170 results about "Remaining life" patented technology

A method for predicting the remaining life and health status of a lithium battery based on LSTM+Mamba includes the following contents: charging and discharging the lithium battery, collecting various lithium battery aging data during the cycle, and preprocessing the data; constructing a multi-layer neural network, which is composed of an LSTM layer, a multi-head attention mechanism, and a Mamba module; constructing a combined weighted loss function with optimized weights to train the multi-layer neural network; and using the multi-layer neural network to predict the remaining life and health status of the lithium battery. In the face of the high nonlinearity of the lithium battery degradation process, the present invention significantly improves the prediction accuracy of the remaining life and health status.

The invention discloses an intelligent prediction method and device for the residual life of equipment, and relates to the field of reliability engineering, and the method comprises the steps: collecting sensor observation data, carrying out the preprocessing of the sensor observation data, and extracting data fluctuation features; based on a time window input strategy, processing the sensor observation data and the data fluctuation characteristics, and determining input characteristics; training a global-local feature extraction network according to the input features, and determining a trained global-local feature extraction network; the global-local feature extraction network comprises a multi-layer time convolution network, a causal convolution gating unit, a two-dimensional compression excitation fusion module and a Transform encoder which are connected in sequence; performing performance verification on the trained global-local feature extraction network, and determining a life prediction model; and predicting the residual life of the to-be-tested equipment according to the life prediction model. According to the invention, the life prediction performance can be comprehensively improved.

The invention discloses a buried pipeline residual life prediction method, relates to the technical field of pipeline prediction in computer measurement, can realize multi-step prediction of the residual life of a buried pipeline, and is small in accumulated error and higher in precision. According to the buried pipeline residual life prediction method, a training set is input into a TFT neural network for network training, a test set is input into the trained TFT neural network for testing, TFT model parameters are stored, and training of the neural network is completed; the TFT neural network comprises a gating residual network GRN module used for processing a nonlinear correlation relation between input data and a prediction target, a variable selection network module used for carrying out important feature screening on static and dynamic variables, and a multi-head attention layer module used for learning a long-term dependency relation of a pipeline life sequence. And a long and short term memory network (LSTM) module, and a quantile regression module for outputting the residual life of the pipeline based on regression of different quantiles.

A steel wire rope remaining life prediction method of a four-rope grab crane comprises the steps that 1, an electromagnetic device is used for magnetization in the axial direction of a steel wire rope; 2, a Hall sensor is installed at the fixed end of the steel wire rope; 3, a Hall sensor monitors changes of a magnetic field around the steel wire rope in real time; 4, whether missing values and abnormal values exist in the collected digital signal sequence or not is checked; if missing values exist, a linear interpolation method is adopted for filling; 5, extracting characteristics related to the damage and residual life of the steel wire rope from the cleaned digital signal data; 6, establishing a magnetization prediction model; 7, magnetic field change characteristic data of the steel wire rope in different use stages are collected, a least square method is adopted for the magnetization prediction model to estimate model parameters, and a loss function is minimized; and 8, predicting the real-time residual life of the steel wire rope. The method can predict the service life of the steel wire rope at high frequency and accurately predict the residual service life of the steel wire rope.

The invention discloses a method and a system for predicting the residual life of a downhole casing in a full life cycle. The method comprises the following steps: acquiring the working pressure, the internal pressure resistance safety coefficient and the extrusion resistance safety coefficient of a to-be-tested casing; based on the working pressure of the to-be-tested casing, the internal pressure resistance safety coefficient and a pre-constructed first model, obtaining the internal pressure resistance safety service time of the to-be-tested casing; obtaining the anti-extrusion safety service time of the to-be-tested casing pipe based on the working pressure and the anti-extrusion safety coefficient of the to-be-tested casing pipe and a pre-constructed second model; and obtaining the residual life of the to-be-tested casing according to the internal pressure-resistant safe service time and the extrusion-resistant safe service time. By means of the method, life prediction of the shale gas downhole tubular column in the whole life cycle can be achieved, sleeve life prediction is more accurate, and the method has more practical production guiding significance.

