Motor driving intelligent management and control system and method based on Internet of Things

Abstract

The invention discloses a motor driving intelligent management and control system and method based on the Internet of Things, and belongs to the technical field of motor intelligent management and control. The method comprises the following steps: generating a set of motors in a factory, collecting operation data of the motors through a monitoring sensor, and transmitting the operation data collected by the monitoring sensor to a database; extracting operation data in the database, analyzing the operation data to generate a first historical load power subset, and performing feature extraction on the first historical load power subset to generate a second historical load power subset; according to the extracted historical load power second subset, establishing an operation feature fitting model, and according to the operation feature fitting model, searching for a pre-optimized motor; and calculating the optimization difference value of the pre-optimized motor, and performing parameter adjustment on the pre-optimized motor according to a calculation result. Data features can be highlighted, and model establishment is accelerated; the operation safety of the motor is improved, and user assets are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent motor control, and specifically to an intelligent motor drive control system and method based on the Internet of Things. Background Technique

[0002] Under the current main theme of green and low-carbon development in the industry, motor drive and control are developing towards high energy efficiency, intelligence and integration. On the one hand, advanced electronic technology and intelligent control technology are constantly intersecting and integrating, promoting the integrated design and manufacture of motor system control, sensing and drive functions. At the same time, for different application fields, related motor products are also developing towards professionalism, differentiation and specialization. On the other hand, under the current global environmental protection policy requirements, the motor industry urgently needs to accelerate the energy-saving transformation of existing production equipment, promote efficient and green production processes, develop a new generation of energy-saving motors, motor systems and control products and testing equipment, and further enhance the core competitiveness of motor and system products.

[0003] In the prior art, when optimizing numerical calculations for a large number of motors in a factory, a large amount of unselected historical data is often used to train the fitting model, which to a certain extent reduces the system calculation efficiency and causes waste of system processing unit resources; and when adjusting parameters, the rate of parameter adjustment is not set, and the motor is easily damaged during the parameter adjustment process.

[0004] Therefore, the present invention discloses an intelligent motor drive control system and method based on the Internet of Things to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent motor drive control system and method based on the Internet of Things to solve the problems raised in the above background technique.

[0006] To solve the above technical problems, the present invention provides the following technical solution: An intelligent motor drive control method based on the Internet of Things, the method includes the following steps: S1: Generate a set of motors in the factory, collect the operation data of the motors through monitoring sensors, and transmit the operation data collected by the monitoring sensors to the database; S2: Extract the operation data from the database, analyze the operation data, use the fast Fourier transform to obtain the minimum period of the change of elements in the historical load power set, split the historical load power set according to the minimum period to generate the first subset of historical load power, and perform feature extraction on the first subset of historical load power to generate the second subset of historical load power; S3: Based on the extracted second subset of historical load power, establish an operating characteristic fitting model, use the operating characteristic fitting model to predict and calculate the load power, further calculate the pre-optimization ratio according to the predicted load power, and search for the pre-optimized motor according to the pre-optimization ratio; S4: Analyze and calculate the motor set to obtain the optimized output efficiency ratio, calculate the optimization difference of the pre-optimized motor according to the optimized output efficiency ratio, and adjust the parameters of the pre-optimized motor according to the calculation results.

[0007] According to the above solution, in step S1, generate a set of motors in the factory, denoted as EM = {EM i |i ∈ [1, N]}; i is a positive integer; where EM i represents the motor with serial number i in the motor set, and N represents the total number of motors in the factory; For the motor EM i , collect the load power and input power of the motor through the monitoring sensor; generate a set of historical load power of the motor EM i , denoted as LP i ={LP i j |j ∈ [1, M]}; j is a positive integer; where LP i j represents the historical load power with serial number j in the historical load power set, and M represents the total number of historical load powers.

