Production energy efficiency optimization method based on AI and industrial internet

Abstract

The invention discloses a production energy efficiency optimization method based on AI and industrial Internet, and particularly relates to the field of production energy efficiency optimizing.The production energy efficiency optimization method comprises the steps that a vibration sensor is installed on frequency conversion production equipment, an equipment monitoring network is constructed, and vibration signals in a no-load stable state are collected; extracting a resonance coupling component with spatial coherence by using a time-frequency feature comparison and blind source separation method; a resonance mode identification model is established based on the graph convolutional neural network, dangerous resonance mode identification is realized, and a frequency collision avoidance instruction is sent; a multi-objective optimization function is further constructed, the optimal working frequency of each device is calculated by using a standard particle swarm optimization algorithm, a result is stored in a device control network, and finally, the frequency is adjusted through an edge controller to ensure that the device works under the optimal frequency combination, so that the problems of energy loss and sudden power consumption increase caused by resonance are effectively suppressed.

Description

Technical Field

[0001] The present invention relates to the technical field of production energy efficiency optimization, and more specifically, to a production energy efficiency optimization method based on AI and industrial Internet. Background Art

[0002] In high-density equipment environments, especially in industrial scenarios such as automobile welding workshops and semiconductor factories, multiple variable-frequency devices (such as air compressors and pump sets) often operate at the same time, and their operating frequencies are controlled by different conditions. Under specific frequency combinations, some devices will experience infrasonic resonance. The operating frequencies of multiple devices are close to the natural frequencies of the devices or there are resonant frequencies between each other. The vibrations will superimpose on each other to produce low-frequency infrasonic waves. This resonance effect may propagate to other devices or environments through the structure of the device itself. At this time, the resonance between devices will trigger the amplification effect of mechanical vibration, resulting in significant ineffective power consumption and energy waste, which will have an adverse effect on production efficiency and equipment life.

[0003] Therefore, how to accurately monitor the vibration characteristics of equipment and suppress infrasonic resonance through intelligent means has become an important issue in industrial production. To address this problem, traditional monitoring methods usually rely on single vibration sensor monitoring and frequency screening, which makes it difficult to accurately identify and analyze complex resonance phenomena, especially the hidden power consumption when multiple devices work together.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a production energy efficiency optimization method based on AI and industrial Internet to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: S1: Install vibration sensors on variable frequency production equipment to establish an equipment monitoring network and collect the original vibration signal sequence of the equipment in a no-load stable state; S2: construct a reference template of time-frequency features based on the original vibration signal sequence, and judge whether the real-time vibration signal features are valid by comparing the feature vector of the real-time vibration signal sequence with the feature matching degree of the reference template; S3: Use a sliding window to perform blind source separation on the collected real-time signal sequence and extract the resonant coupling components with spatial coherence characteristics from the independent vibration components; S4: A weighted graph data structure is constructed based on the independent vibration components after blind source separation, and a resonant mode recognition model is established using a graph convolutional neural network architecture; S5: Connect the trained and verified resonance mode recognition model to the equipment monitoring network to identify dangerous resonance modes, and send frequency collision avoidance instructions to the corresponding equipment nodes according to the recognition results; S6: construct a multi-objective optimization function including a resonance energy transfer coefficient for the device that receives the frequency collision avoidance instruction, solve the optimal operating frequency combination of each frequency conversion device and store it in the device control network; S7: Obtain the optimal operating frequency combination in the device monitoring network, and send a frequency control instruction to the edge controller of the target device to perform a frequency adjustment operation.

[0007] In a preferred embodiment, in S1, installing vibration sensors on variable frequency production equipment to establish an equipment monitoring network, and collecting the original vibration signal sequence of the equipment in a no-load stable state specifically includes: Count all the variable frequency production equipment in the production line, arrange piezoelectric vibration sensors at the installation locations of the variable frequency production equipment, convert all equipment into a node-based physical topology structure based on the location distribution of the sensors, and establish an equipment monitoring network; Configure the time-sensitive network communication protocol, establish a clock synchronization link between device nodes, send periodic timing signals for time alignment, and build a data transmission priority queue based on the device node topology structure; The three-axis vibration signal sequence of the equipment in the no-load stable state is collected, and the denoising algorithm is applied to eliminate the electromagnetic interference noise to obtain the original vibration signal sequence of the equipment with a set time window size.

