Intelligent monitoring system and method for rock wool cutting device

Abstract

The invention provides an intelligent monitoring system and method for a rock wool cutting device, relates to the field of intelligent monitoring, and aims to know the working state of a motor of the rock wool cutting device by analyzing real-time motor temperature data and motor operation vibration signal data. And whether the rock wool cutting device motor needs to be maintained or not is judged based on the working state of the rock wool cutting device motor. Therefore, the actual working state of the motor of the rock wool cutting device can be accurately known so as to guide the maintenance work.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring, and more specifically, to an intelligent monitoring system and method for a rock wool cutting device. Background Art

[0002] The rock wool cutting device is a device specially used for cutting rock wool materials. It can cut rock wool materials into specific shapes and sizes according to different needs. The motor is the core power component of the rock wool cutting device, and its normal operation is directly related to the working efficiency of the entire equipment. As the use time increases, the performance of the motor may gradually decline. In order to keep the motor performance in a good state, the motor needs to be maintained.

[0003] Traditional maintenance methods generally adopt regular maintenance methods. If maintenance is performed according to the regular maintenance method, maintenance may be performed when the equipment does not actually need maintenance, resulting in a waste of resources. If the maintenance interval is too long, maintenance may be performed only after certain problems occur in the equipment, which affects production.

[0004] Therefore, an optimized monitoring solution for rock wool cutting devices is needed. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present application provides an intelligent monitoring system and method for a rock wool cutting device.

[0006] According to one aspect of the present application, there is provided an intelligent monitoring system for a rock wool cutting device, comprising:

[0007] The rock wool cutting device motor monitoring data acquisition module is used to obtain the motor operation vibration signal during the operation of the rock wool cutting device and the motor temperature values ​​at multiple predetermined time points within a predetermined time period;

[0008] A motor monitoring data encoding module for a rock wool cutting device is used to perform feature encoding and feature fusion on the motor operation vibration signal and the motor temperature values ​​at the plurality of predetermined time points to obtain a motor working state feature vector;

[0009] The rock wool cutting device motor maintenance result generation module is used to obtain a monitoring result of whether the motor of the rock wool cutting device needs maintenance based on the motor working state feature vector.

[0010] According to another aspect of the present application, a method for intelligent monitoring of a rock wool cutting device is provided, which comprises:

[0011] Acquire the motor operation vibration signal during the operation of the rock wool cutting device and the motor temperature values ​​at multiple predetermined time points within a predetermined time period;

[0012] Performing feature encoding and feature fusion on the motor operation vibration signal and the motor temperature values ​​at the plurality of predetermined time points to obtain a motor working state feature vector;

[0013] Based on the motor working state characteristic vector, a monitoring result of whether the motor of the rock wool cutting device needs maintenance is obtained.

[0014] This application has significant technical effects due to the adoption of the above technical solutions:

[0015] The rock wool cutting device intelligent monitoring system and method provided in the present application analyzes the real-time motor temperature data and motor operation vibration signal data to understand the working state of the rock wool cutting device motor, and judges whether the rock wool cutting device motor needs maintenance based on the working state of the rock wool cutting device motor. In this way, the actual working state of the rock wool cutting device motor can be accurately understood, and then the maintenance work can be guided. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0017] Figure 1 4 is a system block diagram of an intelligent monitoring system for a rock wool cutting device according to an embodiment of the present application.

[0018] Figure 2 It is a block diagram of a rock wool cutting device motor monitoring data encoding module in a rock wool cutting device intelligent monitoring system according to an embodiment of the present application.

[0019] Figure 3 It is a block diagram of a motor vibration signal feature extraction unit in an intelligent monitoring system for a rock wool cutting device according to an embodiment of the present application.

[0020] Figure 4 This is a block diagram of a rock wool cutting device motor maintenance result generation module in a rock wool cutting device intelligent monitoring system according to an embodiment of the present application.

[0021] Figure 5 The figure is a flow chart of an intelligent monitoring method for a rock wool cutting device according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0023] In today's construction, industrial insulation and many other fields, rock wool materials are widely used due to their excellent thermal insulation, heat insulation and fire resistance. As a device specially used for cutting rock wool materials, the rock wool cutting device plays an extremely critical role in these industries. It can accurately cut rock wool materials into specific shapes and sizes according to different needs. Whether it is regular long strips of rock wool used in the external wall insulation system of large buildings, or complex special-shaped rock wool required for insulation of some special equipment, it can efficiently complete the cutting task.

