A stress monitoring data prediction method and related device

Abstract

This application discloses a method and related apparatus for predicting stress monitoring data, relating to the field of stress monitoring. The method includes: acquiring n actual stress monitoring data points, and using each randomly generated smoothing coefficient as a current smoothing coefficient; for each current smoothing coefficient, performing a quadratic exponential smoothing prediction on the first n-m actual stress monitoring data points to obtain the next m predicted stress monitoring data points; determining a target smoothing coefficient based on each of the next m predicted stress monitoring data points and the next m actual stress monitoring data points; for each current smoothing coefficient, determining an optimized smoothing coefficient based on the current smoothing coefficient, the target smoothing coefficient, and a preset inertia weight; and continuously optimizing the smoothing coefficient until a preset number of iterations is reached, making the selection of the smoothing coefficient more objective and scientific. Performing a quadratic exponential smoothing prediction based on the optimized target smoothing coefficient helps improve the accuracy of the predicted stress monitoring data.

Description

Technical Field

[0001] This application relates to the field of stress monitoring, and in particular to a method and related apparatus for predicting stress monitoring data. Background Technology

[0002] In industrial equipment and mechanical systems, stress monitoring data plays a crucial role. This stress data, acquired in real time by high-precision sensors, covers the stress conditions of the equipment under various operating conditions. It is not only the basis for assessing the health status of the equipment and optimizing maintenance strategies, but also the key to ensuring the long-term stable operation of the system. Therefore, predicting stress monitoring data is particularly important.

[0003] Currently, stress monitoring data is mainly predicted using the quadratic exponential smoothing method, which is the most commonly used time series forecasting method.

[0004] However, the smoothing coefficients in the quadratic exponential smoothing method are usually randomly generated or manually adjusted based on experience, which may lead to inaccurate prediction results. Summary of the Invention

[0005] In view of the above problems, this application provides a method and related apparatus for predicting stress monitoring data, in order to improve the accuracy of predicting stress monitoring data. The specific solution is as follows:

[0006] The first aspect of this application provides a method for predicting stress monitoring data, including:

[0007] Obtain n actual stress monitoring data points, and divide the n actual stress monitoring data points into the first n nm actual stress monitoring data points and the last m actual stress monitoring data points, where m is the preset number of avoidance time nodes, m≥1 and n>m;

[0008] Multiple smoothing coefficients are randomly generated based on a preset range, and each randomly generated smoothing coefficient is used as the current smoothing coefficient.

[0009] For each of the current smoothing coefficients, a quadratic exponential smoothing prediction is performed on the first nm stress monitoring data based on the current smoothing coefficients to obtain the predicted stress monitoring data for the next m data.

[0010] Based on the predicted data of each of the m stress monitoring lines and the actual data of the m stress monitoring lines, the target smoothing coefficient is determined.

[0011] For each of the current smoothing coefficients, an optimized smoothing coefficient is determined based on the current smoothing coefficient, the target smoothing coefficient, and a preset inertia weight.

[0012] Each optimized smoothing coefficient is used as the current smoothing coefficient. The process of performing a quadratic exponential smoothing prediction on the first nm stress monitoring actual data based on the current smoothing coefficient is repeated until the number of iterations reaches the preset number of iterations, and the optimized target smoothing coefficient is obtained.

[0013] Based on the optimized target smoothing coefficient, a second exponential smoothing prediction is performed on the n actual stress monitoring data to obtain the next k predicted stress monitoring data, where k≥1.

[0014] In one possible implementation, the step of performing a quadratic exponential smoothing prediction on the first nm stress monitoring data based on the current smoothing coefficient to obtain the subsequent m stress monitoring prediction data includes:

[0015] For each of the current smoothing coefficients, the first nm stress monitoring data is used as the first target stress monitoring data.

[0016] Based on the current smoothing coefficient, a second exponential smoothing prediction is performed on the actual data of the first target stress monitoring to obtain the next stress monitoring prediction data of the actual data of the first target stress monitoring.

[0017] The first target stress monitoring actual data and the next stress monitoring prediction data of the first target stress monitoring actual data are used as the first target stress monitoring actual data. The process of performing a second exponential smoothing prediction on the first target stress monitoring actual data based on the current smoothing coefficient to obtain the next stress monitoring prediction data of the first target stress monitoring actual data is repeated until the number of return times reaches (m-1) times to obtain the next m stress monitoring prediction data.

[0018] In one possible implementation, determining the target smoothing coefficient based on the predicted data of each of the last m stress monitoring lines and the actual data of the last m stress monitoring lines includes:

[0019] For each set of m stress monitoring prediction data, the Hubey loss function is used to compare the set of m stress monitoring prediction data with the set of m stress monitoring actual data to obtain a set of Hubey losses, which includes m Hubey losses.

[0020] The target group Hubey loss is determined from the Hubey losses of each group, and the current smoothing coefficient corresponding to the target group Hubey loss is determined as the target smoothing coefficient. The sum of the m Hubey losses in the target group Hubey loss is minimized.

[0021] In one possible implementation, the calculation process for the sum of the m Hubey losses includes:

[0022] Obtain the date information of m stress monitoring data corresponding to the m Hube losses;

[0023] Sort the m date information from morning to night, and distribute the m preset loss weights to the m Hube losses corresponding to the sorted m date information in ascending order;

[0024] The sum of the products of each Hubey loss and its corresponding loss weight is obtained by adding them together.

[0025] In one possible implementation, the step of performing quadratic exponential smoothing prediction on the n actual stress monitoring data based on the optimized target smoothing coefficient to obtain the subsequent k predicted stress monitoring data for the n actual stress monitoring data includes:

[0026] The n actual stress monitoring data points are used as the second target actual stress monitoring data points;

[0027] Based on the optimized target smoothing coefficient, a second exponential smoothing prediction is performed on the actual data of the second target stress monitoring to obtain the last stress monitoring prediction data of the actual data of the second target stress monitoring.

