CN117034123B - Fault monitoring system and method for fitness equipment - Google Patents
Fault monitoring system and method for fitness equipment Download PDFInfo
- Publication number
- CN117034123B CN117034123B CN202311089633.XA CN202311089633A CN117034123B CN 117034123 B CN117034123 B CN 117034123B CN 202311089633 A CN202311089633 A CN 202311089633A CN 117034123 B CN117034123 B CN 117034123B
- Authority
- CN
- China
- Prior art keywords
- time sequence
- matrix
- full
- parameter full
- scale parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000011159 matrix material Substances 0.000 claims abstract description 144
- 239000013598 vector Substances 0.000 claims abstract description 93
- 230000011218 segmentation Effects 0.000 claims abstract description 21
- 238000013527 convolutional neural network Methods 0.000 claims description 35
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000007257 malfunction Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000004199 lung function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 230000036642 wellbeing Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
A fault monitoring system for exercise equipment and a method thereof are disclosed. Firstly, arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of a plurality of preset time points into parameter full-time-sequence input matrixes according to time dimensions and sample dimensions, then obtaining an optimized multi-scale parameter full-time-sequence incidence matrix through a multi-scale sensor, then, carrying out feature matrix segmentation on the optimized multi-scale parameter full-time-sequence incidence matrix to obtain a plurality of parameter time-sequence incidence sub-matrixes, then, passing the plurality of parameter time-sequence incidence sub-matrixes through a context encoder to obtain classification feature vectors, and finally, passing the classification feature vectors through a classifier to obtain classification results for indicating whether faults exist in monitored fitness equipment. Thus, the faults of the fitness equipment can be accurately monitored in real time.
Description
Technical Field
The application relates to the field of intelligent monitoring, in particular to a fault monitoring system and a fault monitoring method for fitness equipment.
Background
With the improvement of health consciousness and living standard of modern society, body building becomes an increasingly popular living mode. The exercise machine is a device for exercising the body and improving the level of well-being, which can help people to strengthen heart and lung functions, build muscles, reduce weight, relieve stress, etc.
Exercise equipment may fail after prolonged operation and use, such as mechanical wear, electrical circuit failure, etc. Timely discovery and resolution of these faults is critical to maintaining normal use of exercise equipment and ensuring user safety. The traditional body-building equipment fault monitoring method is usually to diagnose faults by periodically observing, overhauling, hearing, distinguishing or manually setting threshold comparison by a user, but the method has the problems of low timeliness and high misjudgment rate.
Accordingly, an optimized fitness equipment failure monitoring system is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a fault monitoring system and a fault monitoring method for fitness equipment, which can accurately monitor the faults of the fitness equipment in real time.
According to one aspect of the present application, there is provided a fault monitoring system for exercise equipment, comprising: the data acquisition module is used for acquiring temperature values, current values, voltage values, vibration amplitude values and noise values of the monitored fitness equipment at a plurality of preset time points in a preset time period; the parameter full-time distribution module is used for arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of the plurality of preset time points into a parameter full-time input matrix according to the time dimension and the sample dimension; the parameter full-time sequence correlation characteristic extraction module is used for enabling the parameter full-time sequence input matrix to pass through a multi-scale sensor comprising a first convolutional neural network and a second convolutional neural network so as to obtain an optimized multi-scale parameter full-time sequence correlation matrix; the matrix segmentation module is used for carrying out feature matrix segmentation on the optimized multi-scale parameter full-time sequence incidence matrix to obtain a plurality of parameter time sequence incidence sub-matrices; the context global semantic association module is used for enabling the plurality of parameter time sequence association submatrices to pass through a context encoder based on a converter to obtain classification feature vectors; and the fault detection module is used for passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored fitness equipment has faults or not.
According to another aspect of the present application, there is provided a fault monitoring method of an exercise apparatus, comprising: acquiring temperature values, current values, voltage values, vibration amplitude values and noise values of the monitored fitness equipment at a plurality of preset time points in a preset time period; arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of the plurality of preset time points into a parameter full-time input matrix according to the time dimension and the sample dimension; the parameter full-time sequence input matrix passes through a multi-scale sensor comprising a first convolutional neural network and a second convolutional neural network to obtain an optimized multi-scale parameter full-time sequence incidence matrix; performing feature matrix segmentation on the optimized multi-scale parameter full-time sequence incidence matrix to obtain a plurality of parameter time sequence incidence submatrices; passing the plurality of parameter timing correlation sub-matrices through a converter-based context encoder to obtain a classification feature vector; and passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored fitness equipment has faults or not.
Compared with the prior art, the fault monitoring system and the fault monitoring method for the fitness equipment provided by the application have the advantages that firstly, the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values at a plurality of preset time points are arranged into parameter full-time input matrixes according to the time dimension and the sample dimension, then, an optimized multi-scale parameter full-time correlation matrix is obtained through a multi-scale sensor, then, feature matrix segmentation is carried out on the optimized multi-scale parameter full-time correlation matrix to obtain a plurality of parameter time sequence correlation sub-matrixes, then, the plurality of parameter time sequence correlation sub-matrixes are subjected to a context encoder to obtain classification feature vectors, and finally, the classification feature vectors are subjected to a classifier to obtain classification results for indicating whether faults exist in the monitored fitness equipment. Thus, the faults of the fitness equipment can be accurately monitored in real time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art. The following drawings are not intended to be drawn to scale, emphasis instead being placed upon illustrating the principles of the application.
Fig. 1 is a block diagram schematic of a fault monitoring system for exercise equipment according to an embodiment of the present application.