[0024] In the rock wool cutting device, the motor is undoubtedly the core power component. However, as the equipment is used for a long time, the performance of the motor may gradually decline like a machine that runs for a long time. In order to keep the motor performance in a good state and ensure the continuity and efficiency of production, it is very important to maintain the motor.

[0025] Traditional maintenance methods generally adopt regular maintenance methods. In the equipment maintenance plans of many factories, the maintenance cycle is set according to experience or the general usage rules of the equipment. However, this method has obvious disadvantages. Maintenance may be carried out when the equipment is actually in good operating condition and does not need maintenance. This not only wastes valuable resources such as manpower and material resources, but may also cause certain interference to the equipment due to unnecessary disassembly and inspection. If the maintenance interval is too long, maintenance may be carried out only after the equipment has certain problems such as abnormal heating and increased noise. This will affect the production progress and bring greater economic losses to the company. Therefore, an intelligent monitoring solution for rock wool cutting devices is expected.

[0026] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also shown a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks provides new solutions and solutions for the intelligent monitoring of rock wool cutting devices.

[0027] Figure 1 : is a system block diagram of the intelligent monitoring system for rock wool cutting device according to an embodiment of the present application. Figure 1As shown, in the intelligent monitoring system 100 of the rock wool cutting device, it includes: a rock wool cutting device motor monitoring data acquisition module 110, which is used to obtain the motor operation vibration signal during the operation of the rock wool cutting device and the motor temperature value at multiple predetermined time points within a predetermined time period; a rock wool cutting device motor monitoring data encoding module 120, which is used to feature encode and feature fuse the motor operation vibration signal and the motor temperature values ​​at the multiple predetermined time points to obtain a motor working state feature vector; a rock wool cutting device motor maintenance result generation module 130, which is used to obtain a monitoring result of whether the motor of the rock wool cutting device needs maintenance based on the motor working state feature vector.

[0028] In the embodiment of the present application, the rock wool cutting device motor monitoring data acquisition module 110 is used to obtain the motor operation vibration signal during the operation of the rock wool cutting device and the motor temperature value at multiple predetermined time points within a predetermined time period. It should be understood that during the operation of the rock wool cutting device, the motor operation vibration signal collected is a direct reflection of the working state of the motor, and it contains rich information, including frequency component information, amplitude information, phase information, time domain information, etc. of the vibration signal. The components of different frequencies in the vibration signal represent the vibration state of different parts or structures inside the motor; the amplitude of the vibration signal reflects the strength of the vibration, such as the increase in amplitude often means that there are imbalances, looseness and other abnormalities inside the motor; the time domain information of the vibration signal can reveal the dynamic characteristics and periodic change trends of the motor. The motor temperature data at multiple predetermined time points mainly reflects the thermal state of the motor during operation, specifically including information such as temperature change trends and temperature anomalies. In general, the vibration signal and temperature data reflect the operating state of the rock wool cutting device motor from the mechanical and thermodynamic perspectives respectively. The vibration signal mainly focuses on the dynamic performance and fault characteristics of the motor, while the temperature data reflects the thermal load and heat dissipation performance of the motor. Combining the two can provide a more comprehensive understanding of the actual working status of the motor, and based on the analysis results of the vibration signal and temperature data, it can be determined whether the motor needs maintenance. For example, if obvious fault characteristics appear in the vibration signal or the temperature data continues to rise and exceeds the set threshold, it is necessary to stop the machine for inspection and perform corresponding repairs or replace parts. In particular, in a specific implementation of an embodiment of the present application, the motor operation vibration signal data and the motor temperature data can be obtained through an acceleration sensor and a temperature sensor, respectively.

