Lightweight adaptive prediction method for remaining service life of industrial equipment, electronic device and storage medium

Abstract

The embodiment of the present application provides a lightweight adaptive prediction method, electronic device and storage medium for the remaining service life of industrial equipment. The method includes: obtaining continuous operation data generated by equipment components of industrial equipment during operation, and generating an operation time series corresponding to the equipment components based on the continuous operation data; performing resolution reduction processing on the operation time series to obtain a target sequence corresponding to the operation time series; identifying the corresponding resolution level of the target sequence, and determining a target life prediction model corresponding to the target sequence based on the resolution level; wherein the resolution level is used to indicate the complexity of the operation time series; sending the target sequence to the target life prediction model to obtain a life prediction result of the equipment components of the industrial equipment. The method is used to achieve the effect of accurately predicting the life of equipment components of industrial equipment and reducing computing costs.

Description

Technical Field

[0001] The present application relates to the field of data prediction, and in particular to a lightweight adaptive prediction method, electronic device, and storage medium for the remaining useful life of industrial equipment. Background Art

[0002] In industrial scenarios, because industrial processes are often dynamic, using a unified model structure to process all samples when analyzing industrial time series can lead to insufficient model representation capabilities and reduced accuracy. Furthermore, industrial time series data is typically long and high-dimensional. Using complex neural networks to process this data consumes significant computing resources, resulting in high computational costs.

[0003] Furthermore, there is an urgent need for a technical solution that can accurately predict the life of equipment components based on the complexity of the time series and reduce computing costs. Summary of the Invention

[0004] Embodiments of the present application provide a lightweight adaptive prediction method, device, electronic device, storage medium, and program product for the remaining useful life of industrial equipment, so as to accurately predict the life of equipment components based on the complexity of the time series and reduce computing costs.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting the life of an equipment component of industrial equipment, comprising: obtaining continuous operating data generated by the equipment component of the industrial equipment during operation, and generating an operating time series corresponding to the equipment component based on the continuous operating data; performing resolution reduction processing on the operating time series to obtain a target sequence corresponding to the operating time series; identifying the corresponding resolution level of the target sequence, and determining a target life prediction model corresponding to the target sequence based on the resolution level; wherein the resolution level is used to indicate the complexity of the operating time series; and sending the target sequence to the target life prediction model to obtain a life prediction result of the equipment component of the industrial equipment.

[0006] In one possible implementation, the running time series is processed by a first algorithm to obtain a first time series; wherein the first algorithm is used to reduce the resolution corresponding to the running time series to a first resolution level; and the first time series is determined as a target sequence.

[0007] In one possible implementation, the running time series is smoothed through a first sliding window to obtain a smoothed sequence corresponding to the running time series, wherein the smoothed sequence is used to characterize the overall trend of the running time series; the running time series is peak processed through a second sliding window to obtain a peak sequence corresponding to the running time series, wherein the peak sequence is used to characterize the peak trend of the running time series; the running time series is feature extracted through a third sliding window to obtain a frequency feature sequence corresponding to the running time series, wherein the frequency feature sequence is used to characterize the frequency trend of the time series; a first time series is generated based on the smoothed sequence, the peak sequence, and the frequency feature sequence; wherein the window sizes of the first sliding window, the second sliding window, and the third sliding window are the same or different.

[0008] In a possible implementation, the first sliding window is moved along the running time sequence until the first sliding window traverses the running time sequence; the mean of the running time sequence located within the first sliding window each time the first sliding window slides is calculated; the smoothed sequence is generated based on the mean of the running time series obtained each time; the second sliding window is moved along the running time sequence until the second sliding window traverses the running time sequence; the maximum value of the running time series located within the second sliding window each time the second sliding window slides is calculated; the peak sequence is generated based on the maximum value of the running time series obtained each time; the third sliding window is moved along the running time sequence until the third sliding window traverses the running time sequence; the frequency characteristics of the running time series located within the third sliding window each time the third sliding window slides are calculated; and the frequency characteristic sequence is generated based on the frequency characteristics of the running time series obtained each time.

[0009] In one possible embodiment, the target sequence is sent to a life prediction model corresponding to the preset resolution level for processing to obtain a preprocessing result; when the predicted value carried in the preprocessing result falls within a preset confidence interval, the preprocessing result is determined as the life prediction result of the industrial equipment; if the predicted value carried in the preprocessing result does not fall within the preset confidence interval, the running time series is processed by a second algorithm to obtain a second time series; wherein, the second algorithm is used to reduce the resolution corresponding to the running time series to a second resolution level; the second resolution level is greater than the first resolution level; the second time series is determined as the target sequence and sent to a downstream prediction model for processing; wherein, the resolution level corresponding to the downstream prediction model is greater than the resolution level currently corresponding to the target time series.