Fig. 2 is a block diagram schematic of the parameter full-time correlated feature extraction module in a fault monitoring system of exercise equipment according to an embodiment of the present application.
Fig. 3 is a block diagram schematic of the optimization unit in the fault-monitoring system of the exercise apparatus according to an embodiment of the present application.
Fig. 4 is a block diagram schematic of the fault detection module in the fault monitoring system of the exercise apparatus according to an embodiment of the present application.
Fig. 5 is a flow chart of a fault monitoring method of exercise equipment according to an embodiment of the present application.
Fig. 6 is a schematic diagram of a system architecture of a fault monitoring method of exercise equipment according to an embodiment of the present application.
Fig. 7 is an application scenario diagram of a failure monitoring system for exercise equipment according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are also within the scope of the application.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As noted above, exercise equipment may fail after prolonged operation and use, such as mechanical wear, electrical circuit failure, and the like. Timely discovery and resolution of these faults is critical to maintaining normal use of exercise equipment and ensuring user safety. The traditional body-building equipment fault monitoring method is usually to diagnose faults by periodically observing, overhauling, hearing, distinguishing or manually setting threshold comparison by a user, but the method has the problems of low timeliness and high misjudgment rate. Accordingly, an optimized fitness equipment failure monitoring system is desired.
Accordingly, considering that in the actual use process of the exercise equipment, in order to ensure the use effect and safety of the exercise equipment, the fault of the exercise equipment needs to be monitored in real time, and in the fault monitoring of the exercise equipment, the key is to monitor the running state of the exercise equipment, which can be comprehensively determined through analysis of the temperature value, the current value, the voltage value, the vibration amplitude value and the noise value of the exercise equipment. This is because parameters such as temperature, current, voltage, vibration amplitude, noise, etc. can reflect the workload, wear level, and other potential problems of the exercise apparatus in actual operation, and play a vital role in accurately judging the health status of the exercise apparatus. However, since the parameter data have a time sequence cooperative association relationship, and the time sequence cooperative association characteristic presents different association modes under different time sequence periods. Therefore, in the process, the difficulty is how to fully express the time sequence collaborative dynamic association characteristic information of the temperature value, the current value, the voltage value, the vibration amplitude value and the noise value of the fitness equipment, so as to accurately monitor the faults of the fitness equipment in real time, thereby ensuring the use effect and the safety of the fitness equipment.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. The development of deep learning and neural networks provides a new solution idea and scheme for mining time sequence collaborative dynamic association characteristic information of temperature values, current values, voltage values, vibration amplitude values and noise values of the fitness equipment.
Fig. 1 is a block diagram schematic of a fault monitoring system for exercise equipment according to an embodiment of the present application. As shown in fig. 1, a fault monitoring system 100 of exercise equipment according to an embodiment of the present application includes: the data acquisition module 110 is used for acquiring temperature values, current values, voltage values, vibration amplitude values and noise values of the monitored fitness equipment at a plurality of preset time points in a preset time period; the parameter full-time distribution module 120 is configured to arrange the temperature values, the current values, the voltage values, the vibration amplitude values, and the noise values at the plurality of predetermined time points into a parameter full-time input matrix according to a time dimension and a sample dimension; the parameter full-time sequence correlation feature extraction module 130 is configured to pass the parameter full-time sequence input matrix through a multi-scale sensor including a first convolutional neural network and a second convolutional neural network to obtain an optimized multi-scale parameter full-time sequence correlation matrix; the matrix segmentation module 140 is configured to perform feature matrix segmentation on the optimized multi-scale parameter full-time sequence incidence matrix to obtain a plurality of parameter time sequence incidence submatrices; a context global semantic association module 150, configured to pass the plurality of parameter timing association sub-matrices through a context encoder based on a converter to obtain a classification feature vector; and a fault detection module 160, configured to pass the classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether the monitored fitness equipment has a fault.
More specifically, in an embodiment of the present application, the data acquisition module 110 is configured to acquire a temperature value, a current value, a voltage value, a vibration amplitude value, and a noise value of the monitored fitness equipment at a plurality of predetermined time points within a predetermined period of time. In the use process of the fitness equipment in practice, in order to ensure the use effect and the safety of the fitness equipment, the faults of the fitness equipment need to be monitored in real time, and the running state of the fitness equipment can be monitored when the faults of the fitness equipment are monitored, so that the running state can be comprehensively judged by analyzing the temperature value, the current value, the voltage value, the vibration amplitude value and the noise value of the fitness equipment.
In one particular example, the data acquisition module may include a sensor, a data collector, and a communication module. The sensor is used for acquiring a temperature value, a current value, a voltage value, a vibration amplitude value and a noise value of the fitness equipment, and specifically, the temperature sensor, the current sensor, the voltage sensor, the vibration sensor and the noise sensor can be respectively adopted to acquire the data. The temperature value refers to the temperature of the fitness equipment, and can be acquired by using a temperature sensor. During the use process of the body-building equipment, heat is generated due to friction, motor work and other reasons, the change of the temperature value can reflect the working state of the body-building equipment, for example, when the temperature value is too high, the body-building equipment can be indicated to have the problems of overload or failure and the like; the current value refers to the current of the exercise equipment, the electric energy is required to be consumed when the exercise equipment works, the change of the current value can reflect the load condition of the exercise equipment, for example, when the current value is overlarge, the problems of overload or fault and the like of the exercise equipment can be described; the voltage value refers to the voltage of the exercise equipment, the voltage can be acquired by using a voltage sensor, the exercise equipment needs to be supplied with electric energy when in work, the change of the voltage value can reflect the power supply condition of the exercise equipment, for example, when the voltage value is too low, the problem that the exercise equipment has insufficient power supply or faults and the like can be described; the vibration amplitude value refers to the vibration of the fitness equipment, the vibration sensor can be used for collecting the vibration, the fitness equipment can vibrate during working, and the change of the vibration amplitude value can reflect the motion state of the fitness equipment. For example, when the vibration amplitude value is too large, it may be indicated that there is an imbalance or malfunction of the exercise apparatus; the noise value is the noise of the fitness equipment, the noise can be acquired by using the sound sensor, the noise can be generated when the fitness equipment works, the change of the noise value can reflect the working state of the fitness equipment, for example, when the noise value is overlarge, the problem that the fitness equipment has faults or needs maintenance and the like can be described. Further, the data collector is used for processing and storing the data collected by the sensor. The communication module is used for transmitting the acquired data to the monitoring system, and can support various communication protocols such as Wi-Fi, bluetooth, 4G and the like.
