can solve the problems mentioned in the background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a thyristor junction temperature prediction and evaluation method, which includes obtaining a parameter to be predicted and performing data preprocessing on the parameter to be predicted, wherein the parameter to be predicted includes first prediction data and second prediction data;

[0009] Summarizing a first junction temperature prediction model according to the first prediction data, inputting the first prediction data into the trained first junction temperature prediction model, and obtaining a first junction temperature prediction result;

[0010] Summarizing a second junction temperature prediction model according to the second prediction data, inputting the second prediction data into the trained second junction temperature prediction model, and obtaining a second junction temperature prediction result;

[0011] The first junction temperature prediction result and the second junction temperature prediction result are integrated to obtain the final junction temperature prediction result, thereby completing the thyristor junction temperature prediction.

[0012] As a preferred solution of the thyristor junction temperature prediction and evaluation method of the present invention, wherein: the first prediction data includes operating current, ambient temperature, thyristor material characteristic parameters and operating time;

[0013] The second prediction data includes historical operating current, historical ambient temperature, historical fault conditions, cooling system efficiency parameters, and load changes;

[0014] The data preprocessing includes data cleaning and data normalization.

[0015] As a preferred solution of the thyristor junction temperature prediction and evaluation method of the present invention, the step of obtaining the first junction temperature prediction result includes:

[0016] A first prediction function is defined according to the first prediction data, and a calculation formula of the first prediction function is as follows:

[0017]

[0018] Wherein, f(t) is the first prediction parameter, I0 is the current amplitude, T0 is the ambient temperature, α and β are the thyristor material characteristic constants;

[0019] Inputting the first prediction data into the first prediction function, and calculating the first prediction function to obtain a first prediction parameter;

[0020] The first prediction parameter is integrated to obtain a first junction temperature prediction result, and the calculation formula is as follows:

[0021]

[0022] Among them, T final1 is the first junction temperature prediction result, and t1 is the total working time.

[0023] As a preferred solution of the thyristor junction temperature prediction and evaluation method of the present invention, wherein: the second prediction model includes historical data prediction and load change prediction;

[0024] The historical data forecast includes:

[0025] Determine the coverage time range [t0,t n ], and determine the historical working current I(t) data covering the same time range [t0,t n ] historical ambient temperature T env (t) data;

[0026] For each time point t, where t∈[t0, t n ], calculate the current calibration function f1 and the ambient temperature calibration function f2, that is,

[0027] f1=I(t)·α(t)·e -βt

[0028] f2=T enν (t)·γ(t)·e -δt

[0029] Where I(t) is the coverage time range [t0,t n ] historical working current data, T env (t) is the coverage time range [t0,t n ] is the historical ambient temperature, α(t) is the correction coefficient, γ(t) is the environmental influence coefficient, β is the working current attenuation coefficient, and δ is the ambient temperature attenuation coefficient;

[0030] The calculation results of the current calibration function f1 and the ambient temperature calibration function f2 are calculated in the time range [t0,t n ] to obtain the preliminary forecast results based on historical data. The calculation formula is as follows:

[0031]

[0032] Among them, T part1 These are preliminary forecasts based on historical data.

[0033] As a preferred solution of the thyristor junction temperature prediction and evaluation method of the present invention, the load change prediction includes:

[0034] Determine the load power P at each time point i according to the second prediction data load (i) and the corresponding heat dissipation efficiency η(i) data, and determine the fault condition F according to the second prediction data fault (j) and its occurrence time t j data;

[0035] According to the load power P at each time point i load (i) and the corresponding heat dissipation efficiency η(i) data determine the load heat dissipation influence function F1, that is,

[0036]

[0037] Among them, P load (i) is the load power at the i-th time point, η(i) is the heat dissipation efficiency at the i-th time point, t i is the i-th time point, θ is the load change influence coefficient;

[0038] According to the fault condition F fault (j) and its occurrence time t j The data of the fault condition determines the fault condition impact function F2, that is,

[0039]

[0040] Among them, t j is the jth time point, F fault (j) is the jth fault condition;

[0041] The load heat dissipation influence function F1 and the fault condition influence function F2 are combined to obtain a load change prediction function, and the calculation formula is as follows:

[0042]

[0043] Among them, T part2 Predicted value for load change.

