Constant force spring life prediction method and device, electronic equipment, medium and product

Abstract

The invention discloses a constant force spring life prediction method and device, electronic equipment, a medium and a product. The method comprises the following steps: when it is detected that collected service life associated data corresponding to a to-be-detected spring meets a preset service life prediction condition, determining use scene information corresponding to the to-be-detected spring according to the collected service life associated data; wherein the preset life prediction condition at least comprises the condition that the data volume meets a preset data volume threshold value; and determining the corresponding residual service life of the to-be-tested spring at the current moment according to the collected service life associated data and the use scene information. According to the technical scheme of the embodiment, the effect of accurately predicting the residual service life corresponding to the to-be-tested spring in combination with the service life associated data and the use scene information is achieved, and the spring service life prediction precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a method, device, electronic equipment, medium and product for predicting the life of a constant force spring. Background Art

[0002] With the continuous advancement of medical technology, surgical robots are increasingly used in clinical surgery, and their stability and reliability are crucial to the success of the operation. As one of the core components of the lifting joint of the surgical robot, the constant force spring plays a key role in it with its stable output force and good resilience. However, with the increase of usage time, the performance of the constant force spring will gradually decline, resulting in instability of joint movement, which in turn affects the stability and safety of preoperative positioning. Therefore, accurate prediction of the life of the constant force spring is of great significance to improving the safety and reliability of the surgical robot.

[0003] In the related art, the life prediction of the constant force spring in the lifting joint of the surgical robot mainly relies on empirical formulas and offline calibration. However, when the life prediction is based on empirical formulas, the empirical formulas are often based on idealized conditions and are difficult to accurately reflect the complex situations in actual use, resulting in a large deviation between the predicted results and the actual life, and the prediction accuracy is low. When the life prediction is based on offline calibration, it is impossible to dynamically monitor and predict the life of the constant force spring during use. Summary of the invention

[0004] The present invention provides a constant force spring life prediction method, device, electronic device, medium and product, so as to achieve the effect of accurately predicting the remaining service life corresponding to the spring to be tested by combining life-related data and usage scenario information, thereby improving the accuracy of spring life prediction.

[0005] According to one aspect of the present invention, a method for predicting the life of a constant force spring is provided, the method comprising:

[0006] When it is detected that the collected life-related data corresponding to the spring to be tested meets the preset life prediction condition, the use scenario information corresponding to the spring to be tested is determined according to the collected life-related data; wherein the preset life prediction condition at least includes that the data volume meets the preset data volume threshold; the life-related data includes at least one parameter associated with the service life of the spring to be tested;

[0007] The remaining service life of the spring to be tested is determined based on the collected life-related data and the usage scenario information.

[0008] According to another aspect of the present invention, a constant force spring life prediction device is provided, the device comprising:

[0009] A usage scenario determination module is used to determine usage scenario information corresponding to the spring to be tested according to the collected life-related data when it is detected that the collected life-related data corresponding to the spring to be tested meets a preset life prediction condition; wherein the preset life prediction condition includes that the data volume meets a preset data volume threshold; and the life-related data includes at least one parameter associated with the service life of the spring to be tested;

[0010] The remaining service life determination module is used to determine the remaining service life corresponding to the spring to be tested based on the collected life-related data and the usage scenario information.

[0011] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the constant force spring life prediction method described in any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the constant force spring life prediction method described in any embodiment of the present invention when executed.

[0016] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program, and the computer program, when executed by a processor, implements the constant force spring life prediction method described in any embodiment of the present invention.

[0017] The technical solution of this embodiment determines the usage scenario information corresponding to the spring to be tested according to the collected life-related data when it is detected that the collected life-related data corresponding to the spring to be tested meets the preset life prediction conditions; further, determines the remaining service life corresponding to the spring to be tested according to the collected life-related data and the usage scenario information, thereby solving the problem that the constant force spring life prediction method of the related art is difficult to accurately reflect the complex situation in actual use, resulting in low prediction accuracy and inability to dynamically detect and predict the life of the constant force spring during use, and achieves the effect of accurately predicting the remaining service life corresponding to the spring to be tested by combining the life-related data and the usage scenario information, thereby improving the spring life prediction accuracy, and achieving the effect of dynamically detecting and predicting the remaining service life of the spring during the use of the spring, thereby helping to promptly discover potential problems of the spring and take measures to avoid failures.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 is a flow chart of a constant force spring life prediction method provided according to the first embodiment of the present invention;