The invention relates to a residual life evaluation system based on a direction control valve. The residual life evaluation system comprises an acquisition module for acquiring change condition data of the direction control valve through a sensor; the data processing module is used for performing data processing based on the change condition data of the direction control valve acquired by the data acquisition module so as to extract characteristic parameters of the direction control valve; the service life evaluation module is used for predicting the residual service life of the direction control valve based on a pre-established safety threshold value and a relation model; and when the performance parameters of the direction control valve exceed the safety threshold value, the system automatically gives out early warning. Through the sensor installed at the key position of the direction control valve, the system can monitor parameters such as pressure, flow and valve element displacement in real time. Therefore, an operator can know the operation state of the control valve at any time and find potential abnormal conditions in time.

The invention discloses an operation and maintenance method, device and equipment for filtering and separating equipment and a readable storage medium, belongs to the field of gas filtering, and aims to consider that related sensing data of a filter cartridge can reflect the residual life of the filter cartridge, so that a filter cartridge life prediction model is pre-trained, and then in the operation process of the filtering and separating equipment, the residual life of the filter cartridge is predicted. A real-time sensing data set (including at least one of temperature and humidity data of the filter cartridge, a pressure difference value of the surface of the filter cartridge, particle concentration of an inlet and an outlet of the filter cartridge and flow of the outlet of the filter cartridge) is obtained through a preset sensor group, and then the real-time sensing data set is input into a pre-trained filter cartridge service life prediction model to obtain a residual service life prediction value of the filter cartridge. And the prompter is controlled to prompt the residual life prediction value, so that the condition that the filter cartridge is poor in state and short in service life can be found in time and replaced in time, the filtering and separating equipment is prevented from running under the condition that the filter cartridge is poor in state, the filtering effect is guaranteed, and damage to rear-end equipment is avoided.

The invention belongs to the technical field of lithium battery health management, and particularly relates to a lithium battery residual life prediction method based on self-adaptive modal number estimation and multi-scale decomposition, which comprises the following steps of: firstly, acquiring a capacity attenuation sequence of a battery, and then calculating the residual life of the battery through a variational modal decomposition method combining a self-adaptive modal number determination mechanism and Bayesian modal screening. Carrying out adaptive decomposition and denoising on the sequence, and separating a low-frequency trend mode and a medium-high frequency oscillation mode; according to the long-range dependence of the trend mode, a Transform model is adopted for prediction; and for the nonlinear fluctuation characteristics of the oscillation mode, a random forest model is adopted for prediction. And finally, fusing the prediction results of the two groups of components, reconstructing a complete future capacity attenuation curve, and calculating the remaining service life based on a preset failure threshold. According to the method, through adaptive decomposition and grouping modeling, the adaptability, noise immunity and prediction precision of the prediction model to different battery individuals and complex working conditions are effectively improved.

The invention discloses a service life prediction system and an air conditioning system, and the system comprises a data collection module which is used for collecting the operation data of a to-be-predicted device; the data analysis module is used for calculating the life loss of the to-be-predicted device according to the operation data; and the life prediction module is used for estimating the residual life of the to-be-predicted device according to the life loss. Compared with the prior art, the service life of the to-be-predicted device can be accurately predicted according to the environment parameters and the operation parameters of the to-be-predicted device, so that the to-be-predicted device is maintained and replaced in advance, the service life of the whole system is effectively prolonged, and fault risks and resource waste are reduced.

The invention provides a lithium battery residual life detection method and apparatus, an electronic device and a storage medium. The method comprises the steps of performing correlation analysis on a voltage battery capacity curve of each charging interval and a battery health state to obtain a correlation coefficient; when the absolute value of the correlation coefficient is greater than a preset value, constructing a battery voltage characteristic sample set through the battery voltage and the battery capacity of the charging interval, and taking impedance spectrum data corresponding to each charging interval in the battery voltage capacity characteristic sample set as an impedance spectrum characteristic sample set; inputting the battery voltage characteristic sample set into a deep learning model to obtain a predicted impedance spectrum, and training the deep learning model based on the predicted impedance spectrum and the impedance spectrum characteristic sample set; and inputting the charging data of a to-be-predicted lithium battery into the trained deep learning model to obtain a target predicted impedance spectrum, and determining the predicted residual life of the lithium battery based on the equivalent circuit model and the target predicted impedance spectrum. The detection efficiency is improved by detecting the battery voltage characteristics of the lithium battery.