[0044] As a preferred solution of the thyristor junction temperature prediction and evaluation method of the present invention, wherein: the second junction temperature prediction result is obtained; including:

[0045] The preliminary prediction results of historical data T part1 and the initial prediction results of load changes T part2 According to the weight coefficient, weighted fusion is performed to obtain the second junction temperature prediction result, that is,

[0046] T final2 =λ1·T part1 +λ2·T part2

[0047] Among them, λ1 and λ2 are the historical data prediction weight and load change prediction weight respectively.

[0048] As a preferred solution of the thyristor junction temperature prediction and evaluation method of the present invention, wherein: the final junction temperature prediction result is obtained including:

[0049] The weighted average method is used to merge the first junction temperature prediction result and the second junction temperature prediction result, and the adjustment factor is introduced to optimize the prediction effect to obtain the final junction temperature prediction result. The calculation formula is as follows:

[0050] T final =(ωT final1 +L1·(1-ω)T final2 )·L2

[0051] Among them, ω is the final prediction weight, 0<ω<1, and L1 and L2 are dynamic adjustment factors.

[0052] In a second aspect, the present invention provides a thyristor junction temperature prediction and evaluation system, which includes: a data acquisition module, a first junction temperature prediction module, a second junction temperature prediction module and a final junction temperature prediction module;

[0053] The data acquisition module is used to obtain parameters to be predicted and perform data preprocessing on the parameters to be predicted, wherein the parameters to be predicted include first prediction data and second prediction data;

[0054] The first junction temperature prediction module is used to summarize a first junction temperature prediction model according to the first prediction data, and input the first prediction data into the trained first junction temperature prediction model to obtain a first junction temperature prediction result;

[0055] The second junction temperature prediction module is used to summarize a second junction temperature prediction model according to the second prediction data, and input the second prediction data into the trained second junction temperature prediction model to obtain a second junction temperature prediction result;

[0056] The final junction temperature prediction module is used to merge the first junction temperature prediction result and the second junction temperature prediction result to obtain the final junction temperature prediction result and complete the thyristor junction temperature prediction.

[0057] In a third aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, the steps of the thyristor junction temperature prediction and evaluation method are implemented.

[0058] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of the thyristor junction temperature prediction and evaluation method are implemented.

[0059] Compared with the prior art, the beneficial effects of the present invention are that the method of the present invention improves the accuracy and consistency of input data by standardizing and cleaning data; real-time prediction is combined with the current working state to prevent thyristor failure caused by overheating; historical data and load changes are used for prediction to improve the comprehensiveness of the prediction results; and the accuracy and reliability of the prediction are further improved through multi-model fusion and adjustment factor optimization. Combining these steps, the method significantly improves the accuracy and robustness of thyristor junction temperature prediction, ensures the safe and stable operation of thyristors, and has important practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0061] Figure 1 A method flow chart of a thyristor junction temperature prediction and evaluation method and system provided by an embodiment of the present invention;

[0062] Figure 2 An internal structural diagram of a computer device of a thyristor junction temperature prediction and evaluation method and system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned purposes, features and advantages of the present invention more understandable, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0066] Example 1

[0067] Reference Figure 1-Figure 2 , which is the first embodiment of the present invention, and provides a thyristor junction temperature prediction and evaluation method, comprising:

[0068] The present application provides a method for effectively solving the above-mentioned problems. Next, multiple embodiments will be combined to explain in detail how to implement the thyristor junction temperature prediction and evaluation method.

[0069] Figure 1 A method flow chart of a thyristor junction temperature prediction and evaluation method and system is shown, including:

[0070] S1: Obtain parameters to be predicted and perform data preprocessing on the parameters to be predicted, where the parameters to be predicted include first prediction data, second prediction data and third prediction data;

[0071] Further, the first prediction data includes operating current, ambient temperature, thyristor material characteristic parameters and operating time;

[0072] The second prediction data includes historical operating current, historical ambient temperature, historical fault conditions, cooling system efficiency parameters, and load changes;

[0073] Data preprocessing includes data cleaning and data normalization to eliminate noise and outliers and ensure data quality and consistency.