Accordingly, firstly, a preset time period is set in a monitoring system, and a time range needing to be monitored is determined; setting a plurality of preset time points in a preset time period, and determining the time points to be monitored; then, the sensor is arranged at key parts of the body-building equipment, such as a motor, a bearing, a gear and the like, so as to acquire the most accurate data; then, connecting the data collector with the sensor so as to collect the data collected by the sensor; setting acquisition parameters such as acquisition frequency, acquisition time and the like in the data acquisition device; and finally, transmitting the acquired data to a monitoring system through a communication module so as to analyze and process the data.
More specifically, in the embodiment of the present application, the parameter full-time distribution module 120 is configured to arrange the temperature values, the current values, the voltage values, the vibration amplitude values, and the noise values at the plurality of predetermined time points into a parameter full-time input matrix according to a time dimension and a sample dimension. Since there is a cooperative correlation characteristic in the time dimension between the temperature value, the current value, the voltage value, the vibration amplitude value and the noise value of the exercise apparatus, that is, there is a mutual influence between these parameter data. Therefore, in order to accurately detect the working state of the exercise equipment, thereby improving the evaluation accuracy of the faults of the exercise equipment, in the technical scheme of the application, the temperature value, the current value, the voltage value, the vibration amplitude value and the noise value of the plurality of preset time points are further arranged into a parameter full-time input matrix according to the time dimension and the sample dimension, so that the time distribution information of the temperature value, the current value, the voltage value, the vibration amplitude value and the noise value of the exercise equipment in the time dimension and the sample dimension is integrated.
Accordingly, in one specific example, the parameter full-time distribution module 120 is configured to: and arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of the plurality of preset time points into parameter full-time sequence input row vectors according to the time dimension or the sample dimension, and then performing two-dimensional arrangement to obtain the parameter full-time sequence input matrix.
More specifically, in the embodiment of the present application, the parameter full-time-sequence correlation feature extraction module 130 is configured to pass the parameter full-time-sequence input matrix through a multi-scale sensor including a first convolutional neural network and a second convolutional neural network to obtain an optimized multi-scale parameter full-time-sequence correlation matrix. Because the temperature value, the current value, the voltage value, the vibration amplitude value and the noise value of the exercise equipment have volatility and uncertainty in the time dimension and have relevance among various parameter data, the temperature value, the current value, the voltage value, the vibration amplitude value and the noise value of the exercise equipment have different relevant characteristic information under different time period spans and different data type spans. Based on the above, in the technical scheme of the application, the parameter full-time sequence input matrix is further passed through a multi-scale sensor comprising a first convolutional neural network and a second convolutional neural network to obtain an optimized multi-scale parameter full-time sequence correlation matrix. In particular, the first convolutional neural network and the second convolutional neural network adopt two-dimensional convolutional kernels with different scales to perform characteristic mining of the parameter full-time sequence input matrix so as to extract multi-scale time sequence collaborative dynamic association characteristic information between a temperature value, a current value, a voltage value, a vibration amplitude value and a noise value of the fitness equipment under different parameter types and different time spans.
Accordingly, in one specific example, as shown in fig. 2, the parameter full-time sequence correlation feature extraction module 130 includes: a first scale parameter time sequence correlation unit 131, configured to pass the parameter full time sequence input matrix through a first convolutional neural network of the multi-scale sensor to obtain a first scale parameter full time sequence correlation matrix; a second scale parameter time sequence correlation unit 132, configured to pass the parameter full time sequence input matrix through a second convolutional neural network of the multi-scale sensor to obtain a second scale parameter full time sequence correlation matrix, where the first convolutional neural network and the second convolutional neural network respectively use two-dimensional convolutional kernels with different scales; the correlation characteristic fusion unit 133 is configured to fuse the first scale parameter full-time-sequence correlation matrix and the second scale parameter full-time-sequence correlation matrix to obtain the multi-scale parameter full-time-sequence correlation matrix; and an optimizing unit 134, configured to optimize the multi-scale parameter full-time sequence correlation matrix to obtain the optimized multi-scale parameter full-time sequence correlation matrix.
Accordingly, in a specific example, the first scale parameter timing association unit 131 is configured to: and respectively carrying out two-dimensional convolution processing, feature matrix-based mean value pooling processing and nonlinear activation processing on input data in forward transmission of layers by using each layer of a first convolution neural network of the multi-scale sensor so as to output a first scale parameter full-time sequence correlation matrix by the last layer of the first convolution neural network of the multi-scale sensor, wherein the input of the first layer of the first convolution neural network of the multi-scale sensor is the parameter full-time sequence input matrix.
