Inverter life prediction method and device, electronic equipment and storage medium

Abstract

The invention is suitable for the technical field of inverter detection, and provides an inverter service life prediction method and device, electronic equipment and a storage medium, and the inverter service life prediction method comprises the steps: inputting a plurality of sample data sets into an initial service life prediction network, and outputting a first service life prediction value and a first prediction value corresponding to each physical feature; obtaining first training loss information based on the output of the initial life prediction network and the difference between the output of the initial life prediction network and a corresponding target life value and a target value, so as to adjust the initial life prediction network and obtain a candidate life prediction model; outputting a second life prediction value and a second prediction value corresponding to each physical feature based on the candidate life prediction model, and adjusting the candidate life prediction model according to the second training loss information to obtain a target life prediction model; and inputting the aging data of the target inverter into the target life prediction model, and outputting a target life prediction value of the target inverter. According to the scheme, the accuracy and reliability of inverter service life prediction are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of inverter detection, and particularly relates to an inverter life prediction method and device, an electronic device, and a storage medium. BACKGROUND

[0002] An inverter is a core component in energy devices such as photovoltaic systems, electric vehicles, and wind energy systems, and its life is often significantly shorter than that of photovoltaic modules and other equipment, thus easily becoming a key factor limiting system stability and reliability. In order to reduce operation and maintenance costs and prolong the overall life of the equipment, it is of great significance to accurately predict the life of the inverter.

[0003] Existing life prediction methods are usually based on multi-dimensional sensor data during operation, and statistical analysis or machine learning models are used to establish a mapping relationship between life and data. These methods can reflect the degradation trend of the inverter to some extent, but in complex working conditions or scenes with large environmental changes, they often show insufficient accuracy or unstable results. SUMMARY

[0004] Therefore, the embodiments of the present application provide an inverter life prediction method, device, electronic device, and storage medium, which introduce a multi-stage loss function optimization mechanism in the training process, so that the life prediction model has higher stability and robustness in complex operating environments and can converge efficiently, thereby improving the accuracy and reliability of inverter life prediction.

[0005] A first aspect of the embodiments of the present application provides an inverter life prediction method, which comprises: inputting a plurality of sample data sets into an initial life prediction network to obtain a first life prediction value and a first prediction value corresponding to each physical feature; the sample data set is the aging data of a sample inverter, and each sample set corresponds to a first label, which is used to indicate a target life value of the inverter and a target value corresponding to at least one physical feature; obtaining first training loss information based on the difference between the first life prediction value and the target life value, and the difference between the first prediction value corresponding to each physical feature and the target value, adjusting the initial life prediction network using the first training loss information to obtain a candidate life prediction model; inputting a plurality of sample data sets into the candidate life prediction model to obtain a second life prediction value and a second prediction value corresponding to each physical feature; obtain second training loss information based on a difference between the second life prediction value and the target life value, a difference between each of the second prediction values of the physical features and the target values, and a physical residual term, and adjust the candidate life prediction model using the second training loss information to obtain a target life prediction model; the physical residual term is used to constrain the physical quantity output by the candidate life prediction model to satisfy a preset physical equation, so as to represent a deviation degree of the candidate life prediction model from a physical law; input the aging data of the target inverter into the target life prediction model to perform life prediction, and output a target life prediction value of the target inverter.

[0006] The embodiments of the present application first input a plurality of sample data sets into an initial life prediction network to generate a first life prediction value and a first prediction value of each physical feature, and simultaneously provide a life label and a physical feature label for the same batch of data, so that the two are aligned at one time during training, thereby fully utilizing the supervision information; subsequently, a first training loss information is formed by a difference between the first life prediction value and a target life value, and a difference between each of the first prediction values of the physical features and the corresponding target values, to update the parameters, quickly align the supervision, and stabilize the early convergence, thereby obtaining a candidate life prediction model; continue to input the sample data set to obtain a second life prediction value and a second prediction value of the physical feature, to provide a comparable baseline output for the next step of constraint; on this basis, a second training loss information is formed by a difference between the second life prediction value and the target life value, a difference between each of the second prediction values of the physical features and the target values, and a physical residual term, wherein the physical residual term is used to constrain the physical quantity output by the candidate life prediction model to satisfy a preset physical equation, so as to measure and suppress the deviation from the physical law, thereby reducing overfitting and improving the stability across operating conditions, and further obtaining a target life prediction model; finally, input the aging data of the target inverter into the target life prediction model to output a target life prediction value, thereby realizing reliable life evaluation for real scenarios. It can be inferred that the present method takes into account both data supervision and physical consistency, so that the life prediction model has higher stability and robustness under complex operating environments, and can converge efficiently, thereby improving the accuracy and reliability of inverter life prediction.

[0007] In a possible implementation, the initial life prediction network at least includes a convolutional neural network layer, a multi-head self-attention layer, a feedforward neural network layer, and a fully connected layer; and the inputting of the plurality of sample data sets into the initial life prediction network to obtain the first life prediction value and the first prediction value corresponding to each of the physical features includes: input the plurality of sample data sets into the initial life prediction network, and process the plurality of sample data sets input into the convolutional neural network layer to extract local time sequence features, thereby obtaining first intermediate features; inputting the first intermediate feature into the multi-head self-attention layer to capture the correlation of the first intermediate feature in the time sequence, to obtain a second intermediate feature; inputting the second intermediate feature into the feed-forward neural network layer for nonlinear mapping, to obtain a third intermediate feature; inputting the third intermediate feature into the fully connected layer, to obtain the first life prediction value and the first prediction value corresponding to each physical feature.

[0008] In a possible implementation, the first training loss information further includes an initial condition constraint term, the initial condition constraint term representing a deviation degree of the initial life prediction network from a known initial state at an initial time; and the adjusting the initial life prediction network by using the first training loss information to obtain a candidate life prediction model includes: combining a difference between the first life prediction value and the target life value, a difference between the first prediction value corresponding to each physical feature and a target value, and the initial condition constraint term into a first loss function according to weights; performing back propagation and parameter updating on the initial life prediction network by using the first loss function, to obtain the candidate life prediction model.

[0009] In a possible implementation, the second training loss information further includes an initial condition constraint term, the initial condition constraint term further representing a deviation degree of the candidate life prediction model from a known initial state at an initial time; and the adjusting the candidate life prediction model by using the second training loss information to obtain a target life prediction model includes: combining a difference between the second life prediction value and the target life value, a difference between the second prediction value corresponding to each physical feature and a target value, a physical residual term, and the initial condition constraint term into a second loss function according to weights; performing back propagation and parameter updating on the candidate life prediction model by using the second loss function, to obtain the target life prediction model.