The invention discloses a method for evaluating the residual life of an electrical component under the influence of stress fluctuation, and the method comprises the steps: firstly, obtaining the initial state information of the electrical component, including characteristic parameters and initial values thereof; then, a static artificial accelerated aging corrosion test is carried out, and the change value of the characteristic parameters along with time is obtained; based on the change values, the basic weight of each characteristic parameter is determined. And establishing a function relation between the characteristic parameters and time, and describing the aging process. An Arrhenius model is used to calculate an acceleration factor, and the model is adjusted to adapt to different temperature conditions. And obtaining a characteristic parameter degradation model according to the acceleration factor and the function relation. And when the electrical component is only influenced by the environmental stress fluctuation, further establishing a degradation model considering the influence. Finally, according to the operation state of the electrical component, the residual life is evaluated by using a corresponding model, and a scientific basis is provided for maintenance and management. According to the method, various factors are comprehensively considered, the evaluation accuracy is improved, and the system reliability and safety are ensured.

The invention provides a multi-component resource recovery method and device for retired wind power equipment. The method comprises the steps that the component remaining life of each component in the wind power equipment is obtained according to the design life, the real-time damage amount and the failure damage amount of each component in the wind power equipment; the unit residual life of the wind power equipment is obtained according to the assembly residual life of each component in the wind power equipment, and when the unit residual life of the wind power equipment is lower than a preset value, the wind power equipment is decommissioned; all parts of the retired wind power equipment are treated and dismantled; quality detection is conducted on the disassembled part, when the quality of the part does not reach the standard, cutting route planning and cutting parameter determination are conducted on the part, and cutting decomposition is conducted on the part according to the planned cutting route and the determined cutting parameters; and the decomposed materials are sorted and recycled. According to the multi-component resource recycling method and device for the retired wind power equipment, high-quality recycling of multi-component resources in the retired wind power equipment is achieved.

The present application relates to the technical field of nuclear power plant performance testing and discloses a method for assessing the remaining life of a bursting disk in a large-caliber vacuum system of a nuclear power plant, comprising the following steps: S1, obtaining a first sample of a reference bursting disk after a first fatigue test, obtaining a second sample of a bursting disk to be assessed, and performing a bursting test on the first and second samples to obtain a life coefficient; S2, performing a non-metallic material state test on non-metallic debris in the first and second samples after the test, obtaining non-metallic test results of similar non-metallic materials, and obtaining a first remaining life of the bursting disk to be assessed; S3, performing a metallic material state test on metallic debris in the first and second samples after the test to obtain a second remaining life of the bursting disk to be assessed; S4, obtaining a third sample of the bursting disk to be assessed, and performing a second fatigue test to obtain a third remaining life of the bursting disk to be assessed; and S5, obtaining a final remaining life of the bursting disk to be assessed based on the life coefficient, the first, second, and third remaining lives.

The invention relates to the technical field of hydraulic engineering safety monitoring, in particular to a small reservoir residual life prediction method based on a health degree evaluation model, comprising the following steps: constructing a small reservoir health evaluation index system; calculating the health degree of the small reservoir sub-project; calculating the comprehensive health degree of the small reservoir; establishing a nonlinear Wiener process model; estimating model parameter values; predicting the residual life of the small reservoir; the beneficial effects are that according to the small reservoir residual life prediction method based on the health degree evaluation model provided by the invention, the comprehensive health degree value representing the health state of the small reservoir is calculated according to the health degree calculation result of each sub-project of the small reservoir; a degradation model based on a small reservoir health degree index is constructed by using a nonlinear Wiener process, a small reservoir residual life probability density function is deduced, and a small reservoir residual life value can be obtained more accurately.