It should be appreciated that convolutional neural network (Convolutional Neural Network, CNN) is an artificial neural network and has wide application in the fields of image recognition, etc. The convolutional neural network can comprise an input layer, a hidden layer and an output layer, wherein the hidden layer can comprise a convolutional layer, a pooling (pooling) layer, an activation layer, a full connection layer and the like, the upper layer carries out corresponding operation according to input data, an operation result is output to the next layer, and a final result is obtained after the input initial data is subjected to multi-layer operation.
Accordingly, in a specific example, the association feature fusion unit includes: fusing the first scale parameter full-time sequence incidence matrix and the second scale parameter full-time sequence incidence matrix by a fusion formula to obtain the multi-scale parameter full-time sequence incidence matrix, wherein the fusion formula is as follows: wherein/> For the multi-scale parameter full-time sequence incidence matrix,/>For the first scale parameter full-time sequence association matrix,/>For the second scale parameter full time sequence incidence matrix,/>Representing the addition of elements at corresponding positions of the first scale parameter full-time sequence incidence matrix and the second scale parameter full-time sequence incidence matrix,/>And/>Is a weighting parameter for controlling the balance between the first scale parameter full-time-sequence correlation matrix and the second scale parameter full-time-sequence correlation matrix.
Accordingly, in a specific example, as shown in fig. 3, the optimizing unit 134 includes: a matrix expansion subunit 1341, configured to expand the multi-scale parameter full-time sequence correlation matrix into a multi-scale parameter full-time sequence correlation vector; a search optimization subunit 1342, configured to perform weight space fine granularity density prediction search optimization on the multi-scale parameter full-time sequence correlation vector to obtain an optimized multi-scale parameter full-time sequence correlation vector; and a dimension reconstruction subunit 1343, configured to perform dimension reconstruction on the optimized multi-scale parameter full-time sequence correlation vector to obtain the optimized multi-scale parameter full-time sequence correlation matrix.
In the technical scheme of the application, when the parameter full-time-sequence input matrix is obtained through a multi-scale sensor comprising a first convolutional neural network and a second convolutional neural network, the characteristic expression super-resolution of the parameter time sequence-sample local cross-correlation characteristic corresponding to the multi-scale parameter full-time-sequence input matrix is obtained through the first convolutional neural network and the second convolutional neural network respectively, and each characteristic value is obtained by extracting the local time sequence-sample cross-dimension correlation characteristic under the convolutional kernel scale based on the two-dimensional convolutional kernel of the convolutional neural network, so that the first scale parameter full-time-sequence correlation matrix and the second scale parameter full-time-sequence correlation matrix have the characteristic expression super-resolution of the parameter time sequence-sample local cross-correlation characteristic corresponding to the two-dimensional convolutional kernel scale, and therefore, the multi-scale parameter full-time-sequence correlation matrix obtained through fusion of the first scale parameter full-time-sequence correlation matrix and the second scale parameter full-time-sequence correlation matrix also has the multi-dimensional space correlation characteristic under different scale conditions, and thus the expected performance of the multi-scale correlation matrix is improved, and the performance of the multi-scale parameter full-time-sequence correlation matrix is expressed based on the expected performance of the characteristic expression. Therefore, the application performs iterative optimization on the multi-scale parameter full-time sequence correlation matrix, specifically, in each iteration, the multi-scale parameter full-time sequence correlation vector obtained after the multi-scale parameter full-time sequence correlation matrix is expanded is recorded asAnd carrying out fine granularity density prediction search optimization of a weight space, wherein the fine granularity density prediction search optimization is expressed as follows: And/> The optimization matrices of the last and the current iteration are parameter matrices set by adopting different initialization strategies in the iteration process respectively, (e.g./>Set as identity matrix/>Set as the mean diagonal matrix of the feature vectors to be classified),/>Is the multi-scale parameter full-time sequence association vector,/>Is the first iterative feature vector,/>Is a second iterative feature vector,/>And/>Respectively represent feature vectors/>AndAnd/>Is a bias vector, e.g. initially set as a unit vector, and/>Representing the optimized multi-scale parameter full-time sequence associated vector, wherein the iteration end can be set as the multi-scale parameter full-time sequence associated vector before and after iterationAnd/>Cosine similarity between them is smaller than a predetermined threshold,/>Representing a minimum function,/>Representing matrix multiplication,/>Representing the per-position dot multiplication of vectors,/>Representing vector addition.
Here, a full-time sequence correlation vector for the multi-scale parameterSuper-resolution representation characteristics in multi-dimensional context, fine-grained density predictive search optimization of the weight space can be performed by the multi-scale parameter full-time sequence correlation vector/>Feed-forward serialization mapping of vector space of (c) while providing a corresponding fine-grained weight search strategy for dense prediction tasks within a weight search space, reducing the multi-scale parametric full-time-series correlation vector/>, within the weight search spaceAnd (overall sequential complexity) and performing dimension reconstruction on the optimized multi-scale parameter full-time sequence correlation vector to obtain the optimized multi-scale parameter full-time sequence correlation matrix, thereby improving the characteristic expression effect of the multi-scale parameter full-time sequence correlation matrix.
More specifically, in the embodiment of the present application, the matrix splitting module 140 is configured to perform feature matrix splitting on the optimized multi-scale parameter full-time-sequence correlation matrix to obtain a plurality of parameter time-sequence correlation sub-matrices. Considering that the convolutional neural network can extract time sequence collaborative correlation characteristic information among various parameter data of the fitness equipment, the pure CNN method is difficult to learn clear global and remote semantic information interaction due to inherent limitation of convolutional operation. Therefore, in the technical scheme of the application, after the feature matrix segmentation is further performed on the optimized multi-scale parameter full-time sequence incidence matrix to obtain a plurality of parameter time sequence incidence sub-matrices, the plurality of parameter time sequence incidence sub-matrices are encoded in a context encoder based on a converter to extract global context semantic incidence feature information of multi-scale time sequence collaborative dynamic incidence features among a temperature value, a current value, a voltage value, a vibration amplitude value and a noise value of the fitness equipment so as to obtain a classification feature vector.