[0010] In a possible implementation, the calculation of the physical residual term includes the following steps: calculating an inductor current residual and a capacitor voltage residual based on a BOOST circuit average model differential equation; calculating a junction temperature residual based on an IGBT thermal model equation; performing sample dimension average on the inductor current residual, the capacitor voltage residual, and the junction temperature residual to obtain the physical residual term.

[0011] In a possible implementation, the calculation of the initial condition constraint term includes the following steps: obtain initial values of the boost inductor current, the boost capacitor voltage, and the IGBT junction temperature; obtain predicted values of each physical feature at an initial time by the initial life prediction network or the candidate life prediction model, and compare the predicted values with initial values corresponding to the predicted values to determine deviations of the boost inductor current, the boost capacitor voltage, and the IGBT junction temperature at the initial time, respectively; calculate initial condition constraint terms corresponding to the initial life prediction network or the candidate life prediction model according to the deviations of the boost inductor current, the boost capacitor voltage, and the IGBT junction temperature, respectively.

[0012] In a possible implementation, the generation of the first label includes the following steps: construct a target life value based on a ratio of a current remaining life to a rated life, the current remaining life being a length of time remaining until the end of life at a current sample collection time; For each of the physical features, determine a target value corresponding to the physical feature based on a sample measurement value corresponding to the physical feature at a backward adjacent time to the current sample collection time.

[0013] In a possible implementation, the method further includes: save a plurality of weights of the candidate life prediction model and the target life prediction model during the training process; evaluate the models corresponding to the plurality of weights based on a root mean square error and a direction penalty score; select a target life prediction model with an optimal evaluation result to output a target life prediction value of the inverter.

[0014] A second aspect of an embodiment of the application provides an inverter life prediction device, the device including: a first prediction module configured to input a plurality of sample data sets to an initial life prediction network to obtain a first life prediction value and first predicted values corresponding to each of the physical features, the sample sets being aging data of sample inverters, each of the sample sets corresponding to a first label, the first label being used to indicate a target life value of an inverter and target values corresponding to at least one physical feature; a first training module configured to obtain first training loss information based on differences between the first life prediction value and the target life value and differences between the first predicted values corresponding to each of the physical features and target values corresponding to the physical features, and adjust the initial life prediction network by using the first training loss information to obtain a candidate life prediction model; a second prediction module configured to input the plurality of sample data sets into the candidate life prediction model to obtain a second life prediction value and a second prediction value corresponding to each of the physical features; a second training module configured to obtain a second training loss information based on a difference between the second life prediction value and the target life value, a difference between the second prediction value corresponding to each of the physical features and a target value, and a physical residual term, and adjust the candidate life prediction model using the second training loss information to obtain a target life prediction model; the physical residual term is configured to constrain a physical quantity output by the candidate life prediction model to satisfy a preset physical equation, so as to represent a deviation degree of the candidate life prediction model from a physical law; a target output module configured to input aging data of a target inverter into the target life prediction model for life prediction, and output a target life prediction value of the target inverter.

[0015] The third aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method according to the first aspect when executing the computer program.

[0016] The fourth aspect of the embodiments of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method according to the first aspect.

[0017] The fifth aspect of the embodiments of the present application provides a computer program product, which, when executed on an electronic device, causes the electronic device to perform the steps of the method according to the first aspect.

[0018] The beneficial effects of the second aspect to the fifth aspect described above can refer to the beneficial effects of the first aspect described above, and the present application will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0020] Figure 1 is a flowchart of a method of inverter life prediction provided by the embodiments of the present application; Figure 2 is a flowchart of another method of inverter life prediction provided by the embodiments of the present application; Figure 3 is a schematic diagram of a model training process; Figure 4 is a structural schematic diagram of an inverter life prediction device provided by an embodiment of the present application; Figure 5 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0021] In the following description, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, persons having ordinary skill in the art will readily understand that the embodiments of the present application can be practiced without these specific details. In other instances, well-known structures, devices, circuits, and processes have not been described in detail in order to avoid obscuring the description of the present application.

[0022] It should be understood that the term "comprises" as used in the specification and the appended claims indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0023] It should also be understood that the term "and / or" as used herein refers to any one of the associated listed items, combinations thereof, and all possible combinations thereof, and includes these combinations.

[0024] As used in the specification and the appended claims, the term "if' can be interpreted as meaning "when" or "once" or "in response to a determination" or "in response to a detection" depending on the context. Similarly, the phrase "if determined" or "if detected [the described condition or event]" can be interpreted as meaning "once determined" or "in response to a determination" or "once detected [the described condition or event]" or "in response to a detection [the described condition or event]" depending on the context.

[0025] In addition, in the description of the specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0026] It should be understood that the size of the serial number of each step in the embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0027] Inverters are the core components in energy devices such as photovoltaic systems, electric vehicles and wind energy systems, and their lifetimes are often significantly shorter than those of photovoltaic modules and other equipment, thus easily becoming the key factor limiting the stability and reliability of the system. In order to reduce operation and maintenance costs and prolong the overall life of the equipment, it is of great significance to accurately predict the lifetime of the inverter.

[0028] Existing lifetime prediction methods are usually based on multi-dimensional sensor data during operation, and statistical analysis or machine learning models are used to establish the mapping relationship between lifetime and data. These methods can reflect the degradation trend of the inverter to some extent, but in complex working conditions or scenes with large environmental changes, they often show insufficient accuracy or unstable results.

[0029] In order to solve the above problems, the embodiments of the present application provide an inverter lifetime prediction method, device, electronic equipment and storage medium. The inverter lifetime prediction method in the embodiments of the present application first inputs a plurality of sample data sets into an initial lifetime prediction network to generate a first lifetime prediction value and a first prediction value of each physical feature, and the same batch of data provides a lifetime label and a physical feature label at the same time, and the two are aligned at the same time during a training, thereby making full use of the supervision information; then the difference between the first lifetime prediction value and the target lifetime value, and the difference between the first prediction value of each physical feature and the corresponding target value are used to form a first training loss information for parameter updating, which quickly aligns the supervision and stabilizes the early convergence, and obtains a candidate lifetime prediction model; continue to input the sample data set to obtain a second lifetime prediction value and a physical feature second prediction value, which provides a comparable baseline output for the next step of constraint; on this basis, the difference between the second lifetime prediction value and the target lifetime value, the difference between the second prediction value of each physical feature and the target value, and a physical residual term are used to form a second training loss information, wherein the physical residual term is used to constrain the physical quantity output by the candidate lifetime prediction model to satisfy a preset physical equation, so as to measure and suppress the deviation from the physical law, thereby reducing overfitting and improving the stability across conditions, and then obtaining a target lifetime prediction model; finally, the target inverter aging data is input into the target lifetime prediction model to output a target lifetime prediction value, realizing reliable lifetime evaluation for real scenes. Therefore, the method takes into account data supervision and physical consistency, so that the lifetime prediction model has higher stability and robustness in complex operating environments and can converge efficiently, thereby improving the accuracy and reliability of inverter lifetime prediction.