[0021] Figure 2 is a flow chart of a constant force spring life prediction method provided according to the second embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of a training process of a usage scene recognition model provided according to Embodiment 3 of the present invention;

[0023] Figure 4 is a schematic diagram of a constant force spring life prediction process provided according to Embodiment 3 of the present invention;

[0024] Figure 5 is a structural schematic diagram of a constant force spring life prediction device provided according to a fourth embodiment of the present invention;

[0025] Figure 6 It is a structural schematic diagram of an electronic device for implementing the constant force spring life prediction method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1 This is a flow chart of a method for predicting the life of a constant force spring provided in the first embodiment of the present invention. This embodiment is applicable to the case of predicting the remaining service life of a spring. The method can be executed by a constant force spring life prediction device. The constant force spring life prediction device can be implemented in the form of hardware and / or software. The constant force spring life prediction device can be configured in a terminal and / or a server. Figure 1 As shown, the method includes:

[0030] S110. When it is detected that the collected life-related data corresponding to the spring to be tested meets a preset life prediction condition, the use scenario information corresponding to the spring to be tested is determined according to the collected life-related data.

[0031] Among them, the spring to be tested can be a spring to be tested for life. The spring to be tested can be any spring, and optionally, it is a constant force spring set in the lifting joint of the surgical robot. The life-related data can be understood as data that affects the service life of the spring to be tested. The life-related data includes at least one parameter associated with the service life of the spring to be tested. Optionally, the life-related data includes the joint position of the lifting joint where the spring to be tested is located, the joint lifting speed, the joint lifting acceleration, the temperature of the spring to be tested, and the spring tension data of the spring to be tested. In this embodiment, the life-related data can be used to characterize the use of the spring to be tested within a preset time period. The preset life prediction condition can be a pre-set condition for triggering the prediction of the remaining service life of the spring. The preset life prediction condition at least includes that the data volume meets the preset data volume threshold. The preset data volume threshold can be any value, and optionally, it is 500, 1000 or 1500. It should be noted that the preset condition can also include that the data collection time reaches the preset time. Among them, the usage scenario information can be used to indicate the usage scenario of the spring to be tested at the current moment. In this embodiment, the usage scenario information may include at least one of factory calibration test, preoperative automatic deployment and preoperative positioning docking. It is understandable that for the spring to be tested set in the lifting joint, during the factory calibration stage, the lifting joint needs to be stretched frequently, which will be associated with high-intensity use; the preoperative automatic deployment function is driven by the motor module to move the lifting joint at a constant speed for a short distance; the preoperative positioning docking is manually dragging the lifting joint directly to the specified position.

[0032] In this embodiment, during the use of the spring to be tested, in order to detect the remaining service life of the spring to be tested during the use of the spring to be tested, data detection can be performed on at least one parameter associated with the service life of the spring to be tested, and data collection can be performed according to a preset sampling frequency. Then, the collected life-related data corresponding to the spring to be tested can be obtained. Furthermore, when it is detected that the collected life-related data corresponding to the spring to be tested meets the preset life prediction condition, the use scenario information corresponding to the spring to be tested can be determined according to the collected life-related data.

[0033] In practical applications, when predicting the remaining service life of the spring to be tested, it is usually predicted based on the life-related data of the spring to be tested before the current moment. However, the spring to be tested can be used in a variety of different usage scenarios, and there are large differences in the life consumption of the spring to be tested in different usage scenarios. The life-related data only includes the usage of the spring to be tested before the current moment. If the remaining service life is predicted based on the life-related data, the remaining service life prediction may be less accurate.

[0034] In view of the above situation, in this embodiment, the usage scenario information corresponding to the spring to be tested can be determined, and then the remaining service life corresponding to the spring to be tested can be predicted based on the life-related data and the usage scenario information. The life-related data is data that characterizes the usage of the spring to be tested. Therefore, in order to determine the usage scenario information corresponding to the spring to be tested, it can be determined based on the collected life-related data.

[0035] As an optional implementation of this embodiment, during the use of the spring to be tested, the joint position, joint lifting speed, temperature of the spring to be tested and the tension data of the spring to be tested can be detected by the encoder and / or sensor set on the lifting joint where the spring to be tested is located, and the joint position, joint lifting speed, temperature of the spring to be tested and the spring tension data of the lifting joint corresponding to the spring to be tested are obtained, and the acquired data are stored. In addition, the joint lifting acceleration can be determined based on the acquired joint position and joint lifting speed, and the determined joint lifting acceleration is stored. Furthermore, the life-related data corresponding to the collected spring to be tested can be obtained.