[0028] The actual data of the second target stress monitoring and the next stress monitoring prediction data of the actual data of the second target stress monitoring are used as the actual data of the second target stress monitoring. The process of performing a second exponential smoothing prediction on the actual data of the second target stress monitoring based on the optimized target smoothing coefficient is repeated until the number of return times reaches (k-1) times, and the next k stress monitoring prediction data of the n actual stress monitoring data are obtained.

[0029] In one possible implementation, after performing quadratic exponential smoothing prediction on the n actual stress monitoring data based on the optimized target smoothing coefficient to obtain the subsequent k predicted stress monitoring data for the n actual stress monitoring data, the method further includes:

[0030] Obtain the next k stress monitoring data points from the n stress monitoring data points;

[0031] Calculate the difference between the last k actual stress monitoring data points of the n actual stress monitoring data points and the last k predicted stress monitoring data points of the n actual stress monitoring data points;

[0032] Based on the difference and the preset difference, it is determined whether a prediction anomaly has occurred.

[0033] A second aspect of this application provides an apparatus for predicting stress monitoring data, comprising:

[0034] The acquisition unit is used to acquire n actual stress monitoring data and divide the n actual stress monitoring data into the first nm actual stress monitoring data and the last m actual stress monitoring data, where m is the preset number of avoidance time nodes, m≥1 and n>m;

[0035] The first determining unit is used to randomly generate multiple smoothing coefficients based on a preset range, and to use each randomly generated smoothing coefficient as the current smoothing coefficient.

[0036] The first prediction unit is used to perform a quadratic exponential smoothing prediction on the first nm stress monitoring actual data based on the current smoothing coefficient for each of the current smoothing coefficients, so as to obtain the subsequent m stress monitoring prediction data.

[0037] The second determining unit is used to determine the target smoothing coefficient based on the predicted data of each of the last m stress monitoring lines and the actual data of the last m stress monitoring lines.

[0038] The third determining unit is used to determine the optimized smoothing coefficient for each of the current smoothing coefficients, based on the current smoothing coefficient, the target smoothing coefficient, and the preset inertia weight.

[0039] The return unit is used to take each of the optimized smoothing coefficients as the current smoothing coefficients and return to execute the step of performing a quadratic exponential smoothing prediction on the first nm stress monitoring actual data based on the current smoothing coefficients to obtain the next m stress monitoring prediction data, until the number of returns reaches the preset number of iterations and the optimized target smoothing coefficients are obtained.

[0040] The second prediction unit is used to perform a second exponential smoothing prediction on the n actual stress monitoring data based on the optimized target smoothing coefficient, so as to obtain the next k predicted stress monitoring data of the n actual stress monitoring data, where k≥1.

[0041] A third aspect of this application provides a computer program product including computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the stress monitoring data prediction method of the first aspect or any implementation thereof.

[0042] A fourth aspect of this application provides an electronic device, including at least one processor and a memory connected to the processor, wherein:

[0043] The memory is used to store computer programs;

[0044] The processor is used to execute the computer program so that the electronic device can implement the method for predicting stress monitoring data in the first aspect or any implementation thereof.

[0045] The fifth aspect of this application provides a computer storage medium carrying one or more computer programs that, when executed by an electronic device, enable the electronic device to perform a method for predicting stress monitoring data as described in the first aspect or any implementation thereof.

[0046] Based on the above technical solution, this application provides a method and related apparatus for predicting stress monitoring data. The method includes: acquiring n actual stress monitoring data points; randomly generating multiple smoothing coefficients based on a preset range; and using each randomly generated smoothing coefficient as a current smoothing coefficient; for each current smoothing coefficient, performing a quadratic exponential smoothing prediction on the first nm actual stress monitoring data points to obtain the next m predicted stress monitoring data points, where m is a preset number of avoidance time nodes, m≥1 and n>m; determining a target smoothing coefficient based on each of the next m predicted stress monitoring data points and the next m actual stress monitoring data points; for each current smoothing coefficient, determining an optimized smoothing coefficient based on the current smoothing coefficient, the target smoothing coefficient, and a preset inertia weight; using each optimized smoothing coefficient as a current smoothing coefficient, returning to execute the step of performing a quadratic exponential smoothing prediction on the first nm actual stress monitoring data points for each current smoothing coefficient to obtain the next m predicted stress monitoring data points, until the number of returns reaches a preset number of iterations to obtain the optimized target smoothing coefficient; and performing a quadratic exponential smoothing prediction on the n actual stress monitoring data points based on the optimized target smoothing coefficient. This scheme continuously optimizes the smoothing coefficient until a preset number of iterations is reached. At the same time, it introduces inertial weights to make the selection of the smoothing coefficient more objective and scientific. This avoids the limitations of directly using randomly generated smoothing coefficients and manually adjusting the smoothing coefficients, which helps to improve the accuracy of predicted stress monitoring data. Attached Figure Description

[0047] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0048] Figure 1 A flowchart illustrating a method for predicting stress monitoring data provided in an embodiment of this application;

[0049] Figure 2This application provides a schematic diagram comparing monitoring prediction data corresponding to a smoothing coefficient with actual stress monitoring data.

[0050] Figure 3 A schematic diagram comparing monitoring prediction data and actual stress monitoring data corresponding to another smoothness coefficient provided in an embodiment of this application;

[0051] Figure 4 This application provides a schematic diagram illustrating the variation of Hubey loss corresponding to a smoothing coefficient in an embodiment of the present application.

[0052] Figure 5 A schematic diagram illustrating the variation of Hubey loss corresponding to another smoothing coefficient provided in this application embodiment;

[0053] Figure 6 This is a schematic diagram illustrating the change of the optimized smoothing coefficient corresponding to an embodiment of the present application.