[0030] The embodiments of the present application provide an inverter lifetime prediction method, device, electronic equipment, storage medium and computer program.

[0031] Referring to Figure 1 , a flowchart of an inverter lifetime prediction method provided by the embodiments of the present application is shown; as Figure 1As shown, the method can include the following steps: Step 101, inputting a plurality of sample data sets into an initial life prediction network to obtain a first life prediction value and a first prediction value corresponding to each physical feature.

[0032] Wherein, the sample data set is the aging data of a sample inverter, each sample set corresponds to a first label, and the first label is used to indicate the target life value of the inverter and the target value corresponding to at least one physical feature.

[0033] In this embodiment, the aging data of the sample inverter can be obtained based on the aging experiment. Before the accelerated aging experiment is performed, it is first verified that each sensor in the inverter device is working normally. The sensors are arranged around the DC / DC converter and the DC / AC converter of the inverter, and the multi-dimensional sensor data collected includes but is not limited to: temperature, power, direct current voltage / current, three-phase alternating current voltage / current, switching frequency, etc. Subsequently, in the aging test room, a batch of inverters of the same model (the number is P) are respectively subjected to single aging experiment (such as high temperature, electric stress acceleration, load stress, high humidity corrosion, switching frequency acceleration) and random multi-stage comprehensive aging experiment; taking “the inverter cannot stably output a specified amount of alternating voltage” as the experimental termination condition, P complete cycle data are accumulated, and one inverter corresponds to one complete cycle data.

[0034] For one complete cycle data of a sample inverter, the original data of each sensor is recorded as Q 0, which has a typical dimension of q 0, including time t , input voltage (PV voltage) V in , boost circuit (BOOST) inductor current i L , boost circuit (BOOST) capacitor voltage v c , IGBT output voltage V IGBT and output current I IGBT , IGBT shell temperature Tc , switching frequency f sw , duty cycle D , ambient temperature T a , etc. In order to avoid gradient disappearance or explosion in subsequent training, the data is cleaned: Q 0. Firstly, standard normalization is performed according to the rated value of the reference device or the maximum / minimum value under extreme environment; secondly, multiple collinearity analysis is performed to eliminate features irrelevant to the target life value, and a cleaned data set is obtainedQ (dimension q ), based on the dataset Q, a sliding window slicing is performed to generate a sample dataset to construct a plurality of sample datasets (each sample dataset corresponds to a time segment for representing the running state of the inverter in the time segment).

[0035] In a possible implementation, each sample dataset corresponds to a first label, and the first label is used to indicate a target life value of the inverter and a target value corresponding to at least one physical feature.

[0036] Specifically, the generation of the first label includes the following steps: constructing the target life value based on the ratio of the current remaining life of the inverter to the rated life, the current remaining life referring to the remaining time length from the current sample collection time to the end of life; For each physical feature, a target value corresponding to the physical feature is determined based on the sample measurement value corresponding to the physical feature at the backward adjacent time of the current sample collection time.

[0037] In the embodiments of the present application, it is assumed that the at least one physical feature includes: BOOST inductor current i L BOOST capacitor voltage v c IGBT junction temperature Tj Therefore, the first label at least includes the target life value and the target value of i L , v c of the physical features (since the physical residual term is involved in the training process, it is not necessary to set the corresponding target value in the first label). Tj

[0038] For example, the target life value is constructed based on the ratio of the current remaining life to the rated life:

[0039] Where t is the current sample collection time, and T is the rated life of the inverter from the initial operation to the end of life. Thus, the target life value sequence is obtained:

[0040] For example, the construction of the target value corresponding to the physical feature value adopts the sample measurement value corresponding to the backward adjacent time of the current sample collection time as the supervision signal, that is, the measured value at the time t+1 is taken as the target value at the time t, and the corresponding initial value is preset at the initial time, that is, the target value set of the BOOST inductor current t t I ​​​a target value set of the BOOST capacitor voltage V As follows:

[0041]

[0042] a label set corresponding to the sample data set of the P periods Y 、 I 、 V , a continuous data segment is obtained according to a sliding window, the window size is batch_size during training, and the step is 1 / 2 of batch_size; in the obtained data segment set, 1 / 10 is randomly extracted as a test set, and the rest is used as a training set, wherein the training set includes a plurality of sample data sets. Each sample data set in the training data set has a first label, and the first label indicates the target value corresponding to the target life value and at least one physical feature, which meets the needs of subsequent input of the training data set into the initial life prediction network and calculation of the first training loss information.

[0043] wherein the target life value is calculated as (supervision for subsequent first training loss information).

[0044] In the embodiments of the present application, the initial life prediction network can be composed of a convolutional neural network layer, a multi-head self-attention layer, a feedforward neural network layer, and a fully connected layer, for mapping hidden layer features to the percentage of the remaining life cycle of the inverter. For example, the initial life prediction network outputs a first life prediction value of 0.205 at a certain time, which corresponds to a "remaining life cycle of 20.5%".

[0045] In one possible implementation, the construction of the initial life prediction network includes the following steps: extracting local time sequence features in the convolutional neural network layer; introducing position encoding and using time mask in the multi-head self-attention layer to capture time correlation; nonlinear mapping in the feedforward neural network layer; obtaining life prediction values and first prediction values corresponding to each physical feature in the fully connected layer.

[0046] Specifically, on this basis, in another possible implementation, a plurality of sample data sets are input into the initial life prediction network to obtain first life prediction values and first prediction values corresponding to each physical feature, including: The plurality of sample data sets are input to an initial life prediction network, and the plurality of input sample data sets are processed in a convolutional neural network layer to extract local time sequence features to obtain first intermediate features; The first intermediate features are input to a multi-head self-attention layer to capture the correlation of the first intermediate features in the time sequence to obtain second intermediate features; The second intermediate features are input to a feedforward neural network layer for nonlinear mapping to obtain third intermediate features; The third intermediate features are input to a fully connected layer to obtain a first life prediction value and a first prediction value corresponding to each physical feature.

[0047] In the embodiments of the present application, based on the training data set obtained in the above steps, the plurality of sample data sets therein are input to the initial life prediction network in time sequence as a sequence, and the forward calculation process thereof includes: (1) Convolutional neural network layer: extract local time sequence features to obtain first intermediate features.

[0048] Let the input sequence corresponding to a single sample data set be (n is the length of the input sequence; is the input feature vector dimension). One-dimensional convolution is performed along the time dimension to obtain:

[0049] Let H cnn be the first intermediate features.

[0050] (2) Multi-head self-attention layer: introduce position encoding and use time mask to capture time correlation to obtain second intermediate features.

