A smart factory intelligent control method and device based on signal monitoring and a medium

Abstract

The application relates to the technical field of artificial intelligence, and discloses a smart factory intelligent control method and device based on signal monitoring and a medium. The method comprises the following steps: reconstructing each operation signal in a set of operation signals of a smart factory to obtain a reconstructed signal; performing signal enhancement on the basis of the reconstructed signal to obtain an enhanced signal, and identifying a signal source on the basis of the enhanced signal; constructing an operation signal image of the reconstructed signal, and calculating a signal distance between the operation signal image and a reference signal image corresponding to the signal source; identifying an equipment operation category on the basis of the signal distance, performing equipment regulation on the basis of the equipment operation category, obtaining a regulation signal, generating a joint regulation signal on the basis of the regulation signal, and controlling the smart factory by using the joint regulation signal. The application can improve the accuracy of smart factory intelligent control.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a smart factory intelligent control method and device based on signal monitoring and a medium. BACKGROUND

[0002] In a smart factory environment, signal monitoring covers real-time capture and analysis of various types of signals. This includes operational parameter signals from production equipment (such as temperature, pressure, vibration frequency, etc.), location and status signals of logistics systems (such as the location of material transport vehicles, inventory level change signals), environmental monitoring signals (such as temperature and humidity in the workshop, air quality signals), and personnel operation related signals (such as employee clock-in records, device operation instruction signals), etc. Through sensors, instruments and data acquisition devices distributed in every corner of the factory, these signals are efficiently collected and transmitted to the central processing system. Based on the massive data obtained through signal monitoring, the smart factory can precisely control the production process, device operation, resource allocation, and other aspects of the control system.

[0003] Existing signal monitoring methods, such as those based on time and frequency domain basic statistics, require the determination of carrier frequency, sampling frequency, symbol rate and other parameters. The estimated value is sensitive to additive noise and is not suitable for low signal-to-noise ratios. The estimation variance of high-order cumulants is large, making it difficult to accurately estimate in cases of limited data. In non-cooperative BOC (Binary Offset Carrier) signal detection, the cyclic spectrum and its improved algorithm have limited sampling time, and the length of the received data cannot be infinite, which results in the cyclic spectrum of noise being non-constant at non-zero cycle frequencies and a large amount of computation. There is also a deviation problem in the cyclic spectrum envelope of cose-BOC signals at the position of the secondary peak near the double carrier frequency, resulting in poor accuracy of signal monitoring. Therefore, how to improve the accuracy of signal monitoring and more accurately control the smart factory has become a problem to be solved. SUMMARY

[0004] The present application provides a smart factory intelligent control method and device based on signal monitoring, which mainly aims to solve the problem of poor accuracy of smart factory intelligent control.

[0005] To achieve the above purpose, the present application provides a smart factory intelligent control method based on signal monitoring, which comprises:

[0006] Obtaining a set of operation signals of a smart factory, reconstructing each operation signal in the set of operation signals to obtain a reconstructed signal;

[0007] signal enhancement is performed on the running signal according to the reconstructed signal to obtain an enhanced signal, and a signal source of the running signal is identified according to the enhanced signal; wherein the signal enhancement performed on the running signal according to the reconstructed signal to obtain an enhanced signal comprises: performing complete ensemble empirical mode decomposition on the reconstructed signal to obtain decomposition components; and respectively calculating component parameter values of each of the decomposition components;

[0008] The component parameter values of each of the decomposition components are calculated by using the following formula:

[0009]

[0010] M = pK

[0011] wherein Cov(·) represents covariance, Y IMF represents a decomposition component, x represents a reconstructed signal, D(·) represents variance, E(·) represents expectation, and M represents a component parameter value;

[0012] A signal threshold of the reconstructed signal is calculated according to the component parameter values, the decomposition components are screened based on the signal threshold to obtain target components, and an enhanced signal of the running signal is constructed by using the target components;

[0013] A running signal image of the reconstructed signal is constructed, and a signal distance between the running signal image and a reference signal image corresponding to the signal source is calculated;

[0014] A device running category of the running signal is identified according to the signal distance, and a device control is performed on the signal source based on the device running category to obtain a controlled signal;

[0015] A joint control signal of the smart factory is generated according to the controlled signal, and the smart factory is controlled by using the joint control signal.

[0016] Optionally, the signal reconstruction performed on each of the running signals in the running signal set to obtain a reconstructed signal comprises:

[0017] Each of the running signals is sampled by using a preset sampling frequency to obtain a sampled signal;

[0018] The sampled signal is processed by using a Hamming window double interpolation fast Fourier transform to obtain an actual sampling frequency;

[0019] An actual sampled signal of each of the running signals is collected by using the actual sampling frequency;

[0020] The actual sampled signal is reconstructed by using cubic spline interpolation to obtain a reconstructed signal.