[0010] In a possible implementation, the target sequence is sent to each layer of the sub-network of the life prediction model for transfer processing to obtain a transfer prediction result; and the transfer prediction result is determined as the life prediction result.

[0011] In one possible implementation, the target sequence is sent to a first-layer sub-network for processing to obtain a first prediction result; a downstream sub-network of the first-layer sub-network is allowed to perform prediction processing based on the first prediction result to obtain a second prediction result; until the last-layer sub-network of the prediction model outputs a final prediction result, the final prediction result is determined as the transferred prediction result.

[0012] In one possible implementation, the processing result of the i+1th layer subnetwork and the processing result of the i-th layer subnetwork are sent to the classifier corresponding to the i+1th layer subnetwork to obtain a feedback result of the classifier; wherein 1<i+1≤total number of layers of the prediction model subnetwork, and the feedback result is used to indicate the degree of error; the feedback result is multiplied by the weight value of the i+1th layer subnetwork to obtain a first adjustment value, and the i+1th layer subnetwork is adjusted according to the first adjustment value.

[0013] In one possible implementation, the gradient value between each layer of sub-networks is determined, and the gradient value between each layer of sub-networks is multiplied by a gradient alignment factor.

[0014] In the second aspect, an embodiment of the present application provides a lightweight adaptive prediction device for the remaining service life of industrial equipment, including: an acquisition module for acquiring continuous operation data generated by equipment components of industrial equipment during operation, and generating an operation time series corresponding to the equipment components based on the continuous operation data; a resolution module for performing resolution reduction processing on the operation time series to obtain a target sequence corresponding to the operation time series; an identification module for identifying the corresponding resolution level of the target sequence, and determining a target life prediction model corresponding to the target sequence based on the resolution level; wherein the resolution level is used to indicate the complexity of the operation time series; a sending module for sending the target sequence to the target life prediction model to obtain a life prediction result of the industrial equipment.

[0015] In a third aspect, an embodiment of the present application provides a lightweight adaptive prediction device for the remaining useful life of industrial equipment, comprising: a memory, a processor;

[0016] The memory stores computer-executable instructions;

[0017] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementation methods of the first aspect.

[0019] The embodiments of the present application provide a lightweight adaptive prediction method, device, electronic device, storage medium, and program product for the remaining useful life of industrial equipment. By reducing the resolution of the operating time series of the equipment components and then sending the reduced-resolution time series to the life prediction model for prediction, the accuracy of the life prediction is ensured while reducing the computing cost, thereby achieving the effect of accurately predicting the life of the equipment components according to the complexity of the time series and reducing the computing cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0021] Figure 1 Schematic diagram of the process of lightweight adaptive prediction of the remaining useful life of industrial equipment provided in this application Figure 1 ;

[0022] Figure 2 Schematic diagram of the process of lightweight adaptive prediction of the remaining useful life of industrial equipment provided in this application Figure 2 ;

[0023] Figure 3 Schematic diagram of gradient alignment factors for lightweight adaptive prediction of remaining useful life of industrial equipment provided in this application;

[0024] Figure 4 A schematic diagram of the structure of a lightweight adaptive prediction device for the remaining useful life of industrial equipment provided in this application;

[0025] Figure 5 This is a schematic structural diagram of the lightweight adaptive prediction device for the remaining useful life of industrial equipment provided in this application.

[0026] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0028] First, let’s explain the terms involved in this application:

[0029] Time series resolution: The resolution of a time series refers to the minimum time interval between two consecutive observations in continuous time series data. It determines the frequency and granularity of data sampling and is an important indicator of the precision of time series data. When the resolution is low, the time interval between adjacent observations is large, resulting in a higher interval. Conversely, when the resolution is high, the time interval between adjacent observations is small, resulting in a lower interval.

[0030] Time series: refers to a set of data arranged at certain time intervals. These data can be continuous or discrete.

[0031] Figure 1 Schematic diagram of the process of lightweight adaptive prediction of the remaining useful life of industrial equipment provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0032] S101. Acquire continuous operation data generated by a device component of an industrial device during operation, and generate an operation time series corresponding to the device component based on the continuous operation data;

[0033] It should be noted that as equipment operates, its components generate operational data. Analysis of this operational data can be used to predict the remaining life of the equipment components. Furthermore, by combining the remaining lifespans of multiple equipment components, the remaining lifespan of the equipment to which the equipment components correspond can be determined.

[0034] Optionally, various sensors are deployed on the equipment components of the industrial equipment, such as temperature, pressure, vibration, current, voltage, etc. These sensors can monitor the operating status and parameters of the equipment components in real time.