[0008] According to the above solution, in step S2, the historical load power set is a time series of historical load power changing with time. Use the fast Fourier transform to transform the historical load power set into the frequency domain, identify the main periodic components through the spectrogram, and obtain the minimum period as f; starting from the end of the historical load power set, intercept a set with the minimum period f as the length to generate the first subset of historical load power; During the data extraction process, the total number of historical load powers is most likely not divisible by the minimum period. Intercept from the end of the set; it can effectively intercept the data of the historical load power set closest to the real-time moment and improve the accuracy of the subsequent fitting model; Denote the first subset of historical load power with serial number u as LP i u , where LP i u= {LP i （u，v） |v ∈ [1, m i u}, where LP i （u，v） represents the first subset of historical load power LP iu The historical load power with serial number v, m i u represents the total number of historical load powers in the first subset of historical load powers; the historical load powers in the first subset of historical load powers are arranged in reverse order of the time when the monitoring sensor collects operation data.

[0009] Extract the historical load powers with the same serial number in each first subset of historical load powers to generate a second subset of historical load powers, and denote the v-th second subset of historical load powers as SLP i v ={LP i （u，v） |u∈[1, u max}, u max represents the total number of historical load powers in the second subset of historical load powers; or .

[0010] In the actual production activities of the factory, the load power changes continuously over time. Using the fast Fourier transform to obtain the minimum period and splitting and extracting the historical load power set using the minimum period can effectively highlight the characteristics of the historical load power change, which is beneficial to accelerating the establishment of the subsequent operation characteristic fitting model.

[0011] According to the above solution, in step S3, combine the second subset of historical load powers SLP i v with the time variable and arrange them in the order of the monitoring data collection time to generate a second subset of historical load power and time LPT i v ={(T i （u，v）， LP i （u，v） )|u∈[1, u max}; where T i （u，v） is the data acquisition moment of the historical load power LP i （u，v） ; Use the second subset of historical load power and time to establish an operation characteristic fitting model: y = α1 v ×x + α2 v ; where α1 v and α2 v represent fitting coefficients, x represents the independent variable of time, y represents the dependent variable of historical load power, and calculate and solve α1 v and α2 v in the operation characteristic fitting model. The specific calculation formula is as follows: ; ; Establishing different operation characteristic fitting models for different second subsets of historical load power can improve the accuracy of predicting subsequent load power; Using the operation characteristic fitting model, predict and calculate the historical load power and the last element in the second subset of time LPT i v of (T i （ u max，v）， LP i （ u max，v） ), denoted as (T i （ u max+f，v）， LP i （ u max+f，v） ); When v is greater than 1, record the input power of the motor collected by the monitoring sensor at the previous data acquisition moment of (T i （ u max+f，v）， LP i （ u max+f，v） ), denoted as IP i （ u max+f，v-1） ; When v is equal to 1, the said IP i （ u max+f，v-1） is equal to IP i （ u max， m i u） ; Calculate the pre-optimization ratio β of the input power and the predicted load power, and the specific calculation formula is as follows: β = LP i （ u max+f，v） ÷ IP i （ u max+f，v-1） ; Set a threshold β 阈 for the pre-optimization ratio β, and regard the motor with the pre-optimization ratio β less than the threshold β 阈 as the pre-optimized motor.

[0012] Find the pre-optimized motor according to the operation characteristic fitting model, perform subsequent adaptive adjustment, and thus realize the adaptive control of the input power of the motor, reducing the problem of too low power supply efficiency of the motor.

[0013] According to the above solution, in step S4, LP in the historical load power set i j The corresponding input power is denoted as IP i j , for the motor EM i Calculate the output efficiency ratio OER i , and the specific calculation formula is as follows: ; Compare the output efficiency ratios of the motors in the motor set EM, and denote the maximum value among them as the optimized output efficiency ratio OER; Calculate the output efficiency ratios of the motors from historical data, and denote the maximum value among them as the optimized output efficiency ratio, effectively screening out the highest output efficiency ratio that the motors can achieve from practice, and improving the safety of motor parameter adjustment.

[0014] Further calculate the optimization difference OD of the pre-optimized motor according to the optimized output efficiency ratio, and the specific calculation formula is as follows: OD = IP （ u max+f，v-1） - LP （ u max+f，v） ÷ OER; Set a threshold OD for the optimization difference 阈 , if the optimization difference OD is less than or equal to the set optimization difference threshold OD 阈 , then optimize according to the input power adjustment rate set by the system; If the optimization difference OD is greater than the set optimization difference threshold OD 阈 , then the input power adjustment rate OD 阈 ÷ t ≥ V, where t is the data acquisition time period.