[0021] Optionally, the device running category of the running signal is identified according to the signal distance, comprising:

[0022] The signal position of the running signal is identified according to the signal distance, and a target running signal is determined according to the signal position;

[0023] The target running signal is subjected to modal decomposition to obtain a plurality of modal components;

[0024] The correlation coefficient between each of the modal components and the target running signal is calculated;

[0025] The effective modal component of the target running signal is calculated according to the correlation coefficient, and a Hilbert spectrum of the target running signal is constructed according to the effective modal component;

[0026] The target running signal is classified according to the Hilbert spectrum to obtain the device running category of the running signal.

[0027] Optionally, the signal source of the running signal is identified according to the enhanced signal, comprising:

[0028] The signal feature of the enhanced signal is extracted;

[0029] The dual features of the signal feature are extracted by using a pre-constructed dual attention network;

[0030] The dual features are subjected to feature fusion to obtain a fusion feature;

[0031] The enhanced signal is classified according to the fusion feature to obtain the signal source.

[0032] Optionally, the running signal image of the reconstructed signal is constructed, comprising:

[0033] The reconstructed signal is subjected to segmented overlap sampling to obtain segmented signal samples of the reconstructed signal;

[0034] The pixel value corresponding to each sample point in each of the signal samples is calculated;

[0035] The signal image is obtained by image coding according to the pixel value.

[0036] Optionally, the signal distance between the running signal image and the reference signal image corresponding to the signal source is calculated, comprising:

[0037] The adjacent pixel value difference of the running signal image and the reference signal image is calculated respectively;

[0038] A pixel difference sequence matrix is constructed according to the adjacent pixel value difference, and a feature hash value is calculated according to the pixel difference sequence matrix.

[0039] calculating a Hamming distance according to the feature hash value, and taking the Hamming distance as a signal distance;

[0040] The Hamming distance is calculated by using the following formula:

[0041]

[0042] wherein L represents the Hamming distance, represents the gth feature hash value corresponding to the running signal image, represents element-by-element addition, represents the gth feature hash value corresponding to the running signal image.

[0043] Optionally, the device regulation based on the device running category is performed on the signal source to obtain a regulated signal, including:

[0044] determining a device adjustment parameter according to the device running category;

[0045] performing signal type conversion according to the device adjustment parameter to obtain an analog signal;

[0046] encoding the analog signal to obtain a regulated signal.

[0047] In order to solve the above problems, the application further provides a smart factory intelligent control device based on signal monitoring, the device comprising:

[0048] a signal reconstruction module, configured to acquire a running signal set of a smart factory, and perform signal reconstruction on each running signal in the running signal set to obtain a reconstructed signal;

[0049] a signal source identification module, configured to perform signal enhancement on the running signal according to the reconstructed signal to obtain an enhanced signal, and identify a signal source of the running signal according to the enhanced signal; wherein the signal enhancement on the running signal according to the reconstructed signal to obtain the enhanced signal comprises: performing complete set empirical mode decomposition on the reconstructed signal to obtain decomposition components; and calculating a component parameter value of each decomposition component.

[0050] The component parameter value of each decomposition component is calculated by using the following formula:

[0051]

[0052] M = pK

[0053] wherein Cov(·) represents covariance, Y IMF represents a decomposition component, x represents a reconstructed signal, D(·) represents variance, E(·) represents expectation, and M represents a component parameter value.

[0054] calculating a signal threshold of the reconstructed signal according to the component parameter value, screening the decomposition components based on the signal threshold to obtain target components, and constructing an enhanced signal of the running signal by using the target components;

[0055] a signal distance calculation module, configured to construct a running signal image of the reconstructed signal, and calculate a signal distance between the running signal image and a reference signal image corresponding to the signal source;

[0056] a regulation signal construction module, configured to identify a device running category of the running signal according to the signal distance, and perform device regulation on the signal source based on the device running category to obtain a regulation signal;

[0057] a smart factory control module, configured to generate a joint regulation signal of the smart factory according to the regulation signal, and control the smart factory by using the joint regulation signal.

[0058] To solve the above problems, the application further provides a computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the smart factory intelligent control method based on signal monitoring.

[0059] The embodiment of the application can obtain more accurate reconstructed signals by reconstructing each running signal in a running signal set of a smart factory, can obtain enhanced signals by performing signal enhancement on the running signals according to the reconstructed signals, can identify signal sources according to the enhanced signals, can adjust the factory devices corresponding to the running signals accordingly, and can improve the accuracy of smart factory control. The embodiment of the application can reflect the differences between the running signals in different signal segments and the reference signals, and can further reflect the device running states of the signal sources by constructing a running signal image of the reconstructed signal, calculating a signal distance between the running signal image and a reference signal image, and effectively improving the accuracy of smart factory control. The embodiment of the application can identify the device running categories of the running signals according to the signal distance, can perform device regulation on the signal sources to obtain regulation signals, and can generate joint regulation signals of the smart factory according to the regulation signals, so as to realize joint regulation of the smart factory and more accurate intelligent control of the smart factory. Therefore, the smart factory intelligent control method, device and medium based on signal monitoring provided by the application can solve the problem of poor accuracy of smart factory intelligent control. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 a flowchart of the smart factory intelligent control method based on signal monitoring provided by an embodiment of the application;

[0061] Figure 2A flowchart of a signal reconstruction process for each operation signal in a set of operation signals is provided for an embodiment of the present application.

