Cable life detection method and system, electronic equipment and storage medium

Abstract

The invention discloses a cable service life detection method and system, electronic equipment and a storage medium, and relates to the technical field of information detection.Multi-dimensional sensing data of a to-be-detected cable is collected, and a predicted wear rate value and a detected wear rate value of the to-be-detected cable are determined in combination with material attribute information of the to-be-detected cable, so that the service life of the to-be-detected cable is detected, and the service life of the to-be-detected cable is detected. And finally, determining the residual life of the to-be-detected cable by integrating the wear rate prediction value and the wear rate detection value of the to-be-detected cable, so as to remind related workers to replace the to-be-detected cable which is about to break down in time when the residual life of the to-be-detected cable meets a replacement requirement, thereby improving the replacement efficiency of the to-be-detected cable. Therefore, the stability of the data center is prevented from being affected by faults of the to-be-tested cable.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information detection, and in particular to a cable life detection method and system, an electronic device, and a storage medium. BACKGROUND

[0002] Taking a serial attached SCSI (SAS) cable connecting a storage device and a server expansion cabinet as an example, as the scale of a data center expands, the number of SAS cables used is also increasing, and the reliability of the SAS cable will directly affect the stability of the data center. Therefore, how to check the reliability of the SAS cable and replace the cable has become a key research content.

[0003] In the related art, a SAS cable that has obvious damage and bending is regarded as a faulty cable and is replaced by means of manual inspection. However, the manual inspection method cannot find internal problems of the SAS cable, and thus cannot screen cables that are about to fail and replace them in time. Therefore, there is an urgent need for a method that can detect the remaining life of the SAS cable, which is of great significance for replacing cables that are about to fail in time. SUMMARY

[0004] The present application provides a cable life detection method and system, an electronic device, and a storage medium to at least solve the problem that cables that are about to fail cannot be screened and replaced in time in the related art.

[0005] The present application provides a cable life detection method, which includes:

[0006] Obtaining historical sensing data, current sensing data, and material attribute information of a to-be-tested cable;

[0007] Determining a wear rate prediction value of the to-be-tested cable according to the historical sensing data of the to-be-tested cable;

[0008] Determining a crack propagation rate of the to-be-tested cable according to the current sensing data and the material attribute information of the to-be-tested cable;

[0009] Determining a wear rate detection value of the to-be-tested cable according to the crack propagation rate, the current sensing data, and the material attribute information of the to-be-tested cable;

[0010] Determining a remaining life of the to-be-tested cable according to the wear rate prediction value and the wear rate detection value of the to-be-tested cable.

[0011] The application also provides a cable life detection system, comprising: a to-be-tested cable and a cable life detection device, two ends of the to-be-tested cable being connected to physical nodes through connectors, the connectors of the to-be-tested cable being embedded with temperature sensors, plug-pull counters and vibration sensors, and a current sensor being arranged around a middle position of the to-be-tested cable;

[0012] The temperature sensors, the plug-pull counters, the vibration sensors and the current sensor are used to collect current sensing data of the to-be-tested cable;

[0013] The cable life detection device detects the life of the to-be-tested cable based on any one of the cable life detection methods.

[0014] The application also provides a cable life detection device, comprising:

[0015] An acquisition module is configured to acquire historical sensing data, current sensing data and material attribute information of a to-be-tested cable;

[0016] A first determination module is configured to determine a wear rate prediction value of the to-be-tested cable according to the historical sensing data of the to-be-tested cable;

[0017] A second determination module is configured to determine a crack propagation rate of the to-be-tested cable according to the current sensing data and the material attribute information of the to-be-tested cable;

[0018] A third determination module is configured to determine a wear rate detection value of the to-be-tested cable according to the crack propagation rate, the current sensing data and the material attribute information of the to-be-tested cable;

[0019] A detection module is configured to determine a remaining life of the to-be-tested cable according to the wear rate prediction value and the wear rate detection value of the to-be-tested cable.

[0020] The application also provides an electronic device, comprising: a memory configured to store a computer program; and a processor configured to execute the computer program to implement the steps of any one of the cable life detection methods.

[0021] The application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of any one of the cable life detection methods.

[0022] The application also provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the steps of any one of the cable life detection methods.

[0023] Through the application, since the multi-dimensional sensing data of the to-be-tested cable is collected, and the material attribute information of the to-be-tested cable is combined, the wear rate prediction value and the wear rate detection value of the to-be-tested cable are determined respectively, and finally the remaining life of the to-be-tested cable is determined by comprehensively determining the wear rate prediction value and the wear rate detection value of the to-be-tested cable, so that when the remaining life of the to-be-tested cable reaches the replacement requirement, the relevant staff is reminded to replace the to-be-tested cable which is about to fail in time, so as to avoid the influence of the failure of the to-be-tested cable on the stability of the data center. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0025] Figure 1 The flowchart of the cable life detection method provided by the embodiments of the present application is shown in the figure.