[0015] Further setting the rate of input power adjustment is beneficial to improving the safety of motor operation, avoiding damage to the motor caused by a large one-time adjustment of the input power of the motor, and protecting the user's assets.

[0016] Another aspect of the present application provides an intelligent management and control system for motor drive based on the Internet of Things. The system is implemented by applying the above-mentioned intelligent management and control method for motor drive based on the Internet of Things. The system includes a data acquisition module, a database, a data analysis and extraction module, a feature fitting and search module, and an optimization adjustment control module; The output end of the data acquisition module is connected to the input end of the database, the output end of the database is connected to the input end of the data analysis and extraction module, the output end of the data analysis and extraction module is connected to the input end of the data analysis and extraction module, and the output end of the data analysis and extraction module is connected to the input end of the optimization adjustment control module; The data acquisition module is used to generate a set of motors in the factory, collect the operating data of the motors through monitoring sensors, and transmit the operating data collected by the monitoring sensors to the database; The database is used to receive and store the operating data of the motors; The data analysis and extraction module is used to analyze the operating data to generate a first subset of historical load power, and perform feature extraction on the first subset of historical load power to generate a second subset of historical load power; The feature fitting and search module is used to establish an operating feature fitting model according to the extracted second subset of historical load power, and search for pre-optimized motors according to the operating feature fitting model; The optimization and adjustment control module is used to calculate the optimization difference of the pre-optimized motor, and adjust the parameters of the pre-optimized motor according to the calculation result.

[0017] According to the above solution, the data analysis and extraction module includes a data analysis unit and a set extraction unit; The input end of the data analysis unit is connected to the output end of the database, and the output end of the data analysis unit is connected to the input end of the set extraction unit; The data analysis unit is used to convert the historical load power set to the frequency domain by using the fast Fourier transform, identify the main periodic components through the spectrogram, and obtain the minimum period as f; The set extraction unit is used to generate a first subset of historical load power by intercepting a set with a length of the minimum period f starting from the end of the set of historical load power; extract the historical load power with the same serial number in each first subset of historical load power to generate a second subset of historical load power.

[0018] According to the above solution, the feature fitting and search module includes a feature fitting model generation unit and a pre-optimized motor search unit; The input end of the feature fitting model generation unit is connected to the output end of the set extraction unit, and the output end of the feature fitting model generation unit is connected to the input end of the pre-optimized motor search unit; The feature fitting model generation unit is used to generate a feature fitting and search module according to the second subset of historical load power in combination with the least squares method; The pre-optimized motor search unit uses the feature fitting and search module to search for pre-optimized motors.

[0019] According to the above solution, the optimization and adjustment control module includes an optimization difference calculation unit and a parameter adjustment control unit; The input end of the optimization difference calculation unit is connected to the output end of the pre-optimization motor search unit, and the output end of the optimization difference calculation unit is connected to the input end of the parameter adjustment control unit; The optimization difference calculation unit is used to calculate the output efficiency ratio of the motor, and calculate the optimization difference of the pre-optimization motor by using the output efficiency ratio of the motor; The parameter adjustment control unit is used to control the input power adjustment rate according to the magnitude of the optimization difference of the pre-optimization motor.

[0020] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the minimum period is obtained by using the fast Fourier transform, and the historical load power set is split and extracted by using the minimum period, which can effectively highlight the characteristics of the historical load power change, and is beneficial to accelerating the establishment of the subsequent operation characteristic fitting model; the pre-optimization motor is searched according to the operation characteristic fitting model, and subsequent adaptive adjustment is carried out, so as to realize the adaptive control of the input power of the motor, and reduce the problem of too small power supply efficiency of the motor; the rate of input power adjustment is further set, which is beneficial to improving the safety of the motor operation, avoiding damage to the motor caused by a large one-time adjustment of the input power of the motor, and protecting the assets of users. Description of the Drawings

[0021] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings: Figure 1 is a schematic flowchart of a method for intelligent management and control of motor drive based on the Internet of Things according to the present invention; Figure 2 is a schematic structural diagram of a system for intelligent management and control of motor drive based on the Internet of Things according to the present invention. Detailed Embodiments