[0062] Figure 3 A flowchart of a signal enhancement process for the operation signal according to the reconstructed signal is provided for an embodiment of the present application.

[0063] Figure 4 A functional module diagram of an intelligent control device of a smart factory based on signal monitoring is provided for an embodiment of the present application.

[0064] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0066] Embodiments of the present application provide an intelligent control method of a smart factory based on signal monitoring. The execution subject of the intelligent control method of the smart factory based on signal monitoring includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc., which can be configured to execute the method provided by the embodiments of the present application. In other words, the intelligent control method of the smart factory based on signal monitoring can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster, etc. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, etc.

[0067] Referring to Figure 1 A flowchart of an intelligent control method of a smart factory based on signal monitoring is provided for an embodiment of the present application. In the embodiment, the intelligent control method of the smart factory based on signal monitoring includes:

[0068] S1, a set of operation signals of a smart factory is acquired, and each operation signal in the set of operation signals is reconstructed to obtain a reconstructed signal.

[0069] In the embodiment of the present application, the smart factory realizes high intelligence, automation and informatization of the production process by deeply integrating information technology, automation technology and communication technology, and utilizes advanced automation equipment (such as robots, automated production lines, automated warehousing systems, etc.) to reduce manual intervention, improve production efficiency and product quality, collects running signals of each device in the smart factory through sensors, such as running parameter signals (such as temperature, pressure, vibration frequency, etc.), position and state signals of the logistics system (such as the position of the material transport vehicle, the inventory level change signal), environmental monitoring signals (such as the temperature and humidity, air quality signal in the workshop) and personnel operation related signals (such as employee clock-in records, device operation instruction signals) and the like.

[0070] In the embodiment of the present application, referring to Figure 2 As shown in the figure, the signal reconstruction is performed on each running signal in the running signal set to obtain a reconstructed signal, which comprises:

[0071] S21, signal sampling is performed on each running signal by using a preset sampling frequency to obtain a sampling signal;

[0072] S22, the sampling signal is processed by using a Hamming window double interpolation fast Fourier transform to obtain an actual sampling frequency;

[0073] S23, the actual sampling signal of each running signal is collected by using the actual sampling frequency;

[0074] S24, the actual sampling signal is reconstructed by using a cubic spline interpolation to obtain a reconstructed signal.

[0075] In the embodiment of the present application, the number of times of sampling the running signal in a unit time is determined by the preset sampling frequency to obtain a sampling signal, for example, the sampling frequency of 50Hz can be set to sample each original running signal to obtain a sampling signal.

[0076] Further, the sampling signal is processed by using a Hamming window double interpolation fast Fourier transform, which is to apply a Hanning window function to the signal, then perform FFT transform, and finally correct the amplitude and frequency of the frequency spectrum by using an interpolation method to obtain the actual basic frequency of each running signal, and then the signal sampling can be more accurately performed by using the actual sampling signal to provide a basis for subsequent signal reconstruction.

[0077] In the embodiment of the present application, the cubic spline interpolation reconstruction is to fit a plurality of cubic polynomials between the known sampling points, so as to realize the smooth reconstruction of the original signal. It not only can pass through all the known sampling points, but also can ensure the continuity of the first and second derivatives of the interpolation function, so as to obtain a smoother curve.

[0078] In the embodiment of the present application, the sampling signal can be effectively reconstructed, the original shape is recovered, the smoothness of the reconstructed signal is maintained, and a more accurate reconstructed signal is obtained by signal reconstruction on the running signal.

[0079] S2, signal enhancement is performed on the running signal according to the reconstructed signal to obtain an enhanced signal, and the signal source of the running signal is identified according to the enhanced signal.

[0080] In the embodiment of the present application, the signal enhancement is further to optimize the quality of the reconstructed signal, and the signal source of the running signal, such as the device from the smart factory and the specific category of the running signal, can be identified through the enhanced signal.

[0081] In the embodiment of the present application, referring to Figure 3 As shown in the figure, the signal enhancement is performed on the running signal according to the reconstructed signal to obtain an enhanced signal, and the signal source of the running signal is identified according to the enhanced signal.

[0082] S31, the reconstructed signal is subjected to complete ensemble empirical mode decomposition to obtain a decomposition component;

[0083] S32, a component parameter value of each decomposition component is calculated respectively;

[0084] S33, a signal threshold of the reconstructed signal is calculated according to the component parameter value, the decomposition component is screened based on the signal threshold, and a target component is obtained;

[0085] S34, the target component is used to construct the enhanced signal of the running signal.

[0086] In detail, the complete adaptive noise ensemble empirical mode decomposition (CEEMDAN) is an improved empirical mode decomposition (EMD) method for processing nonlinear and non-stationary signals. The adaptive noise and step-by-step average processing are introduced on the basis of EEMD (Ensemble Empirical Mode Decomposition), which can effectively solve the problems of mode aliasing and noise interference.