[0008] In a preferred embodiment, in S2, a reference template of time-frequency features is constructed based on the original vibration signal sequence, and by comparing the feature matching degree between the feature vector of the real-time vibration signal sequence and the reference template, determining whether the real-time vibration signal feature is valid specifically includes: A multi-dimensional feature vector is constructed based on the time domain kurtosis index and frequency domain energy data of the original vibration signal sequence to generate a reference template containing time-frequency features; The equipment monitoring network monitors the real-time vibration signal sequence of the equipment in real time, extracts the corresponding time-frequency feature vector and calculates the feature matching degree with the reference template through cosine similarity. When the matching degree mean of consecutive set sampling periods exceeds the set matching degree threshold, a feature validity confirmation signal is sent.

[0009] In a preferred embodiment, in S3, using a sliding window to perform blind source separation on the collected real-time signal sequence, and extracting the resonant coupling component with spatial coherence characteristics from the independent vibration component specifically includes: When the equipment monitoring network receives a feature valid confirmation signal, a sliding window is used to perform blind source separation on the collected real-time signal sequence; The real-time signal sequence is whitened by diagonalizing the covariance matrix, and the FastICA algorithm is used to perform independent component analysis on the whitened signal. The separation matrix is ​​iteratively solved based on the negative entropy maximization criterion to separate the independent vibration components of each device. Based on the physical topology of the equipment monitoring network, the physical connection stiffness parameters of the equipment nodes are set to construct the transfer constraint matrix, where the physical connection stiffness parameters are calculated as follows: ; In the formula, For equipment To device The physical connection stiffness parameters, For vibration signals in the device With equipment The propagation speed in the connecting medium, For equipment To device The distance For equipment To device The vibration signal attenuation rate; The phase offset of the separated components is corrected by matrix projection operation, and the resonant coupling components with spatial coherence characteristics in the independent vibration components are extracted.

[0010] In a preferred embodiment, in S4, a weighted graph data structure is constructed based on the independent vibration components after blind source separation, and a resonance mode recognition model is established using a graph convolutional neural network architecture, specifically including: The time-frequency characteristics of the independent vibration components and resonant coupling components after blind source separation are integrated with the physical topological coordinate data of the equipment to construct a weighted resonant modal graph. The edge weights of the graph reflect the physical connection stiffness parameters between equipment nodes. A resonant mode recognition model is established using a graph convolutional neural network architecture. The independent vibration components of neighboring device nodes are aggregated layer by layer. The resonant energy transfer coefficient between devices is calculated through a multi-head attention mechanism to generate a resonant coupling strength matrix in the frequency-space dimension. A resonance coupling strength threshold is set, and adjacent device node pairs whose resonance coupling strength exceeds the threshold are marked as dangerous resonance modes, and their dominant resonance coupling strength and energy transfer path are recorded.

[0011] In a preferred embodiment, in S5, the trained and verified resonance mode recognition model is connected to the equipment monitoring network to identify dangerous resonance modes, and the frequency collision avoidance instruction is sent to the corresponding equipment node according to the recognition result, which specifically includes: The historical operation data of the equipment network is selected as the training set and the validation set data to input into the resonance mode identification model, and the model parameters are adjusted based on the matching degree deviation between the predicted resonance coupling strength and the measured dominant resonance coupling strength of the validation set data; When the prediction accuracy of the model verified by a set number of consecutive groups of historical operation data reaches a preset index, the model is connected to the equipment monitoring network to identify dangerous resonance modes, and frequency collision avoidance instructions are sent to adjacent equipment nodes corresponding to the identified dangerous resonance modes.

[0012] In a preferred embodiment, in S6, constructing a multi-objective optimization function including a resonance energy transfer coefficient for the device that receives the frequency collision avoidance instruction, solving the optimal operating frequency combination of each frequency conversion device and storing it in the device control network specifically includes: When the device receives a frequency collision avoidance instruction, it initializes the device operating frequency search space based on the resonance coupling strength matrix in the resonance mode diagram, defines the device adjustable frequency range and the minimum adjustment step, and constructs a multi-objective optimization function including the resonance energy transfer coefficient. The Cauchy mutation mechanism is introduced into the standard particle swarm optimization algorithm. The search radius is expanded by dynamically adjusting the mutation probability. The real-time independent vibration components of the equipment and the coupling strength matrix parameters are input into the multi-objective optimization function. The optimal operating frequency combination of each frequency conversion equipment is solved and stored in the equipment control network.

