Frequency converter remote management system based on Internet of Things

Abstract

The invention relates to the technical field of frequency converter management, solves the technical problems that the prior art cannot adapt to the inherent defect of dynamic frequency modulation of a frequency converter, the defect of local minimum easily occurs and the processing efficiency is low, and particularly relates to a frequency converter remote management system based on the Internet of Things. The method comprises the steps of collecting original data of a frequency converter, calculating an interference threshold value used for carrying out interference data elimination on the original data, and obtaining preprocessed data based on the interference threshold value. By utilizing a group optimization mode, the selection efficiency of the weight value and the threshold value can be greatly improved, the classification accuracy of the operation state of the frequency converter can be improved, and the classification efficiency of the frequency converter is improved. The unsupervised learning competition layer and the supervised learning neural network are connected in series to form a new neural network model, the defect that the neural network has a local minimum value is avoided, the stability of the neural network is greatly improved, and the learning efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of frequency converter management, and in particular to a frequency converter remote management system based on the Internet of Things. Background Art

[0002] A frequency converter is a power electronic device that controls the speed of a motor by adjusting the power supply frequency and voltage. The IoT-based frequency converter remote management system collects operating parameters such as voltage, current, and temperature in real time, and combines edge computing with cloud-based analysis to achieve intelligent monitoring of device status, energy efficiency optimization, and abnormality warnings. Existing technologies usually use traditional fixed filters to implement frequency converter data collection, which cannot adapt to the inherent defects of frequency converter dynamic frequency modulation. In addition, existing technologies use unsupervised neural networks to analyze frequency converter data, which is prone to local minima. At the same time, the amount of learning data is relatively large, and the processing speed is low. Summary of the Invention

[0003] In response to the shortcomings of the existing technology, the present invention provides a frequency converter remote management system based on the Internet of Things, which solves the inherent defects of the existing technology that it cannot adapt to the dynamic frequency modulation of the frequency converter and is prone to the disadvantage of local minimum values, and at the same time solves the technical problem of low processing efficiency. It achieves the goal of accurately identifying burst interference pulses through adaptive thresholds and avoiding the disadvantage of local minimum values. At the same time, it can also reduce the amount of learning data, greatly improve the stability of the neural network, and improve the learning efficiency.

[0004] To solve the above technical problems, the present invention provides the following technical solutions: a remote management system for inverters based on the Internet of Things, the system comprising: Preprocessing module (1) is used to collect the raw data of the inverter , calculated for the original data The interference threshold Y for removing interference data, and the preprocessed data is obtained based on the interference threshold Y ; Alignment module (2) is used to pre-process data Calculate the optimization coefficient after iteration , according to the optimization coefficient Compute aligned tensors ; The hybrid feature module (3) is used to align the tensor Calculate hybrid characteristics for monitoring inverter dynamic characteristics ; Victory meta-module (4) is used to calculate the Calculate the victory yuan after iteration ; Status monitoring module (5) is used to monitor the status of the Calculating dynamic filter values , based on dynamic filter values Obtain the optimized inverter status monitoring model; Remote management module (6) for converting the hybrid characteristics of the inverter The inverter status detection result is input into the inverter status monitoring model, and the inverter status detection result is sent to the remote management center.

[0005] Furthermore, the preprocessing module includes: The carrier frequency filtering module (11) is used to filter the original data Calculate the carrier frequency filter value used for filtering ; Interference threshold module (12) is used to establish a sliding window H with a window length of C and calculate the carrier frequency filtering value inside the window Interference threshold Y; The elimination module (13) is used to filter the carrier frequency value according to the interference threshold Y. Eliminate the interference data in like , then the carrier frequency filtering value To interfere with the data and remove it; like , then the carrier frequency filtering value It is normal data and is retained; Filling module (14), used to obtain adjacent data adjacent to the removed interference data and , calculate the filling data used to supplement the interference data ; Merge module (15) is used to combine normal data and padded data Merge into preprocessed data in chronological order .