[0087] In detail, the complete ensemble empirical mode decomposition is performed on the reconstructed signal to obtain a decomposition component, which includes:

[0088] The reconstructed signal is taken as an original signal, and a preset Gaussian white noise is added to the original signal to obtain a white noise reconstructed signal;

[0089] The white noise reconstructed signal is subjected to modal decomposition to obtain a plurality of modal decomposition components.

[0090] Summing up and averaging the plurality of modal decomposition components to obtain an intrinsic modal component and a residual modal component;

[0091] Taking the residual modal as the original signal and returning to the step of adding the preset Gaussian white noise in the original signal to obtain the white noise reconstructed signal until the residual component is a monotonic function to obtain a plurality of intrinsic modal components;

[0092] Taking the plurality of intrinsic modal components as the decomposition components of the reconstructed signal.

[0093] In detail, the Gaussian white noise of different amplitudes and opposite numbers is added in the original signal to obtain a white noise reconstructed signal, a plurality of modal decomposition components are obtained after the white noise reconstructed signal is subjected to modal decomposition (Empirical Mode Decomposition, EMD), the intrinsic modal component is obtained by summing up and averaging the modal decomposition components, the residual modal component is obtained after the reconstructed signal is subtracted by the intrinsic modal component, the residual modal is taken as the original signal, the step of modal decomposition is repeated until the residual modal component obtained is a monotonic function and cannot be decomposed, and a plurality of decomposition components after the reconstructed signal is subjected to complete ensemble empirical mode decomposition are obtained.

[0094] In the embodiment of the application, the component parameter value of each decomposition component is calculated by using the following formula:

[0095]

[0096] M = pK

[0097] Wherein, Cov(·) represents covariance, Y IMF represents a decomposition component, x represents a reconstructed signal, D(·) represents variance, E(·) represents expectation, and M represents a component parameter value.

[0098] Further, the signal threshold of the reconstructed signal is calculated by using the following formula:

[0099]

[0100] Wherein, V represents a signal threshold, M n represents a component parameter value of the nth decomposition component, N represents the total number of decomposition components, represents the mean value of the component parameter value.

[0101] In the embodiment of the application, the decomposition component lower than the signal threshold is removed as a false component or noise to complete the screening of the decomposition component, and a target component is obtained. The target component is subjected to signal reconstruction to obtain an enhanced signal.

[0102] In the embodiment of the present application, the signal source of the operation signal is identified according to the enhanced signal, comprising:

[0103] Signal features of the enhanced signal are extracted;

[0104] Dual features of the signal features are extracted by using a pre-constructed dual attention network;

[0105] The dual features are fused to obtain fused features;

[0106] The enhanced signal is classified according to the fused features to obtain the signal source.

[0107] In detail, the dual attention network includes a channel attention module and a spatial attention module. The channel attention module performs global maximum pooling and global average pooling on the input signal features in the spatial dimension to extract context features. The spatial attention module generates features representing two different contexts by performing global maximum pooling and global average pooling in the channel dimension, which can increase the feature extraction capability without increasing the calculation amount. Then, the features are fused by element-wise addition to obtain fused features.

[0108] Further, a pre-constructed classifier can be used to classify the enhanced signal to obtain the signal source, such as an SVM classifier, a pre-trained signal classification network, etc.

[0109] In the embodiment of the present application, by performing signal enhancement on the operation signal, the signal noise of the reconstructed signal can be removed, and the interference of irrelevant signals can be avoided. Then, by identifying the signal source of the operation signal, the corresponding factory equipment of the operation signal can be adjusted, and the accuracy of the intelligent factory control can be improved.

[0110] S3, constructing an operation signal image of the reconstructed signal, and calculating a signal distance between the operation signal image and a reference signal image corresponding to the signal source.

[0111] In the embodiment of the present application, the signal image is a two-dimensional image converted from a one-dimensional signal, which is beneficial to analyze the time-frequency characteristics, periodicity, trend and other features of the reconstructed signal.

[0112] In the embodiment of the present application, the operation signal image of the reconstructed signal is constructed, comprising:

[0113] The reconstructed signal is segmented and overlap sampled to obtain segmented signal samples of the reconstructed signal;

[0114] The pixel value corresponding to each sample point in each segmented signal sample is calculated;

[0115] The signal image is obtained by image encoding according to the pixel value.

[0116] In detail, the split overlap sampling is truncating the reconstructed signal, and there is a part of overlap between the next truncated signal and the last truncated signal, so as to improve the diversity of the signal sample, ensure the accuracy of the signal image construction, and obtain the running signal image of the reconstructed signal image in multiple time periods by split overlap sampling.

[0117] In the embodiment of the application, the pixel value of each sample point is normalized and converted into a gray pixel value of 0 to 255, thereby providing a basis for subsequent image coding.