[0035] S102, performing resolution reduction processing on the running time sequence to obtain a target sequence corresponding to the running time sequence;

[0036] S103, identifying a resolution level corresponding to the target sequence, and determining a target life prediction model corresponding to the target sequence according to the resolution level; wherein the resolution level is used to indicate the complexity of the running time series;

[0037] It's important to note that the level of resolution indicates the complexity of a running time series. It's typically related to the frequency of data acquisition, the number of data points, and the range of variation in the data. High-resolution time series contain more detail and variation, while low-resolution time series are more simplified and summarized.

[0038] After downscaling the running time series, it is also necessary to determine the resolution level corresponding to the target sequence. Different resolution levels are preset to correspond to different life prediction models.

[0039] S104: Send the target sequence to a target life prediction model to obtain a lightweight adaptive prediction result of the remaining service life of the industrial equipment.

[0040] A prediction is performed based on the target sequence to obtain a life prediction result of the equipment component, wherein the life prediction result is used to indicate the remaining life of the equipment component.

[0041] It should be noted that the remaining life of the industrial equipment can also be predicted based on the remaining life of the core performance equipment components of the industrial equipment. For example, if the remaining life of the core performance equipment components is 1 month, the remaining life of the industrial equipment is also 1 month.

[0042] The lightweight adaptive prediction method for the remaining useful life of industrial equipment provided in the embodiment of the present application reduces the resolution of the operating time series of the equipment components, and then sends the time series with reduced resolution to the life prediction model for prediction, thereby ensuring the accuracy of the life prediction while reducing the computing cost, and achieving the effect of accurately predicting the life of the equipment components according to the complexity of the time series and reducing the computing cost.

[0043] like Figure 2 As shown, Figure 2 Schematic diagram of the process of lightweight adaptive prediction of the remaining useful life of industrial equipment provided in this application Figure 2 , specifically:

[0044] Input, time series data X Decompose the input time series data X into low resolution (fs) to obtain a series of low resolution signals Z1. Then send the low resolution signal Z1 to the small encoder m for encoding to generate feature vectors . The feature vector Send it to the prediction network to determine The prediction result outputs the classification label Clabel1. If Clabel1 is greater than T1, the remaining useful life (RUL) is output; otherwise, the process continues. Among them, the classification label Clabel1 is the confidence label of the low-resolution sub-network, which is used to indicate the feature vector The confidence level of the prediction is . T1 is the preset confidence threshold. If the confidence value carried by Clabel1 (confidence 1) is greater than T1, it means that the result is credible and the predicted remaining useful life can be directly output.

[0045] If Clabel1 (confidence 1) is less than or equal to T1, the time series data X is decomposed into medium resolution (fm). If the confidence corresponding to the prediction result obtained after decomposing the time series using medium resolution is lower than the confidence corresponding to the medium resolution sub-network, it is determined that the time series data X needs to be decomposed into Z2 using high resolution (fL), and Z2 is encoded using a large encoder to obtain .Will Send it to the prediction network to determine The prediction result outputs the classification label Clabel2. If Clabel2 (confidence 2) is greater than T2, the remaining useful life (RUL) is output; otherwise, the process continues. Use the downstream network (second layer sub-network) corresponding to the high-resolution first layer sub-network to continue Perform prediction processing and output ,Sure The prediction result outputs the classification label Clabel3 (confidence 3). If Clabel3 (confidence 3) is greater than T3, the remaining useful life (RUL) is output; otherwise, the downstream network processing of the current sub-network layer (the third sub-network) is continued.

[0046] Optionally, continue to use the second layer subnet When performing prediction processing, the second layer sub-network can inherit part of the prediction results of the first layer sub-network, that is, and Input into the knowledge collaboration mechanism (KC) to obtain ,Sure The prediction result outputs the classification label Clabel3. If Clabel3 (confidence 3) is greater than T3, the remaining useful life (RUL) is output.

[0047] In one possible implementation, the running time series is processed by a first algorithm to obtain a first time series; wherein the first algorithm is used to reduce the resolution corresponding to the running time series to a first resolution level; and the first time series is determined as a target sequence.

[0048] Operational time series refers to the continuous data sequence generated during the operation of equipment components of industrial equipment. This data typically includes parameters such as temperature, pressure, vibration, current, and voltage, which can reflect the operating status and health of the equipment components.

[0049] The first algorithm is a specific data processing algorithm used to reduce the resolution of running time series. The purpose of this algorithm is to convert high-resolution raw data into lower-resolution data in order to reduce the data volume, improve computational efficiency, or meet specific analysis requirements.