[0006] Furthermore, the alignment module includes: Interconnection module (21) is used to pre-process data Randomly select two different preprocessed data and , and calculate the preprocessed data Mutual information ; Balance module (22) for Calculate the balance coefficient ; Gradient module (23) is used to calculate the equilibrium coefficient Calculate the gradient value ; Iteration module (24) is used to calculate the gradient value Calculate the Iteration coefficient of generation ; Iteration threshold module (25), used to calculate the iteration threshold according to the quantity A ; The optimization coefficient module (26) is used to optimize the coefficient according to the iteration threshold. Determine whether the iteration is finished; like , then the optimization coefficient is repeatedly Calculation of like , then the iteration ends and the final optimization coefficient is obtained ; The optimization alignment module (27) is used to optimize the coefficients Compute aligned tensors .

[0007] Furthermore, the hybrid feature module includes: Scalar tensor module (31) for aligning tensors Get the scalar value tensor by local normalization of the sliding window ; The time domain feature module (32) is used to calculate the time domain feature according to the scale value tensor. The time domain features are obtained by sliding differential method ; Band Energy Module (33) is used to calculate the energy of a frequency band according to the scalar value tensor. Calculates the frequency band energy characteristics used to evaluate the frequency band energy fluctuation of the inverter signal ; Cross-metric module (34), used to collect raw data from the frequency converter Select the sensor pairs with physical association from the sensors , the sensor pair is obtained by local normalization method A scalar-valued tensor of and and calculate the cross metric ; The splicing module (35) is used to , frequency band energy characteristics and cross-metrics Calculating mixed features .

[0008] Furthermore, the victory meta module includes: Preparation module (41) is used to combine multiple mixed features As the input of the input layer, and define the initial learning rate , weight and neighborhood radius ; Euclidean distance module (42), used to calculate multiple mixed features Euclidean distance ; Competition module (43) is used to calculate the Calculate victory points at the competitive level ; The update module (44) is used to update the and neighborhood radius Calculate the updated learning rate and update neighborhood radius ; The control module (45) is used to update the learning rate according to Control victory dollars iterations; like , the iteration ends and the current victory element is output ; like , then recalculate the victory yuan .

[0009] Furthermore, the status monitoring module includes: Implicit module (51) is used to convert multiple victory elements As input, the implicit value is calculated through the implicit function of the hidden layer ; Output module (52) is used to output the implicit value Calculate the output value of the output layer ; The mean square error module (53) is used to define the expected value based on the model , calculate the output value and the mean square error of the expected value The mean square error value ; Optimization model module (54) for optimizing the model based on multiple basis weights , intercept value and intercept threshold Calculate optimization weights , Iteration intercept and iterative cutoff threshold , based on the optimization weights , iterative intercept and iterative cutoff threshold Building an optimization model ; Dynamic screening module (55) is used to filter the Calculating dynamic filter values ; Model building module (56) is used to dynamically filter values Complete the establishment of the inverter status monitoring model; like , then the end and the inverter status monitoring model is obtained; like , then re-train the model.

[0010] Furthermore, the optimization model The expression is: ; in, represents the qth optimization variable value, and p represents the victory element The number of

[0011] Furthermore, the optimization model module (54) includes: Initialization module (541) is used to initialize the basic weights , intercept value and intercept threshold Converted into multiple particles through vector encoding , based on particles The encoded value defines the initial position of each particle ,speed , individual optimal position Optimal position of the group ; Fitness module (542), used to construct a fitness module for guiding particles to migrate to a better area ; Update speed module (543) is used to update the speed Calculate the updated velocity value of the cth particle of the Dth generation ; Update position module (544), used to update the speed value Calculate updated position value ; The optimal position module (545) is used to update the position value according to Calculate the optimal position value ; A judgment module (546) is used to obtain the current number of iterations U and determine whether the iteration should be stopped according to the current number of iterations; like , then continue to iterate like , then stop the iteration and set the optimal position at this time The value is reverse encoded to obtain the optimized weight , iterative intercept and iterative cutoff threshold .