It should be understood that feature matrix slicing refers to the process of dividing a large feature matrix into multiple small sub-matrices. In machine learning, it is often necessary to divide a data set into multiple parts, such as a training set, a validation set, and a test set, in order to train, validate, and test a model. Before these operations are performed, the raw data set needs to be feature matrix segmented for finer processing and management of the data. The feature matrix segmentation may be based on a variety of methods, such as, for example, segmentation by row, segmentation by column, segmentation by block, etc. Wherein, the row-wise segmentation refers to the step of dividing the feature matrix according to the row, wherein each submatrix comprises the same number of rows; column-wise splitting refers to splitting the feature matrix column-wise, wherein each submatrix comprises the same number of columns; the block segmentation refers to the segmentation of the feature matrix according to a fixed-size block, and each sub-matrix contains the same number of rows and columns. The feature matrix segmentation can effectively improve the efficiency and accuracy of data processing, especially when processing large-scale data sets.
More specifically, in an embodiment of the present application, the context global semantic association module 150 is configured to pass the plurality of parameter timing association submatrices through a context encoder based on a converter to obtain a classification feature vector.
Accordingly, in one specific example, the contextual global semantic association module 150 is configured to: expanding the plurality of parameter time sequence correlation sub-matrices into a plurality of parameter time sequence correlation sub-feature vectors; passing the plurality of parameter timing related sub-feature vectors through the converter-based context encoder to obtain a plurality of parameter timing semantic feature vectors; and cascading the plurality of parameter timing semantic feature vectors to obtain the classification feature vector.
More specifically, in an embodiment of the present application, the fault detection module 160 is configured to pass the classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether the monitored fitness equipment has a fault. That is, in the technical solution of the present application, the labels of the classifier include that the monitored fitness equipment has a fault (first label) and that the monitored fitness equipment has no fault (second label), wherein the classifier determines to which classification label the classification feature vector belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a human-defined concept, and in fact, during the training process, the computer model does not have a concept of "whether the monitored exercise equipment has a fault", which is simply two kinds of classification tags, and the probability that the output characteristic is the sum of the two classification tags sign, i.e., p1 and p2 is one. Therefore, the classification result of whether the monitored fitness equipment has faults is actually converted into the classified probability distribution conforming to the classification rule of the natural law through classifying the labels, and the physical meaning of the natural probability distribution of the labels is essentially used instead of the language text meaning of whether the monitored fitness equipment has faults. It should be understood that, in the technical scheme of the application, the classification label of the classifier is a detection evaluation label for detecting whether the monitored fitness equipment has faults, so that after the classification result is obtained, fault monitoring of the fitness equipment can be performed based on the classification result, thereby ensuring the use effect and safety of the fitness equipment.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
Accordingly, in one specific example, as shown in fig. 4, the fault detection module 160 includes: a full-connection encoding unit 161, configured to perform full-connection encoding on the classification feature vector by using a plurality of full-connection layers of the classifier to obtain an encoded classification feature vector; and a classification unit 162, configured to pass the encoded classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In summary, the fault monitoring system 100 of the exercise apparatus according to the embodiment of the present application is illustrated, firstly, the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values at the predetermined time points are arranged as parameter full-time input matrices according to the time dimension and the sample dimension, then an optimized multi-scale parameter full-time correlation matrix is obtained through a multi-scale sensor, then feature matrix segmentation is performed on the optimized multi-scale parameter full-time correlation matrix to obtain a plurality of parameter time-sequence correlation sub-matrices, then the plurality of parameter time-sequence correlation sub-matrices are passed through a context encoder to obtain classification feature vectors, and finally the classification feature vectors are passed through a classifier to obtain classification results for indicating whether the monitored exercise apparatus has faults. Thus, the faults of the fitness equipment can be accurately monitored in real time.
As described above, the fault monitoring system 100 for exercise equipment according to an embodiment of the present application may be implemented in various terminal devices, such as a server or the like having a fault monitoring algorithm for exercise equipment according to an embodiment of the present application. In one example, the fault monitoring system 100 of exercise equipment in accordance with embodiments of the present application may be integrated into the terminal device as a software module and/or hardware module. For example, the fault-monitoring system 100 of exercise equipment in accordance with embodiments of the present application may be a software module in the operating system of the terminal device or may be an application developed for the terminal device; of course, the fault-monitoring system 100 of exercise equipment according to embodiments of the present application can also be one of a number of hardware modules of the terminal device.
Alternatively, in another example, the fault-monitoring system 100 of the exercise apparatus according to an embodiment of the present application and the terminal device may be separate devices, and the fault-monitoring system 100 of the exercise apparatus may be connected to the terminal device through a wired and/or wireless network and transmit interactive information in a agreed data format.