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] Please refer to Figure 1 , the present invention provides a technical solution: a method for intelligent management and control of motor drive based on the Internet of Things, the method includes the following steps: S1: Generate a set of motors in the factory, collect the operation data of the motors through monitoring sensors, and transmit the operation data collected by the monitoring sensors to the database; According to the above solution, in step S1, the set of motors generated in the factory is denoted as EM = {EM i | i ∈ [1, N]}; i is a positive integer; where EM i represents the motor with serial number i in the motor set, and N represents the total number of motors in the factory; For the motor EM i , the load power and input power of the motor are collected through the monitoring sensor; the historical load power of the motor EM i is generated into a set, denoted as LP i = {LP i j | j ∈ [1, M]}; j is a positive integer; where LP i j represents the historical load power with serial number j in the historical load power set, and M represents the total number of historical load powers.

[0024] S2: Extract the operation data in the database, analyze the operation data, use the fast Fourier transform to obtain the minimum period of the change of the elements in the historical load power set, split the historical load power set according to the minimum period to generate the first subset of historical load power, and perform feature extraction on the first subset of historical load power to generate the second subset of historical load power; According to the above solution, in step S2, the historical load power set is a time series of historical load power changing with time. The fast Fourier transform is used to transform the historical load power set into the frequency domain, and the main periodic components are identified through the spectrogram to obtain the minimum period as f; the historical load power set is intercepted from the end of the set to generate a set with the minimum period f as the length to generate the first subset of historical load power; The first subset of historical load power with serial number u is denoted as LP i u , where LP i u= {LP i （u，v） | v ∈ [1, m i u}, where LP i （u，v） represents the historical load power with serial number v in the first subset of historical load power LP i u , and m i u represents the total number of historical load powers in the first subset of historical load power; the historical load powers in the first subset of historical load power are arranged in reverse order according to the time when the monitoring sensor collects the operation data.

[0025] Extract the historical load powers with the same serial number in each first subset of historical load powers to generate a second subset of historical load powers, and denote the v-th second subset of historical load powers as SLP i v ={LP i （u，v） |u ∈ [1, u max}, u max represents the total number of historical load powers in the second subset of historical load powers; or .

[0026] Example 1: In this example, LP i ={1, 2, 1, 2, 1, 2, 1}; The minimum period is 2; Starting from the end of the set, a set with a maximum length of 2 is intercepted to generate the first subset of historical load powers; In this example, M = 7, f = 2, then LP i 1= {1}; LP i 2= {1, 2}; LP i 3= {1, 2}; LP i 4= {1, 2}; Extract the historical load powers with the same serial number in each first subset of historical load powers to generate a second subset of historical load powers, = 4; = 3; Then SLP i 1 = {1, 1, 1, 1}; SLP i 2 = {2, 2, 2}; S3: According to the extracted second subset of historical load powers, establish an operating characteristic fitting model, use the operating characteristic fitting model to predict and calculate the load power, further calculate the pre-optimization ratio according to the predicted load power, and find the pre-optimized motor according to the pre-optimization ratio; According to the above solution, in step S3, combine the second subset of historical load powers SLP i v with the time variable and arrange them in the order of the monitoring data collection time to generate a second subset of historical load power and time LPT i v ={ (T i （u，v）， LP i （u，v） ) |u ∈ [1, u max}; where T i （u，v） is the historical load power LP i（u，v） The data acquisition time Using the historical load power and the second subset of time, establish an operating characteristic fitting model: y = α1 v ×x + α2 v ; where α1 v and α2 v represent fitting coefficients, x represents the independent variable of time, y represents the dependent variable of historical load power. Calculate and solve for α1 v and α2 v in the operating characteristic fitting model. The specific calculation formulas are as follows: ; ; Example 2: For the set SLP i 1 = {1, 1, 1, 1}; Generate the second subset of historical load power and time LPT i 1 = {(1, 1), (3, 1), (5, 1), (2, 1)}; Establish an operating characteristic fitting model: y = α1 1 ×x + α2 1 ; Calculate and solve for α1 1 and α2 1 in the operating characteristic fitting model. Calculate to get α1 1 = 0, α2 1 = 1; Then for the set SLP i 1's operating characteristic fitting model: y = 1; For the set SLP i 2 = {2, 2, 2}; Generate the second subset of historical load power and time LPT i 2 = {(2, 2), (4, 2), (6, 2)}; Establish an operating characteristic fitting model: y = α1 2 ×x + α2 2 ; Calculate and solve for α1 2 and α2 2 in the operating characteristic fitting model. Calculate to get α1 2 = 0, α2 2 = 2; Then for the set SLP i 2's operating characteristic fitting model: y = 2; Adopt different operating characteristic fitting models according to the differences in the second subset of historical load power and time; Predict and calculate the second subset of historical load power and time LPT i vThe (T of the last element in i （ u max，v）， LP i （ u max，v） ) next item, denoted as (T i （ u max+f，v）， LP i （ u max+f，v） ); When v is greater than 1, the input power of the motor collected by the monitoring sensor at the previous fetching time of (T i （ u max+f，v）， LP i （ u max+f，v） ) is denoted as IP i （ u max+f，v-1） ; When v is equal to 1, IP i （ u max+f，v-1） is equal to IP i （ u max， m i u） ; Calculate the pre-optimization ratio β of the input power and the predicted load power, and the specific calculation formula is as follows: β = LP i （ u max+f，v） ÷ IP i （ u max+f，v-1） ; Set a threshold β for the pre-optimization ratio β 阈 , and use the motor with the pre-optimization ratio β less than the threshold β 阈 as the pre-optimized motor.