The invention discloses a method for predicting the residual life of a reinforced concrete bridge based on monitoring data, and belongs to the technical field of bridge life prediction. The method comprises the steps of obtaining a residual life prediction result of a target bridge before reinforcement, and obtaining a reinforcement scheme and a predicted life prolonging effect adopted when the target bridge is reinforced; determining a plurality of to-be-monitored key parameter types through the reinforcement scheme, and generating a corresponding monitoring scheme according to the plurality of key parameter types for deployment of monitoring equipment to complete acquisition of key parameters; and acquiring a key parameter standard value corresponding to the predicted life prolonging effect during numerical simulation, performing numerical comparison on the key parameter standard value and a plurality of acquired key parameters, correcting the predicted life prolonging effect according to a comparison result, and prolonging a residual life prediction result according to a correction result to obtain the residual life of the reinforced concrete bridge. The method can reduce the dependence on the finite element model during prediction of the residual life of the reinforced concrete bridge.

The invention relates to the technical field of steel formwork detection, in particular to a method and device for predicting the remaining life of a steel formwork. The method comprises the following steps: acquiring image data of a steel template, dividing the image data of the steel template to obtain sub-image data of a plurality of steel templates, acquiring steel template mechanical data corresponding to the sub-image data of each steel template, performing feature extraction on the sub-image data of the plurality of steel templates to obtain a plurality of surface feature data, and calculating the surface feature data of the plurality of steel templates according to the surface feature data. Performing feature extraction on the mechanical data to obtain multiple pieces of mechanical feature data; carrying out feature fusion on each piece of surface feature data and the corresponding mechanical feature data to obtain a plurality of sub-fusion features, carrying out feature fusion on each sub-fusion feature according to an application influence factor to obtain a fusion feature matrix, and inputting the fusion feature matrix into a preset steel template residual life prediction model to obtain a prediction result of the residual life of the steel template. And obtaining the residual life of the steel template. By means of the configuration mode, the residual life of the steel formwork can be accurately predicted.

A method of estimating a remaining life span of a driver for driving a load, wherein said driver comprises a power stage arranged for receiving an input voltage and for providing an output to said load, wherein said method comprises the steps of receiving, by a state observer model, a temperature value related to said driver, and receiving a loss value related to a power loss of said driver, determining, by said state observer model, estimated internal states representing component temperature dynamics based on said received temperature value and said received loss value making use of an observer model for mimicking a thermal behavior of said driver, providing, by said state observer model, estimated temperatures of a plurality of electrical components in said driver based on said estimated internal states representing component temperature dynamics using a component matrix, and estimating, by a life span model, said remaining life span of said driver based on said estimated temperatures.

The invention discloses a residual life prediction method and system for an engineering mechanical structural member. The method comprises the steps that S1, a multi-dimensional original data set of the mechanical structural member is collected through a multi-source sensor; s2, performing time-frequency domain feature extraction based on multi-dimensional original data set matching in combination with the inherent frequency and the fault feature frequency, and obtaining a high-dimensional degradation feature set through wavelet packet analysis in combination with characterization damage evolution; s3, utilizing a pre-trained physical memory neural network fusion model CP-NMN to carry out adaptive dimension reduction optimization on the high-dimensional feature set, and obtaining a cross-working-condition same-dimensional health index; and S4, based on the same-dimensional health indexes, dynamically predicting the residual life by adopting a long-short-term memory network, and presetting a life threshold to realize engineering early warning, so that effective monitoring of the health state of the structural member and life prediction can be realized.

The present invention discloses a method and device for predicting the remaining life of a thin-film evaporator used in the production of Lyocell fibers, which relates to the technical field of mechanical fault diagnosis, and includes: collecting vibration data by vibration sensors in a preset area on the surface of the thin-film evaporator cylinder and performing preprocessing, and calculating the characteristic frequencies of key components; vectorially adding the vibration data of individual vibration sensors to construct a one-dimensional convolutional neural network model to obtain a characteristic curve; fitting with a plurality of high-order exponential functions to establish a remaining life characteristic curve; obtaining a data set to establish a one-dimensional convolutional neural network model for predicting the remaining life, inputting the data set into the one-dimensional convolutional neural network model to obtain a remaining life prediction model; and then using the vibration data collected in real time and the characteristic frequencies of key components after processing as the input of the prediction model. The present invention can reduce the complexity of the feature extraction network model, improve the real-time operation of the model, provide more accurate data labels, and effectively improve the accuracy of remaining life prediction.