[0036] In this embodiment, the usage scenario information corresponding to the spring to be tested can be determined according to the collected life-related data by a preset scenario determination method. The scenario determination method can be any method that can determine the usage scenario information of the spring to be tested. Optionally, the usage scenario information of the spring to be tested can be determined according to a usage scenario recognition model; or, the usage scenario information of the spring to be tested can be determined according to a feature matching method, etc.

[0037] Optionally, determining usage scenario information corresponding to the spring to be tested based on the collected life-related data includes: processing the collected life-related data based on a usage scenario recognition model to obtain the usage scenario information corresponding to the spring to be tested.

[0038] The usage scenario recognition model can be understood as a neural network model that takes the life-related data as an input object to recognize the usage scenario information of the spring to be tested based on the life-related data. The usage scenario recognition model can be a neural network model of any model structure, and optionally, a linear regression model, a decision tree model, or a convolutional neural network model.

[0039] In this embodiment, the scene recognition model is obtained by training the neural network model through the sample association data corresponding to multiple sample springs and the actual scene information. It should be noted that before applying the scene recognition model provided by this embodiment, the pre-constructed neural network model can be trained in a supervised or unsupervised manner. Before training the neural network model, multiple training samples can be constructed to train the model based on the training samples. In order to improve the accuracy of the scene recognition model, as many and rich training samples as possible can be constructed. Optionally, the training process of the scene recognition model can be: obtaining multiple training samples; wherein the training samples include sample association data corresponding to the sample spring and actual scene information; for each training sample, the sample association data in the training sample is input into the pre-constructed neural network model, and the predicted scene information is obtained; based on the predicted scene information and the actual scene information in the training sample, the loss value is determined; based on the loss value, the model parameters in the neural network model are corrected, and the convergence of the loss function in the neural network model is used as the training target, so that the trained neural network model is used as the scene recognition model.

[0040] As an optional implementation of this embodiment, when the collected life-related data corresponding to the spring to be tested meets the preset life prediction conditions, the collected life-related data can be input into the usage scenario recognition model. Furthermore, the life-related data can be processed based on the usage scenario recognition model to determine the usage scenario information corresponding to the spring to be tested based on the life-related data.

[0041] Optionally, the usage scenario information corresponding to the spring to be tested is determined based on the collected life-related data, including: performing feature extraction on the collected life-related data to obtain scene-related features; and determining the usage scenario information corresponding to the spring to be tested based on at least one candidate scene information and the scene-related features.

[0042] Among them, the scene-related features can be understood as features associated with the spring usage scene. Optionally, the scene-related features may include load features, usage frequency features, temperature features or environmental features, etc. The candidate scene information may be predetermined usage scene information to be selected. At least one candidate scene information may include factory calibration test, preoperative automatic deployment and preoperative positioning docking, etc.

[0043] As another optional implementation of this embodiment, when the collected life-related data meets the preset life prediction conditions, feature extraction can be performed on the collected life-related data to extract feature information associated with the usage scenario in the life-related data. Then, the extracted feature information can be used as a scene-related feature. Furthermore, feature matching can be performed between at least one candidate scene information and the scene-related feature. Then, the usage scenario information corresponding to the spring to be tested can be determined from the at least one candidate scene information according to the matching result.

[0044] Optionally, based on at least one candidate scene information and scene-related features, determining usage scenario information corresponding to the spring to be tested includes: for at least one candidate scene information, obtaining feature information of the candidate scene information, and when the feature information matches the scene-related features, using the candidate scene information as the usage scenario information corresponding to the spring to be tested.

[0045] The feature information may be features in the candidate scenario information that are associated with the usage scenario.

[0046] As an optional implementation of this embodiment, for at least one candidate scene information, feature information corresponding to the candidate scene information can be obtained. Further, the feature information can be feature matched with the scene-related feature. Furthermore, when the feature information matches the scene-related feature, the candidate scene information corresponding to the feature information can be used as the usage scene information corresponding to the spring to be tested.

[0047] It should be noted that, during the use of the spring to be tested, the device for collecting life-related data continuously collects data from the spring to be tested according to a preset sampling frequency. When the collected life-related data corresponding to the spring to be tested meets the preset life prediction condition, the collected life-related data can be re-tested starting from the currently collected life-related data. Furthermore, when it is detected that the collected life-related data again meets the preset life prediction condition, the use scenario information determination and the following life prediction steps can be repeatedly executed.

