Tube life prediction method, device, equipment and storage medium

Abstract

The present application provides a method, device, equipment and storage medium for predicting the life of a tube, which relates to the field of medical equipment technology. The method obtains a filament current prediction model, a failure current threshold of the current target tube, and filament current data, and obtains target predicted current data based on the filament current data and the filament current prediction model. The life of the current target tube is determined according to the failure current threshold and the target predicted current data. Based on the filament current data of the current target tube and the filament current prediction model, the filament current change trend of the current target tube within the prediction time can be predicted, and the life of the tube can be predicted in combination with the failure current threshold and the target predicted current data. By predicting the life of the tube through the filament current, which is a key factor affecting the life of the tube, the accuracy of the prediction can be improved, equipment shutdown caused by sudden tube failure can be avoided, the reliability of the tube operation can be improved, and the operating cost can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of medical equipment, and in particular to a method, apparatus, device and storage medium for predicting the life of a tube. Background Art

[0002] Computed tomography (CT) is a widely used medical imaging technology that generates cross-sectional images of the scanned object by acquiring and reconstructing X-ray projection images from different angles. One of the core components of a CT machine is the X-ray tube, which generates high-energy X-rays that penetrate the human body and are received by detectors, thereby generating projection data. The X-ray tube primarily consists of a cathode and an anode, containing a heated filament. When current passes through the filament, it heats up and emits electrons. A high-voltage electric field accelerates these electrons to the anode target, where they interact with the target material to produce X-rays.

[0003] Currently, CT equipment generally relies on regular maintenance and tube replacement to ensure normal operation. This approach not only increases operating costs but can also lead to equipment downtime due to sudden tube failure. Therefore, a tube life prediction method is urgently needed to predict tube lifespan in advance. Summary of the Invention

[0004] In view of the shortcomings of the related technologies mentioned above, the present application provides a tube life prediction method, device, equipment and storage medium to solve the above technical problems.

[0005] The present application provides a method for predicting the life of a tube, which is characterized by comprising:

[0006] Obtain the filament current prediction model, the failure current threshold of the current target tube, and the filament current data;

[0007] Based on the filament current data and the filament current prediction model, target predicted current data is obtained, wherein the target predicted current data includes multiple predicted filament currents of the current target bulb, the multiple predicted filament currents are arranged in chronological order, and the target predicted current data is used to characterize a change trend of the filament current of the current target bulb within a prediction time;

[0008] The current target tube life is determined according to the failure current threshold and the target predicted current data.

[0009] In one embodiment of the present application, obtaining a filament current prediction model includes:

[0010] Obtaining a current sample data set and an initial prediction model;

[0011] The initial prediction model is trained based on the current sample data set to obtain a filament current prediction model, and the filament current prediction model is used to predict the change trend of the filament current.

[0012] In one embodiment of the present application, obtaining a current sample data set includes:

[0013] Acquire initial current data, the initial current data including filament current data corresponding to a plurality of sample bulbs, each of the filament current data including a plurality of historical filament currents sorted by time;

[0014] performing data standardization processing on the plurality of historical filament currents to obtain a plurality of standardized data;

[0015] Sliding window processing is performed on the multiple standardized data to obtain multiple historical current sample data, and the multiple historical current sample data constitute the current sample data set.

[0016] In one embodiment of the present application, data normalization is performed on the plurality of historical filament currents to obtain a plurality of standardized data, including:

[0017] Grouping the filament current data according to a preset time period to obtain multiple groups of data to be calculated;

[0018] Performing mean filtering on the historical filament current of each group of the data to be calculated to obtain a plurality of data to be processed;

[0019] Data standardization is performed on each of the data to be processed to obtain a plurality of standardized data.

[0020] In one embodiment of the present application, the current sample data set includes historical current sample data corresponding to a sample tube, and training the initial prediction model based on the current sample data set includes:

[0021] Inputting the historical current sample data into a first prediction model to obtain a first prediction result, wherein the first prediction model is used to capture the dependency relationship of the historical current sample data;

[0022] Inputting the historical current sample data into a second prediction model to obtain a second prediction result, wherein the second prediction model is used to perform data decomposition on the historical current sample data, perform trend quantity prediction and residual quantity prediction respectively, and obtain the second prediction result based on the trend quantity prediction and the residual quantity prediction;

[0023] Inputting the historical current sample data into a third prediction model to obtain a third prediction result, wherein the third prediction model is used to analyze data within a preset data length in the historical current sample data;

[0024] Based on the self-attention mechanism, the first prediction result, the second prediction result, and the third prediction result are first concatenated to obtain model-predicted current data.