[0026] Figure 2 The structure diagram of the cable life detection system provided by the embodiments of the present application is shown in the figure.

[0027] Figure 3 The structure diagram of the to-be-tested cable provided by the embodiments of the present application is shown in the figure.

[0028] Figure 4 The structure diagram of the cable life detection device provided by the embodiments of the present application is shown in the figure.

[0029] Figure 5 The structure diagram of the electronic device provided by the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0031] It should be noted that in the description of the present application, the terms "comprising", "containing" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or equipment. The terms "first", "second" and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence.

[0032] In the field of storage and servers, SAS cables are widely used to connect storage devices and expansion cabinets. With the expansion of the scale of data centers, the number of SAS cables used is also increasing. However, due to the complexity of the working environment, such as the existence of vibration, temperature and humidity changes, electromagnetic interference, and frequent plugging and unplugging operations of the cable, etc., it can cause the SAS cable to be prone to wear, aging and other problems, thereby affecting the stability and reliability of data transmission. Relying on manual inspection to regularly check the appearance of the SAS cable to see if there are obvious damage, bending, etc. This method is inefficient, and it is difficult to find internal problems of the cable, and it is impossible to predict the use and wear of the cable, and to replace it in advance to ensure normal use of the customer.

[0033] To solve the above technical problems, the embodiments of the present application provide a cable life detection method, system, electronic device and storage medium, the method comprising: obtaining historical sensing data, current sensing data and material attribute information of a to-be-tested cable; determining a wear rate prediction value of the to-be-tested cable according to the historical sensing data of the to-be-tested cable; determining a crack propagation rate of the to-be-tested cable according to the current sensing data and the material attribute information of the to-be-tested cable; determining a wear rate detection value of the to-be-tested cable according to the crack propagation rate, the current sensing data and the material attribute information of the to-be-tested cable; and determining a remaining life of the to-be-tested cable according to the wear rate prediction value and the wear rate detection value of the to-be-tested cable. The method provided by the above scheme collects multi-dimensional sensing data of the to-be-tested cable, and combines the material attribute information of the to-be-tested cable to respectively determine the wear rate prediction value and the wear rate detection value of the to-be-tested cable. Finally, the remaining life of the to-be-tested cable is determined by comprehensively considering the wear rate prediction value and the wear rate detection value of the to-be-tested cable, so as to remind the relevant staff to replace the to-be-tested cable in time when the remaining life of the to-be-tested cable reaches the replacement requirement, so as to avoid the influence of the to-be-tested cable failure on the stability of the data center.

[0034] In order for those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0035] The cable life detection method provided by the embodiment of the present application is used for detecting the residual life of a SAS cable and the like, so as to realize timely replacement of the to-be-tested cable about to fail. The execution subject of the embodiment of the present application is an electronic device, such as a server, a desktop computer, a notebook computer, a tablet computer and other electronic devices that can be used for detecting the residual life of a cable.

[0036] As shown in Figure 1 FIG. 1 is a flowchart of a cable life detection method provided by the embodiment of the present application. The method comprises the following steps.

[0037] In step 101, historical sensing data, current sensing data and material attribute information of a to-be-tested cable are acquired.

[0038] The historical sensing data of the to-be-tested cable is sensing data of the to-be-tested cable at multiple time points before the current time point, the current sensing data of the to-be-tested cable is sensing data of the to-be-tested cable at the current time point, and the material attribute information is inherent physical parameter information of a cable material.

[0039] In step 102, a wear rate prediction value of the to-be-tested cable is determined according to the historical sensing data of the to-be-tested cable.

[0040] Specifically, the time series dependence relationship of the historical sensing data can be learned by using an LSTM neural network and the like, and the correlation between the multiple sensing data and the wear rate is determined to perform wear rate prediction of the to-be-tested cable, that is, to obtain the wear rate prediction value of the to-be-tested cable.

[0041] In step 103, a crack propagation rate of the to-be-tested cable is determined according to the current sensing data of the to-be-tested cable and the material attribute information.

[0042] The crack propagation rate of the to-be-tested cable represents the increment of the crack length of the to-be-tested cable after each cycle of load (vibration), and reflects the speed of crack propagation, with a unit of length / cycle.