Fig. 5 is a flow chart of a fault monitoring method of exercise equipment according to an embodiment of the present application. Fig. 6 is a schematic diagram of a system architecture of a fault monitoring method of exercise equipment according to an embodiment of the present application. As shown in fig. 5 and 6, a fault monitoring method of an exercise apparatus according to an embodiment of the present application includes: s110, acquiring temperature values, current values, voltage values, vibration amplitude values and noise values of the monitored fitness equipment at a plurality of preset time points in a preset time period; s120, arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of the plurality of preset time points into a parameter full-time input matrix according to a time dimension and a sample dimension; s130, the parameter full-time sequence input matrix passes through a multi-scale sensor comprising a first convolutional neural network and a second convolutional neural network to obtain an optimized multi-scale parameter full-time sequence incidence matrix; s140, feature matrix segmentation is carried out on the optimized multi-scale parameter full-time sequence incidence matrix so as to obtain a plurality of parameter time sequence incidence sub-matrices; s150, the plurality of parameter time sequence association submatrices pass through a context encoder based on a converter to obtain classification feature vectors; and S160, passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored fitness equipment has faults or not.
In a specific example, in the fault monitoring method of the exercise apparatus, the arranging the temperature values, the current values, the voltage values, the vibration amplitude values, and the noise values at the plurality of predetermined time points into the parameter full-time input matrix according to the time dimension and the sample dimension includes: and arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of the plurality of preset time points into parameter full-time sequence input row vectors according to the time dimension or the sample dimension, and then performing two-dimensional arrangement to obtain the parameter full-time sequence input matrix.
Here, it will be appreciated by those skilled in the art that the specific operation of the respective steps in the above-described malfunction monitoring method of the exercise apparatus has been described in detail in the above description of the malfunction monitoring system 100 of the exercise apparatus with reference to fig. 1 to 5, and thus, repetitive descriptions thereof will be omitted.
Fig. 7 is an application scenario diagram of a failure monitoring system for exercise equipment according to an embodiment of the present application. As shown in fig. 7, in this application scenario, first, temperature values (e.g., D1 illustrated in fig. 7), current values (e.g., D2 illustrated in fig. 7), voltage values (e.g., D3 illustrated in fig. 7), vibration amplitude values (e.g., D4 illustrated in fig. 7), and noise values (e.g., D5 illustrated in fig. 7) of a monitored fitness equipment (e.g., N illustrated in fig. 7) at a plurality of predetermined time points within a predetermined period of time are acquired, and then the temperature values, current values, voltage values, vibration amplitude values, and noise values at the plurality of predetermined time points are input to a server (e.g., S illustrated in fig. 7) where a fault monitoring algorithm of the fitness equipment is deployed, wherein the server is able to process the temperature values, current values, voltage values, vibration amplitude values, and noise values at the plurality of predetermined time points using the fault monitoring algorithm to obtain a result indicating whether a fault is present in the monitored fitness equipment.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the following claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.
Claims (5)
1. A fault monitoring system for exercise equipment, comprising:
The data acquisition module is used for acquiring temperature values, current values, voltage values, vibration amplitude values and noise values of the monitored fitness equipment at a plurality of preset time points in a preset time period;
the parameter full-time distribution module is used for arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of the plurality of preset time points into a parameter full-time input matrix according to the time dimension and the sample dimension;
The parameter full-time sequence correlation characteristic extraction module is used for enabling the parameter full-time sequence input matrix to pass through a multi-scale sensor comprising a first convolutional neural network and a second convolutional neural network so as to obtain an optimized multi-scale parameter full-time sequence correlation matrix;
The matrix segmentation module is used for carrying out feature matrix segmentation on the optimized multi-scale parameter full-time sequence incidence matrix to obtain a plurality of parameter time sequence incidence sub-matrices;
the context global semantic association module is used for enabling the plurality of parameter time sequence association submatrices to pass through a context encoder based on a converter to obtain classification feature vectors; and
The fault detection module is used for passing the classification feature vector through a classifier to obtain a classification result, and the classification result is used for indicating whether the monitored fitness equipment has faults or not;
The parameter full time sequence distribution module is used for:
Arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of the plurality of preset time points into parameter full-time sequence input row vectors according to time dimension or sample dimension, and then performing two-dimensional arrangement to obtain the parameter full-time sequence input matrix;
The parameter full-time sequence associated feature extraction module comprises:
the first scale parameter time sequence correlation unit is used for enabling the parameter full time sequence input matrix to pass through a first convolution neural network of the multi-scale sensor so as to obtain a first scale parameter full time sequence correlation matrix;
The second scale parameter time sequence correlation unit is used for enabling the parameter full time sequence input matrix to pass through a second convolution neural network of the multi-scale sensor to obtain a second scale parameter full time sequence correlation matrix, wherein the first convolution neural network and the second convolution neural network respectively adopt two-dimensional convolution kernels with different scales; and
The association characteristic fusion unit is used for fusing the first scale parameter full-time sequence association matrix and the second scale parameter full-time sequence association matrix to obtain a multi-scale parameter full-time sequence association matrix;
the optimizing unit is used for optimizing the multi-scale parameter full-time sequence incidence matrix to obtain the optimized multi-scale parameter full-time sequence incidence matrix;
wherein the optimizing unit includes:
a matrix expansion subunit, configured to expand the multi-scale parameter full-time sequence correlation matrix into a multi-scale parameter full-time sequence correlation vector;
The searching and optimizing subunit is used for carrying out weight space fine granularity density prediction searching and optimizing on the multi-scale parameter full-time sequence association vector so as to obtain an optimized multi-scale parameter full-time sequence association vector; and
The dimension reconstruction subunit is used for carrying out dimension reconstruction on the optimized multi-scale parameter full-time sequence association vector so as to obtain the optimized multi-scale parameter full-time sequence association matrix;
Wherein the search optimization subunit is configured to: carrying out weight space fine granularity density prediction search optimization on the multi-scale parameter full-time sequence association vector by using the following optimization formula to obtain an optimized multi-scale parameter full-time sequence association vector;
Wherein, the optimization formula is:
，
Wherein, And/>Is the optimal matrix of last and current iteration,/>, respectivelyIs the multi-scale parameter full-time sequence association vector,/>Is the first iterative feature vector,/>Is a second iterative feature vector,/>And/>Respectively represent feature vectorsAnd/>And/>Is a bias vector,/>Representing a minimum function,/>Representing matrix multiplication,/>Representing the per-position dot multiplication of vectors,/>Representing vector addition,/>Representing the optimized multi-scale parameter full-time sequence association vector.