[0025] In one embodiment of the present application, obtaining target predicted current data based on the filament current data and the filament current prediction model includes:

[0026] Determining the filament current data as input data, and performing a data input step, wherein the data input step includes inputting the input data into the filament current prediction model to obtain initial predicted current data;

[0027] executing a data judgment step, the data judgment step including determining whether there is target data in the initial predicted current data, the target data being less than or equal to the failure current threshold;

[0028] If the target data does not exist in the initial predicted current data, executing a data updating step, the data updating step including performing a second splicing on the initial predicted current data and the input data to obtain spliced ​​data; determining the spliced ​​data as the input data, and executing the data input step again;

[0029] If the target data exists in the initial predicted current data, the target predicted current data is determined based on all the initial predicted current data.

[0030] In one embodiment of the present application, obtaining the failure current threshold of the current target tube includes:

[0031] Obtaining a target initial current of the current target tube;

[0032] The product of the target initial current and a preset value is determined as the failure current threshold.

[0033] A weighted sum is performed on the current initial current and the historical initial current to obtain the target initial current.

[0034] To achieve the above-mentioned and other related purposes, the present application provides a device for predicting the life of a tube, comprising:

[0035] A data acquisition module is used to obtain the filament current prediction model, the failure current threshold of the current target tube, and the filament current data;

[0036] a data prediction module, configured to obtain target predicted current data based on the filament current data and the filament current prediction model, wherein the target predicted current data includes a plurality of predicted filament currents of the current target tube, the plurality of predicted filament currents being arranged in chronological order, and the target predicted current data being used to characterize a changing trend of the filament current of the current target tube within a predicted time period;

[0037] The life prediction module is used to determine the current target tube life according to the failure current threshold and the target predicted current data.

[0038] To achieve the above-mentioned purpose and other related purposes, the present application also provides an electronic device, including one or more processors; a memory for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to execute one or more of the aforementioned tube life prediction methods.

[0039] To achieve the above-mentioned purpose and other related purposes, the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a computer processor, the computer executes one or more of the aforementioned tube life prediction methods.

[0040] As described above, the present application provides a method, device, equipment, and storage medium for predicting tube life, which have the following beneficial effects:

[0041] A method for predicting the life of a bulb in the present application obtains a filament current prediction model, a failure current threshold of the current target bulb, and filament current data, obtains target predicted current data based on the filament current data and the filament current prediction model, and determines the life of the current target bulb according to the failure current threshold and the target predicted current data. Based on the filament current data of the current target bulb and the filament current prediction model, the trend of filament current changes within the prediction time of the current target bulb can be predicted, and the life of the bulb can be predicted in combination with the failure current threshold and the target predicted current data. By predicting the life of the bulb by using the filament current, a key factor affecting the life of the bulb, the accuracy of the prediction can be improved, equipment shutdown caused by sudden failure of the bulb can be avoided, the reliability of the bulb operation can be improved, and the operating cost can be reduced.

[0042] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0044] Figure 1 is a flow chart of a method for predicting tube life, shown in an exemplary embodiment of the present application;

[0045] Figure 2 is a schematic diagram showing a sliding window process for a plurality of standardized data according to an exemplary embodiment of the present application;

[0046] Figure 3 It is a structural block diagram of a tube life prediction device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will describe the embodiments of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand the other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for the purpose of illustrating the present application and are not intended to limit the scope of protection of the present application.

[0048] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0049] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0050] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for predicting the life of a tube according to an exemplary embodiment of the present invention. Figure 1 It can be seen that the tube life prediction method can include:

[0051] Step S110 , obtaining a filament current prediction model, a failure current threshold of a current target tube, and filament current data.

[0052] In one embodiment of the present application, a filament current prediction model can be obtained. This filament current prediction model can be used to predict the changing trend of the target tube's filament current over a predicted time period. Furthermore, a failure current threshold and filament current data for the current target tube can be obtained. The failure current threshold can be used to determine whether the filament of the current target tube has failed, thereby serving as a basis for determining the lifespan of the current target tube.

[0053] It should be noted that the filament current is the current required to heat the filament. Its magnitude directly affects the filament's temperature and the number of electrons emitted, thus affecting the generation of X-rays. The magnitude and fluctuation of the filament current is one of the key factors affecting the life of the tube.

[0054] In one possible embodiment, the filament current data may include multiple historical current data within a preset usage period of the current target tube. Initial historical data within the preset usage period of the current target tube may be obtained, the initial historical data may be divided into multiple groups according to a preset division period, and the average of each group of initial historical data may be determined as the historical current data. The preset division period may be one day or 12 hours, and this embodiment of the present application is not limited thereto.

[0055] For example, the starting point of the preset usage time may be the start time of the current target tube, and the length of the preset usage time may be 30 days; the end point of the preset usage time may be the current time, and the length of the preset usage time may be 14 days. This embodiment of the present application is not limited to this.