[0054] Figure 7 A schematic diagram illustrating the change of the optimized smoothing coefficient corresponding to another smoothing coefficient provided in an embodiment of this application;

[0055] Figure 8 A schematic diagram of a stress monitoring data prediction device provided in an embodiment of this application;

[0056] Figure 9 This is a schematic diagram of the hardware structure of a stress monitoring data prediction device provided in an embodiment of this application. Detailed Implementation

[0057] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0058] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0059] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0060] To improve the accuracy of predicted stress monitoring data, this application provides a method for predicting stress monitoring data. The method for predicting stress monitoring data provided in this application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0061] Please see the appendix Figure 1 , Figure 1 This is a flowchart illustrating a method for predicting stress monitoring data provided in an embodiment of this application. The method may include the following steps:

[0062] Step S101: Obtain n actual stress monitoring data points, and divide the n actual stress monitoring data points into the first nm actual stress monitoring data points and the last m actual stress monitoring data points, where m is the preset number of avoidance time nodes, m≥1 and n>m.

[0063] In this application, a connection can be established with a database storing actual stress monitoring data. This typically involves configuring database connection parameters, such as database type, address, port, username, and password. Once the connection is successful, the required n (e.g., 35) actual stress monitoring data points are extracted from the database based on query criteria (e.g., time range, monitoring point number, etc.).

[0064] Furthermore, due to sensor malfunctions, data transmission errors, and other reasons, the extracted stress monitoring data may contain missing values. To maintain data integrity, the mean of the data before and after the missing value can be used for imputation. To remove noise from the extracted stress monitoring data and improve its accuracy, the 3σ principle of normal distribution can be used for denoising. To allow data of different dimensions to be compared and calculated on the same scale, the data can be scaled to a specific range (e.g., between 0 and 1) according to a normalization formula.

[0065] In the preprocessed dataset, when the actual stress monitoring data is relatively stable or shows a clear trend, m can be taken to be larger; conversely, m can be taken to be smaller. This is to avoid inaccurate prediction results due to large data fluctuations or the influence of recent events. Therefore, the first nm (e.g., 33) stress monitoring data can be used as training data, and the last m (e.g., 2) data can be used as validation data to evaluate the model's prediction accuracy. It is important to note that the value of m should not be too large or too small; it needs to be reasonable. If m is too small, the validation data may be insufficient to accurately evaluate the model's predictive ability; if m is too large, it may lead to insufficient training data, affecting the model's training effect. m can also be understood as the number of time points to avoid.

[0066] Step S102: Randomly generate multiple smoothing coefficients based on a preset range, and use each randomly generated smoothing coefficient as the current smoothing coefficient.

[0067] It should be noted that this process utilizes the Sugarcane Rat Algorithm, which does not require a large amount of historical data and can still effectively perform long-term predictions even with scarce data, adapting to various drastically changing environmental conditions. The Sugarcane Rat Algorithm is a swarm intelligence optimization algorithm that can optimize search and optimization problems by simulating the intelligent behavior of sugarcane rats during foraging. The initialization process of the Sugarcane Rat Algorithm includes setting parameters such as the range of individuals in the population, the population size, and the number of iterations. The range of individuals in the population corresponds to the preset range of the smoothing coefficient in this embodiment, which can be determined based on experience, data characteristics, or algorithm requirements. The population size corresponds to the number of smoothing coefficients in this embodiment. The number of iterations refers to the total number of times the algorithm runs, or the number of generations, determining the depth and breadth of the algorithm's exploration in the search space, as well as the probability of finding the optimal solution.

[0068] In this application, multiple (e.g., 200) smoothing coefficients are randomly generated based on a preset range (e.g., [0.0001, 0.9999]). The random generation process ensures a variety of smoothing coefficients, and each randomly generated smoothing coefficient is used as the current smoothing coefficient for analysis and prediction.

[0069] The smoothing coefficient is an important parameter in time series analysis, signal processing, and data smoothing, typically used to control the degree of smoothing—that is, how to balance preserving the original characteristics of the data with noise removal. When using exponential smoothing methods (such as quadratic exponential smoothing) for time series forecasting, the smoothing coefficient determines the degree of influence of historical data on the current forecast value. A higher smoothing coefficient means more emphasis is placed on recent data, while a lower smoothing coefficient means more emphasis is placed on the overall trend of historical data.

[0070] Step S103: For each current smoothing coefficient, perform a second exponential smoothing prediction on the actual stress monitoring data of the first nm lines based on the current smoothing coefficient to obtain the predicted stress monitoring data of the next m lines.

[0071] In this application, firstly, for each current smoothing coefficient, the first nm stress monitoring data points are used as the first target stress monitoring data points. Then, based on the current smoothing coefficient, a second exponential smoothing prediction is performed on the first target stress monitoring data points to obtain the next stress monitoring prediction data point. Finally, the first target stress monitoring data points and the next stress monitoring prediction data point are used as the first target stress monitoring data points, and the process is repeated to return to the step of performing a second exponential smoothing prediction on the first target stress monitoring data points based on the current smoothing coefficient to obtain the next stress monitoring prediction data point, until the number of return steps reaches (m-1) times, resulting in the next m stress monitoring prediction data points.

[0072] Specifically, using the currently selected smoothing coefficient and the actual data of the first target stress monitoring, a quadratic exponential smoothing prediction is performed to obtain the next stress monitoring prediction data. The newly obtained stress monitoring prediction data is then updated to the existing dataset (i.e., the actual data of the first target stress monitoring). Using the updated dataset (i.e., the actual data of the first target stress monitoring and the next stress monitoring prediction data) and the current smoothing coefficient, a quadratic exponential smoothing prediction is performed again to obtain the next stress monitoring prediction data. This process is repeated until the number of iterations reaches (m-1), at which point the prediction stops, resulting in the last m stress monitoring prediction data. The advantage of this method is its flexibility in adapting to data changes, as each prediction is based on the latest dataset, thus improving prediction accuracy. Simultaneously, this method better reflects the trends and periodic changes in the data. However, its disadvantage lies in the large computational load, requiring multiple predictions and data updates.