[0050] The running time series processed by the first algorithm is called the first time series. It retains the main characteristics of the original data but has a lower resolution. This means that the first time series has fewer data points and the time intervals between each data point are larger.

[0051] The primary resolution level refers to the resolution level of the primary time series. It is used to indicate the complexity of the running time series and the level of detail in the data. A higher resolution level means more data points and more detailed information, while a lower resolution level means fewer data points and more simplified information.

[0052] The first time series is designated as the target series in preparation for subsequent analysis or forecasting tasks. The target series is the time series that has undergone resolution reduction and can be used for trend analysis, anomaly detection, forecasting models, or other statistical analysis tasks.

[0053] In one possible implementation, the running time series is smoothed through a first sliding window to obtain a smoothed sequence corresponding to the running time series, wherein the smoothed sequence is used to characterize the overall trend of the running time series; the running time series is peak processed through a second sliding window to obtain a peak sequence corresponding to the running time series, wherein the peak sequence is used to characterize the peak trend of the running time series; the running time series is feature extracted through a third sliding window to obtain a frequency feature sequence corresponding to the running time series, wherein the frequency feature sequence is used to characterize the frequency trend of the time series; a first time series is generated based on the smoothed sequence, the peak sequence, and the frequency feature sequence; wherein the window sizes of the first sliding window, the second sliding window, and the third sliding window are the same or different.

[0054] Optionally, the first sliding window is used to smooth the running time series. Smoothing aims to reduce noise and fluctuations in the data, making it more stable. By calculating the average value of the data within the sliding window or using other smoothing algorithms (such as moving average and exponential smoothing), a corresponding smoothed sequence of the running time series can be obtained. The smoothed sequence is used to characterize the overall trend of the running time series.

[0055] The smoothing formula is as follows:

[0056]

[0057] : Represents the average trend characteristics of the kth dimension at the i-th time step.

[0058] : Indicates the index position of the i-th time step.

[0059] m: Indicates the size of the first sliding window, used to calculate the average value within the specified range.

[0060] Optionally, the second sliding window is used to perform peak processing on the operating time series. Peak processing aims to detect and extract peak points in the time series. These peak points may correspond to important events or abnormalities in the operation of the equipment component. By comparing the sizes of data points within the sliding window, local maxima can be identified, thereby obtaining a peak sequence corresponding to the operating time series. The peak sequence is used to characterize the peak trend of the operating time series.

[0061] The peak processing formula is as follows:

[0062]

[0063] : Indicates the peak trend feature of the kth dimension at the i-th time step.

[0064] j: represents the maximum value to be found in the second sliding window.

[0065] Optionally, the third sliding window is used to perform feature extraction on the running time series. The purpose of feature extraction is to extract useful information from the time series, such as frequency features. By applying Fourier transform or other frequency domain analysis methods within the sliding window, a frequency feature sequence corresponding to the running time series can be obtained. The frequency feature sequence is used to characterize the frequency trend of the time series.

[0066] The feature extraction processing formula is as follows:

[0067]

[0068]

[0069] : Represents the convolution feature (frequency feature) of the i-th time step and the k-th dimension.

[0070] : Represents the convolution kernel of the kth dimension (the third sliding window), which is used to perform convolution operations on time series.

[0071] b: Bias term.

[0072] : Hyperbolic tangent function, as the activation function.

[0073] : Batch normalization operation, used to accelerate training and stabilize gradients.

[0074] The convolution kernel operation is used to extract local frequency information from time series data and capture fine-grained changes and temporal dependencies.

[0075] Optionally, a first time series is generated based on the smoothing sequence, the peak sequence, and the frequency feature sequence. The first time series is a time series that integrates multiple features, integrating information about the overall trend, peak trend, and frequency trend. By combining these three feature sequences according to a certain weight or method, a first time series that more comprehensively and accurately describes the characteristics of the operating time series can be obtained.

[0076] Finally, the output is:

[0077] The window sizes of the first, second, and third sliding windows can be the same or different. The choice of window size depends on the specific analysis requirements and data characteristics. Larger windows provide smoother results but may lose some detail; smaller windows preserve more detail but may introduce more noise.

[0078] Samples vary in feature complexity: For simple samples, low-resolution feature extraction is sufficient for accurate predictions; complex samples, on the other hand, require higher resolution to extract fine-grained information. By dynamically selecting the appropriate resolution, the model can strike a balance between efficiency and accuracy. This adaptability avoids using overly complex models to process simple samples, reducing computational overhead, while also preserving important information in complex samples, ensuring the model's predictive accuracy.