[0056] In an exemplary embodiment, the process of obtaining the failure current threshold of the current target tube in step S110 may include obtaining the target initial current of the current target tube; and determining the product of the target initial current and a preset value as the failure current threshold.

[0057] In one embodiment of the present application, the target initial current may be the average filament current of the current target bulb when the current target bulb is used on the first day. The target initial current may also be the filament current of the current target bulb when the current target bulb is used for the first time.

[0058] In another exemplary embodiment, the process of obtaining the target initial current of the current target tube may further include obtaining the current initial current of the current target tube and the historical initial currents of the historical target tubes; and performing a weighted summation of the current initial current and the historical initial currents to obtain the target initial current. The historical initial current of the historical target tube may be the historical initial current of any historical target tube or the average of all historical initial currents of all historical target tubes.

[0059] It should be noted that the historical initial current of the target tube may be the initial value of the filament current of other tubes in the historical database. The current initial current may be the average filament current of the target tube on the first day of use. The current initial current may also be the filament current of the target tube when it was first used.

[0060] For example, the weight of the current initial current can be 70%, and the weight of the historical initial current can be 30%. , the historical initial current can be , target initial current .

[0061] In one embodiment of the present application, the product of the target initial current and the preset value can be determined as the failure current threshold. The target initial current can be used to represent the current state of the current target tube when it is first used, and the failure current threshold can be used to represent the critical condition for the normal operation of the current target tube.

[0062] Exemplarily, the preset value may be 5%.

[0063] It should be noted that in this embodiment, the failure current threshold is determined by multiplying the target initial current by a preset value. This ensures standardization of the filament failure current thresholds for different tubes, effectively reflecting the specific characteristics of each tube, thereby improving the accuracy of the target tube life prediction in subsequent steps. Furthermore, the fixed ratio setting simplifies the calculation process, making failure prediction more convenient and reliable, facilitating proactive maintenance and replacement, reducing equipment downtime, and improving overall operational efficiency.

[0064] In another exemplary embodiment, the process of obtaining the filament current prediction model in step S110 may include step S111 and step S112.

[0065] Step S111 : obtaining a current sample data set and an initial prediction model.

[0066] In one embodiment of the present application, a current sample data set and an initial prediction model may be obtained. The current sample data set may be used to train the initial prediction model.

[0067] In one possible embodiment, the process of obtaining a current sample data set may include: obtaining initial current data, the initial current data including filament current data corresponding to multiple sample tubes, each filament current data including multiple historical filament currents sorted by time; performing data normalization processing on the multiple historical filament currents to obtain multiple standardized data; performing sliding window processing on the multiple standardized data to obtain multiple historical current sample data, and the multiple historical current sample data constitute a current sample data set.

[0068] In another possible embodiment, the process of performing data normalization processing on multiple historical filament currents to obtain multiple standardized data may include: grouping the filament current data according to a preset time period to obtain multiple groups of data to be calculated; performing mean filtering processing on the historical filament current of each group of data to be calculated to obtain multiple data to be processed; and performing data normalization processing on each data to be processed to obtain multiple standardized data.

[0069] Exemplarily, the current sample data set may be obtained by taking the following steps.

[0070] Step 1: Data Collection

[0071] Multiple initial current data sets are collected from several sample tubes. Each initial current data set can represent the entire lifecycle of the tube, meaning the data is collected from the time the sample tube is installed until it fails. Assuming there are four sample tubes, the collected initial current data can be divided into the first, second, third, and fourth data sets. Each data set represents the current variation of a tube over a specific period of time: the first data set contains initial data, the second data set contains intermediate data, the third data set contains late data, and the fourth data set contains data close to failure. This segmented data structure comprehensively records and analyzes the temporal characteristics of the tube's filament current, providing a scientific basis for predicting tube failure. The collected data sets are then evaluated to see if they meet the above criteria. Any non-compliant data sets should be discarded and the reasons for this eliminated analyzed.

[0072] Step 2: Mean filtering

[0073] The sampling interval for the CT tube filament current is approximately a few seconds, and the amount of data collected is large. However, due to the influence of the operating mode, the filament current will experience large amplitude jumps in a short period of time and at a high frequency (over the entire life of the filament current, the overall filament current shows a decaying trend). For data with such large jumps, the prediction accuracy may be very low. In addition, from a practical point of view, it is not necessary to predict the remaining life of the tube filament based on the prediction of the filament current with an accuracy of seconds or hours. Therefore, it can be processed by taking a daily average method and making predictions on a daily basis. The initial current data collected can be grouped by day (preset time period) to obtain multiple groups of data to be calculated. The weighted average of each group of data to be calculated is then taken to obtain multiple data to be processed.