[0048] S130, determining the remaining service life of the spring to be tested according to the collected life-related data and usage scenario information.

[0049] The remaining service life can be understood as the time period from the current state of the spring to its failure or need to be replaced. Optionally, the remaining service life can be expressed based on the remaining number of uses of the spring to be tested; or, it can also be expressed based on the remaining elongation of the spring to be tested. In this embodiment, in order to enable relevant staff to more clearly understand the remaining service life corresponding to the spring to be tested, so as to process the spring to be tested based on the remaining service life, the remaining service life can be expressed based on the remaining elongation of the spring to be tested.

[0050] In this embodiment, after obtaining the life-related data and usage scenario information corresponding to the spring to be tested, the life-related data and usage scenario information can be processed according to a preset life prediction method to obtain the remaining service life corresponding to the spring to be tested. The preset life prediction method can be any method that can predict the remaining service life of the spring to be tested. Optionally, the remaining service life of the spring to be tested can be predicted according to a life prediction model; or, the remaining service life of the spring to be tested can be predicted by statistical analysis and trend prediction, etc.

[0051] As an optional implementation of this embodiment, after obtaining the life-related data and usage scenario information corresponding to the spring to be tested, the obtained life-related data and usage scenario information can be input into the life prediction model. Then, the life-related data and usage scenario information are processed based on the life prediction model to predict the remaining service life corresponding to the spring to be tested.

[0052] As another optional implementation of this embodiment, after obtaining the life-related data and usage scenario information corresponding to the spring to be tested, statistical analysis and trend prediction can be performed on the obtained life-related data and usage scenario information. Furthermore, the remaining service life corresponding to the spring to be tested can be determined based on the statistical analysis and trend prediction results.

[0053] In this embodiment, when the remaining service life corresponding to the spring to be tested is obtained, the processing method corresponding to the spring to be tested can be determined according to the remaining service life and a preset service life threshold, so that the spring to be tested can be processed based on the processing method.

[0054] As an optional implementation of this embodiment, when the remaining service life corresponding to the spring to be tested is obtained, the remaining service life can be compared with a preset service life threshold. Further, when the remaining service life is greater than the preset service life threshold, the treatment method of the spring to be tested can be determined as no treatment or spring maintenance. When the remaining service life is not greater than the preset usage threshold, the treatment method of the spring to be tested can be determined as spring replacement. Among them, the preset service life threshold can be the maximum elongation that the spring to be tested can withstand.

[0055] The technical solution of this embodiment determines the usage scenario information corresponding to the spring to be tested according to the collected life-related data when it is detected that the collected life-related data corresponding to the spring to be tested meets the preset life prediction conditions; further, determines the remaining service life corresponding to the spring to be tested according to the collected life-related data and the usage scenario information, thereby solving the problem that the constant force spring life prediction method of the related art is difficult to accurately reflect the complex situation in actual use, resulting in low prediction accuracy and inability to dynamically detect and predict the life of the constant force spring during use, and achieves the effect of accurately predicting the remaining service life corresponding to the spring to be tested by combining the life-related data and the usage scenario information, thereby improving the spring life prediction accuracy, and achieving the effect of dynamically detecting and predicting the remaining service life of the spring during the use of the spring, thereby helping to promptly discover potential problems of the spring and take measures to avoid failures.

[0056] Embodiment 2

[0057] Figure 2 It is a flow chart of a constant force spring life prediction method provided in the second embodiment of the present invention. On the basis of the above-mentioned embodiment, the remaining service life of the spring to be tested at the current moment is determined according to the life-related data and the usage scenario information, including: inputting the life-related data and the usage scenario information into the life prediction model to obtain the remaining service life of the spring to be tested at the current moment. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same as or corresponding to the above-mentioned embodiments are not repeated here.

[0058] like Figure 2 As shown, the method includes:

[0059] S210: When it is detected that the collected life-related data corresponding to the spring to be tested meets a preset life prediction condition, the use scenario information corresponding to the spring to be tested is determined according to the collected life-related data.

[0060] S220, inputting the collected life-related data and usage scenario information into a life prediction model to obtain the remaining service life corresponding to the spring to be tested.