[0043] In step 104, a wear rate detection value of the to-be-tested cable is determined according to the crack propagation rate of the to-be-tested cable, the current sensing data and the material attribute information.

[0044] Specifically, the wear rate detection value of the to-be-tested cable can be determined according to the crack propagation rate of the to-be-tested cable, the current sensing data and the material attribute information based on a physical mechanism model of the to-be-tested cable.

[0045] In step 105, a residual life of the to-be-tested cable is determined according to the wear rate prediction value and the wear rate detection value of the to-be-tested cable.

[0046] Specifically, the target wear rate of the to-be-tested cable can be determined by weighted fusion of the wear rate prediction value and the wear rate detection value of the to-be-tested cable, and then the cumulative damage of the to-be-tested cable is determined, and finally the remaining life of the to-be-tested cable is determined according to the cumulative damage of the to-be-tested cable.

[0047] By fusing the wear rate prediction value and the wear rate detection value of the to-be-tested cable, the accuracy of the target wear rate determination result is improved, and then the accuracy of the remaining life detection result of the to-be-tested cable is improved.

[0048] Based on the above embodiments, as an implementable manner, in an embodiment, the wear rate prediction value of the to-be-tested cable is determined according to historical sensing data of the to-be-tested cable, comprising:

[0049] Step 1021, obtaining a wear rate prediction model of the to-be-tested cable;

[0050] Step 1022, inputting the historical sensing data of the to-be-tested cable as a model input into the wear rate prediction model, to determine the wear rate prediction value of the to-be-tested cable according to the historical sensing data of the to-be-tested cable based on the wear rate prediction model.

[0051] The wear rate prediction model can be constructed by using an LSTM neural network.

[0052] Specifically, in an embodiment, the model training sample corresponding to the to-be-tested cable can be obtained; wherein the model training sample includes historical sensing data and historical wear rate measured value of the to-be-tested cable at any historical time; based on the model training sample corresponding to the to-be-tested cable, machine learning model training is performed to obtain the wear rate prediction model of the to-be-tested cable.

[0053] Specifically, before performing the wear rate prediction model training, a large amount of historical sensing data and historical wear rate measured value of the to-be-tested cable are obtained, and CEEMDAN-VMD joint denoising is adopted to preprocess the collected original data (historical sensing data and historical wear rate measured value) such as denoising and filtering, to remove abnormal data caused by factors such as sensor error and electromagnetic interference, and the signal-to-noise ratio is improved by 22dB, improving the accuracy and reliability of the training sample.

[0054] The CEEMDAN-VMD combined denoising is a denoising method combined CEEMDAN (complementary ensemble empirical mode decomposition) and VMD (variational mode decomposition). The CEEMDAN can solve the mode mixing problem of the traditional EMD (empirical mode decomposition), and can separate the high-frequency noise from the effective signal. The VMD can accurately extract the effective signal in the middle and low frequency band by optimizing the variational model, that is, the combination of the two can realize the effect of high-frequency noise removal and middle and low-frequency noise removal. When the collected original data is denoised by using the CEEMDAN-VMD combined denoising, the high-frequency noise in the original data is first identified by CEEMDAN, and the high-frequency noise in the original data is removed, and then the original data after removing the high-frequency noise is identified by VMD to further remove the middle and low-frequency noise.

[0055] Specifically, based on a large amount of experimental data and / or actual data, a mathematical model is established between the service life and wear rate of the SAS cable and various influencing factors such as temperature, current load, and plug-in times. The extracted feature data is divided into a training set and a test set. The training set is used to train the LSMT neural network, and the weights and biases of the network are adjusted so that the network can accurately learn the relationship between the parameter features and the cable life. In the training process, cross-validation and other methods can be used to improve the generalization ability of the model.

[0056] In the training phase, the input feature value (X_train) is extracted from the historical database for a continuous time period. Each sample is the data in a time window (such as the past 1 hour):

[0057] X = [[I(t-k), T(t-k), a_RMS(t-k), N(t-k)], [I(t-k+1), T(t-k+1), a_RMS(t-k+1), N(t-k+1)],..., [I(t-1), T(t-1), a_RMS(t-1), N(t-1)]], where I represents current, T represents temperature, a_RMS represents vibration effective value, and N represents cumulative plug-in times. The label data (y_train) includes the target value corresponding to each input sequence X, which is the true wear rate W_meas(t) at the end of the sequence, i.e. the wear rate measured value. In this way, a sample pair of (input sequence, output value) is formed, where the input sequence is the historical sensor data and the output value is the historical wear rate measured value. A large number of such sample pairs form the training set. The training set is input into the LSTM network for training.