[0013] In a preferred embodiment, in S7, obtaining the optimal operating frequency combination in the device monitoring network and sending a frequency control instruction to the edge controller of the target device to perform a frequency adjustment operation specifically includes: Obtain the optimal operating frequency combination in the device monitoring network, and send frequency control instructions to the edge controller of the target device according to the preset routing table based on the data transmission priority queue; The device node stores the received frequency control instruction into the register, dynamically adjusts the instruction effectiveness timing according to the current operating status of the device, and executes the frequency adjustment operation when the controller ready signal is aligned with the clock synchronization pulse.

[0014] Technical effects and advantages of a production energy efficiency optimization method based on AI and industrial Internet in the present invention: By installing vibration sensors on the frequency conversion equipment and establishing an equipment monitoring network, the original vibration signals in the no-load stable state are collected in real time. The sliding window and blind source separation technology are used to extract independent vibration components, and the resonant coupling components with spatial coherence characteristics are identified from the complex vibration signals. By constructing a weighted graph data structure and using a graph convolutional neural network (GCN) for resonant mode identification, it is possible to accurately identify potential dangerous resonance modes, and effectively avoid resonant coupling between devices through frequency collision avoidance instructions, thereby reducing ineffective power consumption. The multi-objective optimization solution strategy based on the optimization function can determine the optimal operating frequency combination for each frequency conversion device, thereby improving the energy efficiency and stability of the equipment cluster. Through intelligent algorithms and precise vibration monitoring, the entire system can achieve dynamic adjustment, reduce the hidden energy consumption of equipment, and improve overall production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of a production energy efficiency optimization method based on AI and industrial Internet in the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Embodiment 1:

[0017] Figure 1 The present invention provides a production energy efficiency optimization method based on AI and industrial Internet, which includes the following steps: S1: Install vibration sensors on variable frequency production equipment to establish an equipment monitoring network and collect the original vibration signal sequence of the equipment in a no-load stable state; S2: construct a reference template of time-frequency features based on the original vibration signal sequence, and judge whether the real-time vibration signal features are valid by comparing the feature vector of the real-time vibration signal sequence with the feature matching degree of the reference template; S3: Use a sliding window to perform blind source separation on the collected real-time signal sequence and extract the resonant coupling components with spatial coherence characteristics from the independent vibration components; S4: A weighted graph data structure is constructed based on the independent vibration components after blind source separation, and a resonant mode recognition model is established using a graph convolutional neural network architecture; S5: Connect the trained and verified resonance mode recognition model to the equipment monitoring network to identify dangerous resonance modes, and send frequency collision avoidance instructions to the corresponding equipment nodes according to the recognition results; S6: construct a multi-objective optimization function including a resonance energy transfer coefficient for the device that receives the frequency collision avoidance instruction, solve the optimal operating frequency combination of each frequency conversion device and store it in the device control network; S7: Obtain the optimal operating frequency combination in the device monitoring network, and send a frequency control instruction to the edge controller of the target device to perform a frequency adjustment operation.

[0018] In S1, vibration sensors are installed on the variable frequency production equipment to establish an equipment monitoring network, and the original vibration signal sequence of the equipment in a no-load stable state is collected.

[0019] This can be done by querying the database or integrating with the production line equipment management system (such as ERP, SCADA system) to identify and count all variable frequency production equipment (such as air compressors, pump sets, etc.) in the production line. Install piezoelectric vibration sensors at key parts of each equipment (such as motors, bearings, pump bodies, etc.). These locations should be based on the structural characteristics of the equipment to ensure that key vibration sources that may cause failures are monitored. Piezoelectric sensors are suitable for variable frequency equipment because their high sensitivity can effectively capture weak vibration signals, especially resonant signals at low frequencies and infrasonic frequencies.

[0020] Configure and implement the Time Sensitive Network (TSN) protocol. TSN supports real-time data transmission to ensure accurate alignment of communication time between devices. TSN can support high-precision clock synchronization to ensure time consistency of all device nodes and avoid data inconsistency caused by time delays. Configure device nodes to send timing signals within a fixed period and perform clock correction through synchronization algorithms (such as offset adjustment algorithms). After each device node receives the synchronization signal, it adjusts the local clock to achieve global synchronization.