[0051] First linear mapping to obtain query / key / value:

[0052] wherein, is the weight of QKV, is usually , is the number of attention mechanism heads; RoPE is used to encode position information in attention calculation, and the Q and K vectors of each position p are rotated and transformed to naturally contain position information when dot product is performed. RoPE acts on the two-dimensional subspace of the vector through a rotation matrix to add position encoding to Q and K:

[0053] QKV calculation formula after adding the rotated position encoding:

[0054] According to the QKV with the rotation position coding, the second intermediate feature can be obtained.

[0055] (3) The feedforward neural network layer: performing nonlinear mapping to obtain the third intermediate feature.

[0056] Specifically, the second intermediate feature can be mapped to the third intermediate feature by using a nonlinear activation function.

[0057] (4) The fully connected layer: obtaining the first life prediction value.

[0058] The third intermediate feature is linearly projected and mapped to the interval (0, 1) to obtain the life percentage sequence, that is, the first life prediction value; the third intermediate feature is linearly mapped to obtain the first prediction value corresponding to each physical feature. That is, the same layer shares the features, and two fully connected heads are used to output the first life prediction value and the first prediction value corresponding to each physical feature, respectively.

[0059] In the embodiment of the present application, the corresponding first life prediction value is obtained for each sample data set in a batch, which is used to determine the first training loss information in the subsequent step and train the candidate life prediction model.

[0060] In step 102, the first training loss information is obtained based on the difference between the first life prediction value and the target life value, and the difference between the first prediction value corresponding to each physical feature and the target value. The initial life prediction network is adjusted using the first training loss information to obtain the candidate life prediction model.

[0061] The first training loss information is obtained based on the difference between the first life prediction value and the target life value, and the difference between the first prediction value corresponding to each physical feature and the target value.

[0062] In one possible implementation, the first training loss information consists of two parts: one is the difference between the first life prediction value and the target life value, and the difference between the first prediction value corresponding to each physical feature and the target value; the other is the initial condition constraint term, wherein the initial condition constraint term represents the deviation degree of the initial life prediction network from the known initial state at the initial time.

[0063] Specifically, the initial life prediction network is adjusted using the first training loss information to obtain the candidate life prediction model, including: The difference between the first life prediction value and the target life value, the difference between the first prediction value corresponding to each physical feature and the target value, and the initial condition constraint term are combined into a first loss function according to the weights. The initial life prediction network is back propagated and parameter updated using the first loss function to obtain the candidate life prediction model.

[0064] In the embodiments of the present application, the physical characteristics can include BOOST inductor current, BOOST capacitor voltage.

[0065] Specifically, according to the two-step loss design of the present application, only the life prediction difference, the physical characteristic difference and the initial condition constraint term are introduced in the first stage to form a first loss function L 1:

[0066] wherein, is the combination of the life prediction difference and the physical characteristic difference, is the initial condition constraint term, is the weight coefficient of the initial condition constraint term. Assuming that the number of samples is N, The specific calculation formula of is as follows:

[0067] In the above formula, , , respectively correspond to the three prediction values of the initial life prediction network: the first life prediction value, the first prediction value of the BOOST inductor current, and the first prediction value of the BOOST capacitor voltage. Y, I, and V are the target life value, the target value corresponding to the BOOST inductor current, and the target value corresponding to the BOOST capacitor voltage, respectively.

[0068] The initial condition constraint term is as follows:

[0069] wherein, is the IGBT junction temperature prediction value corresponding to the initial life prediction network, , , are the initial value corresponding to the BOOST inductor current, the initial value corresponding to the BOOST capacitor voltage, and the IGBT case temperature, respectively.

[0070] Specifically, the calculation of the initial condition constraint term includes the following steps: Obtain the initial values of the BOOST inductor current, the BOOST capacitor voltage, and the IGBT junction temperature; Obtain the prediction values of the initial life prediction network for each physical characteristic at the initial time, and compare the prediction values with the corresponding initial values to determine the deviations of the BOOST inductor current, the BOOST capacitor voltage, and the IGBT junction temperature at the initial time, respectively; Based on the deviations of the BOOST inductor current, BOOST capacitor voltage, and IGBT junction temperature in the initial lifetime prediction network, the initial condition constraints corresponding to the initial lifetime prediction network are calculated.

[0071] In the embodiments of this application, using L 1 is used as the first training loss information to perform forward computation on the initial lifetime prediction network, based on... L Backpropagation and parameter updates are performed on step 1 until the preset convergence / stopping conditions are met, resulting in a candidate lifetime prediction model. Throughout the training process, the supervision signal comes only from the target lifetime value, the target values ​​corresponding to each physical feature, and the initial condition constraints, thereby stabilizing the fitting of the primary lifetime task and constraining the initial state.

[0072] Step 103: Input multiple sample data sets into the candidate lifetime prediction model to obtain the second lifetime prediction value and the second prediction value corresponding to each physical feature.

[0073] In this embodiment of the application, the sample data set is the same as that in step 101, which is the aging data of the sample inverter. Each sample set has a first tag, which is used to indicate the target life value of the inverter and the target value corresponding to at least one physical feature.

[0074] The candidate lifetime prediction model is obtained by training the initial lifetime prediction network based on multiple sample data sets and the first training loss information.

[0075] Specifically, the multiple sample data sets obtained in step 101 are input into the candidate lifetime prediction model in chronological order. The candidate lifetime prediction model follows the forward computation process of the lifetime prediction network, sequentially extracting local temporal features through a convolutional neural network layer, capturing temporal correlations through a multi-head self-attention layer (including position encoding and temporal masking), performing nonlinear mapping through a feedforward neural network layer, and finally outputting simultaneously in a fully connected layer in a dual-branch manner. One branch obtains the second lifetime prediction value through normalization mapping, and the other branch obtains the second prediction value corresponding to each physical feature through linear mapping.

[0076] Step 104: Based on the difference between the second lifetime prediction value and the target lifetime value, the difference between the second prediction value and the target value corresponding to each physical feature, and the physical residual term, the second training loss information is obtained, and the candidate lifetime prediction model is adjusted using the second training loss information to obtain the target lifetime prediction model.

[0077] The second training loss information is based on the difference between the second lifetime prediction value and the target lifetime value, the difference between each physical feature and the target value, and the physical residual term. The physical residual term is used to constrain the physical quantity output by the candidate life prediction model to satisfy a preset physical equation, so as to represent the deviation degree of the candidate life prediction model from the physical law.

[0078] In a possible implementation, the second training loss information is composed of three parts, one of which is the difference between the second life prediction value and the target life value, and the difference between each physical feature and the target value; the second is the physical residual term; and the third is the initial condition constraint term. That is, the physical residual term is added to the first training loss information, and the same part as the first training loss information will not be described here. Please refer to the description in step 103, and the following will focus on the description of the physical residual term and the initial condition constraint term in this embodiment.