[0058] The LSTM network adjusts its millions of internal parameters (weights and biases) through backpropagation and gradient descent algorithm, to generate a data model. The goal of the adjustment is to minimize the difference between the predicted value W_lstm(t) (wear rate prediction value) calculated by the network according to the input sequence X and the true value W_meas(t) (wear rate measured value).

[0059] In the prediction phase, the system caches the sensor readings (historical sensor data) of a certain period of time (such as 1 hour) in the past. A latest sequence S(t) is constructed in the same format as during training: S(t) = [[I(t-k), T(t-k), a_RMS(t-k), N(t-k)],..., [I(t-1), T(t-1), a_RMS(t-1), N(t-1)]], and the sequence S(t) is input into the LSTM model that has been trained. The model performs mathematical operations layer by layer according to the parameters it has learned, including the forget gate, the input gate, and the output gate. The forget gate determines which irrelevant information in the sequence S(t) to discard. The input gate determines which new information to add to the cell state. The output gate outputs the final prediction result based on the latest working conditions. After complex transformations inside the network, a specific numerical value W_lstm(t) is generated at the final output layer of the network, i.e., the wear rate prediction value of the cable under test is obtained.

[0060] Further, in an embodiment, after determining the wear rate prediction value of the cable under test at any time, the wear rate measured value of the cable under test at the time can be obtained when the time is reached; and the wear rate prediction model is dynamically optimized in weight according to the deviation between the wear rate measured value and the wear rate prediction value of the cable under test at the time.

[0061] Specifically, at time t, the wear rate prediction model determines the wear rate prediction value of the cable under test at time t according to the historical sensor data from time t-k to time t-1. At this time, the wear rate of the cable under test can also be measured by the measurement method, i.e., the wear rate measured value of the cable under test at time t is obtained, and finally the wear rate prediction model is dynamically optimized in weight according to the deviation between the two, to further improve the prediction accuracy of the wear rate prediction model.

[0062] On the basis of the above embodiments, as a kind of implementable mode, in an embodiment, according to the current sensor data and material attribute information of the cable under test, the crack propagation rate of the cable under test is determined, comprising:

[0063] In step 1031, the equivalent stress of the cable under test is determined according to the current effective value of vibration of the cable under test.

[0064] Step 1032, determining the current crack length of the cable to be measured according to the crack propagation rate of the cable to be measured at the previous moment and the crack length at the previous moment;

[0065] Step 1033, determining the instantaneous stress length factor amplitude of the cable to be measured according to the equivalent stress of the cable to be measured and the current crack length;

[0066] Step 1034, determining the crack propagation rate of the cable to be measured according to the instantaneous stress length factor amplitude of the cable to be measured, the first material constant and the second material constant.

[0067] Wherein, the current sensing data includes the current vibration effective value and the current crack length, and the material attribute information includes the first material constant and the second material constant.

[0068] It should be noted that the current vibration effective value (a_RMS(t)) is a quantitative index of the mechanical vibration intensity (unit: g, 1g is about equal to 9.8m / s 2 ), the equivalent stress is a mechanical quantity used for crack propagation calculation, and the instantaneous stress length factor amplitude is the stress intensity of the crack tip.

[0069] Specifically, first, the current vibration effective value which cannot be directly associated with damage is converted into a mechanical quantity (equivalent stress) which can be directly used for crack propagation calculation. Then, the crack length is iteratively updated, that is, the current crack length of the cable to be measured is determined, the equivalent stress size and the crack length are comprehensively considered to determine the instantaneous stress length factor amplitude of the cable to be measured. Finally, by combining the material inherent properties and the mechanical parameters, the crack propagation rate caused by vibration is accurately calculated, that is, the crack propagation rate of the cable to be measured is determined.

[0070] Wherein, the calculation formula of the current crack length of the cable to be measured is as follows:

[0071] a(t)=a(t-1)+D AN (t-1)×ΔN

[0072] Wherein, a(t) represents the crack length of the cable to be measured at t moment, that is, the current crack length, a(t-1) represents the crack length of the cable to be measured at t-1 moment, D AN (t-1) represents the crack propagation rate of the cable to be measured at t-1 moment, and ΔN represents the number of vibration cycles since t-1 moment.

[0073] Specifically, in an embodiment, the instantaneous stress length factor amplitude of the cable to be measured can be determined based on the following formula:

[0074]

[0075] Where ΔK(t) represents the instantaneous stress length factor amplitude of the cable under test, Y represents the preset geometric shape factor, which is a dimensionless coefficient that depends on the crack morphology, Δσ(t) represents the equivalent stress of the cable under test, a(t) represents the current crack length of the cable under test, and π represents pi.