[0027] S4: Analyze and calculate the motor set to obtain the optimized output efficiency ratio, calculate the optimization difference of the pre-optimized motor according to the optimized output efficiency ratio, and adjust the parameters of the pre-optimized motor according to the calculation results.

[0028] According to the above scheme, in step S4, the input power corresponding to LP in the historical load power set i j is denoted as IP i j , and calculate the output efficiency ratio OER i for the motor EM i , and the specific calculation formula is as follows: ; Compare the output efficiency ratios of the motors in the motor set EM, and record the maximum value as the optimized output efficiency ratio OER; Further calculate the optimization difference OD of the pre-optimized motor according to the optimized output efficiency ratio, and the specific calculation formula is as follows: OD = IP （ u max+f，v-1） -LP （ u max+f，v） ÷OER; Set a threshold OD for the optimization difference 阈 , if the optimization difference OD is less than or equal to the set optimization difference threshold OD 阈 , then optimize according to the input power adjustment rate set by the system; If the optimization difference OD is greater than the set optimization difference threshold OD 阈 , then the input power adjustment rate OD 阈 ÷t ≥ V, where t is the data acquisition time period.

[0029] Please refer to Figure 2 , the present invention provides a technical solution: an intelligent management and control system for motor drive based on the Internet of Things, which system includes a data acquisition module, a database, a data analysis and extraction module, a feature fitting and searching module, and an optimization and adjustment control module; The output end of the data acquisition module is connected to the input end of the database, the output end of the database is connected to the input end of the data analysis and extraction module, the output end of the data analysis and extraction module is connected to the input end of the data analysis and extraction module, and the output end of the data analysis and extraction module is connected to the input end of the optimization and adjustment control module; The data acquisition module is used to generate a set of motors in the factory, collect the operation data of the motors through monitoring sensors, and transmit the operation data collected by the monitoring sensors to the database; The database is used to receive and store the operation data of the motors; The data analysis and extraction module is used to analyze the operation data to generate a first subset of historical load power, and perform feature extraction on the first subset of historical load power to generate a second subset of historical load power; The feature fitting and searching module is used to establish an operation feature fitting model according to the extracted second subset of historical load power, and search for pre-optimized motors according to the operation feature fitting model; The optimization and adjustment control module is used to calculate the optimization difference of the pre-optimized motor, and adjust the parameters of the pre-optimized motor according to the calculation result.