[0079] In the embodiment of the application, the physical residual term can consider the following two core contents, that is, BOOST circuit equation residual and IGBT thermal model residual.

[0080] Among them, the BOOST average model differential equation is:

[0081]

[0082] The IGBT thermal model equation is:

[0083] Suppose:

[0084]

[0085]

[0086] Therefore, the physical residual term is designed as:

[0087] In the above formula, , D, , , Five are sensor measurement values, which are input voltage value, duty cycle, environmental temperature, IGBT output current and IGBT output voltage; R, L, C, , , are resistance, inductance, capacitance, heat capacity, thermal resistance, power loss, and except for the power loss , the other several are constants, and the power loss is measured by the measurement value , , switching frequency IGBT junction temperature and single-switch energy loss is calculated, where The equation is curve-fitted from datasheet.

[0088] In one possible implementation, the physical features include: BOOST inductor current, BOOST capacitor voltage, and IGBT junction temperature. The calculation of the physical residual term includes the following steps: calculating inductor current residual and capacitor voltage residual based on the BOOST circuit average model differential equation; calculating junction temperature residual based on the IGBT thermal model equation; averaging the inductor current residual, capacitor voltage residual, and junction temperature residual in the sample dimension to obtain the physical residual term.

[0089] In the embodiments of the present application, the inductor current residual and capacitor voltage residual are calculated based on the BOOST circuit average model differential equation, which requires the use of BOOST inductor current and BOOST capacitor voltage; the junction temperature residual is calculated based on the IGBT thermal model equation, which requires the use of IGBT junction temperature.

[0090] Specifically, on this basis, in another implementation, The second training loss information further includes an initial condition constraint term, and the initial condition constraint term is further used to represent the deviation degree of the candidate life prediction model from the known initial state at the initial time; the candidate life prediction model is adjusted by using the second training loss information to obtain the target life prediction model, including: combining the difference between the second life prediction value and the target life value, the difference between the second prediction value corresponding to each physical feature and the target value, the physical residual term, and the initial condition constraint term according to weights to obtain a second loss function; The candidate life prediction model is back-propagated and parameter updated by using the second loss function to obtain the target life prediction model.

[0091] In the embodiments of the present application, the calculation of the initial condition constraint term includes the following steps: obtaining initial values of the BOOST inductor current, BOOST capacitor voltage, and IGBT junction temperature; obtaining the prediction values of the candidate life prediction model for each physical feature at the initial time, and comparing the prediction values with the corresponding initial values to determine the deviations of the BOOST inductor current, BOOST capacitor voltage, and IGBT junction temperature at the initial time, respectively; According to the deviations corresponding to the BOOST inductance current, the BOOST capacitor voltage, and the IGBT junction temperature in the candidate life prediction model, the initial condition constraint term corresponding to the candidate life prediction model is calculated.

[0092] In the embodiment of the application, the second loss function is: wherein, is a weight coefficient of the physical residual term.

[0093] In the embodiment of the application, the first training loss information is L 2, forward calculation is performed on the candidate life prediction model, back propagation and parameter updating are performed based on L 2, until the preset convergence / stop condition is met, and the target life prediction model is obtained. In the entire training process, the supervision signal is derived from the target life value and the target values corresponding to each physical feature; at the same time, the physical residual term and the initial condition constraint term are used as constraint terms to participate in optimization, so as to improve the stability and reliability of the model under complex working conditions.

[0094] Step 105: input the aging data of the target inverter into the target life prediction model for life prediction, and output the target life prediction value of the target inverter.

[0095] In the embodiment of the application, the aging data collected during the operation of the target inverter is preprocessed (including standard normalization and feature selection) in the same way as step 101, and a sample data set for inference is constructed in the same input format as the training phase; the sample data set is organized into a time series according to the same segmentation method (the window size and step of the sliding window are consistent with the training) as the training phase, and is input into the target life prediction model for forward calculation to obtain a life percentage sequence; the position aligned with the current time is output as the target life prediction value. To ensure consistency with the training supervision, the order, dimension and dimension of the input features are consistent with the training phase, and the output range of the target life prediction model is limited to the interval (0, 1), corresponding to the proportion of the remaining life cycle of the inverter; when a single result is needed within a period of time, the end output or weighted fusion method can be used to determine the target life prediction value after aligning the outputs of the continuous windows by time.

[0096] In this embodiment, first, a plurality of sample data sets are input into an initial life prediction network to generate first life prediction values and first prediction values of each physical feature, and the same batch of data provides life labels and physical feature labels at the same time, and both are trained and aligned at the same time, so as to fully utilize the supervised information; then, the difference between the first life prediction values and the target life values, and the difference between the first prediction values of each physical feature and the corresponding target values are used to form first training loss information for parameter updating, to quickly align the supervision and stabilize the early convergence, and obtain a candidate life prediction model; continue to input the sample data sets to obtain second life prediction values and second prediction values of each physical feature, to provide comparable baseline outputs for the next step of constraint; on this basis, the difference between the second life prediction values and the target life values, the difference between the second prediction values of each physical feature and the target values, and a physical residual term are used to form second training loss information, wherein the physical residual term is used to constrain the physical quantity output by the candidate life prediction model to satisfy a preset physical equation, to measure and suppress the deviation from the physical law, thereby reducing overfitting and improving the cross-condition stability, and further obtaining a target life prediction model; finally, the target inverter aging data are input into the target life prediction model to output target life prediction values, to realize reliable life evaluation facing real scenes. It can be inferred that the method takes into account data supervision and physical consistency, so that the life prediction model has higher stability and robustness under complex operating environments, and can efficiently converge, thereby improving the accuracy and reliability of inverter life prediction.

[0097] Referring to Figure 2 , a flowchart of another method for inverter life prediction provided by an embodiment of the present application is shown; as shown in Figure 2 , the method can include the following steps: Step 201, input a plurality of sample data sets into an initial life prediction network to obtain first life prediction values and first prediction values corresponding to each physical feature.

[0098] Step 202, based on the difference between the first life prediction values and the target life values, and the difference between the first prediction values corresponding to each physical feature and the target values, obtain first training loss information, and use the first training loss information to adjust the initial life prediction network to obtain a candidate life prediction model.

[0099] Step 203, input a plurality of sample data sets into the candidate life prediction model to obtain second life prediction values and second prediction values corresponding to each physical feature.

[0100] Step 204, based on the difference between the second life prediction values and the target life values, the difference between the second prediction values corresponding to each physical feature and the target values, and a physical residual term, obtain second training loss information, and use the second training loss information to adjust the candidate life prediction model to obtain a target life prediction model.

[0101] The steps 201-204 of this embodiment are the same as the steps 101-104 of the previous embodiment, and can be mutually referred to. This embodiment will not be described again here.