[0076] Where, Δσ(t)=k σ ×a_RMS(t), k σ The stress conversion factor is a calibration factor obtained by simultaneously measuring acceleration and cable surface strain through a vibration table experiment and converting them using Huke's law. a_RMS(t) represents the current effective value of vibration of the cable under test.

[0077] Specifically, in one embodiment, the crack propagation rate of the cable under test can be determined based on the following formula:

[0078] D AN (t)=C×(ΔK(t)) m

[0079] Among them, D AN (t) represents the crack propagation rate of the cable under test, ΔK(t) represents the instantaneous stress length factor amplitude of the cable under test, C represents the first material constant, and m represents the second material constant. The first material constant is used to characterize the crack propagation rate of the cable under test, and the second material constant is used to characterize the sensitivity of the crack of the cable under test to the instantaneous stress length factor amplitude.

[0080] Among them, D AN Also known as damage_rate_vibration(t) and da / dN, the crack propagation rate represents the fatigue crack propagation rate, that is, the increment of crack length after each cyclic loading. Its value directly reflects the speed of crack propagation. The first and second material constants are obtained by fitting experimental data.

[0081] It should be noted that, in the embodiments of this application, by converting macroscopic vibration parameters into quantitative indicators of microscopic crack propagation (crack propagation rate), the problem that traditional methods cannot accurately express the accumulation of mechanical damage is solved, laying the foundation for improving the accuracy of the remaining life test results of the cable under test.

[0082] Based on the above embodiments, as an implementable approach, in one embodiment, the wear rate detection value of the cable under test is determined according to the crack propagation rate, current sensing data, and material property information, including:

[0083] Step 1041: Determine the electrothermal damage value of the cable under test based on the current current and current temperature of the cable under test.

[0084] Step 1042: Determine the wear rate detection value of the cable under test based on the electrothermal damage value, crack propagation rate, current number of insertions and removals, and insertion and removal base damage rate of the cable under test.

[0085] The current sensing data includes the current current, current temperature, and current number of insertions and removals, while the material property information includes the insertion and removal damage rate.

[0086] Specifically, by combining the current current and current temperature of the cable under test, the electrothermal damage value of the cable under test is determined. Compared with the electrical damage determined only by the current and the thermal damage determined only by the temperature, this is closer to the actual working conditions and ensures the accuracy of the electrothermal damage calculation.

[0087] Specifically, in one embodiment, the electrothermal damage value of the cable under test can be determined based on the following formula:

[0088]

[0089] Among them, D IH The value of the cable under test is represented by e, which represents the base of the natural logarithm. I(t) represents the current current, T(t) represents the current temperature, α represents the current damage coefficient, and β represents the temperature damage coefficient.

[0090] The current damage coefficient was calibrated through aging experiments, while the temperature damage coefficient was fitted based on the Arrhenius equation.

[0091] Specifically, in one embodiment, the wear rate detection value of the cable under test can be determined based on the following formula:

[0092]

[0093] Among them, D DT (t) represents the wear rate detection value of the cable under test, D IH (t) represents the electrothermal damage value of the cable under test, D AN (t) represents the crack propagation rate of the cable under test, γ represents the vibration damage coefficient, δ represents the basic damage rate from insertion and removal, and N(t) represents the number of insertions and removals. This represents the insertion / removal nonlinearity index.

[0094] Among them, the vibration damage coefficient is calibrated by vibration table test, the insertion and extraction base damage rate represents the reference wear caused by a single insertion and extraction action, which can be calibrated by experiment, and the insertion and extraction nonlinearity index is used to reflect the cumulative nonlinear effect of insertion and extraction damage.

[0095] Furthermore, in one embodiment, the remaining lifespan of the cable under test can be determined based on the following formula:

[0096]

[0097] W(τ) = r(τ) x D KSTM (τ) + (1 - r(τ)) x D DT (τ)

[0098] Wherein, RUL(t) represents the remaining life of the cable to be measured at t time, W(τ) represents the target wear rate of the cable to be measured at τ time, W(t) represents the target wear rate of the cable to be measured at t time, Δτ represents the time interval between τ = 0 to τ = t, D LSTM (τ) represents the wear rate prediction value of the cable to be measured at τ time, D DT (τ) represents the wear rate detection value of the cable to be measured at τ time, r(τ) represents the weighting coefficient, which is determined according to the accuracy of the wear rate prediction value.