[0074] Furthermore, data cleaning includes filling missing values, noise processing, and duplicate value processing;

[0075] Filling missing values ​​The mean was used to fill missing values;

[0076] Noise processing uses smoothing filtering to identify and process noise points in the data, which can be abnormally high / low values;

[0077] Duplicate value processing includes checking whether there are duplicate records in the data set, deleting duplicate records, and ensuring data uniqueness;

[0078] The calculation formula for data normalization is as follows:

[0079]

[0080] Among them, x is the original data, x′ is the normalized data, μ is the mean, and σ is the standard deviation.

[0081] S2: Summarizing a first junction temperature prediction model according to the first prediction data, inputting the first prediction data into the trained first junction temperature prediction model, and obtaining a first junction temperature prediction result;

[0082] Further, the step of obtaining the first junction temperature prediction result includes:

[0083] Predicting the junction temperature of the thyristor according to the first prediction data to obtain a first prediction parameter;

[0084] A first prediction function is defined according to the acquired first prediction data, and a calculation formula of the first prediction function is as follows:

[0085]

[0086] Wherein, f(t) is the first prediction function, I0 is the current amplitude, T0 is the ambient temperature, α and β are the thyristor material characteristic constants;

[0087] Inputting the first prediction data into the first prediction function, calculating the first prediction function, and obtaining a calculation result;

[0088] Calculating the first prediction function is performing integral calculation on the first prediction function;

[0089] Performing normalization processing according to the calculation results to obtain the first junction temperature prediction result;

[0090] Furthermore, the calculation formula of the first prediction model is as follows:

[0091]

[0092] Among them, T final1 is the first junction temperature prediction result, and t1 is the total working time.

[0093] S3: Summarizing a second junction temperature prediction model according to the second prediction data, inputting the second prediction data into the trained second junction temperature prediction model, and obtaining a second junction temperature prediction result;

[0094] The second prediction model includes historical data prediction and load change prediction;

[0095] Furthermore, historical data forecasts include:

[0096] Determine the coverage time range [t0,t n ]’s historical working current I(t) data;

[0097] Determine the time range [t0,t n ] historical ambient temperature T env (t) data;

[0098] Determine the correction coefficient α(t), which is based on experimental or historical data statistical analysis and reflects the effect of the working current on the junction temperature; determine the environmental influence coefficient γ(t), which is based on experimental or historical data statistical analysis and reflects the effect of the ambient temperature on the junction temperature; determine the working current attenuation coefficient β and the ambient temperature attenuation coefficient δ, which reflect the attenuation rate of the effect of the working current and the ambient temperature on the junction temperature;

[0099] In the laboratory or actual operating environment, record the changes in junction temperature at different operating currents and ambient temperatures. The data should cover different time points and multiple operating conditions to ensure the universality and accuracy of the parameters.

[0100] For each time point t, where t∈[t0, t n ], calculate the current calibration function f1 and the ambient temperature calibration function f2, that is,

[0101] f1=I(t)·α(t)·e -βt

[0102] f2=T env(t)·γ(t)·e -δt

[0103] Where I(t) is the coverage time range [t0,t n ] historical working current data, T env (t) is the coverage time range [t0,t n ] is the historical ambient temperature, α(t) is the correction coefficient, γ(t) is the environmental influence coefficient, β is the working current attenuation coefficient, and δ is the ambient temperature attenuation coefficient;

[0104] The calculation results of the current calibration function f1 and the ambient temperature calibration function f2 are calculated in the time range [t0,t n ] to obtain the preliminary forecast results based on historical data. The calculation formula is as follows:

[0105]

[0106] Among them, T part1 These are preliminary forecasts based on historical data.

[0107] Furthermore, historical data prediction has the following embodiments:

[0108] Get the experimental data. The experimental data table is as follows:

[0109] Table 1 Experimental data table

[0110]

[0111] According to the experimental data in the experimental data table, calculate the current calibration function f1 and the ambient temperature calibration function f2. The calculation contents are shown in the following table.