[0012] Furthermore, the optimal position value The calculation formula is: ; in, Represents the ath optimal position value.

[0013] By means of the above technical solution, the present invention provides a remote management system for inverters based on the Internet of Things, which has at least the following beneficial effects: 1. The present invention solves the noise interference problem in traditional inverter signal acquisition in the data preprocessing stage. Through PWM carrier frequency adaptive filtering technology, combined with real-time tracking of the actual switching frequency of the inverter, the digital filter parameters are dynamically adjusted, and the switching noise band centered on the PWM carrier frequency is accurately locked and eliminated. This solves the inherent defect of traditional fixed filters that cannot adapt to the dynamic frequency modulation of the inverter. The invention innovatively introduces a differential pulse detection algorithm, calculates the differential characteristics of the current signal in real time, and combines adaptive thresholds to accurately identify sudden interference pulses caused by grid transients or power device switching, and eliminates and fills sudden interference pulses, thereby improving the fluency and integrity of the data.

[0014] 2. The present invention can enhance multiple features of the inverter operation data by acquiring hybrid features, including time domain, frequency domain and cross-features. Through these features, the analysis and classification of the inverter operation status can be completed more accurately, thereby improving the accuracy of inverter analysis and management.

[0015] 3. The present invention forms a new neural network model by connecting a competitive layer with unsupervised learning and a neural network with supervised learning in series, which avoids the shortcomings of local minima in neural networks in the existing technology. At the same time, it can also reduce the amount of learning data, so that the new neural network can successfully learn and classify and identify data without a huge amount of data, greatly improving the stability of the neural network and improving learning efficiency.

[0016] 4. The present invention can greatly improve the selection efficiency of weights and thresholds by utilizing the method of group optimization, and has smaller test errors and better nonlinear fitting capabilities, which can improve the classification accuracy of the inverter operating status. By connecting the competition layer with unsupervised learning and the neural network with supervised learning in series, a new neural network model is constructed, which avoids the shortcomings of local minima in neural networks in the existing technology. At the same time, it can also reduce the amount of learning data, so that the new neural network can successfully learn and classify and identify data without a huge amount of data, which greatly improves the stability of the neural network and improves learning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 This is a structural block diagram of a frequency converter remote management system based on the Internet of Things of the present invention; Figure 2 This is a structural block diagram of the preprocessing module of the present invention; Figure 3 This is a structural block diagram of the alignment module of the present invention; Figure 4 This is a structural block diagram of the hybrid feature module of the present invention; Figure 5 This is a structural block diagram of the victory unit module of the present invention; Figure 6 This is a structural block diagram of the status monitoring module of the present invention; Figure 7 This is a structural diagram of the optimization model module of the present invention.

[0018] In the figure: 1. Preprocessing module; 11. Carrier frequency filtering module; 12. Interference threshold module; 13. Removal module; 14. Filling module; 15. Merging module; 2. Alignment module; 21. Interaction module; 22. Balance module; 23. Gradient module; 24. Iteration module; 25. Iteration threshold module; 26. Optimization coefficient module; 27. Optimization alignment module; 3. Hybrid feature module; 31. Scaling tensor module; 32. Time domain feature module; 33. Band energy module; 34. Cross-metric module; 35. Splicing module; 4. Victory element module; 41. Preparation module; 42. Euclidean distance module; 43. Competition module; 44. Update module; 45. Control module; 5. State monitoring module; 51. Implicit module; 52. Output module; 53. Mean square error module; 54. Optimization model module; 541. Initialization module; 542. Fitness module; 543. Update speed module; 544. Update position module; 545. Optimal position module; 546. Judgment module; 55. Dynamic screening module; 56. Model building module; 6. Remote management module. DETAILED DESCRIPTION

[0019] To make the above-mentioned objectives, features, and advantages of the present invention more clearly understood, the present invention is further described below in detail with reference to the accompanying drawings and specific embodiments. This will enable a full understanding of how this application uses technical means to solve technical problems and achieve technical effects, and to implement the invention accordingly.