[0073] As an alternative implementation, instead of generating prediction data line by line, a quadratic exponential smoothing method can be used to predict the next m stress monitoring data lines all at once based on all available historical data (the first nm actual stress monitoring data lines). The advantage of this method is its high efficiency, as it can obtain all the necessary prediction data at once. However, it may also lead to lower accuracy in the prediction results due to factors such as model complexity and data nonlinearity.

[0074] The single exponential smoothing method can be specifically referred to in the following formula:

[0075] S t (1) =a*yt +(1-a)*S t-1 (1)

[0076] In the formula, S t (1) y represents the exponentially smoothed value over period t; t S represents the actual value in period t; t-1 (1) represents the first-order exponential smoothing value for period t-1; 'a' represents the smoothing coefficient.

[0077] If only data starting from y1 is available, then the methods for determining the initial value are:

[0078] 1) Let S0 equal y1;

[0079] 2) After accumulating a certain amount of data, take S1 as the simple arithmetic mean of the preceding data.

[0080] When a time series shows no obvious trend, a smoothing coefficient can be used for prediction. The prediction formula is as follows:

[0081] y t+1 '=a*y t +(1-a)*y t '

[0082] In the formula, y t+1 ' represents the predicted value for period t+1, i.e., the smoothed value S for period t. t (1) ;y t ' represents the predicted value for period t, i.e., the smoothed value S for period t-1. t-1 (1) .

[0083] The degree of lag bias in exponentially smoothed value series decreases as the smoothing coefficient increases. However, when the time series exhibits a linear trend, prediction using single exponential smoothing will still show significant lag bias. Therefore, correction is necessary. The formula for double exponential smoothing, based on single exponential smoothing, is as follows:

[0084] S t (2) =a*S t (1) +(1-a)*S t-1 (2)

[0085] In the formula, S t (2) S represents the quadratic exponential smoothed value for period t; t (1) S represents the exponentially smoothed value over period t; t-1(2) This represents the quadratic exponential smoothing value for period t-1.

[0086] The prediction formula for quadratic exponential smoothing is:

[0087] y t+T '=a t +b t *T

[0088] S t (2) =a*S t (1) +(1-a)*S t-1 (2)

[0089] a t =2S t (1) -S t (2)

[0090] b t =a / (1-a)(S t (1) S t (2) )

[0091] In the formula, y t+T ' represents the predicted value for period t+T; T represents the time to forecast backwards.

[0092] Step S104: Determine the target smoothing coefficient based on the predicted data of each of the last m stress monitoring lines and the actual data of the last m stress monitoring lines.

[0093] In this application, firstly, for each set of m predicted stress monitoring data, the Hubey loss function is used to compare the predicted data with the actual data, resulting in a set of Hubey losses, each set comprising m Hubey losses. Then, a target set of Hubey losses is determined from each set, and the current smoothing coefficient corresponding to the target set's Hubey loss is set as the target smoothing coefficient. The goal is to minimize the sum of the m Hubey losses in the target set.

[0094] For better understanding, please refer to the following details. Figure 2 and Figure 3 , Figure 2 This application provides a schematic diagram comparing monitoring prediction data corresponding to a smoothing coefficient with actual stress monitoring data. Figure 3 This is a schematic diagram comparing the monitoring prediction data corresponding to another smoothing coefficient provided in this application embodiment with the actual stress monitoring data.

[0095] The calculation process for the sum of m Hubey losses can specifically include: First, obtaining m date information from m stress monitoring data corresponding to the m Hubey losses. Then, sorting the m date information from earliest to latest, and allocating m preset loss weights to the m Hubey losses corresponding to the sorted m date information in ascending order. Finally, summing the products of each Hubey loss and its corresponding loss weight to obtain the sum of the m Hubey losses.

[0096] It's important to note that to optimize the performance of the prediction model, a suitable smoothing coefficient needs to be found that balances the model's smoothness with its fit to the data. The Hobbey loss function is used as a tool to quantify the prediction error and adjust the smoothing coefficient accordingly. The Hobbey loss function combines the advantages of MSE (mean-square error) and MAE (mean absolute error). When the prediction error is small (less than or equal to a certain threshold δ), MSE is used to penalize the error, which helps maintain the model's sensitivity to the data. When the prediction error is large (greater than the threshold δ), MAE is used, which helps reduce the model's sensitivity to outliers. Specifically, this can be expressed by the following formula:

[0097]

[0098] In the formula, y true This represents the actual value (i.e., the actual stress monitoring data can be substituted); y pred δ represents the predicted value (which can be substituted with stress monitoring prediction data); δ represents the Huber loss parameter; Huber Loss represents the Huber loss.

[0099] In the double exponential smoothing method, since recent data is more important for predicting data in the short term, the m date values ​​are sorted from earliest to latest to ensure that the subsequent weight allocation reflects the influence of time sequence. That is, more recent data should be assigned higher weights. The m preset loss weights are then distributed in ascending order to the m Hubble losses corresponding to the sorted m date values. The weight allocation should match the date order, meaning that later dates should have higher weights for their corresponding Hubble losses. These preset loss weights can be set in advance based on experience or practical needs; they reflect the importance of data at different points in time to the prediction results. The sum of the products of each Hubble loss and its corresponding loss weight is then obtained to obtain the total of the m Hubble losses.