[0029] In the embodiment of the present application, the rock wool cutting device motor monitoring data encoding module 120 is used to perform feature encoding and feature fusion on the motor operation vibration signal and the motor temperature values ​​at the plurality of predetermined time points to obtain a motor working state feature vector. Specifically, Figure 2FIG. 1 is a block diagram of a rock wool cutting device motor monitoring data encoding module in a rock wool cutting device intelligent monitoring system according to an embodiment of the present application. Figure 2 As shown, the rock wool cutting device motor monitoring data encoding module 120 includes: a motor vibration signal feature extraction unit 121, used to perform time domain and frequency domain feature extraction on the motor operation vibration signal to obtain a motor vibration feature vector; a motor temperature timing feature extraction unit 122, used to perform timing feature extraction on the motor temperature values ​​at the multiple predetermined time points to obtain a motor temperature timing feature vector; a motor multi-source feature fusion unit 123, used to fuse the motor vibration feature vector and the motor temperature timing feature vector to obtain the motor working state feature vector.

[0030] More specifically, Figure 3 FIG. 1 is a block diagram of a motor vibration signal feature extraction unit in an intelligent monitoring system for a rock wool cutting device according to an embodiment of the present application. Figure 3 As shown, the motor vibration signal feature extraction unit 121 includes: a signal Fourier transform subunit 1211, which is used to perform Fourier transform on the motor operation vibration signal to obtain a frequency domain statistical feature sequence; a motor vibration frequency domain feature generation subunit 1212, which is used to pass the frequency domain statistical feature sequence through a vibration signal frequency domain statistical feature sequence encoder to obtain a motor vibration frequency domain feature vector; a motor vibration waveform feature generation subunit 1213, which is used to pass the waveform of the motor operation vibration signal through a vibration signal waveform encoder to obtain a motor vibration waveform feature vector; a motor time-frequency domain feature fusion subunit 1214, which is used to fuse the motor vibration frequency domain feature vector and the motor vibration waveform feature vector to obtain the motor vibration feature vector.

[0031] Considering that the vibration signal of the motor of the rock wool cutting device contains rich frequency components, these components are closely related to the operating state and internal faults of the motor. In order to convert the vibration signal from the time domain to the frequency domain, the technical solution of the present application needs to perform Fourier transform on the motor operation vibration signal to obtain a frequency domain statistical feature sequence. Those of ordinary skill in the art should know that Fourier transform is a mathematical transformation method that can convert a signal from the time domain to the frequency domain. In the field of signal processing, Fourier transform is used to analyze the spectral components of a signal, that is, the distribution and intensity of different frequency components in the signal. The frequency domain statistical feature sequence obtained by Fourier transform contains a series of statistical features of the vibration signal of the motor of the rock wool cutting device in the frequency domain, such as the spectral center of gravity, spectral width, spectral peak, etc. These parameters can quantitatively describe the spectral characteristics of the vibration signal. By analyzing the abnormal changes in the frequency domain statistical feature sequence, the performance degradation of the motor can be discovered in time, thereby helping to formulate a reasonable maintenance plan.

[0032] Considering that the frequency domain statistical feature sequence obtained directly from Fourier transform contains rich information, its characterization of the motor operation state is often superficial and cannot deeply understand the actual operation state of the motor. In order to obtain the key features that can represent the actual operation of the motor from the frequency domain statistical feature sequence, it is necessary to pass the frequency domain statistical feature sequence through the vibration signal frequency domain statistical feature sequence encoder to obtain the motor vibration frequency domain feature vector. Through the processing of the vibration signal frequency domain statistical feature sequence encoder, more accurate and effective feature information can be extracted, which is conducive to improving the accuracy of judgment on the motor operation state and whether maintenance is required. In this application, the vibration signal frequency domain statistical feature sequence encoder is a convolutional neural network model including a one-dimensional convolutional layer and a fully connected layer. The convolutional neural network model realizes local perception and weight sharing through the convolutional layer, which helps to reduce the number of model parameters, reduce the computational complexity, and enhance the generalization ability of the model. For one-dimensional data such as the frequency domain statistical feature sequence, the one-dimensional convolutional layer used by the sequence encoder can effectively capture local features. By stacking multiple one-dimensional convolutional layers and fully connected layers, the sequence encoder can construct a deep feature representation to capture more abstract and high-level information in the motor operation vibration signal.