[0112] Table 2 Function calculation table

[0113] Time (t) <![CDATA[Current calibration function f1]]> <![CDATA[Environmental temperature calibration function f2]]> 0 1·0.8·1＝0.8 20·1.2·1＝24 1 2·0.8·0.904837＝1.4477392 22·1.2·0.951229＝25.123402 2 3·0.8·0.818731＝1.963354 24·1.2·0.904837＝26.154144 3 4·0.8·0.740818＝2.370618 26·1.2·0.860708＝26.868823 4 5·0.8·0.670320＝2.681280 28·1.2·0.818731＝27.496615

[0114] By integrating the influence of working current and ambient temperature in the time range [0,4], the preliminary prediction result Tpart1 based on historical data is obtained, that is,

[0115] T part1 =∫0(I(t)·α(t)·e -βt +T env (t)·γ(t)·e -δt )dt

[0116] Numerical integration can be calculated using the trapezoidal rule or Simpson's rule. To simplify, the value at each time point can be calculated and summed, that is,

[0117]

[0118] Assume Δt = 1, then we have,

[0119] Tpart1≈(0.8+24)+(1.447739+25.123402)+(1.963354+26.154144)

[0120] +(2.370618+26.868823)+(2.681280+27.496615)

[0121] ≈24.8+26.571141+28.117498+29.239441+30.177895≈138.906

[0122] The final preliminary prediction result of the historical data is Tpart1≈138.906, which is used in the subsequent junction temperature prediction model.

[0123] Furthermore, the step of determining the correction coefficient α(t), the environmental impact coefficient γ(t), the working current attenuation coefficient β and the ambient temperature attenuation coefficient δ includes:

[0124] In the laboratory or actual operating environment, collect the changes in junction temperature under different operating currents and ambient temperatures;

[0125] The data covers different time points and multiple operating conditions to ensure the universality and accuracy of the parameters;

[0126] Extract operating current, ambient temperature, and junction temperature data from device operation history.

[0127] The data needs to cover a longer period of time to ensure the reliability of statistical analysis;

[0128] The linear regression analysis method is used, with the operating current I(t) as the independent variable and the junction temperature T j (t) is used as the dependent variable, and the coefficient α of the influence of the working current on the junction temperature is obtained by fitting, that is,

[0129] T j (t)=αI(t)+∈

[0130] Among them, ∈ is the error term;

[0131] Using linear regression analysis, the ambient temperature T env (t) as an independent variable, junction temperature T j (t) is used as the dependent variable, and the coefficient γ of the influence of ambient temperature on junction temperature is obtained by fitting, that is,

[0132] T j (t) = γT env (t)+∈

[0133] The nonlinear regression analysis method is used to fit the attenuation effect of working current and ambient temperature on junction temperature, that is,

[0134] T j (t) = αI(t)e -βt +γT env (t)e -δt +∈

[0135] The values ​​of α and γ are estimated using the least squares method, and the values ​​of β and δ are estimated using the nonlinear least squares method;

[0136] By fitting and optimizing experimental data, the parameter value that minimizes the error is selected.

[0137] Furthermore, load change prediction includes,

[0138] Determine the load power P at each time point i according to the second prediction data load (i) and the corresponding heat dissipation efficiency η(i) data;

[0139] Determine each fault condition F according to the second prediction data fault (j) and its occurrence time t j data;

[0140] According to the load power P at each time point i load (i) and the corresponding heat dissipation efficiency η(i) data determine the load heat dissipation influence function F1, that is,

[0141]

[0142] Among them, P load (i) is the load power at the i-th time point, η(i) is the heat dissipation efficiency at the i-th time point, t i is the i-th time point, θ is the load change influence coefficient;

[0143] According to each fault condition F fault (j) and its occurrence time t j The data of the fault condition determines the fault condition impact function F2, that is,

[0144]

[0145] Among them, t j is the jth time point, F fault (j) is the jth fault condition;

[0146] The load heat dissipation influence function F1 and the fault condition influence function F2 are combined to obtain the load change prediction function. The calculation formula is as follows:

[0147]

[0148] Among them, Tpart2 is the load change prediction value.