[0100] To find the optimal smoothing coefficient, multiple Hobby losses corresponding to different smoothing coefficients are compared. The sum of the m Hobby losses in each group reflects the overall predictive performance of that smoothing coefficient. Generally, the smaller the sum of the Hobby losses, the better the smoothing coefficient performs in prediction. Therefore, after comparing the sums of the Hobby losses corresponding to all smoothing coefficients, the group with the smallest sum is selected as the target group Hobby loss. The smoothing coefficient corresponding to this group of Hobby losses is the target smoothing coefficient found on the current dataset.

[0101] For better understanding, please refer to the following details. Figure 4 and Figure 5 , Figure 4 This application provides a schematic diagram illustrating the variation of Hubey loss corresponding to a smoothing coefficient in an embodiment of the present application. Figure 5 This is a schematic diagram illustrating the variation of Hubey loss corresponding to another smoothing coefficient provided in an embodiment of this application.

[0102] Step S105: For each current smoothing coefficient, determine the optimized smoothing coefficient based on the current smoothing coefficient, the target smoothing coefficient, and the preset inertia weight.

[0103] In this application, to prevent local optima, an inertial weight is introduced to simulate the movement mechanism of the giant cane rat, and a new population of individuals is generated. This involves optimizing each current smoothing coefficient to obtain an optimized smoothing coefficient. The specific optimization process can be found in the following formula:

[0104] Optimized smoothing coefficient = Current smoothing coefficient + Inertia weight × (Target smoothing coefficient - Current smoothing coefficient)

[0105] The inertia weight (usually denoted as ω, omega) is a number between 0 and 1 that determines the degree to which the new solution depends on the current solution. When the inertia weight is large, the new solution is more likely to perform a local search in the vicinity of the current solution; when the inertia weight is small, the new solution is more likely to jump out of the current region and perform a global search.

[0106] To more intuitively understand the role of inertia weight, the following example is provided:

[0107] Suppose that during the optimization of the smoothing coefficient, the current smoothing coefficient is 0.6 and the target smoothing coefficient is 0.8. Based on these two values ​​and the preset inertia weight, the optimized smoothing coefficient for the next iteration is determined.

[0108] If the inertia weight is set to 0.9, then according to the formula above, the optimized smoothing coefficient will be calculated as: Optimized smoothing coefficient = 0.6 + 0.9 × (0.8 - 0.6) = 0.6 + 0.18 = 0.78. In this case, the new solution is very close to the current solution of 0.6 and is more inclined to perform local search within the current region.

[0109] If the inertia weight is set to 0.1, then according to the formula above, the optimized smoothing coefficient will be calculated as: optimized smoothing coefficient = 0.6 + 0.1 × (0.8 - 0.6) = 0.6 + 0.02 = 0.62. In this case, although the new solution is still affected by the current solution, it is further away from the current solution and is more likely to jump out of the current region and perform a global search.

[0110] Step S106: Take each optimized smoothing coefficient as the current smoothing coefficient and determine whether the number of returns has reached the preset number of iterations.

[0111] If the number of returns does not reach the preset number of iterations, then return to step S103; if the number of returns reaches the preset number of iterations, then the optimized target smoothing coefficient is obtained.

[0112] In this application, the optimized smoothing coefficient in each iteration is used as the new current smoothing coefficient, and steps S103, S104 and S105 are executed iteratively. In each iteration, a set of prediction data is generated based on the current smoothing coefficient, and the corresponding Hobbes loss is calculated to determine the new target smoothing index. The current smoothing index is then optimized based on the new target smoothing index until the number of iterations reaches the preset number. The algorithm will then stop iterating. The last iteration does not need to execute step S105, that is, it does not need to optimize the current smoothing index based on the new target smoothing index. It is sufficient to calculate the latest target smoothing index (i.e., the optimized target smoothing coefficient).

[0113] For better understanding, please refer to the following details. Figure 6 and Figure 7 , Figure 6 This is a schematic diagram illustrating the change of the optimized smoothing coefficient corresponding to an embodiment of the present application. Figure 7 This is a schematic diagram illustrating the change of the optimized smoothing coefficient corresponding to another smoothing coefficient provided in an embodiment of this application.

[0114] Step S107: Based on the optimized target smoothing coefficient, perform secondary exponential smoothing prediction on the n actual stress monitoring data to obtain the next k predicted stress monitoring data, where k≥1.

[0115] In this application, n actual stress monitoring data points are first used as the second target stress monitoring data points. Then, based on the optimized target smoothing coefficient, a quadratic exponential smoothing prediction is performed on the second target stress monitoring data points to obtain the next stress monitoring prediction data point. Finally, the second target stress monitoring data points and the next stress monitoring prediction data point are used as the second target stress monitoring data points, and the process of performing a quadratic exponential smoothing prediction based on the optimized target smoothing coefficient to obtain the next stress monitoring prediction data point is repeated until the number of repetitions reaches (k-1) times, resulting in the k last stress monitoring prediction data points of the n actual stress monitoring data points.

[0116] Specifically, using the optimized target smoothing coefficient and the actual data of the second target stress monitoring, a quadratic exponential smoothing prediction is performed to obtain the next stress monitoring prediction data for the actual data of the second target stress monitoring. The newly obtained stress monitoring prediction data is then updated to the existing dataset (i.e., the actual data of the second target stress monitoring). Using the updated dataset (i.e., the actual data of the second target stress monitoring and the next stress monitoring prediction data for the actual data of the second target stress monitoring) and the optimized target smoothing coefficient, a quadratic exponential smoothing prediction is performed again to obtain the next stress monitoring prediction data. This process is repeated until the number of iterations reaches (k-1), at which point the prediction stops, resulting in the k next stress monitoring prediction data for the n actual stress monitoring data. The advantage of this method is its flexibility in adapting to data changes, as each prediction is based on the latest dataset, thus improving prediction accuracy. Simultaneously, this method better reflects the trends and periodic changes in the data. However, its disadvantage lies in the large computational load, requiring multiple predictions and data updates.