The application relates to a rotating machine residual life prediction method and system, and belongs to the field of mechanical life prediction. The method comprises the following steps: collecting signals capable of reflecting mechanical life of a rotating machine to be measured at least at two positions, extracting one-dimensional time characteristic data from the signals capable of reflecting mechanical life by using principal component analysis pooling, training a related vector machine by using the one-dimensional time characteristic data, so that the full life cycle of the rotating machine is divided into a period without obvious failure trend and a failure tendency period; training a deep separable convolution gate recurrent unit network by using data of the failure tendency period, and predicting the residual life of the rotating machine in the failure tendency period. The application can improve the prediction accuracy when the residual service life of the rotating machine is predicted.

The invention discloses a klystron residual life prediction system and a klystron residual life prediction method, belongs to the technical field of electron linear accelerators, and aims to solve the problems that no method for predicting the klystron residual life exists, maintenance and replacement are often carried out when the klystron cannot work suddenly, and stocking / replacement of the klystron needs a quite long time, so that the klystron is inconvenient to use. The system comprises a data acquisition unit, a data transmission unit, a data storage unit, a data operation unit and a data output unit. By collecting and analyzing the key operation data of the klystron, the residual life of the klystron can be predicted more accurately, and maintenance or replacement plan errors caused by inaccurate prediction are avoided; by making a maintenance or replacement plan in advance, the shutdown time of equipment caused by sudden failure of the klystron can be shortened, so that economic loss caused by shutdown is reduced, and meanwhile, reasonable spare part inventory management can also avoid extra cost caused by insufficient spare parts or untimely replacement.

The invention provides a consumable service life processing method and device, equipment and a storage medium, and belongs to the technical field of data processing and big data. The method comprises the following steps: in response to execution of a consumable service life determination process, obtaining model information, consumable work order information, accumulated water consumption, water outlet flow and a feedback score of a target water purifier; determining expected life according to the model information and the consumable work order information; according to the consumable work order information, the accumulated water consumption, the water outlet flow and the feedback score, the service life is determined; if the expected life is greater than the used life, calculating a difference value between the expected life and the used life; according to the difference value and the consumable work order information, residual life prompt information is generated; outputting residual life prompt information; if the expected service life is smaller than or equal to the used service life, consumable replacement prompt information is output. According to the method, the problem that the accuracy of a judgment mode for judging whether the consumables need to be replaced or not is low is solved.

To provide a creep life prediction method and a creep life prediction device that can simply and accurately predict the remaining life of a target steel material regardless of the properties of the target steel material.SOLUTION: A creep life prediction method includes: a first nondestructive damage degree identifying step of using a nondestructive evaluation method to identify, as a first nondestructive creep damage degree, a creep damage degree of a target steel material subjected to remaining life prediction at a first time; a first rupture time identifying step for identifying, as a first Larson-Miller rupture time, a creep rupture time of the target steel material at the first time by applying, to a regression equation prescribed by the Larson-Miller method, a first stress imparted to the target steel material until the first time and a first temperature of the target steel material until the first time; and a degree-of-divergence identifying step for identifying a degree of divergence which is a correction value for the first Larson-Miller rupture time, on the basis of the first Larson-Miller rupture time and a first nondestructive rupture time which is a creep rupture time at the first time calculated from the first nondestructive creep damage degree.SELECTED DRAWING: Figure 4

An online intelligent prediction method for the remaining life of an aircraft structure based on acoustic emission is proposed. First, fatigue experiments are conducted on the aircraft structure to obtain raw data of multiple full-life acoustic emission waveform streams. Then, the raw data undergoes sliding window sampling feature extraction, and the parts with good monotonicity are selected to construct health indicators. A portion is randomly selected as the test set, and the remainder is used as the training set. The dataset is then segmented according to the 3σ principle to find the starting prediction point. Finally, in the testing phase, the test set data is input into the trained life prediction model to achieve online intelligent prediction of the remaining life of the aircraft structure. This invention utilizes a combination of DenseNet and contrastive learning to predict the remaining life of the aircraft structure online using intelligent algorithms, achieving good prediction results.