[0149] Furthermore, each fault condition F is defined fault (j) Specifically,

[0150] The impact value of minor faults is set to 1. Minor faults generally refer to small problems that occur during the operation of the equipment, such as temporary temperature fluctuations and instantaneous current increases. Such faults have little impact on the junction temperature, so the impact value is defined as 1.

[0151] The impact value of a medium fault is set to 3. A medium fault refers to a serious problem with the device, such as a local temperature rise or a continuous increase in current. This type of fault has a significant impact on the junction temperature, so the impact value is defined as 3.

[0152] The impact value of a severe fault is set to 5. A severe fault refers to a serious problem with the equipment, such as a failure of a key component or a sharp rise in temperature. This type of fault has a significant impact on the junction temperature, so the impact value is defined as 5.

[0153] Furthermore, the preliminary prediction result Tpart1 of historical data and the preliminary prediction result T part2 According to the weight coefficient, weighted fusion is performed to obtain the second junction temperature prediction result, that is,

[0154] T final2 =λ1·T part1 +λ2·T part2

[0155] Among them, λ1 and λ2 are the historical data prediction weight and load change prediction weight respectively;

[0156] T part1 The range of the value is [T min1 ,T max1 ], representing the minimum and maximum junction temperatures predicted based on historical data;

[0157] T part2 The range of the value is [T min2 ,T max2 ], representing the minimum and maximum junction temperatures predicted based on real-time load changes;

[0158] T final2 The range of the value is [T min ,T max ], representing the minimum and maximum junction temperatures predicted by the second junction temperature, respectively.

[0159] Specifically, in the present invention, the second prediction data is processed through step S3 and input into the trained second junction temperature prediction model to obtain the second junction temperature prediction result; the second prediction model includes historical data prediction and load change prediction, which respectively process data from different sources to improve the prediction accuracy; the historical data prediction is based on the working current I(t) and the ambient temperature T env (t), and combined with the correction coefficient α(t) and the environmental impact coefficient γ(t), as well as the attenuation coefficients β and δ, the preliminary prediction results based on historical data are calculated. This step achieves accurate prediction of junction temperature by comprehensively considering the influence of working current and ambient temperature, and solves the problem of insufficient comprehensive utilization of long-term historical data in the prior art. Load change prediction is achieved through the load power P load (i) and the corresponding heat dissipation efficiency η(i) to calculate the load heat dissipation impact function, and according to the fault condition F fault (j) and its occurrence time t j The fault condition impact function is calculated and the two are integrated to obtain the load change prediction value. This step innovatively introduces the impact of load change and fault condition on junction temperature, and provides a dynamic and comprehensive junction temperature prediction method. Finally, a second junction temperature prediction model is formed by weighted fusion of historical data and load change data, which can more comprehensively and accurately reflect the junction temperature changes under actual operating conditions, solves the problem of insufficient prediction of a single data source, and enhances the accuracy and adaptability of the prediction.

[0160] S4: The first junction temperature prediction result and the second junction temperature prediction result are integrated to obtain a final junction temperature prediction result, thereby completing the prediction.

[0161] Furthermore, the weighted average method is used to merge the first junction temperature prediction result and the second junction temperature prediction result, and the adjustment factor is introduced to optimize the prediction effect to obtain the final junction temperature prediction result. The calculation formula is as follows:

[0162] T final =(ωT final1 +L1·(1-ω)T final2 )·L2

[0163] Among them, ω is the final prediction weight, 0<ω<1, L1 and L2 are dynamic adjustment factors;

[0164] Furthermore, L1, L2 and ω are determined by a neural network algorithm in the present invention. The neural network algorithm includes an adaptive gradient algorithm, a momentum method and other neural network algorithms. The present invention does not specifically limit the algorithm.