[0020] Since the existing technology cannot adapt to the inherent defects of the dynamic frequency modulation of the inverter, and is prone to the disadvantage of local minimum value, and has the technical problem of low processing efficiency, this embodiment proposes a remote management system for inverters based on the Internet of Things, such as Figure 1-7 As shown, the system can accurately identify burst interference pulses through adaptive thresholds and avoid the disadvantages of local minimum values. At the same time, it can also reduce the amount of learning data, greatly improve the stability of the neural network, and improve learning efficiency. The system includes: Preprocessing module 1, used to collect the original data of the inverter , calculated for the original data The interference threshold Y for removing interference data, and the preprocessed data is obtained based on the interference threshold Y ; Preprocessing module 1 includes: Carrier frequency filtering module 11 is used to filter the original data Calculate the carrier frequency filter value used for filtering , the calculation formula is: ;

[0021] ;

[0022] ;

[0023] in, and Represent the adaptive filter coefficients, Indicates the PWM real-time switching frequency, Indicates the sampling period; Interference threshold module 12 is used to establish a sliding window H with a window length of C and calculate the carrier frequency filtering value inside the window The interference threshold Y is calculated as follows: ;

[0024] in, represents the empirical coefficient, Indicates the sliding estimate of the current standard deviation; in practical applications, the empirical coefficient Generally set to -3, current standard deviation sliding estimate It can be obtained through the circuit in the acquisition circuit.

[0025] Elimination module 13, used to filter the carrier frequency value according to the interference threshold Y Eliminate the interference data in like , then the carrier frequency filtering value To interfere with the data and remove it; like , then the carrier frequency filtering value It is normal data and is retained; Filling module 14 is used to obtain adjacent data adjacent to the removed interference data and , calculate the filling data used to supplement the interference data , the calculation formula is: ;

[0026] in, Indicates the b-th filling data; Merging module 15, used to merge normal data and fill data Merge into preprocessed data in chronological order . The present invention has achieved three key technological innovations in the data preprocessing stage, solving the problem of noise interference in traditional inverter signal acquisition. First, through PWM carrier frequency adaptive filtering technology, we track the actual switching frequency of the inverter in real time, dynamically adjust the digital filter parameters, accurately lock and eliminate the switching noise band centered on the PWM carrier frequency, and solve the inherent defect that the traditional fixed filter cannot adapt to the dynamic frequency modulation of the inverter. Secondly, the differential pulse detection algorithm is innovatively introduced to calculate the differential characteristics of the current signal in real time, combined with the adaptive threshold to accurately identify the sudden interference pulses caused by grid transients or power device switching, and mark and eliminate them. It has been verified by actual measurements that this preprocessing scheme improves the system signal-to-noise ratio from 18dB of the traditional scheme to 49dB, with a relative improvement of 171%.

[0027] Alignment module 2 is used to pre-process data Calculate the optimization coefficient after iteration , according to the optimization coefficient Compute aligned tensors ; Preprocess data Contains a variety of data features. To further analyze the operating status of the inverter, it is necessary to obtain these data features in order to perform status analysis more accurately. To solve this problem, the detailed implementation steps are as follows: Interconnection module 21 is used to pre-process data Randomly select two different preprocessed data and , and calculate the preprocessed data Mutual information , the calculation formula is: ; in, Represents preprocessed data The information entropy of A and B represents the preprocessed data and the number of and Represents preprocessed data and Corresponding data values; mutual information refers to the amount of information one variable contains about another variable. Information entropy is a common method for calculating uncertain information and will not be described in detail here. Balance module 22, for Calculate the balance coefficient , the calculation formula is: ;

[0028] in, represents the pth balance coefficient, and ; Gradient module 23, for Calculate the gradient value , the calculation formula is: ;

[0029] in, represents the fth gradient value; Iteration module 24 is used to calculate the gradient value Calculate the Iteration coefficient of generation , the calculation formula is: ;

[0030] in, represents the learning rate, Represents the gradient value In the balance coefficient The value of Iteration threshold module 25, used to calculate the iteration threshold according to the quantity A , the calculation formula is: ;

[0031] in, represents random coefficient; random coefficient It can be generated randomly through a random generator. The random generator is a common method for obtaining random numbers and will not be described in detail here.