[0061] Among them, the life prediction model can be understood as a neural network model that takes life-related data and usage scenario information as input objects to predict the remaining service life of the spring to be tested based on the life-related data and usage scenario information. The life prediction model can be a deep learning model that can be used to predict the remaining service life of the spring, such as a recurrent neural network. Optionally, the life prediction model can be a long short-term memory network (Long Short-Term Memory, LSTM), a gated recurrent unit (Gated Recurrent Unit, GRU), a bidirectional recurrent neural network (Bidirectional Recurrent Neural Network, Bi-RNN) or a deep recurrent neural network (Deep Recurrent Neural Network, DRNN), etc. It should be noted that the advantage of using a recurrent neural network for life prediction is that the time series processing capability of the recurrent neural network can accurately capture the degradation trend of the spring to be tested and improve the accuracy of life prediction.

[0062] In this embodiment, the life prediction model is obtained by training a deep learning model with sample association data, sample usage scenario information, and actual remaining service life corresponding to sample springs in multiple historical time intervals. The prediction moment may be the moment at which the remaining service life prediction is to be performed. Optionally, the prediction moment corresponding to the historical time interval may be the last moment in the historical time interval; or, it may be any moment after the historical time interval, etc.

[0063] It should be noted that before applying the life prediction model provided in this embodiment, the pre-constructed deep learning model can be trained in a supervised or unsupervised manner. Before training the deep learning model, multiple training samples can be constructed to train the model based on the training samples. In order to improve the accuracy of the life prediction model, training samples can be constructed as many and rich as possible. Optionally, the training process of the life prediction model can be: obtaining multiple training samples, wherein the training samples include sample association data and sample usage scenario information corresponding to the sample spring in multiple historical time intervals and the real remaining service life at the prediction moment corresponding to each historical time interval; for each training sample, the sample association data and sample usage scenario information corresponding to the current historical time interval in the training sample are input into the pre-constructed deep learning model to obtain the predicted remaining service life corresponding to the sample spring at the prediction moment; according to the predicted remaining service life and the real remaining service life at the prediction moment corresponding to the current historical time interval in the training sample, the loss value is determined; based on the loss value, the model parameters in the deep learning model are corrected, and the convergence of the loss function in the deep learning model is used as the training target, so that the trained deep learning model is used as the life prediction model.

[0064] Among them, the historical time interval can be a time interval in the life cycle of the sample spring. The historical time interval can be a time interval of any length, and optionally, it is a time interval of the same length as the preset time period. The sample-related data can be a parameter value corresponding to at least one life-related parameter associated with the service life in the historical time interval. The sample usage information can be the usage scenario information of the sample spring in the historical time interval. The real remaining service life can be the actual remaining service life corresponding to the sample spring at the corresponding prediction moment. In this embodiment, the real remaining service life can be determined by the spring elongation corresponding to the sample spring at each moment. Optionally, the real remaining service life can be determined by the following steps: for multiple sample springs, obtain the life cycle data corresponding to the sample spring, wherein the life cycle data includes the spring elongation corresponding to multiple moments; the multiple moments include the moment between the time when the spring starts to be used and the time when the spring ends to be used; for multiple moments, according to the spring elongation corresponding to the moment, the spring elongation corresponding to the time when the spring ends to be used, and the preset elongation, determine the real remaining service life corresponding to the sample spring at the moment.

[0065] Among them, life cycle data can be understood as data characterizing the use of the sample spring from the beginning of use to the end of use. The life cycle data may include the spring elongation corresponding to multiple moments. The multiple moments include the moments from the time the spring starts to be used to the time the spring ends to be used. The spring elongation refers to the difference between the length of the spring after stretching and the initial length of the spring. The spring elongation can characterize the degree of deformation of the spring under external force. The preset elongation can be a predetermined spring elongation. The preset elongation can be an arbitrary value.

[0066] As an optional implementation of this embodiment, for multiple sample springs, life cycle data corresponding to the sample springs can be obtained from the database, and the life cycle data can include spring elongations corresponding to multiple moments, and the multiple moments include the moments from the time when the spring starts to be used to the time when the spring ends. Further, for multiple moments, the spring elongations corresponding to all moments from the moment until the spring ends can be obtained, and the obtained spring elongations can be summed to obtain the total spring elongation corresponding to the moment. Further, the ratio between the total spring elongation and the preset elongation can be determined, and the ratio can be used as the actual remaining service life of the sample spring corresponding to the moment.