[0021] When the equipment is in a stable no-load state, collect three-axis vibration signals (acceleration signals in the three directions of X, Y, and Z). The equipment should be in a constant operating state to ensure that there is no interference from external load changes. These vibration signals will provide the basic vibration characteristic data of the equipment. Use a denoising algorithm (such as wavelet denoising or Kalman filtering) to denoise the collected signals. Electromagnetic interference noise usually appears in the high-frequency area, and the denoising algorithm restores the true characteristics of the signal by filtering out the high-frequency noise components. Set an appropriate time window (such as 1 second, 5 seconds, etc.), and collect the vibration signals of the equipment in segments to form a vibration signal data sequence for each device at different time points.

[0022] In S2, a reference template of time-frequency features is constructed based on the original vibration signal sequence, and whether the real-time vibration signal feature is valid is determined by comparing the feature vector of the real-time vibration signal sequence with the feature matching degree of the reference template.

[0023] The time domain kurtosis index is an index used to measure the peak characteristics of the signal. The larger the time domain kurtosis value of the vibration signal is, the more peak components there are in the signal, which is usually related to abnormal vibration of the equipment. The specific kurtosis calculation formula is: ; In the formula, is the kurtosis value of the vibration signal sequence, Set the number of signal samples in the time window, is the signal value, indicating the amplitude of the ath signal sample, , are the mean and standard deviation of the signal samples within the set time window respectively.

[0024] The vibration signal is converted to the frequency domain through fast Fourier transform (FFT), the energy spectrum of the signal is calculated, the energy distribution information of each frequency band is extracted through the spectrum data, the main frequency components and their corresponding energy values ​​are identified, and the frequency domain features are formed.

[0025] By integrating the kurtosis value in the time domain and the energy data in the frequency domain, we construct the multi-dimensional feature vectors of the equipment. These feature vectors will reflect the vibration characteristics of the equipment and serve as reference features of the normal working state of the equipment without electromagnetic interference, forming a feature reference template.

[0026] The equipment monitoring network monitors the real-time vibration signal sequence of the equipment in real time, extracts the corresponding time-frequency feature vector, and calculates the feature matching degree with the reference template through cosine similarity. The size of each sampling period is consistent with the size of the original vibration signal sequence. The matching degree calculation method is: ; In the formula, is the result of matching calculation. , are the feature vectors of the ath original vibration signal and the real-time vibration signal respectively (including the time domain kurtosis index and frequency domain energy characteristics).

[0027] When the matching average of consecutively set sampling periods (greater than 1) exceeds the set matching threshold (based on the comprehensive setting of the equipment operating environment and the degree of electromagnetic interference, the default setting is 0.95), a feature validity confirmation signal is sent, indicating that the vibration characteristics of the equipment continue to meet the normal working state and there is no complex environmental interference.

[0028] In S3, a sliding window is used to perform blind source separation on the collected real-time signal sequence to extract the resonant coupling components with spatial coherence characteristics from the independent vibration components.

[0029] When the equipment monitoring network receives a feature validation confirmation signal, it indicates that the real-time vibration signal sequence has exceeded the set threshold for feature matching with the reference template, and the signal can be considered valid. At this point, the monitoring network processes the collected original signal sequence in real time through the sliding window technology. The role of the sliding window is to ensure that the signal is analyzed step by step in a continuous data stream to avoid the computational pressure caused by processing large amounts of data at one time. The window size is set to 100ms or shorter to ensure a fast signal response, and the sliding step is set to 20ms or shorter to ensure the accuracy of the signal continuity analysis.

[0030] The real-time signal sequence is whitened by diagonalizing the covariance matrix. Whitening is to diagonalize the covariance matrix of the signal so that the various signal components are no longer correlated. Its main purpose is to eliminate the correlation in the signal and ensure that the subsequent blind source separation can be carried out more effectively.