[0099] Wherein, r(t) is updated by the error e(t-1) = |D LSTM -D MEAS | at the last time, D MEAS represents the wear rate measured value, r(τ) = clip(r(τ-1)-j·sign(e(t-1)), 0, 1), j represents the learning rate, j = 0.001, sign(e(t-1)) is the sign of the error, which is used to determine the weight update direction, and the clip function is used to ensure that the value range of r(τ) is between [0, 1].

[0100] Specifically, by accumulating W(τ) (damage rate per unit time) from τ = 0 time to t, multiplied by the time interval Δτ. Represents the total damage degree accumulated by the system or material at time t (current), the numerical range is usually between 0 and 1, 1 represents complete damage or failure. The unit of RUL(t) is hour, based on the current cumulative damage and the target damage rate W(t) at the current time, the time that the cable to be measured can still run is estimated. The numerator represents the remaining undamaged part, divided by the current target damage rate to determine the remaining life, which improves the accuracy of the determination result of the remaining life.

[0101] Further, in an embodiment, the threshold of the remaining service life can be set according to the specifications and performance requirements of the cable to be measured. For example, when the remaining service life is less than 1000 hours, the warning is started, such as warning through sound and light alarm, email reminder and other ways, and at the same time, a short message is sent to the mobile phone of the operation and maintenance personnel for reminding. At the same time, detailed instructions are provided to the operation and maintenance personnel, including the position of the cable, the current state and other information, which facilitates the operation and maintenance personnel to replace the cable in time during the low peak period of system operation.

[0102] Specifically, in an embodiment, the health degree of the to-be-tested cable can be analyzed according to a target damage rate of the to-be-tested cable, and then the sampling frequency of the sensor and the running frequency of the prediction model are dynamically adjusted according to the health degree, the change trend of the target damage rate is monitored in real time, when the change trend indicates that the health degree switches between levels, the adjustment of the sampling frequency and the model running frequency is automatically triggered, and the energy consumption mode of the sensor is synchronously updated, for example, the power supply power of the sensor is reduced in the healthy state, so as to reduce the energy consumption of the sensor while ensuring the detection accuracy of the residual life of the to-be-tested cable.

[0103] The cable life detection method provided by the embodiment of the application comprises the following steps: obtaining historical sensing data, current sensing data and material attribute information of a to-be-tested cable; determining a wear rate prediction value of the to-be-tested cable according to the historical sensing data of the to-be-tested cable; determining a crack propagation rate of the to-be-tested cable according to the current sensing data and the material attribute information of the to-be-tested cable; determining a wear rate detection value of the to-be-tested cable according to the crack propagation rate, the current sensing data and the material attribute information of the to-be-tested cable; and determining a residual life of the to-be-tested cable according to the wear rate prediction value and the wear rate detection value of the to-be-tested cable. The method provided by the above scheme collects multi-dimensional sensing data of the to-be-tested cable, combines the material attribute information of the to-be-tested cable, respectively determines the wear rate prediction value and the wear rate detection value of the to-be-tested cable, and finally determines the residual life of the to-be-tested cable by comprehensively considering the wear rate prediction value and the wear rate detection value of the to-be-tested cable, so as to remind the relevant staff to replace the to-be-tested cable in time when the residual life of the to-be-tested cable reaches the replacement requirement, so as to avoid the influence of the failure of the to-be-tested cable on the stability of the data center. Moreover, the multi-dimensional parameter collaborative perception is established through the LSTM neural network, the damage dynamics differential equation is established based on the microscopic crack propagation theory, and the problem of cable microscopic damage accumulation effect is solved. The working state of the to-be-tested cable is monitored in real time, the problematic cable can be accurately positioned in time, the operation and maintenance personnel are reminded to replace the cable during the low peak period of system operation, the stability and reliability of the to-be-tested cable operation are improved, and the operation and maintenance cost is reduced.

[0104] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and a general hardware platform as required, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment.

[0105] The embodiment of the application also provides a cable life detection system for executing the cable life detection method provided by the above embodiment.

[0106] As Figure 2The diagram shown is a structural schematic of the cable life testing system provided in this embodiment of the application. The cable life testing system includes a cable under test and a cable life testing device. The two ends of the cable under test are connected to physical nodes through connectors. The connectors of the cable under test are embedded with a temperature sensor, a insertion / removal counter, and a vibration sensor. A current sensor is arranged around the middle of the cable under test.

[0107] Among them, the temperature sensor, insertion / removal counter, vibration sensor, and current sensor are used to collect the current sensing data of the cable under test; the cable life detection device performs life detection on the cable under test based on the cable life detection method provided in the above embodiments.