[0118] Further, for the signal sample of length D 2 The matrix form of the signal image can be expressed as:

[0119]

[0120] In the embodiment of the application, the reference signal image is a signal image of a normal running time reference signal of a signal source, and by calculating the signal distance between the running signal image and the reference signal image corresponding to the signal source, the difference size and difference distribution between the running signal and the reference signal can be analyzed, and then the equipment running category corresponding to the running signal can be determined.

[0121] Specifically, the calculation of the signal distance between the running signal image and the reference signal image corresponding to the signal source comprises:

[0122] The adjacent pixel value difference of the running signal image and the reference signal image is calculated respectively;

[0123] A pixel difference sequence matrix is constructed according to the adjacent pixel value difference, and a feature hash value is calculated according to the pixel difference sequence matrix;

[0124] A Hamming distance is calculated according to the feature hash value, and the Hamming distance is taken as the signal distance.

[0125] In detail, the embodiment of the application calculates the difference of the adjacent pixel value in the order from left to right and from top to bottom, if there are n pixels, an n-1 dimensional pixel difference sequence matrix is formed, each matrix element value greater than zero in the pixel difference sequence matrix is reset to 1, and each matrix element value not greater than zero is reset to 0, and the feature hash value of each matrix element is obtained.

[0126] The Hamming distance is calculated by using the following formula:

[0127]

[0128] Wherein, L represents the Hamming distance, ​a gth feature hash value corresponding to the running signal image, denotes element-wise addition, a gth feature hash value corresponding to the running signal image.

[0129] In the embodiment of the present application, the Hamming distance can reflect the difference between the running signal and the reference signal in different signal segments, and further reflect the running state of the signal source device, thereby effectively improving the accuracy of intelligent factory control.

[0130] S4, identifying the device running category of the running signal according to the signal distance, and performing device regulation on the signal source based on the device running category to obtain a regulated signal.

[0131] In the embodiment of the present application, the device running category is a specific state or mode of the signal source device in the running process, for example, whether the device fails, whether the device runs according to the set program, etc. The device running category can accurately regulate the device.

[0132] In the embodiment of the present application, the device running category is identified according to the signal distance, comprising:

[0133] According to the signal distance, the signal position of the running signal is identified, and a target running signal is determined according to the signal position.

[0134] The target running signal is subjected to modal decomposition to obtain a plurality of modal components.

[0135] The correlation coefficient between each modal component and the target running signal is calculated.

[0136] According to the correlation coefficient, the effective modal component of the target running signal is calculated, and the Hilbert spectrum of the target running signal is constructed according to the effective modal component.

[0137] According to the Hilbert spectrum, the target running signal is classified to obtain the device running category of the running signal.

[0138] In the embodiment of the present application, the signal distance is used to identify the segmented signal sample that may appear abnormal, for example, the signal distance between the third and fourth signal segmented signal samples has a mutation and is greater than a preset distance threshold, then the third and fourth signal segmented signal samples are target running signals, and the corresponding device running category needs to be determined to more accurately monitor the running signal.

[0139] Further, the target operation signal is decomposed into a preset number k of modal components through modal decomposition, and a correlation coefficient between each modal component and the target operation signal is calculated according to a Pearson correlation coefficient, so as to reflect the similarity between the modal component and the target operation signal, and the greater the correlation coefficient, the more similar the target operation signal.

[0140] In detail, it is judged whether the minimum correlation coefficient is less than a preset threshold, for example, whether it is less than 0.2, if not less than the preset threshold, k is k+1, the target operation signal is re-decomposed, until the minimum correlation coefficient is less than the preset threshold, and the decomposition component corresponding to the minimum correlation coefficient is removed as an invalid component, and the remaining decomposition components are Hilbert transformed as effective modal components to obtain the Hilbert spectrum of the target operation signal, and the device operation category of the operation signal can be identified according to the change of the characteristic frequency in the Hilbert spectrum. For example, the characteristic similarity between the change of the characteristic frequency in the Hilbert spectrum and the preset category characteristic frequency change is calculated to determine the device operation category.

[0141] In the embodiment of the application, the signal distance can be identified according to the operation signals of different time periods, so as to more accurately identify the specific state or mode of the device in the operation process, and improve the accuracy of device control.

[0142] In the embodiment of the application, the device control is to adjust the device corresponding to the signal source to the required state to ensure the normal operation of the device.

[0143] In the embodiment of the application, the device control of the signal source based on the device operation category to obtain the control signal includes:

[0144] The device adjustment parameter is determined according to the device operation category;

[0145] The signal type is converted according to the device adjustment parameter to obtain an analog signal;

[0146] The analog signal is encoded to obtain a control signal.

[0147] In the embodiment of the application, the device adjustment parameter is to adjust the device operation category of the signal source to a preset target device state, for example, to adjust the power, voltage, frequency and other operation states and various parameters of the device, to generate a device identifiable control signal, for example, a PWM (pulse width modulation) signal, to realize the control of the device corresponding to the signal source.

[0148] Further, corresponding signal conversion is performed according to the hardware type of each signal source, so as to ensure that the control signal can control the signal source, convert the digital device adjustment parameter into a corresponding analog signal, and encode into a transmissible data signal to obtain the control signal.