[0030] According to the above solution, the data analysis and extraction module includes a data analysis unit and a set extraction unit; The input end of the data analysis unit is connected to the output end of the database, and the output end of the data analysis unit is connected to the input end of the set extraction unit; The data analysis unit is used to convert the historical load power set to the frequency domain by using the fast Fourier transform, identify the main periodic components through the spectrogram, and obtain the minimum period as f; The set extraction unit is used to generate the first sub-set of the historical load power by intercepting the set with the minimum period f as the length starting from the end of the set of the historical load power; extract the historical load powers with the same serial number in each first sub-set of the historical load power to generate the second sub-set of the historical load power.

[0031] According to the above solution, the feature fitting search module includes a feature fitting model generation unit and a pre-optimized motor search unit; The input end of the feature fitting model generation unit is connected to the output end of the set extraction unit, and the output end of the feature fitting model generation unit is connected to the input end of the pre-optimized motor search unit; The feature fitting model generation unit is used to generate the feature fitting search module according to the second sub-set of the historical load power in combination with the least squares method; The pre-optimized motor search unit uses the feature fitting search module to search for the pre-optimized motor.

[0032] According to the above solution, the optimization adjustment control module includes an optimization difference calculation unit and a parameter adjustment control unit; The input end of the optimization difference calculation unit is connected to the output end of the pre-optimized motor search unit, and the output end of the optimization difference calculation unit is connected to the input end of the parameter adjustment control unit; The optimization difference calculation unit is used to calculate the output efficiency ratio of the motor and calculate the optimization difference of the pre-optimized motor by using the output efficiency ratio of the motor; The parameter adjustment control unit is used to control the input power adjustment rate according to the magnitude of the optimization difference of the pre-optimized motor.

[0033] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprises", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0034] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent control method for motor drive based on the Internet of Things, characterized in that, The method includes the following steps: S1: Generate a set of motors in the factory, collect the operating data of the motors through monitoring sensors, and transmit the operating data collected by the monitoring sensors to the database; S2: Extract the operating data from the database, analyze the operating data, use the fast Fourier transform to obtain the minimum period of the change of elements in the historical load power set, split the historical load power set according to the minimum period to generate the first subset of the historical load power, and perform feature extraction on the first subset of the historical load power to generate the second subset of the historical load power; S3: According to the second subset of the historical load power extracted, establish an operating characteristic fitting model, use the operating characteristic fitting model to predict and calculate the load power, further calculate the pre-optimization ratio according to the predicted load power, and find the pre-optimized motor according to the pre-optimization ratio; S4: Analyze and calculate the optimized output efficiency ratio of the motor set, calculate the optimization difference of the pre-optimized motor according to the optimized output efficiency ratio, and adjust the parameters of the pre-optimized motor according to the calculation result.

2. The intelligent control method for motor drive based on the Internet of Things according to claim 1, characterized in that: In step S1, the set of motors generated in the factory is denoted as EM = {EM i | i ∈ [1, N]}; i is a positive integer; where EM i represents the motor with the serial number i in the motor set, and N represents the total number of motors in the factory; For motor EM i , the load power and input power of the motor are collected through a monitoring sensor; the historical load power of motor EM i is used to generate a set, denoted as LP i ={LP i j |j∈[1, M]}; j is a positive integer; where LP i j represents the historical load power with serial number j in the historical load power set, and M represents the total number of historical load powers.

3. The intelligent control method for motor drive based on the Internet of Things according to claim 2, characterized in that: In step S2, the historical load power set is a time series of historical load power changing with time. The fast Fourier transform is used to transform the historical load power set into the frequency domain, and the main periodic components are identified through the spectrogram to obtain the minimum period f; starting from the end of the set, a set with a length of the minimum period f is intercepted from the historical load power set to generate the first subset of the historical load power; Denote the first subset of historical load power with serial number u as LP i u , where LP i u= {LP i （u，v） | v ∈ [1, m i u}, where LP i （u，v） represents the historical load power with serial number v in the first subset of historical load power LP i u , and m i u represents the total number of historical load powers in the first subset of historical load powers; the historical load powers in the first subset of historical load powers are arranged in reverse order of the time when the monitoring sensor collects operation data.