[0165] Furthermore, the present embodiment also provides a thyristor junction temperature prediction and evaluation system, comprising: a data acquisition module, a first junction temperature prediction module, a second junction temperature prediction module and a final junction temperature prediction module;

[0166] The data acquisition module is used to obtain the parameters to be predicted and perform data preprocessing on the parameters to be predicted, wherein the parameters to be predicted include the first prediction data and the second prediction data;

[0167] The first junction temperature prediction module is used to summarize a first junction temperature prediction model according to the first prediction data, and input the first prediction data into the trained first junction temperature prediction model to obtain a first junction temperature prediction result;

[0168] The second junction temperature prediction module is used to summarize a second junction temperature prediction model according to the second prediction data, and input the second prediction data into the trained second junction temperature prediction model to obtain a second junction temperature prediction result;

[0169] The final junction temperature prediction module is used to merge the first junction temperature prediction result and the second junction temperature prediction result to obtain the final junction temperature prediction result and complete the thyristor junction temperature prediction.

[0170] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a comprehensive evaluation method suitable for orderly access of large-scale distributed power sources is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0171] This embodiment further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0172] Acquire a parameter to be predicted, and perform data preprocessing on the parameter to be predicted, wherein the parameter to be predicted includes first prediction data and second prediction data;

[0173] Summarizing a first junction temperature prediction model according to the first prediction data, inputting the first prediction data into the trained first junction temperature prediction model, and obtaining a first junction temperature prediction result;

[0174] Summarizing a second junction temperature prediction model according to the second prediction data, inputting the second prediction data into the trained second junction temperature prediction model, and obtaining a second junction temperature prediction result;

[0175] The first junction temperature prediction result and the second junction temperature prediction result are integrated to obtain the final junction temperature prediction result, thereby completing the thyristor junction temperature prediction.

[0176] Example 2

[0177] Reference Figure 1 - Figure 2 , which is the second embodiment of the present invention, and this embodiment provides a thyristor junction temperature prediction and evaluation method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0178] In this embodiment, a new thyristor junction temperature prediction and evaluation method is adopted, which aims to improve the accuracy and reliability of junction temperature prediction by combining multiple data sources and prediction models. First of all, it is necessary to prepare relevant experimental equipment and data acquisition systems, including thyristor test platforms, temperature sensors, data acquisition systems, etc. The experimental object is a certain type of thyristor. During the experiment, multiple parameters are recorded, including operating current, ambient temperature, thyristor material characteristic parameters, working time, historical operating current, historical ambient temperature, historical fault conditions, heat dissipation system efficiency parameters, and load changes.

[0179] The first prediction data is obtained: including the current operating current, ambient temperature, thyristor material characteristic parameters and operating time.

[0180] Obtain second prediction data: including historical operating current, historical ambient temperature, historical fault conditions, cooling system efficiency parameters and load changes.

[0181] The data are preprocessed, including data cleaning and data normalization, to eliminate noise and outliers and ensure the quality and consistency of the data.

[0182] According to the first prediction data, a first junction temperature prediction model is trained using a machine learning algorithm (such as linear regression, neural network, etc.). During the model training process, a portion of the data is used to optimize the model parameters, and the performance of the model is evaluated through cross-validation.

[0183] The preprocessed first prediction data is input into the trained first junction temperature prediction model to obtain the first junction temperature prediction result.

[0184] According to the second prediction data, a second junction temperature prediction model is established. The model mainly considers the influence of historical data and load changes, and obtains the junction temperature prediction result through the two sub-models of historical data prediction and load change prediction.

[0185] The preprocessed second prediction data is input into the second junction temperature prediction model to obtain a second junction temperature prediction result.

[0186] The first junction temperature prediction result and the second junction temperature prediction result are integrated, and the weighted average method is adopted. An adjustment factor is introduced to optimize the prediction effect to obtain the final junction temperature prediction result.

[0187] During the fusion process, the weights and adjustment factors of each prediction result are adjusted according to the actual situation to ensure the accuracy and reliability of the final prediction result. The specific data is shown in the following table:

[0188] Table 3 The first prediction data and junction temperature prediction results

[0189] Parameter name Test 1 Test 2 Test 3 Test 4 Test 5 Test 6 Working current(A) 50 55 60 65 70 75 Ambient temperature (℃) 25 30 35 40 45 50 Material characteristic parameters (constants) 1.2 1.3 1.4 1.5 1.6 1.7 Working hours (h) 100 150 200 250 300 350 Predicted junction temperature (℃) 80 85 90 95 100 105

[0190] Table 4 Second prediction data and junction temperature prediction results