[0149] Specifically, the form of the control signal can be determined according to the hardware type of the signal source, for example, an analog signal (voltage / current), a digital signal (high / low level, PWM), a communication protocol (I2C, SPI, UART, CAN, Modbus, etc.), and the control signal can be obtained by using a corresponding control code to control the device of the signal source.

[0150] S5, generating a joint control signal of the smart factory according to the control signal, and controlling the smart factory by using the joint control signal.

[0151] In the embodiment of the application, the joint control signal is an overall signal required for device adjustment of the entire smart factory, and the joint control signal can realize overall control of the devices in the smart factory.

[0152] In the embodiment of the application, the generating of the joint control signal of the smart factory according to the control signal comprises:

[0153] calculating the task priority of the control signal;

[0154] generating a control signal queue according to the task priority;

[0155] constructing the joint control signal of the smart factory according to the control signal queue.

[0156] In detail, the task priority can be determined according to the category of each control signal, the emergency degree of the control signal, the resource requirement of the control signal, etc. For example, the control signal related to device abnormality, the control signal with the shortest execution time, or the control signal with greater relevance to the smart factory can be processed preferentially. The priority rules can be set according to the category of the control signal, so as to determine the task priority between multiple control signals.

[0157] For example, the weight can be assigned to each type of control signal and the emergency degree of the control signal, and the task priority can be determined by multi-dimensionally scoring and weighted summing each control signal according to the weight.

[0158] In detail, each control signal is sent to the corresponding device for execution according to the control signal queue, so as to realize the collaborative optimization of the multi-device system in the smart factory.

[0159] Further, the regulation task with the highest priority is taken as the first task in the regulation signal queue, and the regulation signals are transmitted in sequence according to the regulation signal queue when the joint regulation signal is executed, so that the joint regulation of the smart factory is realized, and the intelligent control of the smart factory is more accurate.

[0160] As Figure 4 shown in the figure is a functional module diagram of the smart factory intelligent control device based on signal monitoring provided by an embodiment of the application.

[0161] The smart factory intelligent control device based on signal monitoring 400 can be installed in an electronic device. According to the functions to be implemented, the smart factory intelligent control device based on signal monitoring 400 can include a signal reconstruction module 401, a signal source identification module 402, a signal distance calculation module 403, a regulation signal construction module 404, and a smart factory control module 405. The modules of the application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0162] In this embodiment, the functions of each module / unit are as follows:

[0163] The signal reconstruction module 401 is configured to obtain a set of operation signals of a smart factory, reconstruct each operation signal in the set of operation signals to obtain a reconstructed signal.

[0164] The signal source identification module 402 is configured to perform signal enhancement on the operation signal according to the reconstructed signal to obtain an enhanced signal, and identify the signal source of the operation signal according to the enhanced signal. Wherein, the signal enhancement on the operation signal according to the reconstructed signal to obtain an enhanced signal comprises: performing complete ensemble empirical mode decomposition on the reconstructed signal to obtain a decomposition component; and calculating a component parameter value of each decomposition component.

[0165] The component parameter value of each decomposition component is calculated by the following formula:

[0166]

[0167]

[0168] Wherein, Cov(·) represents covariance, Y IMF represents a decomposition component, x represents a reconstructed signal, D(·) represents variance, E(·) represents expectation, and M represents a component parameter value.

[0169] A signal threshold of the reconstructed signal is calculated according to the component parameter value, the decomposition components are screened based on the signal threshold to obtain target components, and an enhanced signal of the running signal is constructed by using the target components;

[0170] The signal distance calculation module 403 is configured to construct a running signal image of the reconstructed signal, and calculate a signal distance between the running signal image and a reference signal image corresponding to the signal source;

[0171] The regulation signal construction module 404 is configured to identify a device running category of the running signal according to the signal distance, and perform device regulation on the signal source based on the device running category to obtain a regulation signal;

[0172] The smart factory control module 405 is configured to generate a joint regulation signal of the smart factory according to the regulation signal, and control the smart factory by using the joint regulation signal.

[0173] In detail, each module in the smart factory intelligent control device 400 based on signal monitoring in the embodiment of the present application adopts the same technical means as the smart factory intelligent control method based on signal monitoring in the above Figures 1 to 3 , and can produce the same technical effects, which will not be described here.

[0174] For example, although not shown, the electronic device can further include a power supply (such as a battery) for powering each component. Preferably, the power supply can be logically connected to the at least one processor 501 through a power management device, so as to realize functions such as charge management, discharge management, and power consumption management through the power management device. The power supply can also include one or more direct current or alternating current power supplies, recharging devices, power supply fault detection circuits, power supply converters or inverters, power supply status indicators, and any other components. The electronic device can also include various sensors, Bluetooth modules, Wi-Fi modules, and the like, which will not be described here.

[0175] It should be understood that the embodiments are only for illustration, and the scope of the patent application is not limited by the structure.