[0067] Exemplarily, the actual remaining service life of the sample spring at any time can be determined by the following formula:

[0068]

[0069] Among them, life t Represents the actual remaining service life of the sample spring at time t; T represents the time when the spring ends its use; Δd t represents the spring elongation; d represents the preset elongation.

[0070] In this embodiment, when the actual remaining service life corresponding to the sample spring at each moment is obtained, the sample association data and sample usage scenario information corresponding to the sample spring in each historical time interval can be obtained, and a training sample corresponding to the sample spring can be constructed based on the sample association data, sample usage scenario information and the actual remaining service life.

[0071] As an optional implementation of this embodiment, for multiple training samples, the sample association data and sample usage scenario information corresponding to the current historical time interval in the training sample can be input into a pre-built deep learning model. Then, the sample association data and sample usage scenario information can be processed based on the deep learning model, and the predicted remaining service life of the sample spring at the predicted moment corresponding to the current historical time interval can be output. Further, the predicted remaining service life can be compared with the actual remaining service life at the predicted moment corresponding to the current historical time interval in the training sample to determine the loss value. Then, the model parameters in the deep learning model can be corrected according to the loss value. Afterwards, the training error of the loss function in the deep learning model, that is, the loss parameter, can be used as a condition for detecting whether the current loss function has reached convergence, for example, the training error is less than the preset error or the error change trend tends to be stable, or whether the current model iteration number is equal to the preset number of times, etc. If the detection reaches the convergence condition, for example, the training error of the loss function is less than the preset error or the error change tends to be stable, it indicates that the deep learning model training is completed. At this time, the iterative training can be stopped, and the trained deep learning model can be used as a life prediction model. If it is detected that the convergence condition is not met at present, other training samples can be further obtained to train the deep learning model until the training error of the loss function is within the preset range. When the training error of the loss function reaches convergence, a trained life prediction model can be obtained.

[0072] The technical solution of this embodiment is to determine the usage scenario information corresponding to the spring to be tested based on the collected life-related data when it is detected that the collected life-related data corresponding to the spring to be tested meets the preset life prediction conditions; further, the collected life-related data and the usage scenario information are input into the life prediction model to obtain the remaining service life corresponding to the spring to be tested, thereby achieving the effect of accurately predicting the remaining service life corresponding to the spring to be tested at the corresponding moment based on the life-related data and the usage scenario information through the life prediction model, and further, the degradation trend of the spring can be accurately captured through the life prediction model, thereby improving the accuracy of the spring life prediction.

[0073] Embodiment 3

[0074] Figure 3 It is a schematic diagram of a training process of a scene recognition model provided according to Embodiment 3 of the present invention. Figure 4 Schematic diagram of a constant force spring life prediction process according to Embodiment 3 of the present invention. This embodiment is an optional embodiment of the above-mentioned embodiments of the invention. Figure 3 and Figure 4 As shown, the method of the embodiment of the present invention may specifically include:

[0075] like Figure 3 As shown, first, the offline historical data corresponding to the sample spring is obtained. Then, the offline historical data is preprocessed to obtain the sample associated data corresponding to the sample spring. Then, the sample associated data is classified and labeled by usage scenario to obtain the actual usage scenario information corresponding to the sample spring. Furthermore, a training sample can be constructed according to the sample associated data corresponding to the sample spring and the actual usage scenario information to obtain a scene recognition model based on the training sample training.

[0076] like Figure 4 As shown, during the use of the spring to be tested, the life-related data corresponding to the spring to be tested is collected, and when it is detected that the amount of collected life-related data reaches a preset data volume threshold, the collected life-related data is processed according to the scene recognition model to obtain the usage scenario information corresponding to the spring to be tested. Furthermore, the life-related data and the usage scenario information can be input into the life prediction model. Furthermore, based on the feature fusion layer, long short-term memory network layer, fully connected layer, and output layer in the life prediction model, the life-related data and the usage scenario information can be processed in sequence to obtain the remaining service life corresponding to the spring to be tested.

[0077] The technical solution of this embodiment achieves the effect of accurately predicting the remaining service life of the spring to be tested at a corresponding moment based on the life-related data and usage scenario information through the life prediction model. Furthermore, the life prediction model can accurately capture the degradation trend of the spring, thereby improving the accuracy of the spring life prediction.

[0078] Embodiment 4

[0079] Figure 5 Schematic diagram of a constant force spring life prediction device provided by the fourth embodiment of the present invention. Figure 5 As shown, the device includes: a usage scenario determination module 310 and a remaining service life determination module 320.