[0074] For example, suppose the data for one day is (that is, the data to be calculated), the average current value of the day after processing (that is, the data to be processed) is:

[0075] (Formula 1)

[0076] Step 3: Data standardization

[0077] Data standardization is performed on all data to be processed. Data standardization is an important step in data preprocessing. It can eliminate dimensionality effects, accelerate convergence, improve model performance, and avoid numerical instability, thus preparing for subsequent model training and testing.

[0078] For example, standardization is to transform the data into a standard normal distribution with a mean of 0 and a standard deviation of 1. Assume that the data to be processed is , the standardized data is , the formula is:

[0079] (Formula 2)

[0080] in, is the mean of all data to be processed, is the standard deviation of all data to be processed. Through this process, all data to be processed will be adjusted to the same scale, ready for subsequent model training and testing.

[0081] Step 4: Sliding Window Processing

[0082] The core idea of ​​sliding window processing is to slide a fixed-size window on the data sequence and gradually process subsets of the data sequence. Figure 2 As shown in Figure 2, it is a schematic diagram of sliding window processing for multiple standardized data. Figure 2 It can be seen that given a length of Data series (that is, multiple standardized data), select Length window and Length window, select sliding step , the sliding window operation will construct multiple historical sequences and label sequences. The calculation formula for the number of samples obtained after sliding the window is as follows:

[0083] (Formula 3)

[0084] For example, The input sequence is , No. The tag sequence is In this way, sliding window processing converts the original data into multiple samples suitable for model training and prediction, enabling the model to learn the temporal dependencies and trends in the data series.

[0085] Step 5: Divide the training set and test set

[0086] Any initial current data is divided, and a small part of the front part and other initial current data are used as a training set for training the model, and the rest of the part is used as a test set to evaluate the generalization performance of the model.

[0087] For example, a specific method for dividing the training and test sets can be: first, take a set of initial current data, combine the first small portion of this data with all other initial current data to form the training set for model training; then, use the remaining data from this initial current data set as the test set to evaluate the model's generalization performance. This division method ensures that the model fully learns the characteristics of each tube during training, while accurately evaluating the model's performance on unseen data during testing.

[0088] Step S112 : training the initial prediction model based on the current sample data set to obtain a filament current prediction model.

[0089] Among them, the filament current prediction model is used to predict the changing trend of the filament current.

[0090] In one embodiment of the present application, a current sample dataset may include historical current sample data corresponding to a sample bulb. An initial prediction model may be trained based on the current sample dataset to obtain a filament current prediction model. The initial prediction model may include a first prediction model, a second prediction model, and a third prediction model. Based on a self-attention mechanism, a first prediction result output by the first prediction model, a second prediction result output by the second prediction model, and a third prediction result output by the third prediction model may be concatenated to obtain model-predicted current data. The loss function of the initial prediction model may be a mean-squared error (MSE), which quantifies the difference between the current data predicted by the initial prediction model and the actual current.

[0091] For example, the formula for mean square error is as follows:

[0092] (Formula 4)

[0093] in, is the number of samples, It is The true value of the sample, It is The predicted value of the sample.

[0094] MSE measures the difference between the model's predictions and the actual results by calculating the square of all prediction errors and taking the average. This formula can help minimize large errors when training the model and improve overall prediction performance.

[0095] In one embodiment, the process of training the initial prediction model based on the current sample data set in step S112 to obtain the filament current prediction model may include steps S1121 to S1124.

[0096] Step S1121: inputting historical current sample data into a first prediction model to obtain a first prediction result.

[0097] The first prediction model can be used to capture the dependency relationship of historical current sample data.

[0098] For example, the first prediction model can be an LSTM (Long Short-Term Memory) model, which can effectively capture long-term dependencies in sequence data. The first prediction model can also be a Gated Recurrent Unit (GRU) or Transformer model.

[0099] Step S1122: input the historical current sample data into the second prediction model to obtain a second prediction result. The second prediction model is used to perform data decomposition on the historical current sample data, and then perform trend quantity prediction and residual quantity prediction respectively, and obtain the second prediction result based on the trend quantity prediction and the residual quantity prediction.

[0100] In one embodiment of the present application, historical current sample data can be input into a second prediction model to obtain a second prediction result. The second prediction result obtained based on trend quantity prediction and residual quantity prediction is more comprehensive in feature extraction.

[0101] Exemplarily, the second prediction model can be a DLinear model. The DLinear model can decompose historical current sample data into a trend value and a residual value. This decomposition helps the model better understand the different components in the sequence. The trend value can capture long-term trends, while the residual value can capture short-term fluctuations or noise. The decomposed trend value and residual value are modeled independently. This allows the model to learn the characteristics of each component without interfering with each other, which helps to more accurately capture the different characteristics of the sequence.