[0117] As an alternative implementation, instead of generating prediction data line by line, a quadratic exponential smoothing method is used to directly predict the next k stress monitoring prediction data points based on all available historical data (n actual stress monitoring data points) in one go. The advantage of this method is its high efficiency, as it can obtain all the necessary prediction data at once. However, it may also lead to lower accuracy in the prediction results due to factors such as model complexity and data nonlinearity.

[0118] In summary, the present application provides a method for predicting stress monitoring data. This method includes: acquiring n actual stress monitoring data points; randomly generating multiple smoothing coefficients based on a preset range; and using each randomly generated smoothing coefficient as a current smoothing coefficient. For each current smoothing coefficient, performing a quadratic exponential smoothing prediction on the first nm actual stress monitoring data points to obtain the next m predicted stress monitoring data points, where m is a preset number of avoidance time nodes, m ≥ 1 and n > m. Determining a target smoothing coefficient based on the next m predicted stress monitoring data points and the next m actual stress monitoring data points. For each current smoothing coefficient, determining an optimized smoothing coefficient based on the current smoothing coefficient, the target smoothing coefficient, and a preset inertia weight. Using each optimized smoothing coefficient as a current smoothing coefficient, returning to the step of performing a quadratic exponential smoothing prediction on the first nm actual stress monitoring data points for each current smoothing coefficient to obtain the next m predicted stress monitoring data points, until the number of returns reaches a preset number of iterations, obtaining the optimized target smoothing coefficient. Performing a quadratic exponential smoothing prediction on the n actual stress monitoring data points based on the optimized target smoothing coefficient. This scheme continuously optimizes the smoothing coefficient until a preset number of iterations is reached. At the same time, it introduces inertial weights to make the selection of the smoothing coefficient more objective and scientific. This avoids the limitations of directly using randomly generated smoothing coefficients and manually adjusting the smoothing coefficients, which helps to improve the accuracy of predicted stress monitoring data.

[0119] Based on the above embodiments, the method may further include: first, acquiring the last k stress monitoring data points from the n actual stress monitoring data points; then, calculating the difference between the last k stress monitoring data points from the n actual stress monitoring data points and the last k predicted stress monitoring data points from the n actual stress monitoring data points; finally, determining whether a prediction anomaly has occurred based on the difference and a preset difference.

[0120] The difference between the last k data points of n actual stress monitoring data and the corresponding last k predicted data points reflects the degree of discrepancy between the predicted and actual data. Based on the calculated difference and a preset difference threshold (i.e., the preset difference value), it can be determined whether a prediction anomaly has occurred. If the difference exceeds the preset difference threshold, the prediction is considered to be abnormal.

[0121] For ease of understanding, an example is given below: Under a test load of 30.8t, stress monitoring data for a certain point on a ship unloader is collected over 40(n+k) days. The first 35(n) days' stress monitoring data are used to optimize the global optimal smoothing coefficient using the Big Cane Mouse algorithm (the optimized target smoothing coefficient). Then, a quadratic exponential smoothing method is used for prediction to obtain the predicted stress monitoring data for the next 5(k) days. The difference between the last k actual stress monitoring data and the last k predicted stress monitoring data is the prediction error. See Table 2 for details.

[0122] Table 2

[0123] Number of periods (days) Measured value Predicted value 1 error Predicted value 2 error 36 47.04 46.34 -0.70 46.94 -0.10 37 46.60 46.48 -0.12 46.77 -0.17 38 47.09 46.68 -0.39 46.32 -0.75 39 46.23 46.51 +0.28 46.38 +0.15 40 46.77 46.62 -0.15 46.63 -0.14

[0124] As can be seen from the table, after multiple predictions using the above method, the prediction error is small, all below the preset difference (e.g., 0.80), indicating that the method has good reliability.

[0125] Furthermore, in the event of prediction anomalies, different weights can be set for different points, as detailed in the following formula:

[0126]

[0127] In the formula, p represents the predicted anomaly level, n is the predefined number of consecutive exceedances of the threshold, and y i For the predicted or actual value, t is a predefined threshold; g is the range that can exceed the threshold under theoretical conditions. If there are multiple thresholds with different standards, g can be the difference between two different standards. If there is only one standard, g can be selected according to the actual situation.

[0128] In summary, this embodiment, by comparing the error with a predefined threshold, can promptly detect stress exceeding the normal range, thereby enhancing early warning capabilities and helping to prevent structural damage or safety accidents caused by abnormal stress. By setting weights for different points, resource allocation can be optimized based on the importance of each point to the overall structure. Points with higher weights can receive more attention and monitoring resources to ensure the safety of the overall structure.

[0129] The above describes a method for predicting stress monitoring data provided by embodiments of this application. The following describes the apparatus for performing the above-described method for predicting stress monitoring data.

[0130] Please see Figure 8 , Figure 8 This is a schematic diagram of a stress monitoring data prediction device provided in an embodiment of this application.

[0131] like Figure 8 As shown, the device for predicting stress monitoring data includes:

[0132] The acquisition unit 11 is used to acquire n stress monitoring actual data and divide the n stress monitoring actual data into the first nm stress monitoring actual data and the last m stress monitoring actual data, where m is the preset number of avoidance time nodes, m≥1 and n>m.

[0133] The first determining unit 12 is used to randomly generate multiple smoothing coefficients based on a preset range, and to use each randomly generated smoothing coefficient as the current smoothing coefficient.

[0134] The first prediction unit 13 is used to perform a quadratic exponential smoothing prediction on the first nm stress monitoring actual data for each of the current smoothing coefficients, based on the current smoothing coefficients, to obtain the subsequent m stress monitoring prediction data.

[0135] The second determining unit 14 is used to determine the target smoothing coefficient based on the predicted data of each of the last m stress monitoring lines and the actual data of the last m stress monitoring lines.