[0033] The waveform of the motor running vibration signal is an important basis for judging whether the motor of the rock wool cutting device needs maintenance. It contains information such as motor amplitude, frequency, phase and change trend. In order to extract the key features in the waveform and form a more concise and accurate representation of the motor running state, it is necessary to pass the waveform of the motor running vibration signal through a vibration signal waveform encoder to obtain a motor vibration waveform feature vector. Through the processing of the vibration signal waveform encoder, high-dimensional waveform data can be converted into low-dimensional feature vectors, reducing the complexity of data processing. In this application, the vibration signal waveform encoder is a convolutional neural network model using non-overlapping convolution kernels. Non-overlapping convolution kernels do not overlap during the convolution process, which means that each convolution operation processes an independent area, thereby reducing the amount of calculation, which helps to improve the processing efficiency of the encoder, and since non-overlapping convolution kernels do not overlap during the convolution process, each pixel on the output feature map corresponds to a unique area on the input feature map, avoiding redundancy and repetition of information, which enables the encoder to more accurately extract key features in the waveform.

[0034] In an embodiment of the present application, a possible implementation method of passing the waveform of the motor running vibration signal through a vibration signal waveform encoder to obtain a motor vibration waveform feature vector may be: using each layer of the vibration signal waveform encoder to perform the following operations on the input data in the forward transfer of the layer: using the convolution units of each layer of the vibration signal waveform encoder to perform convolution processing based on a non-overlapping convolution kernel on the input data to obtain a convolution feature map; using the pooling units of each layer of the vibration signal waveform encoder to perform global mean pooling processing on each feature matrix along the channel dimension on the convolution feature map to obtain a pooling feature map; using the activation units of each layer of the vibration signal waveform encoder to perform nonlinear activation on the feature values ​​of each position in the pooling feature map to obtain an activation feature map; wherein the output of the last layer of the vibration signal waveform encoder is the motor vibration waveform feature vector.

[0035] Considering that the motor vibration frequency domain eigenvector and the motor vibration waveform eigenvector reflect the vibration characteristics of the motor from different angles. The frequency domain eigenvector focuses on analyzing the frequency components and energy distribution of the vibration signal, and can reveal information such as the natural frequency, harmonic components and fault characteristic frequency of the motor. The waveform eigenvector more intuitively displays the time domain waveform of the vibration signal, including key information such as amplitude, phase and change trend. In order to comprehensively utilize the advantages of these two vectors in the frequency domain and time domain, it is necessary to fuse the motor vibration frequency domain eigenvector and the motor vibration waveform eigenvector in the technical solution of the present application to obtain the motor vibration eigenvector. The motor vibration eigenvector obtained after fusion can monitor the operating status of the motor in real time. When the motor vibrates abnormally, its vibration eigenvector will change accordingly. By analyzing and judging these changes in real time through the intelligent monitoring system, potential problems of the motor can be discovered in time, and maintenance plans can be formulated according to the actual situation of the motor.

[0036] In an embodiment of the present application, a possible implementation method of fusing the motor vibration frequency domain feature vector and the motor vibration waveform feature vector to obtain the motor vibration feature vector may be: fusing the motor vibration frequency domain feature vector and the motor vibration waveform feature vector using the following fusion formula to obtain the motor vibration feature vector; wherein the fusion formula is:

[0037]

[0038] Wherein, V1 is the vibration characteristic vector of the motor, V a is the motor vibration frequency domain feature vector, V b is the motor vibration waveform feature vector, It represents the addition of the elements at corresponding positions of the motor vibration frequency domain feature vector and the motor vibration waveform feature vector, and α and β are weighted parameters for controlling the balance between the motor vibration frequency domain feature vector and the motor vibration waveform feature vector in the motor vibration feature vector.

[0039] During the operation of the rock wool cutting device motor, the motor temperature is constantly changing. In order to perform a timing analysis on this dynamic data and extract the trend of the motor temperature change, it is necessary to first arrange the motor temperature values ​​of the multiple predetermined time points into a motor temperature timing input vector according to the time dimension. By processing the temperature data as a timing input vector, the timing analysis method can be fully utilized to process it, that is, the motor temperature timing input vector is passed through the motor temperature timing encoder to obtain the motor temperature timing feature vector. The motor temperature timing encoder is an encoder specifically used for processing timing data, which can effectively extract the key features and laws in the timing data. Through the processing of the encoder, the original temperature timing input vector can be converted into a higher-level feature representation. In this application, the motor temperature timing encoder is a recurrent neural network model. The recurrent neural network model introduces a cyclic connection to enable the network to retain historical information, and use this information to process the current input, so that it can well capture the long-term dependencies in the input motor temperature timing data, which is conducive to understanding the long-term change trends and periodic laws in the motor temperature data.