[0102] It should be noted that the DLinear (Decomposition-Linear) model is a time series forecasting method that decomposes data into trend and residual components and then performs linear processing on these components to make predictions. The specific formula is as follows:

[0103] ①Data decomposition: Assume that the input historical current sample data is ,Will Decomposed into trend volume and residual .

[0104] (Formula 5)

[0105] ②Trend volume prediction: Perform linear prediction and set the linear model weight to , bias is .

[0106] (Formula 6)

[0107] ③ Residual amount prediction: Perform linear prediction and set the linear model weight to , bias is .

[0108] (Formula 7)

[0109] ④ Combined prediction: Combine the prediction results of trend quantity and residual quantity to obtain the final second prediction result.

[0110] (Formula 8)

[0111] Step S1123: input the historical current sample data into the third prediction model to obtain a third prediction result.

[0112] The third prediction model is used to analyze data within a preset data length in the historical current sample data.

[0113] In one embodiment of the present application, considering that the degree of data degradation increases in the later period, a third prediction model is introduced to make it pay more attention to the later period data.

[0114] Exemplarily, the third prediction model may be a Lookback model. The preset data length may be a Lookback value, which may indicate how many time steps of input information the Lookback model needs to consider when predicting the output.

[0115] In step S1124 , based on the self-attention mechanism, the first prediction result, the second prediction result, and the third prediction result are first concatenated to obtain model-predicted current data.

[0116] In one embodiment of the present application, the self-attention mechanism is a method used in deep learning to capture the dependencies between elements in an input sequence. Self-attention calculates the correlation between each element in the input sequence and all other elements to generate a weighted sum. The specific formula is as follows:

[0117] ① Input representation: Assume that the input sequence is ,in is the first elements.

[0118] ②Linear transformation: transform the input sequence Mapping to query vector , key vector Sum value vector .

[0119] (Formula 9)

[0120] in, is the weight matrix that needs to be learned.

[0121] ③Calculate attention weight: Calculate query vector through dot product and key vector similarity and divided by the scaling factor To stabilize the gradient, use The function converts similarity into attention weights.

[0122] (Formula 10)

[0123] in, is the dimension of the key vector. is the key vector The transpose of .

[0124] ④Calculation output: value vector Perform weighted sum to get the final output.

[0125] (Formula 11)

[0126] The Self-Attention mechanism can capture the dependencies between elements in the sequence by calculating the correlation between each element in the input sequence and all other elements to generate a weighted sum.

[0127] In an exemplary embodiment of the present application, the first prediction model may be an LSTM model, the second prediction model may be a DLinear model, and the third prediction model may be a Lookback model. The process of obtaining the model-predicted current data based on the historical current sample data by the initial prediction model may include:

[0128] Input historical current sample data into the LSTM model to generate the first prediction result .

[0129] (Formula 12)

[0130] in, It is the historical current sample data.

[0131] The DLinear model decomposes historical current sample data into trend quantity and residual quantity, and improves the prediction accuracy of the model by independently processing these two parts of features.

[0132] (Formula 13)

[0133] (Formula 14)

[0134] (Formula 15)

[0135] (Formula 16)

[0136] in, is the second prediction result.

[0137] Use the Lookback model to analyze the changes in the data in the later period and generate the third prediction results .

[0138] (Formula 17)

[0139] The prediction results generated by the LSTM model, DLinear model and Lookback model are spliced ​​together, and the attention weight of each part is calculated using the self-attention mechanism to generate the model prediction current data .

[0140] (Formula 18)

[0141] Through the above steps and methods, the model can effectively predict the future trend of CT tube filament current changes, helping to make scientific decisions on maintenance and replacement.

[0142] In addition, it should be noted that when training the initial prediction model, the loss function of the initial prediction model can be the mean-square error (MSE). At the same time, the gradient descent algorithm can be used to iteratively adjust the initial prediction model parameters to minimize the value of the loss function.

[0143] Step S120 : obtaining target predicted current data based on the filament current data and the filament current prediction model.

[0144] The target predicted current data may include multiple predicted filament currents of the current target tube, the multiple predicted filament currents are arranged in chronological order, and the target predicted current data is used to characterize the changing trend of the filament current of the current target tube within the predicted time.

[0145] In one embodiment of the present application, the filament current data can be input into the filament current prediction model to obtain target predicted current data. The filament current prediction model is the same as the initial prediction model and can include a first prediction model, a second prediction model, a third prediction model, and a self-attention mechanism.

[0146] In an exemplary embodiment, the process of obtaining target predicted current data based on the filament current data and the filament current prediction model in step S120 may include steps S121 to S124 .

[0147] In step S121 , the filament current data is determined as input data, and a data input step is performed. The data input step includes inputting the input data into a filament current prediction model to obtain initial predicted current data.