[0102] At step 205, the plurality of weights of the candidate life prediction model and the target life prediction model are saved during the training process.

[0103] At step 206, the models corresponding to the plurality of weights are evaluated based on the root mean square error and the direction penalty score.

[0104] At step 207, the target life prediction model with the optimal evaluation result is selected for outputting the target life prediction value of the inverter.

[0105] In the embodiments of the present application, the plurality of weights of the candidate life prediction model and the target life prediction model are saved at a preset frequency during the training process, and the models corresponding to the plurality of weights are uniformly evaluated based on the test set divided at step 101 after the training is completed. When evaluating, the target life value of each sample in the test set is recorded as , the life prediction value output by the corresponding model is recorded as , and the total number of samples is n.

[0106] To measure the consistency of the prediction and the reality, the root mean square error (RMSE) is calculated:

[0107] The smaller the RMSE is, the smaller the overall error is. On the other hand, to reflect the influence of the error direction on the operation and maintenance risk, the direction penalty score (Effectiveness Score) is calculated, and different penalty weights are applied to overestimation and underestimation:

[0108] The exponential form is used for nonlinear weighting, and the difference in the denominator is used to reflect the different intensity of the directional penalty, so as to preferentially reduce the potential risk caused by “prediction being too large” under the same RMSE.

[0109] After the above evaluation is completed, the RMSE and the direction penalty score of the models corresponding to the saved weights are comprehensively sorted, and the one with the best comprehensive performance is selected as the target life prediction model for deployment according to the criterion of “the smallest RMSE and the optimal direction penalty score”. Subsequently, according to step 105, the collected inverter aging data is input into the selected target life prediction model after being preprocessed in the same way as the training, and the target life prediction value at the corresponding time is calculated by forward calculation, so as to guide the repair and replacement strategy.

[0110] In a possible implementation, before the model is evaluated, the following model training can be performed: The initial life prediction network is initialized by using the Xavier algorithm, and the first loss function is used L 1 (consisting of the difference between the first life prediction value and the target life value, the difference between the first prediction value of each physical feature and the target value, and the initial condition constraint term) is trained until the preset convergence / stop condition is met, and the model M0 (i.e., the candidate life prediction model) is obtained.

[0111] The parameters of M0 are used as initial weights, and the second loss function L 2 (including the difference between the second life prediction value and the target life value, the difference between the first prediction value of each physical feature and the target value, the physical residual term, and the initial condition constraint term) is used to continue training, and the model M1 (i.e., the target life prediction model) is obtained.

[0112] The initial life prediction network is reinitialized by using the Xavier algorithm, and the second loss function L 2 from the beginning is directly used to train the model M2, which is used for comparison with M1 obtained by transfer learning. L

[0113] The initial life prediction network is structurally simplified by removing the position encoding (e.g., removing the rotational position encoding) in the multi-head self-attention layer while keeping the rest of the structure and hyperparameters consistent, and the Xavier algorithm is used for initialization, and the first loss function L 1 is used to train the model M3.

[0114] The above training process can save multiple weights of each stage at a preset frequency to facilitate unified evaluation and optimal model selection based on the root mean square error and the direction penalty score.

[0115] In step 208, the aging data of the target inverter is input into the target life prediction model for life prediction, and the target life prediction value of the target inverter is output.

[0116] Step 208 of the present embodiment is the same as step 105 of the foregoing embodiment, and can be mutually referred to. The present embodiment will not be repeated here.

[0117] ​Compared with the previous embodiment, the application embodiment saves multiple sets of weights and evaluates and selects the optimal band based on the RMSE and the direction penalty score, which can bring higher landing reliability and safety. On the one hand, multiple weights are saved during the training process and evaluated offline, avoiding the contingency of "using the last training result as the deployment model", reducing the risk caused by overfitting and training fluctuations, and improving the generalization stability. On the other hand, in addition to RMSE, the direction penalty score is introduced to "highly estimate and give heavier penalty", which can explicitly suppress the optimistic bias, preferentially select the model that is more conservative and safe for operation and maintenance, and reduce the hidden danger of missing the maintenance window due to overestimation of life. Finally, the combination of the two realizes the closed loop of "multiple candidates-quantitative evaluation-optimal selection", so that the selected target life prediction model is constrained in both accuracy (RMSE) and risk control (direction penalty), which improves the credibility and usability of the target life prediction value as a whole, and further optimizes the maintenance decision and the life cycle cost.

[0118] Referring to Figure 3 , a model training process schematic diagram is shown. As Figure 3 indicated, the model training process can be summarized as: First, run the test on the same type of inverter in the accelerated aging experiment and collect the full cycle raw data. After completing the sensor self-check, the temperature, power, direct / alternating voltage and current, duty cycle, switching frequency and other multi-dimensional signals are merged into the raw data set. Then, data cleaning is performed, and each channel is normalized according to the rated value or extreme value, and multiple collinearity analysis is carried out to eliminate features irrelevant to life, to obtain the cleaned "data".

[0119] On this basis, the complete cycle is divided into continuous data segments according to the sliding window, and a training data set composed of multiple sample data sets and their first labels is constructed, the first label is used to indicate the target life value of the inverter and the target value corresponding to at least one physical feature. In parallel, the "Loss set" is formed according to the loss design and splitting, which includes the first loss function used for the first stage training (composed of the difference between the first life prediction value and the target life value, the difference between the first prediction value corresponding to each physical feature and the target value, and the initial condition constraint term) and the second loss function used for the second stage training (composed of the difference between the second life prediction value and the target life value, the difference between the second prediction value corresponding to each physical feature and the target value, the physical residual term and the initial condition constraint term).

[0120] Then enter the "model training" node: the initial life prediction network is initialized with Xavier, the first loss function is used for back propagation and parameter update, and a candidate life prediction model is obtained; it is judged whether the last loss training is completed, if not, the second stage is entered, the second loss function is used for continuous training (transfer learning can be performed on the first model weight), and the target life prediction model is output until the preset convergence / stop condition is met. After training, "model saving" is performed, and multiple weights can be saved at the frequency set during training for subsequent evaluation and optimization; thus the current training process ends.

[0121] Referring to Figure 4 , a structure diagram of an inverter life prediction device provided by an embodiment of the present application is shown; only parts related to the embodiments of the present application are shown for ease of description.