[0079] In a possible implementation, the first sliding window is moved along the running time sequence until the first sliding window traverses the running time sequence; the mean of the running time sequence located within the first sliding window each time the first sliding window slides is calculated; the smoothed sequence is generated based on the mean of the running time series obtained each time; the second sliding window is moved along the running time sequence until the second sliding window traverses the running time sequence; the maximum value of the running time series located within the second sliding window each time the second sliding window slides is calculated; the peak sequence is generated based on the maximum value of the running time series obtained each time; the third sliding window is moved along the running time sequence until the third sliding window traverses the running time sequence; the frequency characteristics of the running time series located within the third sliding window each time the third sliding window slides are calculated; and the frequency characteristic sequence is generated based on the frequency characteristics of the running time series obtained each time.

[0080] In one possible embodiment, the target sequence is sent to a life prediction model corresponding to the preset resolution level for processing to obtain a preprocessing result; when the predicted value carried in the preprocessing result falls within a preset confidence interval, the preprocessing result is determined as the life prediction result of the industrial equipment; if the predicted value carried in the preprocessing result does not fall within the preset confidence interval, the running time series is processed by a second algorithm to obtain a second time series; wherein, the second algorithm is used to reduce the resolution corresponding to the running time series to a second resolution level; the second resolution level is greater than the first resolution level; the second time series is determined as the target sequence and sent to a downstream prediction model for processing; wherein, the resolution level corresponding to the downstream prediction model is greater than the resolution level currently corresponding to the target time series.

[0081] By comparing the predicted values ​​in the preprocessing results with the preset confidence interval, we can determine whether the prediction is reliable. If so, the preprocessing results can be used directly as the lifespan prediction results. If not, the running time series needs to be further processed using a second algorithm to obtain a second time series, which is determined as the target series and then sent to the downstream prediction model for processing. This ensures the accuracy and reliability of the prediction results.

[0082] In a possible implementation, the target sequence is sent to each layer of the sub-network of the life prediction model for transfer processing to obtain a transfer prediction result; and the transfer prediction result is determined as the life prediction result.

[0083] In one possible implementation, the target sequence is sent to a first-layer sub-network for processing to obtain a first prediction result; a downstream sub-network of the first-layer sub-network is allowed to perform prediction processing based on the first prediction result to obtain a second prediction result; until the last-layer sub-network of the prediction model outputs a final prediction result, the final prediction result is determined as the transferred prediction result.

[0084] The first sub-network is the first layer of the lifespan prediction model. It receives the target sequence and performs preliminary processing. After processing by the first sub-network, an intermediate prediction result, called the first prediction result, is generated. This result is based on a preliminary analysis of the target sequence. Sub-networks downstream of the first sub-network refer to other layers in the model, which perform further prediction processing based on the first prediction result. These sub-networks can progressively extract deeper features and perform more complex analysis and prediction. After processing by these downstream sub-networks, another intermediate prediction result, called the second prediction result, is generated. This result is based on a comprehensive analysis of the first prediction result and deeper features, providing more information about the lifespan of the equipment component. The final prediction result is the comprehensive output of the entire model, resulting from processing and analysis at all levels, and is the most accurate prediction of the equipment component lifespan. The final prediction result is determined as the transferred prediction result, which is used to guide maintenance and replacement decisions for the equipment.

[0085] In one possible implementation, the processing result of the i+1th layer subnetwork and the processing result of the i-th layer subnetwork are sent to the classifier corresponding to the i+1th layer subnetwork to obtain a feedback result of the classifier; wherein 1<i+1≤total number of layers of the prediction model subnetwork, and the feedback result is used to indicate the degree of error; the feedback result is multiplied by the weight value of the i+1th layer subnetwork to obtain a first adjustment value, and the i+1th layer subnetwork is adjusted according to the first adjustment value.

[0086] The i+1th layer of the lifespan prediction model receives the results from the previous (i-th) layer and performs further processing. A classifier is a machine learning algorithm that assigns input data to predefined categories. The classifier evaluates the results of the i+1th layer and provides feedback. The feedback is the classifier's assessment of the i+1th layer's results. This result indicates the degree of error between the results and the actual labels. The weight value is a measure of the importance of each feature in the model. The weight value is used to adjust the parameters of the i+1th layer subnetwork to reduce error and improve prediction accuracy. The first adjustment value is calculated based on the feedback and the weight value. This value is used to adjust the i+1th layer subnetwork to improve its performance. The total number of subnetwork layers in the prediction model refers to the total number of subnetworks in the lifespan prediction model. This number determines the complexity and capabilities of the model.

[0087] In one possible implementation, the gradient value between each layer of sub-networks is determined, and the gradient value between each layer of sub-networks is multiplied by a gradient alignment factor.