[0040] In an embodiment of the present application, one possible implementation method of arranging the motor temperature values ​​of the plurality of predetermined time points into a motor temperature timing input vector according to the time dimension and then obtaining the motor temperature timing feature vector through a motor temperature timing encoder may be: processing the motor temperature timing input vector according to the following formula to obtain the motor temperature timing feature vector; wherein the formula is:

[0041] s t =f(Ux t +Ws t-1 )

[0042] O t =g(Vs t )

[0043] Among them, x t Represents the input at the current moment, s t-1 represents the output of the hidden layer at the previous moment, U represents the weight of the input sample at the current moment, W represents the weight of the hidden layer output at the previous moment, s t represents the input of the hidden layer at the current moment, V represents the sample weight of the output, f and g are activation functions, O t Represents the output of the hidden layer at the current moment.

[0044] The motor vibration characteristic vector mainly reflects the mechanical vibration characteristics of the motor during operation, including vibration frequency, amplitude, and waveform; the motor temperature time series characteristic vector provides the trend and law of the motor temperature change over time, revealing the thermal state of the motor; in order to comprehensively utilize the information of the two dimensions of mechanical vibration and thermal state to form a more comprehensive and accurate description of the motor working state, in the technical solution of the present application, it is necessary to fuse the motor vibration characteristic vector and the motor temperature time series characteristic vector to obtain the motor working state characteristic vector. The fused motor working state characteristic vector can more accurately reflect the actual operating state and potential faults of the motor. When the motor working state is detected to be abnormal, the system can issue maintenance reminders in time to avoid fault expansion and downtime losses.

[0045] In the embodiment of the present application, the rock wool cutting device motor maintenance result generation module 130 is used to obtain a monitoring result of whether the motor of the rock wool cutting device needs maintenance based on the motor working state feature vector. Specifically, Figure 4 FIG. 1 is a block diagram of a maintenance result generation module for a motor of a rock wool cutting device in an intelligent monitoring system for a rock wool cutting device according to an embodiment of the present application. Figure 4 As shown, the rock wool cutting device motor maintenance result generation module 130 includes: a motor working state feature optimization unit 131, which is used to perform feature sparse optimization on the motor working state feature vector based on information entropy change measurement to obtain an optimized motor working state feature vector; an optimized motor working state feature analysis classification unit 132, which is used to pass the optimized motor working state feature vector through a maintenance result generator based on a classifier to obtain a classification result, and the classification result is used to indicate whether the motor of the rock wool cutting device needs to be maintained.

[0046] In particular, considering that in the process of acquiring the motor vibration signal and temperature value, the information collected may overlap in the representation of the motor working state, which will lead to redundancy in the fused motor working state feature vector, and when using methods such as Fourier transform and timing encoder to extract features, some features that do not have sufficient discrimination will be generated. These features have limited characterization capabilities for the motor working state, but are still included in the feature vector, which will also lead to feature redundancy in the motor working state feature vector. The redundant features in the motor working state feature vector will weaken the role of other important features in the vector, resulting in a reduction in the discrimination between different classification results, that is, a run on categories. In the technical solution of the present application, it is necessary to perform feature sparse optimization on the motor working state feature vector based on the information entropy change metric to obtain an optimized motor working state feature vector.

[0047] Specifically, in an embodiment of the present application, feature sparse optimization based on information entropy change measurement is performed on the motor working state feature vector to obtain an optimized motor working state feature vector, including: extracting each row vector of the motor maintenance prediction parameter space to obtain a set of motor maintenance prediction parameter row vectors; calculating the motor maintenance class probability entropy degradation simulation value between the motor working state feature vector and each motor maintenance prediction parameter row vector in the set of motor maintenance prediction parameter row vectors to obtain a set of motor maintenance class probability entropy degradation simulation values; calculating the square root of the sum of squares of the motor maintenance class probability entropy degradation simulation values ​​to obtain a motor maintenance entropy degradation modulation value; based on the motor maintenance entropy degradation modulation value, feature distribution modulation is performed on the motor working state feature vector to obtain the optimized motor working state feature vector.