[0122] The inverter life prediction device 400 comprises: The first prediction module 401 is configured to input a plurality of sample data sets into an initial life prediction network to obtain a first life prediction value and a first prediction value corresponding to each physical feature; the sample data set is the aging data of a sample inverter, and each sample set corresponds to a first label, which is used to indicate a target life value of the inverter and a target value corresponding to at least one physical feature; The first training module 402 is configured to obtain first training loss information based on the difference between the first life prediction value and the target life value, and the difference between the first prediction value corresponding to each physical feature and the target value, and adjust the initial life prediction network by using the first training loss information to obtain a candidate life prediction model; The second prediction module 403 is configured to input a plurality of sample data sets into the candidate life prediction model to obtain a second life prediction value and a second prediction value corresponding to each physical feature; The second training module 404 is configured to obtain second training loss information based on the difference between the second life prediction value and the target life value, the difference between the second prediction value corresponding to each physical feature and the target value, and a physical residual term, and adjust the candidate life prediction model by using the second training loss information to obtain a target life prediction model; the physical residual term is used to constrain the physical quantity output by the candidate life prediction model to satisfy a preset physical equation, so as to represent the deviation degree of the candidate life prediction model from the physical law; The target output module 405 is configured to input the aging data of a target inverter into the target life prediction model for life prediction, and output a target life prediction value of the target inverter.

[0123] In the embodiments of the present application, the initial life prediction network comprises at least a convolutional neural network layer, a multi-head self-attention layer, a feedforward neural network layer, and a fully connected layer; the first prediction module 401 can further comprise: The first feature determination module is configured to input a plurality of sample data sets into an initial life prediction network, and perform processing on the plurality of input sample data sets in a convolutional neural network layer to extract local time sequence features and obtain first intermediate features. The second feature determination module is configured to input the first intermediate features into a multi-head self-attention layer to capture the correlation of the first intermediate features in a time sequence and obtain second intermediate features. The third feature determination module is configured to input the second intermediate features into a feedforward neural network layer for nonlinear mapping to obtain third intermediate features. The first prediction value determination module is configured to input the third intermediate features into a fully connected layer to obtain first life prediction values and first prediction values corresponding to each physical feature.

[0124] In the embodiment of the present application, the first training loss information further includes an initial condition constraint term, and the initial condition constraint term represents the deviation degree of the initial life prediction network from the known initial state at the initial time; the first training module 402 can further include: The first loss function generation module is configured to combine the difference between the first life prediction values and the target life values, the difference between the first prediction values corresponding to each physical feature and the target values, and the initial condition constraint term according to weights to generate a first loss function. The first model determination module is configured to perform back propagation and parameter update on the initial life prediction network by using the first loss function to obtain a candidate life prediction model.

[0125] In the embodiment of the present application, the second training loss information further includes an initial condition constraint term, and the initial condition constraint term is further used to represent the deviation degree of the candidate life prediction model from the known initial state at the initial time; the second training module 404 can further include: The second loss function generation module is configured to combine the difference between the second life prediction values and the target life values, the difference between the second prediction values corresponding to each physical feature and the target values, the physical residual term, and the initial condition constraint term according to weights to generate a second loss function. The second model determination module is configured to perform back propagation and parameter update on the candidate life prediction model by using the second loss function to obtain a target life prediction model.

[0126] In the embodiment of the present application, the second training module 404 can further include: The first physical residual calculation module is configured to calculate inductance current residual and capacitance voltage residual based on a BOOST circuit average model differential equation. The second physical residual calculation module is configured to calculate junction temperature residual based on an IGBT thermal model equation. The physical residual term determination module is configured to average the inductance current residual, the capacitance voltage residual, and the junction temperature residual in the sample dimension to obtain a physical residual term.

[0127] In the embodiments of the present application, the first training module and the second training module are specifically further configured to: obtain initial values of the BOOST inductance current, the BOOST capacitance voltage, and the IGBT junction temperature; obtain predicted values of each physical feature at the initial time by the initial life prediction network or the candidate life prediction model, and compare the predicted values with the corresponding initial values to determine the deviations of the BOOST inductance current, the BOOST capacitance voltage, and the IGBT junction temperature at the initial time, respectively; According to the deviations of the BOOST inductance current, the BOOST capacitance voltage, and the IGBT junction temperature in the initial life prediction network or the candidate life prediction model, respectively, the initial condition constraint term corresponding to the initial life prediction network or the candidate life prediction model is calculated.

[0128] In the embodiments of the present application, the data acquisition module 401 can specifically include: The target life value determination module is configured to construct a target life value based on the proportion of the current remaining life to the rated life of the inverter, and the current remaining life refers to the remaining time length from the current sample collection time to the end of life; The target value determination module is configured to determine, for each physical feature, a target value corresponding to the physical feature based on the sample measurement value corresponding to the physical feature at the backward adjacent time of the current sample collection time.

[0129] In the embodiments of the present application, the inverter life prediction device 400 can specifically further include: The weight saving module is configured to save a plurality of weights of the candidate life prediction model and the target life prediction model during the training process; The model evaluation module is configured to evaluate the models corresponding to the plurality of weights based on the root mean square error and the direction penalty score; The selection module is configured to select the target life prediction model with the optimal evaluation result to output the target life prediction value of the inverter.

[0130] The inverter life prediction device 400 provided in the embodiments of the present application can be applied in the inverter life prediction method provided in the foregoing embodiments, and details are referred to the description of the inverter life prediction method provided in the foregoing embodiments, which will not be described herein again.

[0131] Referring to Figure 5 , a structural schematic diagram of an electronic device provided in an embodiment of the present application is shown. As Figure 5 shown, the electronic device 500 of this embodiment includes at least one processor 510 (Figure 5 The inverter lifetime prediction method described above is implemented by the processor 510 executing the computer program 521 stored in the memory 520.

[0132] The electronic device 500 can be a server, a physical server, a computing device, etc. The electronic device can include, but not limited to, the processor 510, the memory 520. Those skilled in the art can understand that the electronic device 500 can include more or less components than those shown, or can combine some components, or include different components, for example, the electronic device 500 can also include an input / output device, a network access device, etc. Figure 5 The electronic device 500 is only an example and does not constitute a limitation on the electronic device 500, and can include more or less components than those shown, or can combine some components, or include different components, for example, the electronic device 500 can also include an input / output device, a network access device, etc.

[0133] The processor 510 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.

[0134] The memory 520 can be an internal storage unit of the electronic device 500 in some embodiments, for example, a hard disk or a memory of the electronic device 500. The memory 520 can also be an external storage device of the electronic device 500 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 520 can include both an internal storage unit and an external storage device of the electronic device 500. The memory 520 is used to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of a computer program, etc. The memory 520 can also be used to temporarily store data that has been output or will be output.

[0135] In a particular implementation, the processor 510, the memory 520, and the computer program 521 described in the embodiments of the present application can perform the embodiments of the method for predicting the life of an inverter of the present application, which will not be described herein again.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual applications, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments, which will not be described herein again.

[0137] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0138] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0139] In the embodiments provided in the present application, it should be understood that the disclosed devices / equipment and methods can be implemented in other ways. For example, the device / equipment embodiments described above are only schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0140] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed to multiple network units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0141] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0142] If the integrated module / unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier wave signal, telecommunication signal and software distribution medium, etc. It should be noted that the content included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electric carrier wave signal and telecommunication signal.