[0080] Among them, the usage scenario determination module 310, when it is detected that the collected life-related data corresponding to the spring to be tested meets the preset life prediction conditions, determines the usage scenario information corresponding to the spring to be tested according to the collected life-related data; wherein the preset life prediction conditions at least include that the data volume meets the preset data volume threshold; the life-related data includes at least one parameter associated with the service life of the spring to be tested; the remaining service life determination module 320 is used to determine the remaining service life corresponding to the spring to be tested according to the collected life-related data and the usage scenario information.

[0081] The technical solution of this embodiment determines the usage scenario information corresponding to the spring to be tested according to the collected life-related data when it is detected that the collected life-related data corresponding to the spring to be tested meets the preset life prediction conditions; further, determines the remaining service life corresponding to the spring to be tested according to the collected life-related data and the usage scenario information, thereby solving the problem that the constant force spring life prediction method of the related art is difficult to accurately reflect the complex situation in actual use, resulting in low prediction accuracy and inability to dynamically detect and predict the life of the constant force spring during use, and achieves the effect of accurately predicting the remaining service life of the spring to be tested at the corresponding moment by combining the life-related data and the usage scenario information, thereby improving the spring life prediction accuracy, and achieving the effect of dynamically detecting and predicting the remaining service life of the spring during the use of the spring, thereby helping to promptly discover potential problems of the spring and take measures to avoid failures.

[0082] Optionally, a usage scenario determination module 310 is specifically used to process the collected life-related data according to a usage scenario recognition model to obtain usage scenario information corresponding to the spring to be tested; wherein the usage scenario recognition model is obtained by training a neural network model with sample association data corresponding to multiple sample springs and actual usage scenario information.

[0083] Optionally, the usage scenario determination module 310 includes: a feature extraction unit and a usage scenario information determination unit.

[0084] A feature extraction unit, used for extracting features from the collected lifespan-related data to obtain scene-related features;

[0085] The usage scenario information determination unit is used to determine the usage scenario information corresponding to the spring to be tested based on at least one candidate scenario information and the scenario-related features.

[0086] Optionally, a usage scenario information determination unit is specifically used to obtain feature information of at least one candidate scenario information, and when the feature information matches the scene-associated feature, use the candidate scenario information as usage scenario information corresponding to the spring to be tested.

[0087] Optionally, the remaining service life determination module 320 is specifically used to input the collected life-related data and the usage scenario information into the life prediction model to obtain the remaining service life corresponding to the spring to be tested; wherein the life prediction model is obtained by training a deep learning model through sample-related data, sample usage scenario information and actual remaining service life corresponding to sample springs in multiple historical time intervals.

[0088] Optionally, the device further includes: a training sample acquisition module, a predicted remaining useful life determination module, a loss value determination module and a model parameter adjustment module.

[0089] A training sample acquisition module, used to acquire multiple training samples, wherein the training samples include sample association data and sample usage scenario information corresponding to a plurality of historical time intervals of the sample spring and the actual remaining service life at the prediction moment corresponding to each of the historical time intervals;

[0090] A predicted remaining service life determination module is used to input the sample association data and sample usage scenario information corresponding to the current historical time interval in the training sample into a pre-built deep learning model for each training sample, so as to obtain the predicted remaining service life corresponding to the sample spring at the prediction moment;

[0091] a loss value determination module, configured to determine a loss value according to the predicted remaining useful life and the actual remaining useful life at the predicted moment corresponding to the current historical time interval in the training sample;

[0092] A model parameter adjustment module is used to modify the model parameters in the deep learning model based on the loss value, and take the convergence of the loss function in the deep learning model as a training goal, so as to use the trained deep learning model as a life prediction model.

[0093] Optionally, the device further includes: a life cycle data acquisition module and a real remaining useful life determination module.

[0094] A life cycle data acquisition module, for acquiring life cycle data corresponding to a plurality of sample springs, wherein the life cycle data includes spring elongation corresponding to a plurality of moments; the plurality of moments include moments from the time when the spring starts to be used to the time when the spring ends to be used;

[0095] The real remaining service life determination module is used to determine the real remaining service life of the sample spring corresponding to the multiple moments according to the spring elongation corresponding to the moment, the spring elongation corresponding to the moment when the spring ends use and the preset elongation.

[0096] The constant force spring life prediction device provided in the embodiment of the present invention can execute the constant force spring life prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0097] Embodiment 5

[0098] Figure 6 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0099] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0100] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0101] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a constant force spring life prediction method.