[0108] For example, such as Figure 3 The diagram shown is a structural schematic of the cable under test provided in this application embodiment. Taking the two ends of the cable under test as connected to an expansion cabinet, storage and server equipment respectively through connectors, and the cable under test as a SAS cable, the connectors are embedded with a temperature sensor, a insertion / removal counter and a vibration sensor, and a current sensor is arranged around the middle position to form a MEMS sensor array. The temperature, cumulative number of insertions / removals and the effective value of vibration of the cable under test are calculated by weighted calculation or average calculation of the sensor data collected by the two connectors.

[0109] The embodiments of this application also provide a cable life testing device for performing the cable life testing method provided in the above embodiments.

[0110] like Figure 4 The diagram shown is a structural schematic of the cable life testing device provided in an embodiment of this application. The cable life testing device 40 includes: an acquisition module 401, a first determination module 402, a second determination module 403, a third determination module 404, and a detection module 405.

[0111] The system comprises the following modules: an acquisition module for acquiring historical and current sensor data and material property information of the cable under test; a first determination module for determining the predicted wear rate of the cable under test based on its historical sensor data; a second determination module for determining the crack propagation rate of the cable under test based on its current sensor data and material property information; a third determination module for determining the detected wear rate of the cable under test based on its crack propagation rate, current sensor data, and material property information; and a detection module for determining the remaining lifespan of the cable under test based on its predicted and detected wear rates.

[0112] For a description of the features in the embodiment corresponding to the cable life testing device, please refer to the relevant description in the embodiment corresponding to the cable life testing method, which will not be repeated here.

[0113] Embodiments of this application also provide an electronic device, such as...Figure 5 As shown in FIG. 1, a structural schematic diagram of an electronic device provided by an embodiment of the present application is shown, which includes a processor 10 and a memory 20, the memory 20 storing a computer program, and the processor 10 is configured to run the computer program to perform the steps in any of the above cable life detection method embodiments.

[0114] An embodiment of the present application further provides a computer readable storage medium, which stores a computer program, wherein the computer program is configured to perform the steps in any of the above cable life detection method embodiments when running.

[0115] In an example embodiment, the above computer readable storage medium can include, but is not limited to, a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0116] An embodiment of the present application further provides a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the steps in any of the above cable life detection method embodiments.

[0117] An embodiment of the present application further provides another computer program product, which includes a non-volatile computer readable storage medium, and the non-volatile computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps in any of the above cable life detection method embodiments.

[0118] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in the above description in a general manner. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0119] The above describes in detail the cable life detection method, system, electronic device and storage medium provided by the present application. The principles and implementation modes of the present application are described by applying specific examples, and the above description of the embodiments is only applicable to help understand the method of the present application and its core idea. It should be pointed out that, for those skilled in the art, without departing from the principles of the present application, the present application can be improved and modified in several ways, and these improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. A method for detecting cable life, characterized in that, include: Acquire historical sensor data, current sensor data, and material property information of the cable under test; Based on the historical sensor data of the cable under test, the predicted wear rate of the cable under test is determined; Based on the current sensing data and material property information of the cable under test, the crack propagation rate of the cable under test is determined. The wear rate detection value of the cable under test is determined based on the crack propagation rate, current sensor data, and material property information of the cable under test. The remaining lifespan of the cable under test is determined based on the predicted wear rate and the detected wear rate.

2. The cable life testing method according to claim 1, characterized in that, The step of determining the predicted wear rate of the cable under test based on historical sensing data of the cable under test includes: Obtain the wear rate prediction model for the cable under test; The historical sensor data of the cable under test is used as the model input and input into the wear rate prediction model. Based on the wear rate prediction model, the predicted wear rate of the cable under test is determined according to the historical sensor data of the cable under test.

3. The cable life testing method according to claim 2, characterized in that, The method for obtaining the wear rate prediction model for the cable under test includes: Obtain the model training samples corresponding to the cable under test; wherein, the model training samples include historical sensing data and historical wear rate measured values ​​of the cable under test at any historical moment; Based on the model training samples corresponding to the cable under test, a machine learning model is trained to obtain a wear rate prediction model for the cable under test.

4. The cable life testing method according to claim 2, characterized in that, The method further includes: After determining the predicted wear rate of the cable under test at any given time, the measured wear rate of the cable under test at that time is obtained. Based on the deviation between the measured wear rate of the cable under test at that moment and the predicted wear rate, the wear rate prediction model is dynamically optimized with weights.