[0143] The above-mentioned embodiment methods can also be completed by a computer program product, when the computer program product runs on the electronic device, so that the electronic device executes the steps in each method embodiment described above.

[0144] The above examples are only used to illustrate the technical solutions of the present application, but not to limit it. Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent ones. The modification or replacement does not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method of inverter lifetime prediction, characterized by, The method comprises: inputting a plurality of sample data sets into an initial life prediction network to obtain first life prediction values and first prediction values corresponding to each physical feature; each sample data set is aging data of a sample inverter, and each sample data set corresponds to a first label indicating a target life value of the inverter and a target value corresponding to at least one physical feature; based on the difference between the first life prediction value and the target life value, the difference between the first prediction value corresponding to each physical feature and the target value, first training loss information is obtained, and the initial life prediction network is adjusted by using the first training loss information to obtain a candidate life prediction model; inputting a plurality of sample data sets into the candidate life prediction model to obtain second life prediction values and second prediction values corresponding to each physical feature; based on the difference between the second life prediction value and the target life value, the difference between the second prediction value corresponding to each physical feature and the target value, and a physical residual term, second training loss information is obtained, and the candidate life prediction model is adjusted by using the second training loss information to obtain a target life prediction model; the physical residual term is used to constrain the physical quantity output by the candidate life prediction model to satisfy a preset physical equation, so as to represent the deviation degree of the candidate life prediction model from the physical law; inputting aging data of a target inverter into the target life prediction model for life prediction, and outputting a target life prediction value of the target inverter.

2. The method of claim 1, wherein, The initial life prediction network at least comprises a convolutional neural network layer, a multi-head self-attention layer, a feedforward neural network layer and a fully connected layer; the inputting a plurality of sample data sets into the initial life prediction network to obtain first life prediction values and first prediction values corresponding to each physical feature comprises: inputting the plurality of sample data sets into the initial life prediction network, processing the plurality of input sample data sets in the convolutional neural network layer to extract local time sequence features, and obtaining first intermediate features; inputting the first intermediate features into the multi-head self-attention layer to capture the correlation of the first intermediate features in the time sequence, and obtaining second intermediate features; inputting the second intermediate features into the feedforward neural network layer for nonlinear mapping, and obtaining third intermediate features; inputting the third intermediate features into the fully connected layer to obtain the first life prediction values and the first prediction values corresponding to each physical feature.

3. The method of claim 1, wherein, The first training loss information further comprises an initial condition constraint term representing the deviation degree of the initial life prediction network from the known initial state at the initial time; the adjusting the initial life prediction network by using the first training loss information to obtain the candidate life prediction model comprises: combining the difference between the first life prediction value and the target life value, the difference between the first prediction value corresponding to each physical feature and the target value, and the initial condition constraint term into a first loss function according to weights; The initial life prediction network is back propagated and parameter updated by using the first loss function, to obtain the candidate life prediction model.

4. The method of claim 1, wherein, The second training loss information further includes an initial condition constraint term, and the initial condition constraint term is further used to represent a deviation degree of the candidate life prediction model from a known initial state at an initial time; and the candidate life prediction model is adjusted by using the second training loss information, to obtain a target life prediction model, including: combining a difference between the second life prediction value and the target life value, a difference between a second prediction value corresponding to each physical feature and a target value, a physical residual term, and the initial condition constraint term according to weights into a second loss function; the candidate life prediction model is back propagated and parameter updated by using the second loss function, to obtain the target life prediction model.

5. The method of claim 4, wherein, the calculation of the physical residual term includes the following steps: calculating an inductance current residual and a capacitance voltage residual based on a BOOST circuit average model differential equation; calculating a junction temperature residual based on an IGBT thermal model equation; averaging the inductance current residual, the capacitance voltage residual, and the junction temperature residual in a sample dimension to obtain the physical residual term.

6. The method of any one of claims 3 or 4, wherein, the calculation of the initial condition constraint term includes the following steps: obtaining initial values of a BOOST inductance current, a BOOST capacitance voltage, and an IGBT junction temperature; obtaining prediction values of each physical feature at an initial time by the initial life prediction network or the candidate life prediction model, and comparing the prediction values with corresponding initial values to determine deviations of the BOOST inductance current, the BOOST capacitance voltage, and the IGBT junction temperature at the initial time, respectively; calculating an initial condition constraint term corresponding to the initial life prediction network or the candidate life prediction model according to the deviations of the BOOST inductance current, the BOOST capacitance voltage, and the IGBT junction temperature, respectively.

7. The method of claim 1, wherein, the generation of the first label includes the following steps: constructing a target life value based on a ratio of a current remaining life to a rated life, the current remaining life being a remaining time length from a current sample collection time to a life termination time; for each physical feature, determining a target value corresponding to the physical feature based on a sample measurement value corresponding to the physical feature at a backward adjacent time of a current sample collection time.

8. The method of claim 1, wherein, The method further includes: saving a plurality of weights of the candidate life prediction model and the target life prediction model during a training process; evaluating models corresponding to the plurality of weights based on a root mean square error and a direction penalty score; selecting a target life prediction model with an optimal evaluation result to output a target life prediction value of the inverter.

9. An apparatus for inverter lifetime prediction, the apparatus comprising: The device includes: The first prediction module is configured to input a plurality of sample data sets into an initial life prediction network to obtain a first life prediction value and a first prediction value corresponding to each physical feature; the sample data set is aging data of a sample inverter, and each sample data set corresponds to a first label, which is used to indicate a target life value of the inverter and a target value corresponding to at least one physical feature; The first training module is configured to obtain a first training loss information based on a difference between the first life prediction value and the target life value, and a difference between the first prediction value corresponding to each physical feature and the target value, adjust the initial life prediction network based on the first training loss information, and obtain a candidate life prediction model; The second prediction module is configured to input a plurality of sample data sets into the candidate life prediction model to obtain a second life prediction value and a second prediction value corresponding to each physical feature; The second training module is configured to obtain a second training loss information based on a difference between the second life prediction value and the target life value, a difference between the second prediction value corresponding to each physical feature and the target value, and a physical residual term, adjust the candidate life prediction model based on the second training loss information, and obtain a target life prediction model; the physical residual term is used to constrain a physical quantity output by the candidate life prediction model to satisfy a preset physical equation, so as to represent a deviation degree of the candidate life prediction model from a physical law; The target output module is configured to input aging data of a target inverter into the target life prediction model for life prediction, and output a target life prediction value of the target inverter.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1 to 8.

11. A computer-readable storage medium storing a computer program, wherein the computer program comprises the following steps of: The computer program is executed by the processor to implement the method of any one of claims 1 to 8.

Images