[0136] The third determining unit 15 is used to determine an optimized smoothing coefficient for each of the current smoothing coefficients, based on the current smoothing coefficient, the target smoothing coefficient, and a preset inertia weight.

[0137] Return unit 16 is used to take each of the optimized smoothing coefficients as the current smoothing coefficients and return to execute the step of performing a second exponential smoothing prediction on the first nm stress monitoring actual data based on the current smoothing coefficients to obtain the next m stress monitoring prediction data, until the number of return times reaches the preset number of iterations, and the optimized target smoothing coefficient is obtained.

[0138] The second prediction unit 17 is used to perform a second exponential smoothing prediction on the n actual stress monitoring data based on the optimized target smoothing coefficient, so as to obtain the next k predicted stress monitoring data of the n actual stress monitoring data, where k≥1.

[0139] In one possible implementation, the first prediction unit 13 includes:

[0140] The first determining subunit is used to take the previous nm stress monitoring actual data as the first target stress monitoring actual data for each of the current smoothing coefficients.

[0141] The first prediction subunit is used to perform a second exponential smoothing prediction on the actual data of the first target stress monitoring based on the current smoothing coefficient, so as to obtain the next stress monitoring prediction data of the actual data of the first target stress monitoring.

[0142] The first return subunit is used to take the first target stress monitoring actual data and the next stress monitoring prediction data of the first target stress monitoring actual data as the first target stress monitoring actual data, and return to execute the step of performing a second exponential smoothing prediction on the first target stress monitoring actual data based on the current smoothing coefficient to obtain the next stress monitoring prediction data of the first target stress monitoring actual data, until the number of return times reaches (m-1) times, and the next m stress monitoring prediction data are obtained.

[0143] In one possible implementation, the second determining unit 14 includes:

[0144] The comparison subunit is used to compare the predicted stress monitoring data with the actual stress monitoring data using the Hubey loss function for each of the last m stress monitoring prediction data, and to obtain a set of Hubey losses, wherein the set of Hubey losses includes m Hubey losses.

[0145] The second determining subunit is used to determine the target group Hubey loss from each group of Hubey losses, and to determine the current smoothing coefficient corresponding to the target group Hubey loss as the target smoothing coefficient, wherein the sum of m Hubey losses in the target group Hubey loss is minimized.

[0146] In one possible implementation, the device further includes:

[0147] The information acquisition unit is used to acquire m date information of the m stress monitoring actual data corresponding to the m Hubey losses.

[0148] The allocation unit is used to sort the m date information from morning to evening, and to allocate the m preset loss weights to the m Hubble losses corresponding to the sorted m date information in ascending order.

[0149] The summation unit is used to sum the products of each Hubey loss and the corresponding loss weights of each Hubey loss to obtain the sum of the m Hubey losses.

[0150] In one possible implementation, the second prediction unit 17 includes:

[0151] The third determining subunit is used to take the n stress monitoring actual data as the second target stress monitoring actual data.

[0152] The second prediction subunit is used to perform a second exponential smoothing prediction on the actual data of the second target stress monitoring based on the optimized target smoothing coefficient, so as to obtain the next stress monitoring prediction data of the actual data of the second target stress monitoring.

[0153] The second return subunit is used to take the actual data of the second target stress monitoring and the next stress monitoring prediction data of the actual data of the second target stress monitoring as the actual data of the second target stress monitoring, and return to execute the step of performing a second exponential smoothing prediction on the actual data of the second target stress monitoring based on the optimized target smoothing coefficient to obtain the next stress monitoring prediction data of the actual data of the second target stress monitoring, until the number of return times reaches (k-1) times, and obtains the next k stress monitoring prediction data of the n actual data of stress monitoring.

[0154] In one possible implementation, the device further includes:

[0155] The data acquisition unit is used to acquire the last k stress monitoring data points of the n stress monitoring data points.

[0156] The calculation unit is used to calculate the difference between the last k actual stress monitoring data points of the n actual stress monitoring data points and the last k predicted stress monitoring data points of the n actual stress monitoring data points.

[0157] The fourth determining unit is used to determine whether a prediction anomaly has occurred based on the difference and a preset difference.

[0158] This application also provides an electronic device in its embodiments. (See reference...) Figure 9 The diagram illustrates a structural schematic suitable for implementing the electronic device in the embodiments of this application. The electronic device in the embodiments of this application may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 9 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0159] like Figure 9 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 into a random access memory (RAM) 903. When the electronic device is powered on, the RAM 903 also stores various programs and data required for the operation of the electronic device. The processing unit 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0160] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 908 including, for example, memory cards, hard drives, etc.; and communication devices 909. Communication device 909 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 9 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0161] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the stress monitoring data prediction methods provided in this application.

[0162] This application also provides a computer-readable storage medium carrying one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the stress monitoring data prediction methods provided in this application.

[0163] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0164] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0165] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0166] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. A method for predicting stress monitoring data, characterized in that, include: Obtain n actual stress monitoring data points, and divide the n actual stress monitoring data points into the first n nm actual stress monitoring data points and the last m actual stress monitoring data points, where m is the preset number of avoidance time nodes, m≥1 and n>m; Multiple smoothing coefficients are randomly generated based on a preset range, and each randomly generated smoothing coefficient is used as the current smoothing coefficient. For each of the current smoothing coefficients, a quadratic exponential smoothing prediction is performed on the first nm stress monitoring data based on the current smoothing coefficients to obtain the predicted stress monitoring data for the next m data. Based on the predicted data of each of the m stress monitoring lines and the actual data of the m stress monitoring lines, the target smoothing coefficient is determined. For each of the current smoothing coefficients, an optimized smoothing coefficient is determined based on the current smoothing coefficient, the target smoothing coefficient, and a preset inertia weight. Each optimized smoothing coefficient is used as the current smoothing coefficient. The process of performing a quadratic exponential smoothing prediction on the first nm stress monitoring actual data based on the current smoothing coefficient is repeated until the number of iterations reaches the preset number of iterations, and the optimized target smoothing coefficient is obtained. Based on the optimized target smoothing coefficient, a second exponential smoothing prediction is performed on the n actual stress monitoring data to obtain the next k predicted stress monitoring data, where k≥1.