[0031] The FastICA algorithm is used to perform independent component analysis (ICA) on the whitened signal in order to separate the independent vibration components of each device. The FastICA algorithm is based on the negentropy maximization criterion. It maximizes the negentropy (i.e., non-Gaussianity) of the signal by continuously iteratively optimizing the separation matrix W, thereby achieving blind source separation. The specific expression of the implementation process of the negentropy maximization criterion is: ; Where w is the basis vector being optimized, is the updated weight vector, indicating the direction of each independent component. By gradually optimizing w, the most independent component can be extracted from the real-time signal. N is the number of signals in the sliding window. is the frequency domain eigenvector of the ith signal, is the current weight vector w and the signal The inner product of represents the projection of the extracted signal component on a certain dimension. is the learning rate, which is used to control the magnitude of each update. g(y) is a nonlinear function (y is an arbitrary variable). Common choices include tanh(y), Or other high-order functions. The role of this function is to increase the nonlinear components of the signal, making the independent components more independent. The maximization of negative entropy depends on the non-Gaussianity of the signal. Nonlinear functions are used to enhance this non-Gaussianity, thereby effectively extracting independent components.

[0032] Negative entropy is defined as the degree of non-Gaussianity of a signal and is used to measure the independence of the signal. Each separated signal component represents an independent vibration source, corresponding to different vibration modes of the device.

[0033] Based on the physical topology of the equipment monitoring network, the physical connection stiffness parameters of the equipment nodes are set to construct the transfer constraint matrix, where the physical connection stiffness parameters are calculated as follows: ; In the formula, For equipment To device The physical connection stiffness parameters, For vibration signals in the device With equipment The propagation speed in the connecting medium, For equipment To device The distance For equipment To device The vibration signal attenuation rate, the above variable values ​​are obtained from actual tests, the size of the physical connection stiffness parameter determines the coupling strength of the vibration signal between the devices, and thus affects the degree of the resonance coupling effect. The transfer constraint matrix will serve as the basis for subsequent transfer function calculation and signal correction.

[0034] After independent component analysis, each separated vibration component is affected by the physical topology and the propagation delay and phase offset between devices. In order to ensure that the separated vibration components can accurately reflect the vibration coupling relationship between devices, the matrix projection operation is used to correct the phase offset of the separated signal.

[0035] By using the transfer constraint matrix to correct the phase of each independent vibration component, the vibration signal of each device node is adjusted to conform to the actual propagation path. The goal of the matrix projection calculation is to minimize the phase offset of the signal and ensure the spatiotemporal consistency of the vibration signal. Identify the frequency components that appear synchronously between multiple device nodes. These frequency components show spatial coherence (the common method is to calculate the Pearson correlation coefficient), that is, these frequencies are significantly expressed in the vibration signals of multiple devices. By setting a correlation threshold, filter out those frequency components that have a high correlation in the vibration signals of multiple devices (for example, the correlation coefficient is greater than the set value). These components are the resonant coupling frequencies. Energy is extracted from these resonant frequencies, the corresponding resonant coupling modes are identified, and a basis is provided for subsequent vibration control and energy optimization.

[0036] In S4, a weighted graph data structure is constructed based on the independent vibration components after blind source separation, and a resonant mode recognition model is established using a graph convolutional neural network architecture.

[0037] The time-frequency characteristics of the independent vibration components and resonant coupling components after blind source separation are fused with the physical topological coordinate data of the equipment to construct a weighted resonant modal graph. The edge weights of the graph reflect the physical connection stiffness parameters between device nodes.

[0038] The constructed resonance mode graph is used as the input of the graph convolutional neural network (GCN), where the node features include the vibration signal features (time-frequency features) of the equipment, and the edge weights are the physical connection stiffness parameters between the equipment. The vibration feature information of the neighboring nodes is aggregated layer by layer, and the node features are weighted and summed with the features of its neighboring nodes through convolution operations to obtain the resonance information between the nodes.

[0039] On the basis of graph convolutional network, a multi-head attention mechanism is added to strengthen the information aggregation of a specific neighborhood by calculating the attention weight between each device node and its neighboring nodes. Through the multi-head attention mechanism, different resonance coupling modes between device nodes can be captured, and the resonance energy transfer coefficient between each pair of device nodes can be calculated. The specific expression is: ; In the formula, , are the feature vectors of node o and node p respectively, and are the weight matrices of the qth and kth dimensions in the attention mechanism, respectively, where k is the dimension of the vector. The calculated attention coefficient represents the resonance energy transfer coefficient. Based on the calculation result of the resonance energy transfer coefficient, a square matrix of H*H (H is the total number of nodes in the device monitoring network) is established. The resonant coupling strength matrix as a frequency-space dimension.