2. The fitness equipment fault monitoring system according to claim 1, wherein the first scale parameter timing correlation unit is configured to:
And respectively carrying out two-dimensional convolution processing, feature matrix-based mean value pooling processing and nonlinear activation processing on input data in forward transmission of layers by using each layer of a first convolution neural network of the multi-scale sensor so as to output a first scale parameter full-time sequence correlation matrix by the last layer of the first convolution neural network of the multi-scale sensor, wherein the input of the first layer of the first convolution neural network of the multi-scale sensor is the parameter full-time sequence input matrix.
3. The fitness equipment fault monitoring system of claim 2, wherein the contextual global semantic association module is configured to:
Expanding the plurality of parameter time sequence correlation sub-matrices into a plurality of parameter time sequence correlation sub-feature vectors;
Passing the plurality of parameter timing related sub-feature vectors through the converter-based context encoder to obtain a plurality of parameter timing semantic feature vectors; and
Cascading the plurality of parameter time sequence semantic feature vectors to obtain the classification feature vector.
4. A fault monitoring system for exercise equipment according to claim 3, wherein the fault detection module comprises:
the full-connection coding unit is used for carrying out full-connection coding on the classification characteristic vectors by using a plurality of full-connection layers of the classifier so as to obtain coded classification characteristic vectors; and
And the classification unit is used for passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
5. A method for monitoring a fitness machine for faults, comprising:
acquiring temperature values, current values, voltage values, vibration amplitude values and noise values of the monitored fitness equipment at a plurality of preset time points in a preset time period;
Arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of the plurality of preset time points into a parameter full-time input matrix according to the time dimension and the sample dimension;
The parameter full-time sequence input matrix passes through a multi-scale sensor comprising a first convolutional neural network and a second convolutional neural network to obtain an optimized multi-scale parameter full-time sequence incidence matrix;
Performing feature matrix segmentation on the optimized multi-scale parameter full-time sequence incidence matrix to obtain a plurality of parameter time sequence incidence submatrices;
Passing the plurality of parameter timing correlation sub-matrices through a converter-based context encoder to obtain a classification feature vector; and
The classification feature vector is passed through a classifier to obtain a classification result, and the classification result is used for indicating whether the monitored fitness equipment has faults or not;
The method comprises the steps of arranging temperature values, current values, voltage values, vibration amplitude values and noise values of a plurality of preset time points into a parameter full-time input matrix according to a time dimension and a sample dimension, and comprises the following steps:
Arranging the temperature values, the current values, the voltage values, the vibration amplitude values and the noise values of the plurality of preset time points into parameter full-time sequence input row vectors according to time dimension or sample dimension, and then performing two-dimensional arrangement to obtain the parameter full-time sequence input matrix;
Wherein, pass the said parameter full time sequence input matrix through the multiscale perceptron comprising first convolutional neural network and second convolutional neural network in order to get the full time sequence incidence matrix of optimized multiscale parameter, including:
the parameter full-time sequence input matrix passes through a first convolution neural network of the multi-scale sensor to obtain a first scale parameter full-time sequence incidence matrix;
the parameter full-time sequence input matrix passes through a second convolution neural network of the multi-scale sensor to obtain a second scale parameter full-time sequence incidence matrix, wherein the first convolution neural network and the second convolution neural network respectively adopt two-dimensional convolution kernels with different scales; and
Fusing the first scale parameter full-time sequence incidence matrix and the second scale parameter full-time sequence incidence matrix to obtain a multi-scale parameter full-time sequence incidence matrix;
Optimizing the multi-scale parameter full-time sequence incidence matrix to obtain the optimized multi-scale parameter full-time sequence incidence matrix;
wherein optimizing the multi-scale parameter full-time sequence incidence matrix to obtain the optimized multi-scale parameter full-time sequence incidence matrix comprises the following steps:
Expanding the multi-scale parameter full-time sequence correlation matrix into a multi-scale parameter full-time sequence correlation vector;
carrying out fine granularity density prediction search optimization of a weight space on the multi-scale parameter full-time sequence association vector to obtain an optimized multi-scale parameter full-time sequence association vector; and
Performing dimension reconstruction on the optimized multi-scale parameter full-time sequence association vector to obtain the optimized multi-scale parameter full-time sequence association matrix;
Carrying out weight space fine granularity density prediction search optimization on the multi-scale parameter full-time sequence association vector to obtain an optimized multi-scale parameter full-time sequence association vector, wherein the method comprises the following steps of: carrying out weight space fine granularity density prediction search optimization on the multi-scale parameter full-time sequence association vector by using the following optimization formula to obtain an optimized multi-scale parameter full-time sequence association vector;
Wherein, the optimization formula is:
，