[0032] Optimization coefficient module 26 is used to optimize the coefficient according to the iteration threshold Determine whether the iteration is finished; like , then return to the interconnection module 21 to repeat the optimization coefficient Calculation of like , then the iteration ends and the final optimization coefficient is obtained ; Optimization alignment module 27, used to optimize the coefficients Compute aligned tensors , the calculation formula is: ;

[0033] in, Represents the tth aligned tensor, by preprocessing the data Preprocessing can obtain Aligned tensor of , align tensors It can more accurately reflect the working status of the inverter, thereby helping subsequent steps to analyze and manage the inverter status more accurately and quickly, and improve the efficiency and accuracy of data processing.

[0034] Mixed feature module 3, used to align tensors Calculate hybrid characteristics for monitoring inverter dynamic characteristics ; Align tensors After optimizing the accuracy and efficiency of the data, you also need to align the tensors The features are decomposed and mixed features are formed In order to solve this problem, the specific methods adopted are as follows: Scaling tensor module 31, for aligning tensors based on Get the scalar value tensor by local normalization of the sliding window ; Local normalization is a method of normalizing a tensor in a local area through a sliding window, which can enhance local contrast or reduce the inconsistency of local features. Local normalization is a common tensor processing method and will not be described in detail here.

[0035] The time domain feature module 32 is used to calculate the time domain feature according to the scale value tensor. The time domain features are obtained by sliding differential method ; The sliding differentiation method is often used in time domain feature extraction to smooth signals, enhance local contrast or normalize features. When used in conjunction with the local normalization method, the differentiation results can be further processed to enhance features. The sliding differentiation method is a common tensor processing method and will not be described in detail here.

[0036] Band energy module 33, used to calculate the frequency band energy according to the scale value tensor Calculates the frequency band energy characteristics used to evaluate the frequency band energy fluctuation of the inverter signal , the calculation formula is: ;

[0037] Where j represents the imaginary unit, f represents the frequency component, and T represents the alignment tensor The length of the corresponding alignment time period, t represents the time corresponding to the frequency f; Cross-metric module 34, used to collect raw data from the inverter Select the sensor pairs with physical association from the sensors , the sensor pair is obtained by local normalization method A scalar-valued tensor of and , and calculate the cross metric , the calculation formula is: ;

[0038] in, represents the c-th cross metric, Represents the calculation of scalar value tensors and The outer product of The splicing module 35 is used to , frequency band energy characteristics and cross-metrics Calculating mixed features , the calculation formula is:

[0039] in, represents the t-th mixed feature, Representing time domain features , frequency band energy characteristics and cross-metrics splicing, by mixing features The acquisition of multiple features of the inverter operation data, including time domain, frequency domain and cross-features, can improve the analysis and classification of the inverter operation status more accurately, thereby improving the accuracy of inverter analysis and management.

[0040] Victory meta-module 4, used to calculate the value of the mixed feature Calculate the victory yuan after iteration Since the neural network in the prior art is prone to falling into local minima and the network performance is unstable, which affects the normal monitoring and analysis, in order to solve this problem, this embodiment proposes a more detailed implementation method as follows: Preparation module 41, for combining multiple mixed features As the input of the input layer, and define the initial learning rate , weight and neighborhood radius ; Here we first build the input layer of the model and define the key model parameters based on practical experience.