[0088] The gradient alignment strategy optimizes the training of different subnetworks by assigning different training gradients to upstream and downstream subnetworks. The knowledge collaboration mechanism allows the downstream network to leverage the knowledge of the upstream network for collaborative reasoning and learn more accurate multi-scale features. Its purpose is to improve the model's reasoning ability and performance.

[0089] like Figure 3 As shown, Figure 3 Schematic diagram of the gradient alignment factor for lightweight adaptive prediction of the remaining useful life of industrial equipment provided in this application. Specifically, a gradient alignment factor is introduced that directly affects the gradient of the model. During the backpropagation process, the gradient of each parameter is multiplied by this alignment factor to appropriately adjust the gradient size. The gradient alignment factor is calculated as follows:

[0090]

[0091] Formula composition:

[0092] 1. Gradient symbol: Represents the loss function for the bth task About the parameters of the ath task gradient.

[0093] 2. Gradient alignment factor: This part consists of two main components:

[0094] Product term: is a multiplication expression that spans all intermediate tasks d from a to b, assigning a scaling factor to each task. The purpose of this factor is to adjust the gradients from subsequent tasks so that they do not dominate when updating the parameters of the current task.

[0095] Division term: It is a direct scaling of the gradient of task b. It ensures that even if task b is the last one in the sequence, its gradient will not have too much influence on the overall learning process.

[0096] Gradient alignment logic:

[0097] The formula performs a normalization of the gradients, making the impact of all tasks on parameter updates more balanced during training. The multiplication term reduces the gradient contribution of all tasks from a to b, preventing later tasks from having too much influence on the parameter updates of earlier tasks. The division term directly reduces the size of the gradient of the bth task, ensuring that the gradient size between different tasks is relatively balanced. Finally, after combining all these adjustment factors, the result is shown as This shows that the gradient of each task is appropriately scaled by its position in the task sequence.

[0098] Specifically, a knowledge transfer path is added between every two adjacent classifiers. The basic temporal feature representation Zi∈ R Li∗dmodel (dmodel represents the dimensionality of the feature representation) of stage i is superimposed with the basic temporal feature representation Zi+1 of stage i+1, resulting in Zconi+1, which is then used in the i+1 classifier to obtain more accurate prediction results. In this case, each classifier (except the first) can be viewed as performing residual learning, applying different weights to different dynamic layers of the network, solving the problem of inconsistent gradients during dynamic network training and inference.

[0099] The embodiment of the present application provides a lightweight adaptive prediction method for the remaining useful life of industrial equipment, which obtains continuous operating data generated by equipment components of industrial equipment during operation, and generates an operating time series corresponding to the equipment components based on the continuous operating data; performs resolution reduction processing on the operating time series to obtain a target sequence corresponding to the operating time series; identifies the corresponding resolution level of the target sequence, and determines a target life prediction model corresponding to the target sequence based on the resolution level; wherein the resolution level is used to indicate the complexity of the operating time series; sends the target sequence to the target life prediction model to obtain a lightweight adaptive prediction result of the remaining useful life of the industrial equipment, thereby achieving accurate prediction of the life of the equipment components based on the complexity of the time series and reducing computing costs.

[0100] Figure 4The schematic diagram of the structure of the lightweight adaptive prediction device for the remaining service life of industrial equipment provided by this application is as follows: Figure 4 As shown, the lightweight adaptive prediction device 40 for the remaining useful life of industrial equipment provided in this embodiment includes:

[0101] An acquisition module 401 is configured to acquire continuous operation data generated by a device component of an industrial device during operation, and generate an operation time series corresponding to the device component based on the continuous operation data;

[0102] A resolution module 402 is configured to perform resolution reduction processing on the running time sequence to obtain a target sequence corresponding to the running time sequence;

[0103] an identification module 403 for identifying a resolution level corresponding to the target sequence and determining a target life prediction model corresponding to the target sequence according to the resolution level; wherein the resolution level is used to indicate the complexity of the running time series;

[0104] The sending module 404 is configured to send the target sequence to a target life prediction model to obtain a life prediction result of the industrial equipment.

[0105] In one possible implementation, the resolution module 402 is further used to process the running time series through a first algorithm to obtain a first time series; wherein the first algorithm is used to reduce the resolution corresponding to the running time series to a first resolution level; and determine the first time series as a target sequence.

[0106] In one possible embodiment, the resolution module 402 is also used to smooth the running time series through a first sliding window to obtain a smoothed sequence corresponding to the running time series, wherein the smoothed sequence is used to characterize the overall trend of the running time series; perform peak processing on the running time series through a second sliding window to obtain a peak sequence corresponding to the running time series, wherein the peak sequence is used to characterize the peak trend of the running time series; perform feature extraction processing on the running time series through a third sliding window to obtain a frequency feature sequence corresponding to the running time series, wherein the frequency feature sequence is used to characterize the frequency trend of the time series; generate a first time series based on the smoothed sequence, the peak sequence, and the frequency feature sequence; wherein the window sizes of the first sliding window, the second sliding window, and the third sliding window are the same or different.