[0040] A resonance coupling strength threshold is set (comprehensively set based on the coefficient size in the resonance coupling strength matrix and the size of the device resonance coupling component), and adjacent device node pairs whose resonance coupling strength exceeds the threshold are marked as dangerous resonance modes, and their dominant resonance coupling strength and energy transfer path are recorded.

[0041] In S5, the trained and verified resonance mode recognition model is connected to the equipment monitoring network to identify dangerous resonance modes, and a frequency collision avoidance instruction is sent to the corresponding equipment node according to the recognition result.

[0042] Select the historical operation data of the equipment network as the training set and validation set. These historical data include the vibration signals of the equipment nodes under different operating conditions, especially the vibration data of the equipment when resonance occurs. The data set should contain the vibration signals of the equipment in normal operation and when dangerous resonance occurs, to ensure that the model can identify the diversity and variability of resonance modes. Select a certain proportion of data from the historical operation data as the training set, and the data should cover the vibration signals of the equipment under different working conditions such as no load, light load, and heavy load. Select the equipment operation data of different time periods as the validation set for model testing and parameter adjustment.

[0043] The selected training set data is input to train the resonance mode recognition model. The model mainly predicts the frequency and intensity of possible resonance based on the vibration signal characteristics of the equipment (time-frequency characteristics, kurtosis index). During training, the supervised learning method is used. Through the labeled dangerous resonance mode data, the model continuously adjusts the parameters and learns the relationship between the vibration signal pattern and the resonance phenomenon.

[0044] The predicted resonance coupling strength is calculated by the trained model and compared with the measured resonance coupling strength in the validation set data. The mean square error index is used to evaluate the accuracy of the model prediction and adjust the model parameters to minimize the prediction error.

[0045] The trained and verified resonance mode recognition model is connected to the equipment monitoring network. The equipment monitoring network collects the vibration signal of the equipment in real time and inputs it into the resonance mode recognition model for real-time analysis. The model identifies whether the equipment is in a dangerous resonance mode state based on the real-time vibration signal. The standard of a dangerous resonance mode is that the equipment produces a significant resonance coupling effect at a certain operating frequency, resulting in excessive energy transfer, which may cause equipment damage or ineffective energy consumption. When the vibration signal of the equipment matches the resonance frequency predicted by the model and identifies the dangerous resonance mode, the model will output a frequency collision avoidance command signal to indicate which equipment is in a dangerous resonance state.

[0046] In S6, a multi-objective optimization function including a resonance energy transfer coefficient is constructed for the device that receives the frequency collision avoidance instruction, and the optimal operating frequency combination of each frequency conversion device is solved and stored in the device control network.

[0047] After the device receives the frequency collision avoidance instruction, it first initializes the frequency search space according to the working characteristics of the device. The working frequency range of the device is determined by the lowest frequency and highest frequency adjustment range of the device, and the minimum step size of the frequency adjustment is determined by the minimum frequency change scale of the device.

[0048] According to the resonance coupling strength matrix between devices and the real-time vibration characteristics of the devices, a multi-objective optimization function including the resonance energy transfer coefficient is constructed. The purpose of this function is to reduce power consumption or improve work efficiency as much as possible while avoiding resonance between devices. Therefore, the actual purpose is to minimize the resonance coupling strength between devices, that is, to obtain Less than a set threshold, to avoid dangerous resonance modes, while at the same time or as much as possible to improve the working efficiency of the equipment, the specific expression is: ; In the formula, is the optimization function set, It is a coefficient that balances power consumption and resonance coupling. It is set based on the actual device energy consumption and the resonance energy transfer coefficient. is the actual power consumption of the oth device, is the current operating frequency of device o.

[0049] In order to improve the search capability of the particle swarm optimization algorithm, the Cauchy mutation mechanism is introduced. The Cauchy mutation mechanism dynamically adjusts the search radius of particles by introducing a new mutation probability. Specifically, the Cauchy mutation mechanism increases the global search capability of particle positions, especially when the search space is large, it can prevent the local optimal solution from being trapped. The search radius is expanded by dynamically adjusting the mutation probability, and the real-time independent vibration components of the equipment and the coupling strength matrix parameters are input into the multi-objective optimization function. After all particles are updated, the fitness (optimization target) of each particle is calculated to obtain the optimal frequency combination, that is, the equipment operating frequency that can minimize the resonance coupling intensity and power consumption, and the corresponding parameters are sent to the equipment monitoring network.