[0176] The present application also provides an electronic device, which can include a processor, a memory, a communication bus, and a communication interface, and can also include a computer program stored in the memory and executable on the processor, such as the welding stability improvement method program of the heterogeneous titanium alloy laser welding technology.

[0177] The processor may, in some embodiments, be composed of integrated circuits, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits of the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, combinations of various control chips, etc. The processor is the control unit of the electronic device, connects various components of the electronic device through various interfaces and lines, executes programs or modules stored in the memory (such as the program of the welding stability improvement method of the heterogeneous titanium alloy laser welding technology), calls data stored in the memory, and performs various functions and processes data of the electronic device.

[0178] The memory includes at least one type of readable storage medium, including flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. The memory may, in some embodiments, be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory may, in other embodiments, also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the memory may include both the internal storage unit and the external storage device of the electronic device. The memory can be used not only to store application software and various data installed on the electronic device, such as the code of the program of the welding stability improvement method of the heterogeneous titanium alloy laser welding technology, but also to temporarily store data that has been or will be output.

[0179] The communication bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize the connection and communication between the memory, the processor, etc.

[0180] The communication interface is used for communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface can include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device and other electronic devices. The user interface can be a display, an input unit (such as a keyboard), and optionally, the user interface can also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch, etc. Among them, the display can also be appropriately called a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0181] Only the electronic device with components is shown in the figure, and those skilled in the art can understand that the structure shown in the figure does not constitute a limitation on the electronic device, and can include fewer or more components than the figure, or combine certain components, or different component arrangements.

[0182] For example, although not shown, the electronic device can also include a power supply (such as a battery) for powering each component. Preferably, the power supply can be connected to the at least one processor logic through a power management system, so as to realize functions such as charge management, discharge management, and power consumption management through the power management system. The power supply can also include one or more direct current or alternating current power supplies, a recharging system, a power supply fault detection circuit, a power supply converter or inverter, a power supply status indicator, and any other components. The electronic device can also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described here.

[0183] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the related steps in the corresponding embodiment of the accompanying drawings, which is not described here.

[0184] Further, the modules / units integrated in the electronic device, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or system capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM).

[0185] The application further provides a computer readable storage medium, which stores a computer program, and the computer program can realize the following steps when executed by a processor of an electronic device:

[0186] Obtain a running signal set of the smart factory, reconstruct each running signal in the running signal set to obtain a reconstructed signal;

[0187] Perform signal enhancement on the running signal according to the reconstructed signal to obtain an enhanced signal, and identify a signal source of the running signal according to the enhanced signal; wherein the signal enhancement on the running signal according to the reconstructed signal to obtain an enhanced signal comprises: performing complete set empirical mode decomposition on the reconstructed signal to obtain a decomposition component; and calculating a component parameter value of each decomposition component respectively.

[0188] The component parameter value of each decomposition component is calculated by using the following formula:

[0189]

[0190] M = pK

[0191] Wherein, Cov(·) represents covariance, Y IMF represents a decomposition component, x represents a reconstructed signal, D(·) represents variance, E(·) represents expectation, and M represents a component parameter value.

[0192] Calculate a signal threshold of the reconstructed signal according to the component parameter value, screen the decomposition component based on the signal threshold to obtain a target component, and construct the enhanced signal of the running signal by using the target component.

[0193] Construct a running signal image of the reconstructed signal, and calculate a signal distance between the running signal image and a reference signal image corresponding to the signal source.

[0194] Identify a device running category of the running signal according to the signal distance, and perform device regulation on the signal source based on the device running category to obtain a regulated signal.

[0195] Generate a joint regulation signal of the smart factory according to the regulated signal, and control the smart factory by using the joint regulation signal.

[0196] In several embodiments provided in the application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the modules is only a logical function division, and another division mode can be used in actual implementation.

[0197] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, i.e., may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment of the present application according to actual needs.

[0198] In addition, each functional module in various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0199] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0200] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any additional reference signs in the claims should not be considered as limiting the claims involved.

[0201] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0202] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The plurality of units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names and not to indicate any particular order.

[0203] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A smart factory intelligent control method based on signal monitoring, characterized in that, The method comprises: acquiring a set of operation signals of a smart factory, reconstructing each operation signal in the set of operation signals to obtain a reconstructed signal; performing signal enhancement on the operation signal according to the reconstructed signal to obtain an enhanced signal, and identifying a signal source of the operation signal according to the enhanced signal; wherein the signal enhancement on the operation signal according to the reconstructed signal to obtain an enhanced signal comprises: performing complete set empirical mode decomposition on the reconstructed signal to obtain decomposition components; and calculating a component parameter value of each decomposition component; the component parameter value of each decomposition component is calculated by using the following formula: where Cov( ) denotes covariance, Y IMF denotes a decomposition component, x denotes a reconstructed signal, D( ) denotes variance, E( ) denotes expectation, and M denotes a component parameter value; a signal threshold of the reconstructed signal is calculated according to the component parameter value, the decomposition components are screened based on the signal threshold to obtain target components, and the enhanced signal of the operation signal is constructed by using the target components; an operation signal image of the reconstructed signal is constructed, and a signal distance between the operation signal image and a reference signal image corresponding to the signal source is calculated; a device operation category of the operation signal is identified according to the signal distance, the signal source is controlled based on the device operation category to obtain a control signal; a joint control signal of the smart factory is generated according to the control signal, and the smart factory is controlled by using the joint control signal.