[0107] In one possible embodiment, the resolution module 402 is further used to move the first sliding window along the running time sequence until the first sliding window traverses the running time sequence; calculate the mean of the running time sequence located within the first sliding window each time the first sliding window slides; generate the smoothed sequence based on the mean of the running time sequence obtained each time; move the second sliding window along the running time sequence until the second sliding window traverses the running time sequence; calculate the maximum value of the running time sequence located within the second sliding window each time the second sliding window slides; generate the peak sequence based on the maximum value of the running time sequence obtained each time; move the third sliding window along the running time sequence until the third sliding window traverses the running time sequence; calculate the frequency characteristics of the running time sequence located within the third sliding window each time the third sliding window slides; and generate the frequency characteristic sequence based on the frequency characteristics of the running time sequence obtained each time.

[0108] In one possible embodiment, the sending module 404 is further used to send the target sequence to a life prediction model corresponding to the preset resolution level for processing to obtain a preprocessing result; when the predicted value carried in the preprocessing result falls within a preset confidence interval, the preprocessing result is determined as the life prediction result of the industrial equipment; if the predicted value carried in the preprocessing result does not fall within the preset confidence interval, the running time series is processed by a second algorithm to obtain a second time series; wherein the second algorithm is used to reduce the resolution corresponding to the running time series to a second resolution level; the second resolution level is greater than the first resolution level; the second time series is determined as the target sequence and sent to a downstream prediction model for processing; wherein the resolution level corresponding to the downstream prediction model is greater than the resolution level currently corresponding to the target time series.

[0109] In a possible implementation, the sending module 404 is further configured to send the target sequence to each layer of the sub-network of the life prediction model for transfer processing to obtain a transfer prediction result; and determine the transfer prediction result as the life prediction result.

[0110] In one possible implementation, the sending module 404 is further configured to send the target sequence to a first-layer sub-network for processing to obtain a first prediction result; allow a downstream sub-network of the first-layer sub-network to perform prediction processing based on the first prediction result to obtain a second prediction result; and until the last-layer sub-network of the prediction model outputs a final prediction result, the final prediction result is determined as the transferred prediction result.

[0111] In one possible implementation, the sending module 404 is further used to send the processing results of the i+1th layer sub-network and the processing results of the i-th layer sub-network to the classifier corresponding to the i+1th layer sub-network to obtain a feedback result of the classifier; wherein, 1<i+1≤total number of layers of the prediction model sub-network, and the feedback result is used to indicate the degree of error; the feedback result is multiplied by the weight value of the i+1th layer sub-network to obtain a first adjustment value, and the i+1 layer sub-network is adjusted according to the first adjustment value.

[0112] In one possible implementation, the gradient value between each layer of sub-networks is determined, and the gradient value between each layer of sub-networks is multiplied by a gradient alignment factor.

[0113] The lightweight adaptive prediction device for the remaining useful life of industrial equipment provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar, and are not described in detail in this embodiment.

[0114] Figure 5 This is a schematic diagram of the structure of the lightweight adaptive prediction device for the remaining service life of industrial equipment provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus 504.

[0115] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that the at least one processor 501 performs the above method.

[0116] The specific implementation process of the processor 501 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0117] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0118] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.

[0119] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0120] The present application also provides a lightweight adaptive prediction device for the remaining useful life of industrial equipment, comprising: a memory, a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor performs the above-mentioned method.

[0121] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0122] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0123] The readable storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0124] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0125] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0126] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0127] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0128] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0129] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0130] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A lightweight adaptive prediction method for the remaining useful life of industrial equipment, characterized in that: include: Acquire continuous operation data generated by a device component of the industrial equipment during operation, and generate an operation time series corresponding to the device component according to the continuous operation data; Performing resolution reduction processing on the running time sequence to obtain a target sequence corresponding to the running time sequence; Identifying a resolution level corresponding to the target sequence, and determining a target life prediction model corresponding to the target sequence according to the resolution level; wherein the resolution level is used to indicate the complexity of the running time sequence; Sending the target sequence to a target life prediction model to obtain a life prediction result of a device component of the industrial equipment; The step of performing resolution reduction processing on the running time sequence to obtain a target sequence corresponding to the running time sequence includes: processing the running time sequence through a first algorithm to obtain a first time sequence; wherein the first algorithm is used to reduce the resolution corresponding to the running time sequence to a first resolution level; and determining the first time sequence as a target sequence; The target sequence is sent to the target life prediction model to obtain the life prediction result of the equipment component of the industrial equipment, including: Sending the target sequence to a life prediction model corresponding to the preset resolution level for processing to obtain a preprocessing result; In the case where the predicted value carried in the preprocessing result falls within a preset confidence interval, determining the preprocessing result as the life prediction result of the industrial equipment; If the predicted value carried in the preprocessing result does not fall within the preset confidence interval, the running time series is processed by a second algorithm to obtain a second time series; wherein the second algorithm is used to reduce the resolution corresponding to the running time series to a second resolution level; the second resolution level is greater than the first resolution level; Determine the second time series as a target series and send it to a downstream prediction model for processing; wherein the resolution level corresponding to the downstream prediction model is greater than the resolution level currently corresponding to the target series; The target sequence is sent to the target life prediction model to obtain the life prediction result of the equipment component of the industrial equipment, including: Sending the target sequence to each layer of the life prediction model sub-network for transfer processing to obtain a transfer prediction result; The transfer prediction result is determined as the life prediction result.