2. The method for predicting stress monitoring data according to claim 1, characterized in that, For each of the current smoothing coefficients, a quadratic exponential smoothing prediction is performed on the first nm stress monitoring data to obtain the predicted stress monitoring data for the next m data, including: For each of the current smoothing coefficients, the first nm stress monitoring data is used as the first target stress monitoring data. Based on the current smoothing coefficient, a second exponential smoothing prediction is performed on the actual data of the first target stress monitoring to obtain the next stress monitoring prediction data of the actual data of the first target stress monitoring. The first target stress monitoring actual data and the next stress monitoring prediction data of the first target stress monitoring actual data are used as the first target stress monitoring actual data. The process of performing a second exponential smoothing prediction on the first target stress monitoring actual data based on the current smoothing coefficient to obtain the next stress monitoring prediction data of the first target stress monitoring actual data is repeated until the number of return times reaches (m-1) times to obtain the next m stress monitoring prediction data.

3. The method for predicting stress monitoring data according to claim 1, characterized in that, The determination of the target smoothing coefficient based on the predicted data of each of the last m stress monitoring lines and the actual data of the last m stress monitoring lines includes: For each set of m stress monitoring prediction data, the Hubey loss function is used to compare the set of m stress monitoring prediction data with the set of m stress monitoring actual data to obtain a set of Hubey losses, which includes m Hubey losses. The target group Hubey loss is determined from the Hubey losses of each group, and the current smoothing coefficient corresponding to the target group Hubey loss is determined as the target smoothing coefficient. The sum of the m Hubey losses in the target group Hubey loss is minimized.

4. The method for predicting stress monitoring data according to claim 3, characterized in that, The calculation process for the sum of the m Hubey losses includes: Obtain the date information of m stress monitoring data corresponding to the m Hube losses; Sort the m date information from morning to night, and distribute the m preset loss weights to the m Hube losses corresponding to the sorted m date information in ascending order; The sum of the products of each Hubey loss and its corresponding loss weight is obtained by adding them together.

5. The method for predicting stress monitoring data according to claim 1, characterized in that, The step of performing a quadratic exponential smoothing prediction on the n actual stress monitoring data based on the optimized target smoothing coefficient to obtain the subsequent k predicted stress monitoring data for the n actual stress monitoring data includes: The n actual stress monitoring data points are used as the second target actual stress monitoring data points; Based on the optimized target smoothing coefficient, a second exponential smoothing prediction is performed on the actual data of the second target stress monitoring to obtain the last stress monitoring prediction data of the actual data of the second target stress monitoring. The actual data of the second target stress monitoring and the next stress monitoring prediction data of the actual data of the second target stress monitoring are used as the actual data of the second target stress monitoring. The process of performing a second exponential smoothing prediction on the actual data of the second target stress monitoring based on the optimized target smoothing coefficient is repeated until the number of return times reaches (k-1) times, and the next k stress monitoring prediction data of the n actual stress monitoring data are obtained.

6. The method for predicting stress monitoring data according to claim 1, characterized in that, After performing quadratic exponential smoothing prediction on the n actual stress monitoring data based on the optimized target smoothing coefficient to obtain the subsequent k predicted stress monitoring data for the n actual stress monitoring data, the method further includes: Obtain the next k stress monitoring data points from the n stress monitoring data points; Calculate the difference between the last k actual stress monitoring data points of the n actual stress monitoring data points and the last k predicted stress monitoring data points of the n actual stress monitoring data points; Based on the difference and the preset difference, it is determined whether a prediction anomaly has occurred.

7. A method and apparatus for predicting stress monitoring data, characterized in that, include: The acquisition unit is used to acquire n actual stress monitoring data and divide the n actual stress monitoring data into the first nm actual stress monitoring data and the last m actual stress monitoring data, where m is the preset number of avoidance time nodes, m≥1 and n>m; The first determining unit is used to randomly generate multiple smoothing coefficients based on a preset range, and to use each randomly generated smoothing coefficient as the current smoothing coefficient. The first prediction unit is used to perform a quadratic exponential smoothing prediction on the first nm stress monitoring actual data based on the current smoothing coefficient for each of the current smoothing coefficients, so as to obtain the subsequent m stress monitoring prediction data. The second determining unit is used to determine the target smoothing coefficient based on the predicted data of each of the last m stress monitoring lines and the actual data of the last m stress monitoring lines. The third determining unit is used to determine the optimized smoothing coefficient for each of the current smoothing coefficients, based on the current smoothing coefficient, the target smoothing coefficient, and the preset inertia weight. The return unit is used to take each of the optimized smoothing coefficients as the current smoothing coefficients and return to execute the step of performing a quadratic exponential smoothing prediction on the first nm stress monitoring actual data based on the current smoothing coefficients to obtain the next m stress monitoring prediction data, until the number of returns reaches the preset number of iterations and the optimized target smoothing coefficients are obtained. The second prediction unit is used to perform a second exponential smoothing prediction on the n actual stress monitoring data based on the optimized target smoothing coefficient, so as to obtain the next k predicted stress monitoring data of the n actual stress monitoring data, where k≥1.

8. A computer program product, characterized in that, It includes computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the method for predicting stress monitoring data as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program to enable the electronic device to implement the method for predicting stress monitoring data as described in any one of claims 1 to 6.

10. A computer storage medium, characterized in that, The storage medium carries one or more computer programs that, when executed by an electronic device, enable the electronic device to implement the method for predicting stress monitoring data as described in any one of claims 1 to 6.

Images