[0148] In one embodiment of the present application, when performing current prediction based on filament current data and a filament current prediction model, the filament current data may be first determined as input data, and a data input step may be performed. The initial predicted current data may represent a current trend of the current of the current target tube over a future period of time. The length of the initial predicted current data may be the length of the prediction time, and the length of the initial predicted current data may be greater than 0 and less than or equal to the length of the input data.

[0149] For example, if a certain data in the initial predicted current data represents a current prediction value for a certain day, the initial predicted current may represent a current trend of the current target tube in the next few days.

[0150] Step S122 , executing a data judgment step, the data judgment step includes determining whether there is target data in the initial predicted current data, and the target data is less than or equal to the failure current threshold.

[0151] In one embodiment of the present application, after the initial predicted current data is obtained, a data judgment step may be performed to determine whether there is target data that is less than or equal to the failure current threshold in the initial predicted current data.

[0152] In step S123, if the failure current threshold does not exist in the initial predicted current data, a data updating step is executed. The data updating step includes performing a second splicing on the initial predicted current data and the input data to obtain spliced ​​data; determining the spliced ​​data as the input data, and executing the data input step again.

[0153] In one embodiment of the present application, if the target data does not exist in the initial predicted current data, the failure time of the current target tube has not been predicted. In this case, the filament current of the current target tube needs to be predicted again.

[0154] It should be noted that performing a second splicing of the initial predicted current data and the input data and performing current prediction again can maintain the consistency of the prediction sequence.

[0155] Step S124 : if target data exists in the initial predicted current data, target predicted current data is determined based on all the initial predicted current data.

[0156] In one embodiment of the present application, when a failure current threshold is present in the initial predicted current data, it can be determined that the remaining life of the current target tube has been predicted. All predicted current data can then be spliced ​​in time sequence to obtain target predicted current data. Each data point in the target predicted current data can represent the predicted current at a predicted time point.

[0157] For example, after the initial prediction model training is completed and the filament current prediction model is obtained, the filament current of the CT tube can be predicted. A recursive prediction method is adopted. For a new tube, data can be collected within 30 days from its use as the input of the filament current prediction model. , to predict the filament current in a later period of time , and reuse the predicted data and historical real data as the input of the model again , and then predict the data for a period of time, and repeat this process to reach the required target prediction length. As shown below:

[0158] (Formula 19)

[0159] Among them, p is the model prediction length, . p can be equal to .

[0160] Step S130: determining the current target tube life according to the failure current threshold and the target predicted current data.

[0161] In one embodiment of the present application, target data less than or equal to the failure current threshold may be searched in the target predicted current data, and the current target tube life may be determined based on the ranking of the target data in the target predicted current data.

[0162] For example, each data in the target predicted current data represents the predicted current for a certain day, and the ranking of the target data in the target predicted current data may be 50, so it can be determined that the current target tube life is 50 days.

[0163] It should be noted that the embodiments of this application construct a filament current prediction model with a self-attention mechanism. By integrating LSTM, DLinear, Lookback, and Self-Attention, the model achieves high-precision prediction of CT tube filament current. The LSTM model solves the problem of long-term dependencies, the DLinear model comprehensively extracts data features, the Lookback model focuses on late data degradation, and the self-attention mechanism optimizes the weights of each component. By integrating these advantages, the filament current prediction model significantly improves prediction accuracy and robustness, providing a scientific basis for equipment maintenance, reducing downtime, and improving operational efficiency.

[0164] In summary, the solution of the embodiment of the present application obtains the filament current prediction model, the failure current threshold of the current target tube, and the filament current data, and obtains the target predicted current data based on the filament current data and the filament current prediction model, and determines the life of the current target tube according to the failure current threshold and the target predicted current data. Based on the filament current data of the current target tube and the filament current prediction model, the filament current change trend of the current target tube within the prediction time can be predicted, and the life of the tube can be predicted in combination with the failure current threshold and the target predicted current data. By predicting the life of the tube by the filament current, which is a key factor affecting the life of the tube, the accuracy of the prediction can be improved, equipment shutdown caused by sudden failure of the tube can be avoided, the reliability of the tube operation can be improved, and the operating cost can be reduced.

[0165] Figure 3 FIG. 1 is a block diagram of a device for predicting the life of a tube according to an exemplary embodiment of the present invention. Figure 3 As shown, the exemplary tube life prediction device 300 includes:

[0166] The data acquisition module 310 is used to acquire the filament current prediction model, the failure current threshold of the current target tube, and the filament current data.

[0167] The data prediction module 320 is used to obtain target predicted current data based on the filament current data and the filament current prediction model. The target predicted current data includes multiple predicted filament currents of the current target tube. The multiple predicted filament currents are arranged in chronological order. The target predicted current data is used to characterize the changing trend of the filament current of the current target tube within the prediction time.