2. The method according to claim 1, characterized in that After the running time series is processed by a first algorithm, a first time series is obtained, including: Smoothing the running time series through a first sliding window to obtain a smoothed sequence corresponding to the running time series, wherein the smoothed sequence is used to characterize the overall trend of the running time series; Performing peak processing on the running time series through a second sliding window to obtain a peak sequence corresponding to the running time series, wherein the peak sequence is used to characterize a peak trend of the running time series; Performing feature extraction processing on the running time series through a third sliding window to obtain a frequency feature sequence corresponding to the running time series, wherein the frequency feature sequence is used to characterize the frequency trend of the time series; Generate a first time series based on the smoothing sequence, the peak sequence, and the frequency feature sequence; The window sizes of the first sliding window, the second sliding window, and the third sliding window are the same or different.

3. The method according to claim 2, characterized in that include: Moving the first sliding window along the running time sequence until the first sliding window traverses the running time sequence; Calculating the mean of the running time series within the first sliding window each time the first sliding window slides; Generate the smoothed sequence according to the mean of the running time series obtained by each sliding; Moving the second sliding window along the running time sequence until the second sliding window traverses the running time sequence; Calculating the maximum value of the running time series within the second sliding window each time the second sliding window slides; Generate the peak sequence according to the maximum value of the running time series obtained by each sliding; Moving the third sliding window along the running time sequence until the third sliding window traverses the running time sequence; Calculating the frequency characteristics of the running time series within the third sliding window each time the third sliding window slides; The frequency feature sequence is generated according to the frequency feature of the running time series obtained by each sliding.

4. The method according to claim 1, characterized in that The target sequence is sent to each layer of the sub-network of the life prediction model for transfer processing, including: Sending the target sequence to the first layer sub-network for processing to obtain a first prediction result; Allowing a downstream sub-network of the first layer of sub-network to perform prediction processing based on the first prediction result to obtain a second prediction result; Until the last layer of sub-network of the prediction model outputs the final prediction result, the final prediction result is determined as the transferred prediction result.

5. The method according to claim 1, characterized in that Before determining the transfer prediction result as the target processing result, the method further includes: Send the processing result of the i+1th layer subnetwork and the processing result of the ith layer subnetwork to the classifier corresponding to the i+1th layer subnetwork to obtain the feedback result of the classifier; wherein 1<i+1≤total number of layers of the prediction model subnetwork, and the feedback result is used to indicate the degree of error; The feedback result is multiplied by the weight value of the i+1th layer sub-network to obtain a first adjustment value, and the i+1th layer sub-network is adjusted according to the first adjustment value.

6. The method according to claim 1, characterized in that Before determining the transfer prediction result as the target processing result, the method further includes: Determine the gradient value between each layer of sub-networks, and multiply the gradient value between each layer of sub-networks by the gradient alignment factor.

7. A lightweight adaptive prediction device for the remaining useful life of industrial equipment, characterized in that: include: An acquisition module, used to acquire continuous operation data generated by a device component of the industrial equipment during operation, and generate an operation time series corresponding to the device component according to the continuous operation data; A resolution module, used for performing resolution reduction processing on the running time sequence to obtain a target sequence corresponding to the running time sequence; an identification module, used to identify the resolution level corresponding to the target sequence, and determine the target life prediction model corresponding to the target sequence according to the resolution level; wherein the resolution level is used to indicate the complexity of the running time sequence; A sending module, used for sending the target sequence to a target life prediction model to obtain a life prediction result of the industrial equipment; The device is used to execute the method according to any one of claims 1 to 6.

8. A lightweight adaptive prediction device for the remaining useful life of industrial equipment, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

Images