[0050] In S7, the optimal operating frequency combination in the device monitoring network is obtained, and a frequency control instruction is sent to the edge controller of the target device to perform a frequency adjustment operation.

[0051] The device monitoring network uses a time-sensitive network communication protocol and implements communication scheduling between devices through priority queues. The frequency control instructions of each device node will be placed in the data transmission queue and sent to the edge controller of the target device according to the preset routing table.

[0052] The device node stores the received frequency control instructions into the register, dynamically adjusts the instruction effectiveness timing according to the current operating status of the device, and performs the frequency adjustment operation when the controller ready signal is aligned with the clock synchronization pulse, ensuring that the device operates at the optimal frequency to avoid resonance and improve the operating energy efficiency of the device.

[0053] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0054] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0055] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0056] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0057] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0058] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0059] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0060] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0061] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0062] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A production energy efficiency optimization method based on AI and industrial Internet, characterized in that: The steps include: S1: Install vibration sensors on variable frequency production equipment to establish an equipment monitoring network and collect the original vibration signal sequence of the equipment in a no-load stable state; S2: construct a reference template of time-frequency features based on the original vibration signal sequence, and judge whether the real-time vibration signal features are valid by comparing the feature vector of the real-time vibration signal sequence with the feature matching degree of the reference template; S3: Use a sliding window to perform blind source separation on the collected real-time signal sequence and extract the resonant coupling components with spatial coherence characteristics from the independent vibration components; S4: A weighted graph data structure is constructed based on the independent vibration components after blind source separation, and a resonant mode recognition model is established using a graph convolutional neural network architecture; S5: Connect the trained and verified resonance mode recognition model to the equipment monitoring network to identify dangerous resonance modes, and send frequency collision avoidance instructions to the corresponding equipment nodes according to the recognition results; S6: construct a multi-objective optimization function including a resonance energy transfer coefficient for the device that receives the frequency collision avoidance instruction, solve the optimal operating frequency combination of each frequency conversion device and store it in the device control network; S7: Obtain the optimal operating frequency combination in the device monitoring network, and send a frequency control instruction to the edge controller of the target device to perform a frequency adjustment operation.

2. According to claim 1, a production energy efficiency optimization method based on AI and industrial Internet is characterized in that: In S1, vibration sensors are installed on variable frequency production equipment to establish an equipment monitoring network, and the original vibration signal sequence of the equipment in the no-load stable state is collected, including: Count all the variable frequency production equipment in the production line, arrange piezoelectric vibration sensors at the installation locations of the variable frequency production equipment, convert all equipment into a node-based physical topology structure based on the location distribution of the sensors, and establish an equipment monitoring network; Configure the time-sensitive network communication protocol, establish a clock synchronization link between device nodes, send periodic timing signals for time alignment, and build a data transmission priority queue based on the device node topology structure; The three-axis vibration signal sequence of the equipment in the no-load stable state is collected, and the denoising algorithm is applied to eliminate the electromagnetic interference noise to obtain the original vibration signal sequence of the equipment with a set time window size.

3. According to claim 2, a production energy efficiency optimization method based on AI and industrial Internet is characterized in that: In S2, a reference template of time-frequency features is constructed based on the original vibration signal sequence, and the feature matching degree of the feature vector of the real-time vibration signal sequence is compared with that of the reference template to determine whether the real-time vibration signal feature is valid. Specifically, the following steps are performed: A multi-dimensional feature vector is constructed based on the time domain kurtosis index and frequency domain energy data of the original vibration signal sequence to generate a reference template containing time-frequency features; The equipment monitoring network monitors the real-time vibration signal sequence of the equipment in real time, extracts the corresponding time-frequency feature vector and calculates the feature matching degree with the reference template through cosine similarity. When the matching degree mean of consecutive set sampling periods exceeds the set matching degree threshold, a feature validity confirmation signal is sent.