[0041] Euclidean distance module 42, used to calculate multiple mixed features Euclidean distance , the calculation formula is: ;

[0042] in, represents the oth Euclidean distance, represents the domain function, represents the basic weight; Competition module 43, for Calculate victory points at the competitive level , the expression is: ;

[0043] in, Indicates the Lth victory unit; Update module 44 is used to update the learning rate and neighborhood radius Calculate the updated learning rate and update neighborhood radius , the calculation formula is:

[0044] ;

[0045] Among them, INT represents the rounding function, U represents the current number of learning times, and l represents the neighborhood radius of the lth generation. ; Control module 45, used to update the learning rate according to Control victory dollars iterations; like , the iteration ends and the current victory element is output ; like , then return to the preparation module 41 and recalculate the victory yuan Since the learning rate is a continuously decaying quantity, after multiple iterations, the learning rate is used to determine whether the iteration has ended. By connecting a competitive layer with unsupervised learning and a neural network with supervised learning in series, a new neural network model is formed. This avoids the shortcomings of local minima in neural networks in existing technologies, while also reducing the amount of learning data. This allows the new neural network to successfully learn and classify data without requiring a large amount of data, greatly improving the stability of the neural network and improving learning efficiency.

[0046] Status monitoring module 5, used to monitor the status of the Calculating dynamic filter values , based on dynamic filter values Get the optimized inverter status monitoring model; Based on the previous step, it is necessary to convert the victory element For further processing, the detailed implementation steps are as follows: Hidden module 51, for multiple victory elements As input, the implicit value is calculated through the implicit function of the hidden layer , the calculation formula is: ; Among them, P represents victory yuan the number of represents the basic weight, Represents the intercept value; the intercept value can be implied by The vertical intercept of x represents the function The independent variable in .

[0047] Output module 52, used to output the implicit value Calculate the output value of the output layer , the calculation formula is: ;

[0048] Where N represents the implicit value the number of Indicates the intercept threshold; intercept threshold It is obtained by peak detection method, which is a commonly used method to obtain the intercept threshold. The method is not described here.

[0049] Mean square error module 53, used to define the expected value according to the model , calculate the output value and the mean square error of the expected value The mean square error value , the calculation formula is: ;

[0050] in, Represents the fth mean square error value; expected value It can be set as the data under the normal state of the inverter, can be set according to the experience of the staff, or can be set according to the average of the normal values of the inverter's historical data.

[0051] Optimizing model module 54, for , intercept value and intercept threshold Calculate optimization weights , iterative intercept and iterative cutoff threshold , based on the optimization weights , iterative intercept and iterative cutoff threshold Building an optimization model , the expression is: ;

[0052] in, represents the qth optimization variable value, and p represents the victory element the number of Initialization module 541 is used to initialize the basic weight , intercept value and intercept threshold Converted into multiple particles through vector encoding , based on particles The encoded value defines the initial position of each particle ,speed , individual optimal position Optimal position of the group ; Fitness module 542, used to construct a fitness module for guiding particles to migrate to a better area , the expression is: ;

[0053] in, and represent the actual particle position and the expected particle position in the particle swarm, respectively, where , R represents the logarithm of the positions of the two particles, and Z represents the fitness independent variable; Update speed module 543, for updating speed according to the speed Calculate the updated velocity value of the cth particle of the Dth generation , the calculation formula is:

[0054] in, represents the inertia weight, and They represent the acceleration coefficients, and represent random numbers, and , ; Update position module 544, used to update the speed value Calculate updated position , the calculation formula is: ;

[0055] in, Indicates the xth updated position value; The optimal position module 545 is used to update the position value according to Calculate the optimal position value , the calculation formula is: ;

[0056] in, represents the ath optimal position value; A judgment module 546 is used to obtain the current number of iterations U and determine whether the iteration should be stopped according to the current number of iterations; like , then returns to the fitness module 542 to continue iteration; like , then stop the iteration and set the optimal position value at this time Perform reverse encoding to obtain optimized weights , iterative intercept and iterative cutoff threshold The optimal position value in the particle swarm algorithm is often used in reverse coding. Reversely obtain optimization weights , iterative intercept and iterative cutoff threshold The method is not described here.