The present invention provides an adaptive prediction method and device for the remaining life of bearings of coal mine machinery and equipment, belonging to the technical field of bearing remaining life prediction; solves the problem of how to more accurately predict the development rate of bearing damage and the remaining life of the bearing after a bearing fault is detected; comprises the following steps: collecting the vibration signal and rotation speed of the bearing, sequentially calculating the bearing vibration characteristic-energy level and energy level; smoothing the bearing vibration characteristic-energy level and energy level; sequentially calculating the actual damage degree of the bearing based on the smoothed vibration characteristic-energy level and energy level; updating the model parameters of the bearing physical model based on the deviation between the actual damage degree of the bearing and the bearing damage degree predicted by the bearing physical model; and providing a prediction of the bearing damage degree and the remaining life of the bearing based on the updated model parameters of the bearing physical model; the present invention is applied to the prediction of the remaining life of the bearing.

This invention discloses a method for predicting the remaining life of brake friction pads, belonging to the field of brake life prediction. The method includes the following steps: S1, obtaining an initial effective feature set based on Pearson correlation coefficient and strong wear correlation features; S2, constructing a multi-physics coupled nonlinear wear degradation model for the friction pads and outputting multi-physics degradation parameters; S3, obtaining the optimal low-dimensional feature set through dual-source fusion; S4, optimizing the hyperparameters of the hybrid basis learner group using a dynamically perturbed improved gray wolf algorithm; S5, constructing a weighted fusion remaining life prediction model and completing accuracy evaluation and error correction; S6, online adaptive updating to achieve real-time remaining life prediction and life threshold warning. Using the above-mentioned method for predicting the remaining life of brake friction pads, high-precision prediction of the entire life cycle of brake friction pads through online dynamic adaptive updating is achieved, significantly improving prediction reliability and engineering application value.

A server (2) acquires first data related to a load applied to a vehicle body of an electrically powered mobile body, acquires second data related to operation of a battery (14) mounted on the mobile body, calculates a remaining life of the vehicle body based on the first data, calculates a remaining life of the battery based on the second data, compares the remaining life of the vehicle body with the remaining life of the battery (14), and in a case where the remaining life of the vehicle body is shorter than the remaining life of the battery (14), instructs at least one of activation of a function that is not used among a plurality of functions using electric power in the mobile body and performance improvement of a function that is being used.

The present invention relates to an excavator. To solve the problem of unbalanced operation of the two oil pumps in an excavator with a dual-pump configuration, the present invention constructs a hydraulic oil supply control system, method, control device, and excavator. The control system includes a first oil pump, a first main valve, a third main valve, a second oil pump, and a second main valve whose oil inlet is connected to the second oil pump. The first main valve and the third main valve oil inlet are both connected to the first oil pump. The control system also includes: an oil supply distribution valve connected between the oil inlet of the third main valve and the second oil pump for controlling the on-off of the oil supply line between the third main valve and the second oil pump; a detection device for detecting the life parameters of the oil pumps; a controller for calculating the remaining life value of the corresponding oil pumps based on the life parameters; and controlling the displacement of each oil pump and the on-off of the oil supply distribution valve based on the remaining life value of the oil pumps when the third main valve is switched. The present invention realizes oil supply coordination between the two pumps, achieves balanced operation of the two pumps, and prevents premature excessive wear and failure of one pump.

The invention discloses an ICEEMDAN-ISOMAP-Transform-based method for predicting the residual life of an intelligent barrier machine of a highway toll station. The method comprises the following steps: 1, collecting vibration signals of a bearing in the intelligent barrier machine in the vertical direction and the horizontal direction; 2, the stability and accuracy of signal decomposition are improved through an ICEEMDAN algorithm; 3, performing time domain and frequency domain feature extraction work on the denoised vibration signals; 4, performing feature dimensionality reduction and reconstruction on the multi-dimensional time domain and frequency domain features by adopting an ISOMAP algorithm; and 5, taking the dimensionality-reduced and reconstructed features as the input of a Transform model, and realizing the prediction of the residual life of the intelligent barrier machine through model training. According to the method, how to establish the nonlinear relation between the original vibration signal and the residual life curve of the intelligent barrier machine is emphatically considered from the data driving direction, especially the work of signal noise reduction and multi-dimensional feature reconstruction, and the prediction performance of the Transform model can be greatly improved.