5. The cable life testing method according to claim 1, characterized in that, The step of determining the crack propagation rate of the cable under test based on the current sensing data and material property information of the cable under test includes: The equivalent stress of the cable under test is determined based on the current effective value of the vibration. The current crack length of the cable under test is determined based on the crack propagation rate and crack length of the cable under test at the previous moment. The instantaneous stress length factor amplitude of the cable under test is determined based on the equivalent stress and current crack length of the cable under test. The crack propagation rate of the cable under test is determined based on the instantaneous stress length factor amplitude, the first material constant, and the second material constant. The current sensing data includes the current effective value of vibration and the current crack length, and the material property information includes the first material constant and the second material constant.

6. The cable life testing method according to claim 5, characterized in that, The step of determining the instantaneous stress length factor amplitude of the cable under test based on the equivalent stress and current crack length of the cable under test includes: The instantaneous stress length factor amplitude of the cable under test is determined based on the following formula: Wherein, ΔK(t) represents the instantaneous stress length factor amplitude of the cable under test, Y represents the preset geometric shape factor, Δσ(t) represents the equivalent stress of the cable under test, a(t) represents the current crack length of the cable under test, and π represents pi.

7. The cable life testing method according to claim 5, characterized in that, The step of determining the crack propagation rate of the cable under test based on the instantaneous stress length factor amplitude, the first material constant, and the second material constant includes: The crack propagation rate of the cable under test is determined based on the following formula: D AN (t)=C×(ΔK(t)) m Among them, D AN (t) represents the crack propagation rate of the cable under test, ΔK(t) represents the instantaneous stress length factor amplitude of the cable under test, C represents the first material constant, and m represents the second material constant. The first material constant is used to characterize the crack propagation rate of the cable under test, and the second material constant is used to characterize the sensitivity of the crack of the cable under test to the instantaneous stress length factor amplitude.

8. The cable life testing method according to claim 1, characterized in that, The step of determining the wear rate detection value of the cable under test based on the crack propagation rate, current sensor data, and material property information includes: The electrothermal damage value of the cable under test is determined based on the current current and current temperature of the cable under test. The wear rate detection value of the cable under test is determined based on the electrothermal damage value, crack propagation rate, current number of insertions and removals, and insertion and removal base damage rate of the cable under test. The current sensing data includes the current current, current temperature, and current number of insertions and removals, and the material property information includes the basic damage rate of insertions and removals.

9. The cable life testing method according to claim 8, characterized in that, The step of determining the electrothermal damage value of the cable under test based on the current current and current temperature of the cable under test includes: The electrothermal damage value of the cable under test is determined based on the following formula: Among them, D I1 (t) represents the electrothermal damage value of the cable under test, e represents the base of the natural logarithm, I(t) represents the current current, T(t) represents the current temperature, α represents the current damage coefficient, and β represents the temperature damage coefficient.

10. The cable life testing method according to claim 8, characterized in that, The determination of the wear rate detection value of the cable under test based on the electrothermal damage value, crack propagation rate, current number of insertions and removals, and insertion / removal base damage rate includes: The wear rate detection value of the cable under test is determined based on the following formula: Among them, D DT (t) represents the wear rate detection value of the cable under test, D IH (t) represents the electrothermal damage value of the cable under test, D AN (t) represents the crack propagation rate of the cable under test, γ represents the vibration damage coefficient, δ represents the basic damage rate of insertion and removal, and N(t) represents the current number of insertions and removals. This represents the insertion / removal nonlinearity index.

11. The cable life testing method according to claim 1, characterized in that, The step of determining the remaining lifespan of the cable under test based on the predicted wear rate and the detected wear rate includes: The remaining lifespan of the cable under test is determined based on the following formula: W(τ)=r(τ)×D KSTM (τ)+(1-r(τ))×D DT (t) Where RUL(t) represents the remaining lifespan of the cable under test at time t, W(τ) represents the target wear rate of the cable under test at time τ, Δτ represents the time interval between τ = 0 and τ = t, and D LSTM (τ) represents the predicted wear rate of the cable under test at time τ, D DT (τ) represents the wear rate detection value of the cable under test at time τ, and r(τ) represents the weighting coefficient, which is determined based on the accuracy of the wear rate prediction value.

12. A cable life testing system, characterized in that, include: The cable under test and the cable life testing device are provided. The two ends of the cable under test are connected to physical nodes through connectors. The connectors of the cable under test are embedded with temperature sensors, insertion / removal counters and vibration sensors. A current sensor is arranged around the middle position of the cable under test. The temperature sensor, insertion / removal counter, vibration sensor, and current sensor are used to collect the current sensing data of the cable under test. The cable life testing device performs life testing on the cable under test based on the cable life testing method as described in any one of claims 1 to 11.

13. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the cable life detection method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the cable life detection method as described in any one of claims 1 to 11.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the cable life detection method as described in any one of claims 1 to 11.

Images