[0168] The life prediction module 330 is used to determine the current target tube life according to the failure current threshold and the target predicted current data.

[0169] In a possible implementation, the data acquisition module may also be used to:

[0170] Obtaining a current sample data set and an initial prediction model;

[0171] The initial prediction model is trained based on the current sample data set to obtain a filament current prediction model, which is used to predict the changing trend of the filament current.

[0172] In a possible implementation, the data acquisition module may also be used to:

[0173] Acquire initial current data, the initial current data including filament current data corresponding to a plurality of sample bulbs, each filament current data including a plurality of historical filament currents sorted by time;

[0174] Performing data normalization processing on multiple historical filament currents to obtain multiple standardized data;

[0175] Sliding window processing is performed on the multiple standardized data to obtain multiple historical current sample data, and the multiple historical current sample data constitute a current sample data set.

[0176] In a possible implementation, the data acquisition module may also be used to:

[0177] Grouping the filament current data according to a preset time period to obtain multiple groups of data to be calculated;

[0178] Performing mean filtering on the historical filament current of each group of data to be calculated to obtain multiple data to be processed;

[0179] Perform data standardization on each piece of data to be processed to obtain multiple standardized data.

[0180] In a possible implementation, the current sample data set includes historical current sample data corresponding to the sample tube, and the data acquisition module may further be used to:

[0181] Inputting historical current sample data into a first prediction model to obtain a first prediction result, wherein the first prediction model is used to capture the dependency relationship of the historical current sample data;

[0182] Inputting the historical current sample data into a second prediction model to obtain a second prediction result, wherein the second prediction model is used to perform data decomposition on the historical current sample data, perform trend quantity prediction and residual quantity prediction respectively, and obtain the second prediction result based on the trend quantity prediction and the residual quantity prediction;

[0183] Inputting the historical current sample data into a third prediction model to obtain a third prediction result, wherein the third prediction model is used to analyze data within a preset data length in the historical current sample data;

[0184] Based on the self-attention mechanism, the first prediction result, the second prediction result, and the third prediction result are first concatenated to obtain the model predicted current data.

[0185] In a possible implementation, the data prediction module may also be used to:

[0186] Determining the filament current data as input data and executing a data input step, the data input step including inputting the input data into a filament current prediction model to obtain initial predicted current data;

[0187] Executing a data judgment step, the data judgment step includes determining whether there is target data in the initial predicted current data, and the target data is less than or equal to a failure current threshold;

[0188] If the target data does not exist in the initial predicted current data, a data updating step is performed, the data updating step including performing a second splicing of the initial predicted current data and the input data to obtain spliced ​​data; determining the spliced ​​data as the input data, and performing the data input step again;

[0189] If target data exists in the initial predicted current data, target predicted current data is determined based on all the initial predicted current data.

[0190] In a possible implementation, the data acquisition module may also be used to:

[0191] Get the target initial current of the current target tube;

[0192] The product of the target initial current and the preset value is determined as the failure current threshold.

[0193] In a possible implementation, the data acquisition module may also be used to:

[0194] Obtain the current initial current of the current target tube and the historical initial current of the historical target tube;

[0195] The current initial current and the historical initial current are weightedly summed to obtain the target initial current.

[0196] It should be noted that the tube life prediction device provided in the above-mentioned embodiment and the tube life prediction method provided in the above-mentioned embodiment share the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiments and will not be repeated here. In actual applications, the tube life prediction device provided in the above-mentioned embodiment can, as needed, distribute the aforementioned functions among different functional modules. This means that the internal structure of the system can be divided into different functional modules to perform all or part of the functions described above, and this is not a limitation herein.

[0197] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by one or more processors, the electronic device implements the tube life prediction method provided in the above-mentioned embodiments.

[0198] Another aspect of the present application provides a computer-readable storage medium storing a computer program. When executed by a computer processor, the computer program causes the computer to perform the bulb life prediction methods provided in the aforementioned embodiments. The computer-readable storage medium may be included in the electronic device described in the aforementioned embodiments, or may exist independently and not be incorporated into the electronic device.

[0199] Another aspect of the present application provides a computer program product or computer program, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the bulb life prediction method provided in each of the above-described embodiments.

[0200] In the embodiments of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance. Throughout the specification and claims, the terms "including" and "comprising" are open-ended terms and should be interpreted as "including but not limited to."