[0102] In some embodiments, the constant force spring life prediction method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the constant force spring life prediction method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the constant force spring life prediction method in any other appropriate manner (for example, by means of firmware).

[0103] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0104] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0105] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0106] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0107] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0108] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0109] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0110] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting the life of a constant force spring, characterized in that: include: When it is detected that the collected life-related data corresponding to the spring to be tested meets the preset life prediction condition, the use scenario information corresponding to the spring to be tested is determined according to the collected life-related data; wherein the preset life prediction condition at least includes that the data volume meets the preset data volume threshold; the life-related data includes at least one parameter associated with the service life of the spring to be tested; The remaining service life of the spring to be tested is determined based on the collected life-related data and the usage scenario information.

2. The constant force spring life prediction method according to claim 1, characterized in that: The determining of the usage scenario information corresponding to the spring to be tested according to the collected life-related data includes: Processing the collected life-related data according to the usage scenario recognition model to obtain usage scenario information corresponding to the spring to be tested; The usage scenario recognition model is obtained by training a neural network model using sample association data corresponding to multiple sample springs and actual usage scenario information.

3. The constant force spring life prediction method according to claim 1, characterized in that: The determining of the usage scenario information corresponding to the spring to be tested according to the collected life-related data includes: Extracting features from the collected lifespan-related data to obtain scene-related features; Based on at least one candidate scene information and the scene-related features, the usage scene information corresponding to the spring to be tested is determined.

4. The constant force spring life prediction method according to claim 3, characterized in that: The determining, based on at least one candidate scene information and the scene-related feature, the usage scene information corresponding to the spring to be tested includes: For at least one candidate scene information, characteristic information of the candidate scene information is obtained, and when the characteristic information matches the scene-related characteristic, the candidate scene information is used as the usage scene information corresponding to the spring to be tested.

5. The constant force spring life prediction method according to claim 1, characterized in that: The determining the remaining service life of the spring to be tested according to the collected life-related data and the usage scenario information includes: Inputting the collected life-related data and the usage scenario information into a life prediction model to obtain the remaining service life corresponding to the spring to be tested; The life prediction model is obtained by training a deep learning model based on sample association data corresponding to the sample spring, sample usage scenario information, and actual remaining service life.

6. The constant force spring life prediction method according to claim 5, characterized in that: Also includes: Acquire multiple training samples, wherein the training samples include sample association data and sample usage scenario information corresponding to the sample spring in multiple historical time intervals and the actual remaining service life at the prediction moment corresponding to each of the historical time intervals; For each of the training samples, the sample association data and sample usage scenario information corresponding to the current historical time interval in the training sample are input into a pre-built deep learning model to obtain the predicted remaining service life of the sample spring at the prediction time; Determine a loss value according to the predicted remaining useful life and the actual remaining useful life at the predicted moment corresponding to the current historical time interval in the training sample; The model parameters in the deep learning model are modified based on the loss value, and the convergence of the loss function in the deep learning model is used as a training target, so that the trained deep learning model can be used as a life prediction model.

7. The method for predicting the life of a constant force spring according to claim 6, characterized in that: Also includes: For a plurality of sample springs, life cycle data corresponding to the sample springs are obtained, wherein the life cycle data includes spring elongation corresponding to a plurality of moments; the plurality of moments include moments from the time when the spring starts to be used to the time when the spring ends to be used; For the plurality of moments, the actual remaining service life of the sample spring corresponding to the moment is determined based on the spring elongation corresponding to the moment, the spring elongation corresponding to the moment when the spring ends use, and the preset elongation.

8. A constant force spring life prediction device, characterized in that: include: A usage scenario determination module is used to determine usage scenario information corresponding to the spring to be tested according to the collected life-related data when it is detected that the collected life-related data corresponding to the spring to be tested meets a preset life prediction condition; wherein the preset life prediction condition at least includes that the data volume meets a preset data volume threshold; and the life-related data includes at least one parameter associated with the service life of the spring to be tested; The remaining service life determination module is used to determine the remaining service life corresponding to the spring to be tested based on the collected life-related data and the usage scenario information.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the constant force spring life prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the constant force spring life prediction method described in any one of claims 1-7 when executed.

11. A computer program product, characterized in that The computer program product comprises a computer program which, when executed by a processor, implements the constant force spring life prediction method according to claims 1-7.

Images