4. The intelligent control method for motor drive based on the Internet of Things according to claim 3, characterized in that: Extract the historical load powers with the same serial number in each first subset of the historical load powers to generate a second subset of the historical load powers, and denote the v-th second subset of the historical load powers as SLP i v ={LP i （u，v） |u∈[1, u max}, u max represents the total number of the historical load powers in the second subset of the historical load powers; or .

5. The intelligent control method for motor drive based on the Internet of Things according to claim 4, characterized in that: In step S3, the second subset SLP of historical load power i v is combined with the time variable and arranged in the order of the monitoring data acquisition time to generate the second subset LPT of historical load power and time i v ={ ( T i （u，v）， LP i （u，v） ), where u ∈ [1, u max }, where T i （u，v） is the data acquisition time of the historical load power LP i （u，v） ; Using the historical load power and the second subset of time, establish an operating characteristic fitting model: y = α1 v ×x + α2 v ; where α1 v and α2 v represent fitting coefficients, x represents the independent variable of time, y represents the dependent variable of historical load power, and calculate and solve for α1 v and α2 v in the operating characteristic fitting model. The specific calculation formula is as follows: ； 。 6. The intelligent control method for motor drive based on the Internet of Things according to claim 5, characterized in that: Predict and calculate the historical load power and the second subset LPT of time using the operation feature fitting model i v for the last element in i （ u max，v）， LP i （ u max，v） ), denoted as (T i （ u max+f，v）， LP i （ u max+f，v） ); When v is greater than 1, the input power of the motor collected by the monitoring sensor at the previous data acquisition moment of (T i （ u max+f，v）， LP i （ u max+f，v） ) is denoted as IP i （ u max+f，v-1） ; when v is equal to 1, the IP i （ u max+f，v-1） is equal to IP i （ u max， m i u） ; calculate the pre-optimization ratio β of the input power to the predicted load power, and the specific calculation formula is as follows: β = LP i （ u max+f，v） ÷ IP i （ u max+f，v-1） ; Set a threshold β for the pre-optimized ratio β 阈 , and use the motor with the pre-optimized ratio β less than the threshold β 阈 as the pre-optimized motor.

7. An intelligent control method for motor drive based on the Internet of Things according to claim 6, characterized in that: In step S4, the input power corresponding to LP in the historical load power set is denoted as IP i j For the motor EM i j calculate the output efficiency ratio OER i The specific calculation formula is as follows: i ​ ； Compare the output efficiency ratios of the motors in the motor set EM, and record the maximum value as the optimized output efficiency ratio OER.

8. The method for intelligent control and management of motor drive based on the Internet of Things according to claim 7, characterized in that: Further calculate the optimization difference OD of the pre-optimized motor according to the optimized output efficiency ratio, and the specific calculation formula is as follows: OD=IP （ u max+f，v-1） -LP （ u max+f，v） ÷OER; Set the threshold OD for optimizing the difference 阈 If the optimized difference OD is less than or equal to the set optimized difference threshold OD 阈 then optimize according to the input power adjustment rate set by the system; If the optimized difference OD is greater than the set optimized difference threshold OD 阈 , then the input power adjustment rate OD 阈 ÷t≥V, where t is the data acquisition time period.

9. An intelligent management and control system for motor drive based on the Internet of Things, the system is implemented by applying the intelligent management and control method for motor drive based on the Internet of Things according to any one of claims 1-8, characterized in that, The system includes a data acquisition module, a database, a data analysis and extraction module, a feature fitting and search module, and an optimization adjustment and control module; The data acquisition module is used to generate a set of motors in the factory, collect the operating data of the motors through monitoring sensors, and transmit the operating data collected by the monitoring sensors to the database; The database is used to receive and store the operating data of the motors; The data analysis and extraction module is used to analyze the operating data to generate the first subset of the historical load power, and perform feature extraction on the first subset of the historical load power to generate the second subset of the historical load power; The feature fitting and search module is used to establish an operating characteristic fitting model according to the second subset of the historical load power extracted, and find the pre-optimized motor according to the operating characteristic fitting model; The optimization adjustment and control module is used to calculate the optimization difference of the pre-optimized motor, and adjust the parameters of the pre-optimized motor according to the calculation result.

Images