[0191] Parameter name Test 1 Test 2 Test 3 Test 4 Test 5 Test 6 Historical working current (A) 48 53 58 63 68 73 Historical ambient temperature (℃) 24 29 34 39 44 49 Historical fault conditions (number of times) 1 2 3 4 5 6 Heat dissipation efficiency (%) 85 80 75 70 65 60 Load change (%) 90 85 80 75 70 65 Predicted junction temperature (℃) 78 83 88 93 98 103

[0192] It can be seen from the above experimental data analysis that the method of the present invention has significant advantages and innovations in junction temperature prediction. First, it can be seen from the data in Table 3 that the first prediction model can accurately predict the junction temperature of the thyristor under different working conditions. The changes in the working current and ambient temperature directly affect the junction temperature prediction results. The model can better capture the changing trends of these parameters and give reasonable prediction results.

[0193] The data in Table 4 further proves the effectiveness of the second prediction model. The second prediction model not only considers the data of the current working state, but also integrates multiple factors such as historical working current, ambient temperature, historical fault conditions, and load changes to make a more comprehensive and accurate prediction of the junction temperature. By integrating historical data and load change prediction results, the model can maintain a high prediction accuracy under variable working conditions.

[0194] In summary, it can be seen that the method of the present invention significantly improves the accuracy of junction temperature prediction by fusing the results of the first prediction model and the second prediction model. The fused prediction results take into account more influencing factors and can more comprehensively reflect the actual working state of the thyristor.

[0195] During the fusion process, the weights and adjustment factors of each prediction result are dynamically adjusted according to the actual situation, so that the final prediction result is more flexible and accurate, and can adapt to different working conditions and environmental changes.

[0196] Through the second prediction model, the method of the present invention makes full use of historical working data, can introduce the influence of historical data into the junction temperature prediction, and improves the reliability and robustness of the prediction result.

[0197] During the prediction process, the impact of load changes on junction temperature is fully considered, making the prediction results closer to the actual working conditions.

[0198] Compared with the prior art, the method of the present invention can not only accurately predict the junction temperature of the thyristor, but also has higher flexibility and adaptability. By introducing the integration of multiple data sources and prediction models, the method of the present invention can still maintain a high prediction accuracy under variable working conditions, fully demonstrating its innovation and superiority.

[0199] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0200] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0201] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0202] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0203] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0204] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0205] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for predicting and evaluating thyristor junction temperature, characterized in that: include, Acquire a parameter to be predicted, and perform data preprocessing on the parameter to be predicted, wherein the parameter to be predicted includes first prediction data and second prediction data; Summarizing a first junction temperature prediction model according to the first prediction data, inputting the first prediction data into the trained first junction temperature prediction model, and obtaining a first junction temperature prediction result; Summarizing a second junction temperature prediction model according to the second prediction data, inputting the second prediction data into the trained second junction temperature prediction model, and obtaining a second junction temperature prediction result; The first junction temperature prediction result and the second junction temperature prediction result are integrated to obtain the final junction temperature prediction result, thereby completing the thyristor junction temperature prediction.

2. The thyristor junction temperature prediction and evaluation method according to claim 1, characterized in that: The first prediction data includes operating current, ambient temperature, thyristor material characteristic parameters and operating time; The second prediction data includes historical operating current, historical ambient temperature, historical fault conditions, cooling system efficiency parameters, and load changes; The data preprocessing includes data cleaning and data normalization.

3. The thyristor junction temperature prediction and evaluation method according to claim 2, characterized in that: The step of obtaining the first junction temperature prediction result includes: A first prediction function is defined according to the first prediction data, and a calculation formula of the first prediction function is as follows: Wherein, f(t) is the first prediction parameter, I0 is the current amplitude, T0 is the ambient temperature, α and β are the thyristor material characteristic constants; Inputting the first prediction data into the first prediction function, and calculating the first prediction function to obtain a first prediction parameter; The first prediction parameter is integrated to obtain a first junction temperature prediction result, and the calculation formula is as follows: Among them, T final1 is the first junction temperature prediction result, and t1 is the total working time.