2. The signal monitoring based smart factory intelligent control method of claim 1, wherein, The signal reconstruction of each operation signal in the set of operation signals to obtain a reconstructed signal comprises: each operation signal is signal sampled by using a preset sampling frequency to obtain a sampled signal; the sampled signal is processed by using a Hamming window double interpolation fast Fourier transform to obtain an actual sampling frequency; the actual sampling signal of each operation signal is collected by using the actual sampling frequency; the actual sampling signal is reconstructed by using cubic spline interpolation to obtain a reconstructed signal.

3. The signal monitoring based smart factory intelligent control method of claim 1, wherein, The identification of the device operation category of the operation signal according to the signal distance comprises: a signal position of the operation signal is identified according to the signal distance, and a target operation signal is determined according to the signal position; the target operation signal is modal decomposed to obtain a plurality of modal components; a correlation coefficient between each modal component and the target operation signal is calculated; an effective modal component of the target operation signal is calculated according to the correlation coefficient, and a Hilbert spectrum of the target operation signal is constructed according to the effective modal component; the target operation signal is classified according to the Hilbert spectrum to obtain the device operation category of the operation signal.

4. The signal monitoring based smart factory intelligent control method of claim 1, wherein, The identification of the signal source of the operation signal according to the enhanced signal comprises: a signal feature of the enhanced signal is extracted; a double feature of the signal feature is extracted by using a pre-constructed double attention network; the double feature is fused to obtain a fused feature; the enhanced signal is classified according to the fused feature to obtain a signal source.

5. The signal monitoring based smart factory intelligent control method as claimed in claim 1, wherein, The construction of the operation signal image of the reconstructed signal comprises: the reconstructed signal is segmented and overlap sampled to obtain segmented signal samples of the reconstructed signal; a pixel value corresponding to each sample point in each signal sample is calculated; According to the pixel value, image coding is performed to obtain a signal image.

6. The signal monitoring based smart factory intelligent control method as claimed in claim 1, wherein, The signal distance between the running signal image and a reference signal image corresponding to the signal source is calculated, including: The difference values of adjacent pixel values of the running signal image and the reference signal image are calculated respectively; A pixel difference sequence matrix is constructed according to the difference values of adjacent pixel values, and a feature hash value is calculated according to the pixel difference sequence matrix; A Hamming distance is calculated according to the feature hash value, and the Hamming distance is taken as the signal distance; The Hamming distance is calculated by the following formula: wherein L represents a Hamming distance, denotes the gth feature hash value corresponding to the running signal image, denotes element-wise addition, denotes the gth feature hash value corresponding to the running signal image.

7. The signal monitoring based smart factory intelligent control method as claimed in claim 1, wherein, The device is regulated based on the device running category to obtain a regulated signal, including: Device adjustment parameters are determined according to the device running category; Signal type conversion is performed according to the device adjustment parameters to obtain an analog signal; The analog signal is encoded to obtain a regulated signal.

8. A smart factory intelligent control device based on signal monitoring, characterized in that, The device includes: A signal reconstruction module is configured to obtain a running signal set of a smart factory, and reconstruct each running signal in the running signal set to obtain a reconstructed signal; A signal source identification module is configured to enhance the running signal according to the reconstructed signal to obtain an enhanced signal, and identify the signal source of the running signal according to the enhanced signal; wherein the enhanced signal is obtained by enhancing the running signal according to the reconstructed signal, including: performing complete set empirical mode decomposition on the reconstructed signal to obtain decomposition components; and calculating component parameter values of each decomposition component respectively; The component parameter values of each decomposition component are calculated by the following formula: M = ρK where Cov( ) denotes covariance, Y IMF denotes a decomposition component, x denotes a reconstructed signal, D( ) denotes variance, E( ) denotes expectation, and M denotes a component parameter value; Signal threshold values of the reconstructed signal are calculated according to the component parameter values, the decomposition components are screened based on the signal threshold values to obtain target components; and the enhanced signal of the running signal is constructed using the target components; A signal distance calculation module is configured to construct a running signal image of the reconstructed signal, and calculate the signal distance between the running signal image and a reference signal image corresponding to the signal source; A regulated signal construction module is configured to identify the device running category of the running signal according to the signal distance, and regulate the signal source based on the device running category to obtain a regulated signal; A smart factory control module is configured to generate a joint regulated signal of the smart factory according to the regulated signal, and control the smart factory using the joint regulated signal.

9. A computer readable storage medium storing a computer program, characterized in that, The computer program is executed by a processor to implement the smart factory intelligent control method based on signal monitoring according to any one of claims 1 to 7. The computer program is executed by a processor to implement the smart factory intelligent control method based on signal monitoring according to any one of claims 1 to 7.

Images