[0048] In an embodiment of the present application, another expression of performing feature sparse optimization based on information entropy change measurement on the motor working state feature vector to obtain an optimized motor working state feature vector can be: processing the motor working state feature vector according to the following formula to obtain an optimized motor working state feature vector; wherein the formula is:

[0049] P = {p1, p2, ..., P j , ..., p n}

[0050] D j =Softmax(M m v c +H m p j +b m )

[0051]

[0052]

[0053] Among them, P represents the set of row vectors of motor maintenance prediction parameters, p1, p2, p j 、p n represents the first, second, jth and nth motor maintenance prediction parameter row vectors in the set of motor maintenance prediction parameter row vectors, v c represents the motor working state feature vector, Softmax represents the normalized exponential function, M m represents the first weight matrix, H m represents the second weight matrix, b m represents the bias vector, D jrepresents the jth motor maintenance class probability entropy degradation simulation value of the set of motor maintenance class probability entropy degradation simulation values, t represents the motor maintenance entropy degradation modulation value, v c ⊙t represents the calculation of the motor working state characteristic vector v c Each eigenvalue of the t-th power, represents the i-th eigenvalue of the motor working state eigenvector, α represents a predetermined hyperparameter, represents addition by position, and V' represents the optimized motor working state characteristic vector.

[0054] In the technical solution of the present application, the motor working state feature vector has feature redundancy, which leads to the problem of inter-category squeeze relative to the class label of the classifier when it is classified and judged by the classifier, affecting the classification iteration effect. Based on this, in the technical solution of the present application, the motor working state feature vector is subjected to feature sparse optimization based on information entropy change measurement, which first extracts each row vector from the motor maintenance prediction parameter space of the classifier to form a row vector set. Then, the motor maintenance class probability entropy degradation simulation value between the motor working state feature vector and each row vector in the above row vector set is calculated to measure the uncertainty or information entropy change of the motor working state feature vector under given parameters. Then, all motor maintenance class probability entropy degradation simulation values ​​are squared and summed, and then the square root is taken to obtain a comprehensive motor maintenance entropy degradation modulation value, which reflects the degree of entropy change of the entire system when processing the feature vector. Finally, the motor working state feature vector is adjusted according to the motor maintenance entropy degradation modulation value obtained above. Specifically, the attribute set of the motor working state feature vector is represented in a power series based on the entropy degradation modulation value, and a set aggregated bounded deviation represented by an aggregation radius based on each attribute value of the motor working state attribute vector is added, so as to perform attribute selection and sparse optimization on the motor working state attribute vector under a unified entropy degradation modulation value restriction standard, so as to ensure that the attribute vector contains sufficient data but is not too cumbersome so as to introduce unnecessary interference or redundancy.

[0055] Finally, the optimized motor working state feature vector is passed through a maintenance result generator based on a classifier to obtain a classification result, and the classification result is used to indicate whether the motor of the rock wool cutting device needs to be maintained. That is, whether the motor of the rock wool cutting device needs to be maintained is classified and judged based on the motor working state information contained in the optimized motor working state feature vector. A classifier is a machine learning model, and it needs to be trained using a labeled training data set before making a classification judgment. Through training, the classifier learns the mapping relationship from raw data to maintenance results, and then when the new optimized motor working state feature vector is input into the trained classifier, the classifier will output a result indicating whether the motor of the rock wool cutting device needs to be maintained. In this way, it is possible to decide when to perform maintenance based on the actual operating conditions of the motor, thereby avoiding unnecessary waste of resources and aggravation of equipment failures caused by untimely maintenance.

[0056] In summary, the rock wool cutting device intelligent monitoring system 100 based on the embodiment of the present application is explained, which analyzes the real-time motor temperature data and motor operation vibration signal data to understand the working state of the rock wool cutting device motor, and judges whether the rock wool cutting device motor needs maintenance based on the working state of the rock wool cutting device motor. In this way, the actual working state of the rock wool cutting device motor can be accurately understood, and then the maintenance work can be guided.

[0057] As described above, the intelligent monitoring system 100 for rock wool cutting devices according to the embodiment of the present application can be implemented in various terminal devices, such as a server for intelligent monitoring of rock wool cutting devices. In one example, the intelligent monitoring system 100 for rock wool cutting devices according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the intelligent monitoring system 100 for rock wool cutting devices can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the intelligent monitoring system 100 for rock wool cutting devices can also be one of the many hardware modules of the terminal device.