[0201] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, any equivalent modifications or alterations accomplished by a person of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A method for predicting tube life, characterized in that: include: Obtain the filament current prediction model, the failure current threshold of the current target tube, and the filament current data; Based on the filament current data and the filament current prediction model, target predicted current data is obtained, wherein the target predicted current data includes multiple predicted filament currents of the current target bulb, the multiple predicted filament currents are arranged in chronological order, and the target predicted current data is used to characterize a change trend of the filament current of the current target bulb within a prediction time; determining the life of the current target tube according to the failure current threshold and the target predicted current data; Get the filament current prediction model, including: Obtaining a current sample data set and an initial prediction model; Training the initial prediction model based on the current sample data set to obtain a filament current prediction model, wherein the filament current prediction model is used to predict a change trend of the filament current; The current sample data set includes historical current sample data corresponding to the sample tube, and training the initial prediction model based on the current sample data set includes: Inputting the historical current sample data into a first prediction model to obtain a first prediction result, wherein the first prediction model is used to capture the dependency relationship of the historical current sample data; Inputting the historical current sample data into a second prediction model to obtain a second prediction result, wherein the second prediction model is used to perform data decomposition on the historical current sample data, perform trend quantity prediction and residual quantity prediction respectively, and obtain the second prediction result based on the trend quantity prediction and the residual quantity prediction; Inputting the historical current sample data into a third prediction model to obtain a third prediction result, wherein the third prediction model is used to analyze data within a preset data length in the historical current sample data; Based on the self-attention mechanism, the first prediction result, the second prediction result, and the third prediction result are first concatenated to obtain model-predicted current data.

2. The method for predicting tube life according to claim 1, characterized in that: Get the current sample data set, including: Acquire initial current data, the initial current data including filament current data corresponding to a plurality of sample bulbs, each of the filament current data including a plurality of historical filament currents sorted by time; performing data standardization processing on the plurality of historical filament currents to obtain a plurality of standardized data; Sliding window processing is performed on the plurality of standardized data to obtain a plurality of historical current sample data, and the plurality of historical current sample data constitute the current sample data set.

3. The method for predicting tube life according to claim 2, characterized in that: Performing data normalization processing on the plurality of historical filament currents to obtain a plurality of standardized data, including: Grouping the filament current data according to a preset time period to obtain multiple groups of data to be calculated; Performing mean filtering on the historical filament current of each group of the data to be calculated to obtain a plurality of data to be processed; Data standardization is performed on each of the data to be processed to obtain a plurality of standardized data.

4. The method for predicting tube life according to claim 1, wherein: Obtaining target predicted current data based on the filament current data and the filament current prediction model includes: Determining the filament current data as input data, and performing a data input step, wherein the data input step includes inputting the input data into the filament current prediction model to obtain initial predicted current data; executing a data judgment step, the data judgment step including determining whether there is target data in the initial predicted current data, the target data being less than or equal to the failure current threshold; If the target data does not exist in the initial predicted current data, executing a data updating step, the data updating step including performing a second splicing on the initial predicted current data and the input data to obtain spliced ​​data; determining the spliced ​​data as the input data, and executing the data input step again; If the target data exists in the initial predicted current data, the target predicted current data is determined based on all the initial predicted current data.

5. The method for predicting tube life according to claim 1, wherein: Get the failure current threshold of the current target tube, including: Obtaining a target initial current of the current target tube; The product of the target initial current and a preset value is determined as the failure current threshold.

6. A device for predicting the life of a tube, characterized in that: include: A data acquisition module is used to obtain the filament current prediction model, the failure current threshold of the current target tube, and the filament current data; a data prediction module, configured to obtain target predicted current data based on the filament current data and the filament current prediction model, wherein the target predicted current data includes a plurality of predicted filament currents of the current target tube, the plurality of predicted filament currents being arranged in chronological order, and the target predicted current data being used to characterize a changing trend of the filament current of the current target tube within a predicted time period; A life prediction module, configured to determine the life of the current target tube according to the failure current threshold and the target predicted current data; Get the filament current prediction model, including: Obtaining a current sample data set and an initial prediction model; Training the initial prediction model based on the current sample data set to obtain a filament current prediction model, wherein the filament current prediction model is used to predict a change trend of the filament current; The current sample data set includes historical current sample data corresponding to the sample tube, and training the initial prediction model based on the current sample data set includes: Inputting the historical current sample data into a first prediction model to obtain a first prediction result, wherein the first prediction model is used to capture the dependency relationship of the historical current sample data; Inputting the historical current sample data into a second prediction model to obtain a second prediction result, wherein the second prediction model is used to perform data decomposition on the historical current sample data, perform trend quantity prediction and residual quantity prediction respectively, and obtain the second prediction result based on the trend quantity prediction and the residual quantity prediction; Inputting the historical current sample data into a third prediction model to obtain a third prediction result, wherein the third prediction model is used to analyze data within a preset data length in the historical current sample data; Based on the self-attention mechanism, the first prediction result, the second prediction result, and the third prediction result are first concatenated to obtain model-predicted current data.

7. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to execute the tube life prediction method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the bulb life prediction method according to any one of claims 1 to 5.

Images