4. The production energy efficiency optimization method based on AI and industrial Internet according to claim 3 is characterized in that: In S3, a sliding window is used to perform blind source separation on the collected real-time signal sequence, and the resonant coupling components with spatial coherence characteristics in the independent vibration components are extracted, specifically including: When the equipment monitoring network receives a feature valid confirmation signal, a sliding window is used to perform blind source separation on the collected real-time signal sequence; The real-time signal sequence is whitened by diagonalizing the covariance matrix, and the FastICA algorithm is used to perform independent component analysis on the whitened signal. The separation matrix is ​​iteratively solved based on the negative entropy maximization criterion to separate the independent vibration components of each device. Based on the physical topology of the equipment monitoring network, the physical connection stiffness parameters of the equipment nodes are set to construct the transfer constraint matrix, where the physical connection stiffness parameters are calculated as follows: ； In the formula, For equipment To device The physical connection stiffness parameters, For vibration signals in the device With equipment The propagation speed in the connecting medium, For equipment To device The distance For equipment To device The vibration signal attenuation rate; The phase offset of the separated components is corrected by matrix projection operation, and the resonant coupling components with spatial coherence characteristics in the independent vibration components are extracted.

5. The production energy efficiency optimization method based on AI and industrial Internet according to claim 4 is characterized in that: In S4, a weighted graph data structure is constructed based on the independent vibration components after blind source separation, and a resonant mode recognition model is established using a graph convolutional neural network architecture, including: The time-frequency characteristics of the independent vibration components and resonant coupling components after blind source separation are integrated with the physical topological coordinate data of the equipment to construct a weighted resonant modal graph. The edge weights of the graph reflect the physical connection stiffness parameters between equipment nodes. A resonant mode recognition model is established using a graph convolutional neural network architecture. The independent vibration components of neighboring device nodes are aggregated layer by layer. The resonant energy transfer coefficient between devices is calculated through a multi-head attention mechanism to generate a resonant coupling strength matrix in the frequency-space dimension. A resonance coupling strength threshold is set, and adjacent device node pairs whose resonance coupling strength exceeds the threshold are marked as dangerous resonance modes, and their dominant resonance coupling strength and energy transfer path are recorded.

6. The production energy efficiency optimization method based on AI and industrial Internet according to claim 5 is characterized in that: In S5, the trained and verified resonance mode recognition model is connected to the equipment monitoring network to identify dangerous resonance modes, and a frequency collision avoidance instruction is sent to the corresponding equipment node according to the recognition result, which specifically includes: The historical operation data of the equipment network is selected as the training set and the validation set data to input into the resonance mode identification model, and the model parameters are adjusted based on the matching degree deviation between the predicted resonance coupling strength and the measured dominant resonance coupling strength of the validation set data; When the prediction accuracy of the model verified by a set number of consecutive groups of historical operation data reaches a preset index, the model is connected to the equipment monitoring network to identify dangerous resonance modes, and frequency collision avoidance instructions are sent to adjacent equipment nodes corresponding to the identified dangerous resonance modes.

7. The production energy efficiency optimization method based on AI and industrial Internet according to claim 6 is characterized in that: In S6, a multi-objective optimization function including a resonance energy transfer coefficient is constructed for the device that receives the frequency collision avoidance instruction, and the optimal operating frequency combination of each frequency conversion device is solved and stored in the device control network, which specifically includes: When the device receives a frequency collision avoidance instruction, it initializes the device operating frequency search space based on the resonance coupling strength matrix in the resonance mode diagram, defines the device adjustable frequency range and the minimum adjustment step, and constructs a multi-objective optimization function including the resonance energy transfer coefficient. The Cauchy mutation mechanism is introduced into the standard particle swarm optimization algorithm. The search radius is expanded by dynamically adjusting the mutation probability. The real-time independent vibration components of the equipment and the coupling strength matrix parameters are input into the multi-objective optimization function. The optimal operating frequency combination of each frequency conversion equipment is solved and stored in the equipment control network.

8. The production energy efficiency optimization method based on AI and industrial Internet according to claim 7 is characterized in that: In S7, obtaining the optimal operating frequency combination in the device monitoring network and sending a frequency control instruction to the edge controller of the target device to perform a frequency adjustment operation specifically includes: Obtain the optimal operating frequency combination in the device monitoring network, and send frequency control instructions to the edge controller of the target device according to the preset routing table based on the data transmission priority queue; The device node stores the received frequency control instruction into the register, dynamically adjusts the instruction effectiveness timing according to the current operating status of the device, and executes the frequency adjustment operation when the controller ready signal is aligned with the clock synchronization pulse.

Images