[0058] Alternatively, in another example, the intelligent monitoring system 100 for rock wool cutting devices and the terminal device may be separate devices, and the intelligent monitoring system 100 for rock wool cutting devices may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0059] Figure 5 Flow chart of the intelligent monitoring method of rock wool cutting device according to the embodiment of the present application. Figure 5As shown, in the intelligent monitoring method of the rock wool cutting device, the following steps are included: S110, obtaining the motor operation vibration signal during the operation of the rock wool cutting device and the motor temperature values ​​at multiple predetermined time points within a predetermined time period; S120, performing feature encoding and feature fusion on the motor operation vibration signal and the motor temperature values ​​at the multiple predetermined time points to obtain a motor working state feature vector; S130, based on the motor working state feature vector, obtaining a monitoring result of whether the motor of the rock wool cutting device needs maintenance.

[0060] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned rock wool cutting device intelligent monitoring method have been referred to above. Figures 1 to 4 The description of the intelligent monitoring system for rock wool cutting device has been introduced in detail, and therefore, its repeated description will be omitted.

[0061] In summary, the intelligent monitoring method of the rock wool cutting device based on the embodiment of the present application is explained, which analyzes the real-time motor temperature data and motor operation vibration signal data to understand the working state of the rock wool cutting device motor, and judges whether the rock wool cutting device motor needs maintenance based on the working state of the rock wool cutting device motor. In this way, the actual working state of the rock wool cutting device motor can be accurately understood, and then the maintenance work can be guided.

[0062] Finally, the present application also relates to a computer-readable storage medium for implementing an intelligent monitoring method for a rock wool cutting device according to one or more embodiments of the present application. The computer-readable storage medium mentioned herein includes various types of computer storage media, which may be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a computer-readable storage medium may include RAM, ROM, EPROM, E2PROM, registers, hard disks, removable disks, CD-ROMs or other optical disk storage, disk storage or other magnetic storage devices, or any other temporary or non-temporary medium that can be used to carry or store desired program code units in the form of instructions or data structures and can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. The description of the computer-readable storage medium according to the present application can refer to the explanation of the intelligent monitoring method for a rock wool cutting device according to the present application, and no further description will be given.

[0063] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details of the above application are only for the purpose of illustration and ease of understanding, rather than limitation, and the above details do not limit the present application to the use of the above specific details to be implemented.

[0064] In this application, words such as "including", "comprising", "having", etc. are open words, meaning "including but not limited to", and can be used interchangeably therewith. The words "or" and "and" used herein mean the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably therewith.

[0065] It should also be noted that in the system and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0066] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present application.

[0067] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. An intelligent monitoring system for rock wool cutting device, characterized in that: include: The rock wool cutting device motor monitoring data acquisition module is used to obtain the motor operation vibration signal during the operation of the rock wool cutting device and the motor temperature values ​​at multiple predetermined time points within a predetermined time period; A motor monitoring data encoding module for a rock wool cutting device is used to perform feature encoding and feature fusion on the motor operation vibration signal and the motor temperature values ​​at the plurality of predetermined time points to obtain a motor working state feature vector; The rock wool cutting device motor maintenance result generation module is used to obtain a monitoring result of whether the motor of the rock wool cutting device needs maintenance based on the motor working state feature vector.

2. The intelligent monitoring system for rock wool cutting device according to claim 1, characterized in that: The rock wool cutting device motor monitoring data encoding module includes: A motor vibration signal feature extraction unit, used for extracting the time domain and frequency domain features of the motor operation vibration signal to obtain a motor vibration feature vector; A motor temperature time series feature extraction unit, used for extracting time series features of the motor temperature values ​​at the plurality of predetermined time points to obtain a motor temperature time series feature vector; The motor multi-source feature fusion unit is used to fuse the motor vibration feature vector and the motor temperature time series feature vector to obtain the motor working state feature vector.