[0057] Dynamic screening module 55, for filtering Calculating dynamic filter values , the calculation formula is: ;

[0058] in, and Represent the weight coefficients, Represents the mean square error value The mean of Represents the mean square error value The standard deviation of Model building module 56, used to dynamically filter values Complete the establishment of the inverter status monitoring model; like , then the end and the inverter status monitoring model is obtained; like , then return to module 53 to retrain the model, and solve the problem of selecting connection weights and thresholds of neural networks in the prior art by utilizing the group optimization method. The prior art sets them according to experimental experience, and then adjusts the connection weights and thresholds during the training process. This method requires repeated adjustments to the connection weights and thresholds, which seriously affects the learning efficiency of the neural network. The present invention is based on a group optimization method, which can greatly improve the selection efficiency of weights and thresholds, and has smaller test errors and better nonlinear fitting capabilities, and can improve the classification accuracy of the inverter operating status. By connecting a competitive layer with unsupervised learning and a neural network with supervised learning in series, a new neural network model is formed, which avoids the shortcomings of local minima in neural networks in the prior art, and can also reduce the amount of learning data, so that the new neural network does not need a huge amount of data to successfully learn and classify and identify data, greatly improving the stability of the neural network and improving learning efficiency.

[0059] Remote management module 6, used to convert the hybrid characteristics of the inverter Input into the inverter status monitoring model yields inverter status detection results, including normal operation, abnormalities, and shutdowns. These results are then sent to the remote management center. The remote management center uses these detection results to remotely manage the inverter, triggering alerts that are automatically sent to the operator's mobile phone or industrial control system. This shortens fault response time, predicts component aging, enables proactive replacement of spare parts, avoids unexpected downtime, and extends equipment life. The remote management center can modify inverter parameters remotely without requiring on-site operation.

[0060] Those skilled in the art will appreciate that all or part of the steps in the above-mentioned embodiment methods can be accomplished by instructing the relevant hardware through a program. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to in detail. For the above embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For relevant parts, please refer to the partial description of the method embodiments.

[0062] The above embodiments provide a detailed introduction to the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A remote management system for frequency converters based on the Internet of Things, characterized in that: The system includes: Preprocessing module (1) is used to collect the raw data of the inverter , calculated for the original data The interference threshold Y for removing interference data, and the preprocessed data is obtained based on the interference threshold Y , Alignment module (2) is used to pre-process data Calculate the optimization coefficient after iteration , according to the optimization coefficient Compute aligned tensors ; The hybrid feature module (3) is used to align the tensor Calculate hybrid characteristics for monitoring inverter dynamic characteristics ; Victory meta-module (4) is used to calculate the Calculate the victory yuan after iteration ; Status monitoring module (5) is used to monitor the status of the Calculating dynamic filter values , based on dynamic filter values Obtain the optimized inverter status monitoring model; Remote management module (6) for converting the hybrid characteristics of the inverter The inverter status detection result is input into the inverter status monitoring model, and the inverter status detection result is sent to the remote management center.

2. The inverter remote management system based on the Internet of Things according to claim 1, characterized in that: The pre-processing module (1) comprises: The carrier frequency filtering module (11) is used to filter the original data Calculate the carrier frequency filter value used for filtering ; Interference threshold module (12) is used to establish a sliding window H with a window length of C and calculate the carrier frequency filtering value inside the window Interference threshold Y; The elimination module (13) is used to filter the carrier frequency value according to the interference threshold Y. Eliminate the interference data in like , then the carrier frequency filtering value To interfere with the data and remove it; like , then the carrier frequency filtering value It is normal data and is retained; Filling module (14), used to obtain adjacent data adjacent to the removed interference data and , calculate the filling data used to supplement the interference data ; Merge module (15) is used to combine normal data and padded data Merge into preprocessed data in chronological order .

3. The inverter remote management system based on Internet of Things according to claim 1, characterized in that: The alignment module (2) comprises: Interconnection module (21) is used to pre-process data Randomly select two different preprocessed data and , and calculate the preprocessed data Mutual information ; Balance module (22) for Calculate the balance coefficient ; Gradient module (23) is used to calculate the equilibrium coefficient Calculate the gradient value ; Iteration module (24) is used to calculate the gradient value Calculate the Iteration coefficient of generation ; Iteration threshold module (25), used to calculate the iteration threshold according to the quantity A ; The optimization coefficient module (26) is used to optimize the coefficient according to the iteration threshold. Determine whether the iteration is finished; like , then the optimization coefficient is repeatedly Calculation of like , then the iteration ends and the final optimization coefficient is obtained ; The optimization alignment module (27) is used to optimize the coefficients Compute aligned tensors .