4. The thyristor junction temperature prediction and evaluation method according to claim 3, characterized in that: The second prediction model includes historical data prediction and load change prediction; The historical data forecast includes: Determine the coverage time range [t0,t n ], and determine the historical working current I(t) data covering the same time range [t0,t n ] historical ambient temperature T env (t) data; For each time point t, where t∈[t0, t n ], calculate the current calibration function f1 and the ambient temperature calibration function f2, that is, f1=I(t)·α(t)·e -βt f2=T env (t)·γ(t)·e -δt Where I(t) is the coverage time range [t0,t n ] historical working current data, T env (t) is the coverage time range [t0,t n ] is the historical ambient temperature, α(t) is the correction coefficient, γ(t) is the environmental influence coefficient, β is the working current attenuation coefficient, and δ is the ambient temperature attenuation coefficient; The calculation results of the current calibration function f1 and the ambient temperature calibration function f2 are calculated in the time range [t0,t n ] to obtain the preliminary forecast results based on historical data. The calculation formula is as follows: Among them, T part1 These are preliminary forecasts based on historical data.

5. The thyristor junction temperature prediction and evaluation method according to claim 4, characterized in that: The load change prediction includes: Determine the load power P at each time point i according to the second prediction data load (i) and the corresponding heat dissipation efficiency η(i) data, and determine the fault condition F according to the second prediction data fault (j) and its occurrence time t j data; According to the load power P at each time point i load (i) and the corresponding heat dissipation efficiency η(i) data determine the load heat dissipation influence function F1, that is, Among them, P load (i) is the load power at the i-th time point, η(i) is the heat dissipation efficiency at the i-th time point, t i is the i-th time point, θ is the load change influence coefficient; According to the fault condition F fault (j) and its occurrence time t j The data of the fault condition determines the fault condition impact function F2, that is, Among them, t j is the jth time point, F fault (j) is the jth fault condition; The load heat dissipation influence function F1 and the fault condition influence function F2 are combined to obtain a load change prediction function, and the calculation formula is as follows: Among them, T part2 Predicted value for load change.

6. The thyristor junction temperature prediction and evaluation method according to claim 5, characterized in that: The second junction temperature prediction result is obtained; include, The preliminary prediction results of historical data T part1 and the initial prediction results of load changes T part2 The second junction temperature prediction result is obtained by weighted fusion according to the weight coefficient, that is, T finl2 =λ1·T part1 +λ2·T part2 Among them, λ1 and λ2 are the historical data prediction weight and load change prediction weight respectively.

7. The method for predicting and evaluating thyristor junction temperature according to claim 6, characterized in that: The final junction temperature prediction result includes: The weighted average method is used to merge the first junction temperature prediction result and the second junction temperature prediction result, and the adjustment factor is introduced to optimize the prediction effect to obtain the final junction temperature prediction result. The calculation formula is as follows: T final =(ωT final1 +L1·(1-ω)T final2 )·L2 Among them, ω is the final prediction weight, 0<ω<1, and L1 and L2 are dynamic adjustment factors.

8. A thyristor junction temperature prediction and evaluation system, based on the thyristor junction temperature prediction and evaluation method according to any one of claims 1 to 7, characterized in that: It includes a data acquisition module, a first junction temperature prediction module, a second junction temperature prediction module and a final junction temperature prediction module; The data acquisition module is used to obtain parameters to be predicted and perform data preprocessing on the parameters to be predicted, wherein the parameters to be predicted include first prediction data and second prediction data; The first junction temperature prediction module is used to summarize a first junction temperature prediction model according to the first prediction data, and input the first prediction data into the trained first junction temperature prediction model to obtain a first junction temperature prediction result; The second junction temperature prediction module is used to summarize a second junction temperature prediction model according to the second prediction data, and input the second prediction data into the trained second junction temperature prediction model to obtain a second junction temperature prediction result; The final junction temperature prediction module is used to merge the first junction temperature prediction result and the second junction temperature prediction result to obtain the final junction temperature prediction result and complete the thyristor junction temperature prediction.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the thyristor junction temperature prediction and evaluation method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the thyristor junction temperature prediction and evaluation method according to any one of claims 1 to 7 are implemented.

Images