3. The intelligent monitoring system for rock wool cutting device according to claim 2, characterized in that: The motor vibration signal feature extraction unit comprises: A signal Fourier transform subunit, used for performing Fourier transform on the motor operation vibration signal to obtain a frequency domain statistical feature sequence; A motor vibration frequency domain feature generation subunit, used for passing the frequency domain statistical feature sequence through a vibration signal frequency domain statistical feature sequence encoder to obtain a motor vibration frequency domain feature vector; A motor vibration waveform feature generating subunit, used for passing the waveform of the motor running vibration signal through a vibration signal waveform encoder to obtain a motor vibration waveform feature vector; The motor time-frequency domain feature fusion subunit is used to fuse the motor vibration frequency domain feature vector and the motor vibration waveform feature vector to obtain the motor vibration feature vector.

4. The intelligent monitoring system for rock wool cutting device according to claim 3 is characterized in that: The motor temperature timing feature extraction unit is used to: arrange the motor temperature values ​​of the plurality of predetermined time points into a motor temperature timing input vector according to the time dimension and then pass it through a motor temperature timing encoder to obtain the motor temperature timing feature vector.

5. The intelligent monitoring system for rock wool cutting device according to claim 4, characterized in that: The vibration signal frequency domain statistical feature sequence encoder is a convolutional neural network model including a one-dimensional convolution layer and a fully connected layer, the vibration signal waveform encoder is a convolutional neural network model using non-overlapping convolution kernels, and the motor temperature timing encoder is a recurrent neural network model.

6. The intelligent monitoring system for rock wool cutting device according to claim 5, characterized in that: The rock wool cutting device motor maintenance result generation module includes: A motor working state feature optimization unit, used for performing feature sparse optimization on the motor working state feature vector based on information entropy change measurement to obtain an optimized motor working state feature vector; The motor working state feature parsing and classification unit is optimized, and is used to pass the optimized motor working state feature vector through a classifier-based maintenance result generator to obtain a classification result, and the classification result is used to indicate whether the motor of the rock wool cutting device needs to be maintained.

7. The intelligent monitoring system for rock wool cutting device according to claim 6, characterized in that: The motor working state characteristic optimization unit is used for: Extracting each row vector of the motor maintenance prediction parameter space to obtain a set of motor maintenance prediction parameter row vectors; Calculating the motor maintenance class probability entropy degradation simulation value between the motor working state characteristic vector and each motor maintenance prediction parameter row vector in the set of motor maintenance prediction parameter row vectors to obtain a set of motor maintenance class probability entropy degradation simulation values; Calculating the square root of the sum of squares of the motor maintenance class probability entropy degradation simulation values ​​to obtain the motor maintenance entropy degradation modulation value; Based on the motor maintenance entropy degradation modulation value, the motor working state feature vector is subjected to feature distribution modulation to obtain the optimized motor working state feature vector.

8. An intelligent monitoring method for a rock wool cutting device, characterized in that: include: Acquire the motor operation vibration signal during the operation of the rock wool cutting device and the motor temperature values ​​at multiple predetermined time points within a predetermined time period; Performing feature encoding and feature fusion on the motor operation vibration signal and the motor temperature values ​​at the plurality of predetermined time points to obtain a motor working state feature vector; Based on the motor working state characteristic vector, a monitoring result of whether the motor of the rock wool cutting device needs maintenance is obtained.

9. The intelligent monitoring method for rock wool cutting device according to claim 8, characterized in that: The motor operation vibration signal and the motor temperature values ​​at the plurality of predetermined time points are feature encoded and feature fused to obtain a motor working state feature vector, including: Extracting the motor vibration signal in the time domain and the frequency domain to obtain a motor vibration feature vector; Extracting time series features of the motor temperature values ​​at the plurality of predetermined time points to obtain a motor temperature time series feature vector; The motor vibration feature vector and the motor temperature time series feature vector are fused to obtain the motor working state feature vector.

10. The intelligent monitoring method for rock wool cutting device according to claim 9, characterized in that: Based on the motor working state characteristic vector, a monitoring result of whether the motor of the rock wool cutting device needs maintenance is obtained, including: Performing feature sparse optimization based on information entropy change measurement on the motor working state feature vector to obtain an optimized motor working state feature vector; The optimized motor working state feature vector is passed through a maintenance result generator based on a classifier to obtain a classification result, and the classification result is used to indicate whether maintenance is required for the motor of the rock wool cutting device.

Images