4. The inverter remote management system based on Internet of Things according to claim 1, characterized in that: The hybrid feature module (3) includes: Scalar tensor module (31) for aligning tensors Get the scalar value tensor by local normalization of the sliding window ; The time domain feature module (32) is used to calculate the time domain feature according to the scale value tensor. The time domain features are obtained by sliding differential method ; Band Energy Module (33) is used to calculate the energy of a frequency band according to the scalar value tensor. Calculates the frequency band energy characteristics used to evaluate the frequency band energy fluctuation of the inverter signal ; Cross-metric module (34), used to collect raw data from the frequency converter Select the sensor pairs with physical association from the sensors , the sensor pair is obtained by local normalization method A scalar-valued tensor of and and calculate the cross metric ; The splicing module (35) is used to , frequency band energy characteristics and cross-metrics Calculating mixed features .

5. The inverter remote management system based on Internet of Things according to claim 1, characterized in that: The victory element module (4) includes: Preparation module (41) is used to combine multiple mixed features As the input of the input layer, and define the initial learning rate , weight and neighborhood radius ; Euclidean distance module (42), used to calculate multiple mixed features Euclidean distance ; Competition module (43) is used to calculate the Calculate victory points at the competitive level ; The update module (44) is used to update the and neighborhood radius Calculate the updated learning rate and update neighborhood radius ; The control module (45) is used to update the learning rate according to Control victory dollars iterations; like , the iteration ends and the current victory element is output ; like , then recalculate the victory yuan .

6. The inverter remote management system based on Internet of Things according to claim 1, characterized in that: The state monitoring module (5) comprises: Implicit module (51) is used to convert multiple victory elements As input, the implicit value is calculated through the implicit function of the hidden layer ; Output module (52) is used to output the implicit value Calculate the output value of the output layer ; The mean square error module (53) is used to define the expected value based on the model , calculate the output value and the mean square error of the expected value The mean square error value ; Optimization model module (54) for optimizing the model based on multiple basis weights , intercept value and intercept threshold Calculate optimization weights , Iteration intercept and iterative cutoff threshold , based on the optimization weights , iterative intercept and iterative cutoff threshold Building an optimization model ; Dynamic screening module (55) is used to filter the Calculating dynamic filter values ; Model building module (56) is used to dynamically filter values Complete the establishment of the inverter status monitoring model; like , then the end and the inverter status monitoring model is obtained; like , then re-train the model.

7. The inverter remote management system based on Internet of Things according to claim 6, characterized in that: The optimization model The expression is: ； in, represents the qth optimization variable value, and p represents the victory element The number of 8. The inverter remote management system based on Internet of Things according to claim 6, characterized in that: The optimization model module (54) includes: Initialization module (541) is used to initialize the basic weights , intercept value and intercept threshold Converted into multiple particles through vector encoding , based on particles The encoded value defines the initial position of each particle ,speed , individual optimal position Optimal position of the group ; Fitness module (542), used to construct a fitness module for guiding particles to migrate to a better area ; Update speed module (543) is used to update the speed Calculate the updated velocity value of the cth particle of the Dth generation ; Update position module (544), used to update the speed value Calculate updated position value ; The optimal position module (545) is used to update the position value according to Calculate the optimal position value ; A judgment module (546) is used to obtain the current number of iterations U and determine whether the iteration should be stopped according to the current number of iterations; like , then continue to iterate; like , then stop the iteration and set the optimal position at this time The value is reverse encoded to obtain the optimized weight , iterative intercept and iterative cutoff threshold .

9. The inverter remote management system based on Internet of Things according to claim 8, characterized in that: The optimal position The value is calculated as: ； in, Represents the ath optimal position value.

Images