Wherein, And/>Is the optimal matrix of last and current iteration,/>, respectivelyIs the multi-scale parameter full-time sequence association vector,/>Is the first iterative feature vector,/>Is a second iterative feature vector,/>And/>Respectively represent feature vectorsAnd/>And/>Is a bias vector,/>Representing a minimum function,/>Representing matrix multiplication,/>Representing the per-position dot multiplication of vectors,/>Representing vector addition,/>Representing the optimized multi-scale parameter full-time sequence association vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311089633.XA CN117034123B (en) | 2023-08-28 | 2023-08-28 | Fault monitoring system and method for fitness equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311089633.XA CN117034123B (en) | 2023-08-28 | 2023-08-28 | Fault monitoring system and method for fitness equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117034123A CN117034123A (en) | 2023-11-10 |
| CN117034123B true CN117034123B (en) | 2024-05-07 |
Family
ID=88626345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311089633.XA Active CN117034123B (en) | 2023-08-28 | 2023-08-28 | Fault monitoring system and method for fitness equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117034123B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117251718B (en) * | 2023-11-20 | 2024-02-13 | 吉林省拓达环保设备工程有限公司 | Intelligent aeration management system based on artificial intelligence |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115359304A (en) * | 2022-10-17 | 2022-11-18 | 山东建筑大学 | Single image feature grouping-oriented causal invariance learning method and system |
| CN115564203A (en) * | 2022-09-23 | 2023-01-03 | 杭州国辰智企科技有限公司 | Equipment real-time performance evaluation system and method based on multi-dimensional data cooperation |
| CN115761642A (en) * | 2022-11-23 | 2023-03-07 | 华能伊敏煤电有限责任公司 | Image processing-based crushing operation monitoring method and system |
| CN115908517A (en) * | 2023-01-06 | 2023-04-04 | 广东工业大学 | Low-overlap point cloud registration method based on corresponding point matching matrix optimization |
| CN115979660A (en) * | 2022-08-18 | 2023-04-18 | 天津大学 | Filter fault diagnosis method for internal combustion engine based on MPA optimization |
| CN116458852A (en) * | 2023-06-16 | 2023-07-21 | 山东协和学院 | Rehabilitation training system and method based on cloud platform and lower limb rehabilitation robot |
| CN116482524A (en) * | 2023-04-23 | 2023-07-25 | 云南远信科技有限公司 | Power transmission and distribution switch state detection method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8036997B2 (en) * | 2005-06-16 | 2011-10-11 | Board Of Trustees Of Michigan State University | Methods for data classification |
-
2023
- 2023-08-28 CN CN202311089633.XA patent/CN117034123B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115979660A (en) * | 2022-08-18 | 2023-04-18 | 天津大学 | Filter fault diagnosis method for internal combustion engine based on MPA optimization |
| CN115564203A (en) * | 2022-09-23 | 2023-01-03 | 杭州国辰智企科技有限公司 | Equipment real-time performance evaluation system and method based on multi-dimensional data cooperation |
| CN115359304A (en) * | 2022-10-17 | 2022-11-18 | 山东建筑大学 | Single image feature grouping-oriented causal invariance learning method and system |
| CN115761642A (en) * | 2022-11-23 | 2023-03-07 | 华能伊敏煤电有限责任公司 | Image processing-based crushing operation monitoring method and system |
| CN115908517A (en) * | 2023-01-06 | 2023-04-04 | 广东工业大学 | Low-overlap point cloud registration method based on corresponding point matching matrix optimization |
| CN116482524A (en) * | 2023-04-23 | 2023-07-25 | 云南远信科技有限公司 | Power transmission and distribution switch state detection method and system |
| CN116458852A (en) * | 2023-06-16 | 2023-07-21 | 山东协和学院 | Rehabilitation training system and method based on cloud platform and lower limb rehabilitation robot |
Non-Patent Citations (1)
| Title |
|---|
| 基于参数优化VMD和增强多尺度排列熵的单向阀故障诊断;潘震 等;《振动与冲击》;20200815(第15期);第125-132页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117034123A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117034123B (en) | Fault monitoring system and method for fitness equipment | |
| CN117040917A (en) | Intelligent switch with monitoring and early warning functions | |
| CN111397902A (en) | Rolling bearing fault diagnosis method based on feature alignment convolutional neural network | |
| CN117041017B (en) | Intelligent operation and maintenance management method and system for data center | |
| CN116247824B (en) | Control method and system for power equipment | |
| CN116795886B (en) | Data analysis engine and method for sales data | |
| CN117116498A (en) | Mobile ward-round data processing system and method thereof | |
| CN116703642A (en) | Intelligent management system of product manufacturing production line based on digital twin technology | |
| CN116929815A (en) | Equipment working state monitoring system and method based on Internet of things | |
| CN116482524A (en) | Power transmission and distribution switch state detection method and system | |
| CN117158923A (en) | Remote home-care monitoring method based on meta universe | |
| CN111898704A (en) | Method and device for clustering content samples | |
| CN116911929A (en) | Advertisement service terminal and method based on big data | |
| CN115046766A (en) | Small sample bearing fault diagnosis method based on two-dimensional gray image self-adaptive subspace | |
| CN117037427B (en) | Geological disaster networking monitoring and early warning system | |
| CN116451139B (en) | Live broadcast data rapid analysis method based on artificial intelligence | |
| Qin et al. | Remaining useful life prediction using temporal deep degradation network for complex machinery with attention-based feature extraction | |
| CN116966513A (en) | Monitoring method and system for fitness equipment | |
| CN117155706A (en) | Network abnormal behavior detection method and system | |
| CN116934304B (en) | Intelligent power distribution room equipment operation maintenance management system and method thereof | |
| CN117094453B (en) | Scheduling optimization system and method for virtual power plant | |
| CN117668753A (en) | System and method for analyzing equipment performance based on industrial park | |
| CN116934304A (en) | Intelligent power distribution room equipment operation maintenance management system and method thereof | |
| CN117192416A (en) | Battery monitoring system and method based on BMS system | |
| CN117333717A (en) | Security monitoring method and system based on network information technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |