Ultra-efficient intelligent explosion-proof motor dynamic regulation and control system based on edge calculation

Abstract

The invention discloses a super-efficient intelligent explosion-proof motor dynamic regulation and control system based on edge calculation, which relates to the technical field of motor dynamic regulation and control and comprises an edge data acquisition module, a data preprocessing module, a real-time load prediction module, a dynamic compensation module, an energy efficiency safety game control module, a cluster collaborative optimization module and an execution module. The edge data acquisition module is used for acquiring motor operation state parameters and environment safety parameters by adopting a multi-sensor fusion technology to obtain original sensing data; the data preprocessing module is used for carrying out noise reduction processing on the original sensing data by adopting a sliding window filtering method, and extracting a vibration signal characteristic frequency band through a wavelet transform method to obtain standardized time sequence data; and the real-time load prediction module is used for carrying out modeling analysis on the standardized time series data by adopting a time-space convolutional network (TCN) to obtain an initial load prediction value.

Description

Technical Field

[0001] The present invention relates to the technical field of motor dynamic regulation, and in particular to a super-efficient intelligent explosion-proof motor dynamic regulation system based on edge computing. Background Art

[0002] The technical field of motor dynamic regulation mainly focuses on how to achieve real-time monitoring, analysis, and regulation of the operating state of motors through advanced sensing, communication, computing, and control technologies. This field covers from basic data acquisition, signal processing, pattern recognition to advanced machine learning, optimization algorithms, and the design and application of distributed control systems. Therefore, how to use advanced technical means to improve the intelligence level and safety of the super-efficient intelligent explosion-proof motor dynamic regulation system has become one of the urgent problems to be solved currently.

[0003] In the field of motor dynamic regulation, the original sensing data usually contains a large amount of noise. If the noise is not effectively processed, it will directly affect the quality of data analysis, making the results of fault diagnosis and load prediction inaccurate. Moreover, most of the existing load prediction methods adopt simple statistical models or rule-based methods, which are difficult to capture complex patterns and long-term and short-term dependencies in time series, resulting in inaccurate prediction results and unable to meet the requirements of efficient energy efficiency management and fault prevention. At the same time, most traditional control systems adopt fixed or preset control strategies and lack the ability to dynamically adjust according to real-time changes, unable to adapt to complex and changeable actual operating environments, restricting the flexibility and response speed of the system. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a super-efficient intelligent explosion-proof motor dynamic regulation system based on edge computing to solve the problem that most of the existing load prediction methods adopt simple statistical models or rule-based methods, which are difficult to capture complex patterns and long-term and short-term dependencies in time series, resulting in inaccurate prediction results and unable to meet the requirements of efficient energy efficiency management and fault prevention.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a super-efficient intelligent explosion-proof motor dynamic regulation system based on edge computing, which includes:

[0008] An edge data acquisition module, a data preprocessing module, a real-time load prediction module, a dynamic compensation module, an energy efficiency and safety game control module, a cluster collaborative optimization module, and an execution module;

[0009] The edge data acquisition module is used to collect the motor operation state parameters and environmental safety parameters by using multi-sensor fusion technology to obtain the original sensing data;

[0010] The data preprocessing module is used to denoise the original sensing data by using the sliding window filtering method and extract the vibration signal characteristic frequency band by using the wavelet transform method to obtain the standardized time series data;

[0011] The real-time load prediction module is used to model and analyze the standardized time series data by using the temporal convolutional network (TCN) to obtain the initial load prediction value;

[0012] The dynamic compensation module is used to correct the residual of the initial load prediction value by using the recursive least squares (RLS) method to obtain the high-precision load prediction value;

[0013] The energy efficiency and safety game control module is used to optimize the high-precision load prediction value and environmental parameters by using the multi-objective reinforcement learning algorithm, and generate the optimal energy efficiency and safety control instruction by dynamically calculating the critical safety threshold;

[0014] The cluster collaborative optimization module is used to collaboratively calculate the optimal energy efficiency and safety control instruction by using the distributed algorithm (ADMM), introduce the Nash game equilibrium strategy, and output the PWM regulation parameters of each motor;

[0015] The execution module is used to send the PWM regulation parameters to the motor driver to execute physical control.

[0016] As a preferred solution of the edge computing-based ultra-high efficiency intelligent explosion-proof motor dynamic regulation system of the present invention, wherein: the step of collecting the motor operation state parameters and environmental safety parameters by using the multi-sensor fusion technology to obtain the original sensing data is as follows:

[0017] Three groups of high-precision industrial-grade sensor arrays are used for data collection;

[0018] The three groups of high-precision industrial-grade sensors include a motor state monitoring group, an environmental monitoring group, and a mechanical monitoring group;

[0019] The motor state monitoring group includes a Hall current sensor, a differential voltage sensor, and a MEMS vibration sensor;

[0020] The environmental monitoring group includes an infrared methane sensor and a PT100 temperature sensor;

[0021] The mechanical monitoring group includes a six-axis inertial measurement unit and an acoustic emission sensor;

[0022] Design a hard synchronization acquisition scheme based on timestamps, and generate a 10MHz synchronous clock signal through a Field Programmable Gate Array (FPGA), which is distributed to each sensor node to collect the motor operating state parameters and environmental safety parameters, and obtain the original sensing data;

[0023] The motor operating state parameters include the current, voltage, speed, and temperature of the motor;

[0024] The environmental safety parameters include methane concentration and vibration spectrum.

[0025] As a preferred embodiment of the ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing of the present invention, the following steps are taken: the original sensing data is denoised by using a sliding window filtering method, and the characteristic frequency band of the vibration signal is extracted by using a wavelet transform method to obtain standardized time series data. The specific steps are as follows:

[0026] Define the sliding window size. For the data at each time point, use all the data points within the sliding window to calculate the arithmetic mean of the points;

[0027] Select the Morlet wavelet as the mother wavelet function for time-frequency analysis, apply wavelet transform to the denoised time series data, and obtain wavelet coefficients at different scales and translations;

[0028] By analyzing the results of the wavelet transform, determine the specific frequency band that is closely related to the motor fault or operating state;

[0029] Standardize the wavelet coefficients of the extracted characteristic frequency band to obtain the standardized time series data.

[0030] As a preferred embodiment of the ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing of the present invention, the following steps are taken: the standardized time series data is modeled and analyzed by using a Temporal Convolutional Network (TCN) to obtain an initial load prediction value. The specific steps are as follows:

[0031] Based on the characteristics of the motor operating state parameters, define the convolution kernel size and the number of network layers, and define the output of each layer as representing the hidden state at the l-th layer and time point t;

[0032] Introduce a residual connection between each layer so that information can be directly transmitted from the previous layer to the subsequent layers. The expression is:

[0033]

[0034] where, is the hidden state at the l-th layer and time point t in the TCN model, ReLU is the activation function, and Conv is a one-dimensional convolution operation;

[0035] The mean squared error loss function \(L\) is used to evaluate the performance of the model, and its expression is:

[0036]

[0037] where \(y\) i represents the actual load value, is the load value predicted by the TCN model;

[0038] The Adam optimization algorithm is selected to adjust the model parameters to minimize the above loss function, and its expression is:

[0039]

[0040] where \(\theta\) t is the model parameter, \(\alpha\) is the learning rate, and are the first and second moment estimates of the gradient respectively;

[0041] The standardized time series data is input into the trained TCN model to obtain the load prediction value corresponding to each time point.

[0042] As a preferred solution of the ultra - efficient intelligent explosion - proof motor dynamic regulation system based on edge computing described in the present invention, wherein: the recursive least squares method (RLS) is used to correct the residual of the initial load prediction value to obtain a high - precision load prediction value, and the specific steps are as follows:

[0043] Set the initial parameters for the RLS algorithm;

[0044] Set the initially estimated weight vector as a zero vector, indicating no prior knowledge, and set the initial covariance matrix;

[0045] Use the initial load prediction value obtained after the standardized time series data is processed by the TCN model as the input of the RLS algorithm;

[0046] Use the RLS algorithm to correct the residual of the initial load prediction value. For each time point \(t\), calculate its residual \(e(t)\), and the expression is:

[0047]

[0048] where \(y(t)\) is the actual load value, \(\varphi(t)\) is the regression vector containing current and past load information, is the weight vector estimated at the previous moment;

[0049] According to the update rule of the RLS algorithm, first calculate the gain vector, then update the weight vector, and finally update the covariance matrix;

[0050] Use the updated weight vector Predict the new input data to obtain a high-precision load prediction value.

[0051] As a preferred embodiment of the ultra-high efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing according to the present invention, wherein: the multi-objective reinforcement learning algorithm is used to optimize the high-precision load prediction value and environmental parameters, and the optimal energy efficiency safety control instruction is generated by dynamically calculating the critical safety threshold. The specific steps are as follows:

[0052] Use the multi-objective reinforcement learning algorithm MORL to optimize the high-precision load prediction value and environmental parameters;

[0053] The environmental parameters include methane concentration C(t) and temperature T(t);

[0054] Define the multi-objective function, and the expression is:

[0055] J(θ) = w1R eff (β) + w2R safe (β);

[0056] Wherein, R eff (β) represents the energy efficiency return, R safe (θ) represents the safety return, and w1 and w2 are weight coefficients;

[0057] Use the dynamic calculation method to determine the critical safety threshold S th (t), and the expression is:

[0058] S th (t) = αC(t) + βT(t) + γ;

[0059] Wherein, α, β, and γ are constants obtained based on experimental data and historical analysis, and are used to adjust the influence degree of different factors on the safety threshold;

[0060] Use the MORL algorithm to generate the optimal control instruction.

[0061] As a preferred embodiment of the ultra-high efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing according to the present invention, wherein: the distributed algorithm ADMM is used to perform collaborative calculation on the optimal energy efficiency safety control instruction, and the Nash game equilibrium strategy is introduced to output the PWM regulation parameters of each motor. The expression is:

[0062] Define the state set S of all motors;

[0063] Set the initial Lagrange multiplier in the ADMM algorithm to a zero vector, and the penalty parameter, which is used to adjust the strictness of the constraint conditions;

[0064] For each motor, set the corresponding control instruction using the optimal energy efficiency safety control instruction;

[0065] For each iteration and for each motor, update its local variables by solving a minimization problem, expressed as:

[0066]

[0067] where f i (x i ) represents the cost function of the i-th motor, related to energy efficiency and safety objectives, and x j represents the variables of adjacent motors, determined by the network topology, is the Lagrange multiplier at the current iteration;

[0068] Adjust the Lagrange multiplier using an update rule and optimize the interaction between motors using the concept of Nash equilibrium;

[0069] At the end of each iteration, check whether Nash equilibrium is reached, that is, no motor can obtain a better result by changing its own strategy alone;

[0070] When is satisfied, Nash equilibrium is reached, where is the current strategy and x i ′ is any possible alternative strategy;

[0071] Use the finally determined set of control instructions as input to generate the PWM control parameters for each motor.

[0072] As a preferred solution of the ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing described in the present invention, wherein: the expression for sending the PWM control parameters to the motor driver to execute physical control is:

[0073] Adopt the communication protocol between the edge computing platform and the motor driver;

[0074] Convert the PWM control parameters into a form suitable for processing by the target driver;

[0075] Send the converted PWM control parameters to the motor driver using the selected communication protocol;

[0076] After receiving the data packet, the motor driver parses it to extract the PWM control parameters and adjusts the operating state of the motor according to the parameters;

[0077] Use the motor driver to control the motor to run according to the new PWM signal.

[0078] In a second aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing as described in the first aspect of the present invention is implemented.

[0079] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing as described in the first aspect of the present invention is implemented.

[0080] The beneficial effects of the present invention are as follows: the original sensing data is denoised by the sliding window filtering method, and the characteristic frequency band of the vibration signal is extracted by the wavelet transform method to obtain the standardized time series data, effectively removing noise interference and improving data quality. The standardized time series data is modeled and analyzed by the temporal convolutional network TCN to obtain the initial load prediction value. The advanced machine learning model is used to capture the complex patterns in the time series, making the load prediction more accurate. This not only helps to identify possible load fluctuations in advance but also supports the dynamic adjustment of the motor's working state to optimize energy efficiency. The initial load prediction value is corrected by the recursive least squares method RLS to obtain a high-precision load prediction value. The RLS algorithm is used to continuously update the prediction model and correct the prediction error, further improving the accuracy of the load prediction. It can ensure highly accurate load prediction even in a complex and changeable actual operating environment, promoting the implementation of more refined control strategies. Description of the Drawings

[0081] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0082] Figure 1 It is a schematic diagram of the ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing in Embodiment 1. Detailed Embodiments

[0083] To make the above objects, features, and advantages of the present invention more obvious and understandable, the detailed embodiments of the present invention will be described in detail below with reference to the drawings in the specification.

[0084] In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0085] Secondly, as used herein, "one embodiment" or "an embodiment" refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other.

[0086] Example 1, referring to Figure 1 , is the first embodiment of the present invention. This embodiment provides a super-efficient intelligent explosion-proof motor dynamic regulation system based on edge computing, including:

[0087] An edge data acquisition module, a data preprocessing module, a real-time load prediction module, a dynamic compensation module, an energy efficiency and safety game control module, a cluster collaborative optimization module, and an execution module;

[0088] The edge data acquisition module is used to collect motor operation state parameters and environmental safety parameters by using multi-sensor fusion technology to obtain raw sensing data;

[0089] Furthermore, three groups of high-precision industrial-grade sensor arrays are used for data acquisition;

[0090] The three groups of high-precision industrial-grade sensors include a motor state monitoring group, an environmental monitoring group, and a mechanical monitoring group;

[0091] The motor state monitoring group includes a Hall current sensor, a differential voltage sensor, and a MEMS vibration sensor;

[0092] The environmental monitoring group includes an infrared methane sensor and a PT100 temperature sensor;

[0093] The mechanical monitoring group includes a six-axis inertial measurement unit and an acoustic emission sensor;

[0094] Design a hard synchronization acquisition scheme based on timestamps, and generate a 10MHz synchronization clock signal through a field programmable gate array (FPGA) and distribute it to each sensor node to collect motor operation state parameters and environmental safety parameters, and obtain raw sensing data;

[0095] The motor operation state parameters include the current, voltage, speed, and temperature of the motor;

[0096] The environmental safety parameters include methane concentration and vibration spectrum;

[0097] It should be noted that by using three groups of high-precision industrial sensor arrays for data acquisition and designing a hard synchronization acquisition scheme based on timestamps, the time consistency among sensor nodes is ensured, thereby improving the accuracy and reliability of the original sensing data. It can not only effectively capture the changes in the motor operating state and environmental safety parameters, but also provide a solid foundation for subsequent data processing and analysis, contributing to more precise motor control and fault diagnosis.

[0098] A data preprocessing module is used to perform noise reduction processing on the original sensing data by using a sliding window filtering method and extract the characteristic frequency band of the vibration signal through a wavelet transform method to obtain standardized time series data;

[0099] Furthermore, the size of the sliding window is defined. For the data at each time point, the arithmetic mean of the points is calculated using all the data points within the sliding window;

[0100] The Morlet wavelet is selected as the mother wavelet function for time-frequency analysis, and wavelet transform is applied to the denoised time series data to obtain wavelet coefficients at different scales and translations;

[0101] By analyzing the results of the wavelet transform, a specific frequency band closely related to motor faults or operating states is determined;

[0102] The wavelet coefficients of the extracted characteristic frequency band are standardized to obtain standardized time series data;

[0103] It should be noted that using the sliding window filtering method and wavelet transform technology to perform noise reduction processing and feature extraction on the original sensing data can significantly reduce noise interference and improve signal quality. By selecting the Morlet wavelet as the mother wavelet function for time-frequency analysis, a specific frequency band closely related to motor faults or operating states can be effectively identified, which not only improves the usability of the data, but also provides high-quality input data for subsequent load prediction, contributing to improving the stability and reliability of the entire system.

[0104] A real-time load prediction module is used to perform modeling analysis on the standardized time series data by using a spatio-temporal convolutional network (TCN) to obtain an initial load prediction value;

[0105] Furthermore, based on the characteristics of the motor operating state parameters, the size of the convolutional kernel and the number of network layers are defined, and the output of each layer is defined as representing the hidden state at the l-th layer and time point t;

[0106] A residual connection is introduced between each layer so that information can be directly passed from the previous layer to subsequent layers. The expression is:

[0107]

[0108] Among them, is the hidden state of the l-th layer and time point t in the TCN model, ReLU is the activation function, and Conv is the one-dimensional convolution operation;

[0109] The mean squared error loss function L is used to evaluate the model performance, and the expression is:

[0110]

[0111] Among them, y i represents the actual load value, is the load value predicted by the TCN model;

[0112] The Adam optimization algorithm is selected to adjust the model parameters to minimize the above loss function, and the expression is:

[0113]

[0114] Among them, θ t is the model parameter, α is the learning rate, and are the first and second moment estimates of the gradient respectively;

[0115] The standardized time series data is input into the trained TCN model to obtain the load prediction value corresponding to each time point;

[0116] It should be noted that using the spatio-temporal convolutional network TCN to model and analyze the standardized time series data can capture the complex patterns and long-term and short-term dependencies in the time series, so as to provide more accurate initial load prediction values. The design of the TCN model combined with residual connections further enhances the learning ability and stability of the model, making the prediction results more reliable, which is of great significance for early warning of potential load fluctuations and optimizing the motor operation efficiency, and helps to reduce energy consumption and extend the service life of the equipment.

[0117] The dynamic compensation module is used to perform residual correction on the initial load prediction value by using the recursive least squares method RLS to obtain a high-precision load prediction value;

[0118] Furthermore, initial parameters are set for the RLS algorithm;

[0119] Let the initially estimated weight vector be a zero vector, indicating no prior knowledge, and set the initial covariance matrix;

[0120] The initial load prediction value obtained after processing the standardized time series data by the TCN model is used as the input of the RLS algorithm;

[0121] The residual correction of the initial load prediction value is carried out by using the RLS algorithm. For each time point t, its residual e(t) is calculated, and the expression is:

[0122]

[0123] where y(t) is the actual load value, φ(t) is the regression vector containing the current and past load information, is the weight vector estimated at the previous moment;

[0124] According to the update rule of the RLS algorithm, first calculate the gain vector, then update the weight vector, and finally update the covariance matrix;

[0125] Use the updated weight vector to predict the new input data and obtain a high-precision load prediction value;

[0126] It should be noted that the recursive least squares method RLS can dynamically adjust the prediction model to adapt to the changes in actual operations by performing residual correction on the initial load prediction value, so as to obtain a higher-precision load prediction value. It can not only quickly respond to the real-time changes of the load, but also continuously improve the prediction accuracy, providing a solid basis for the subsequent energy efficiency and safety game control, and helping to maintain the efficient and stable operating state of the motor in a complex and changeable operating environment and improve the performance of the overall system.

[0127] The energy efficiency and safety game control module is used to optimize the high-precision load prediction value and environmental parameters by using the multi-objective reinforcement learning algorithm, and generate the optimal energy efficiency and safety control instruction by dynamically calculating the critical safety threshold;

[0128] Furthermore, the multi-objective reinforcement learning algorithm MORL is used to optimize the high-precision load prediction value and environmental parameters;

[0129] The environmental parameters include methane concentration C(t) and temperature T(t);

[0130] Define the multi-objective function, and the expression is:

[0131] J(θ) = w1R eff (θ) + w2R safe (θ);

[0132] where R eff (θ) represents the energy efficiency return, R safe (θ) represents the safety return, and w1 and w2 are weight coefficients;

[0133] Use the dynamic calculation method to determine the critical safety threshold S th (t), and the expression is:

[0134] Sth f(t) = αC(t) + βT(t) + γ;

[0135] Among them, α, β, and γ are constants obtained based on experimental data and historical analysis, and are used to adjust the influence degree of different factors on the safety threshold;

[0136] The MORL algorithm is used to generate the optimal control instruction;

[0137] It should be noted that the multi-objective reinforcement learning algorithm MORL combined with the method of dynamically calculating the critical safety threshold can maximize the energy efficiency return on the premise of ensuring the system safety. By defining a multi-objective function including energy efficiency and safety return, and determining the critical safety threshold according to experimental data and historical analysis, the generation of the optimal energy efficiency safety control instruction is realized, which not only improves the system safety, but also optimizes the energy efficiency performance, and helps to reduce the energy consumption while meeting the safety requirements.

[0138] The cluster collaborative optimization module is used to perform collaborative calculation on the optimal energy efficiency safety control instruction by using the distributed algorithm ADMM, introduce the Nash game equilibrium strategy, and output the PWM regulation parameters of each motor;

[0139] Furthermore, define the state set S of all motors;

[0140] Set the initial Lagrange multiplier in the ADMM algorithm as a zero vector, and the penalty parameter, which is used to adjust the strictness of the constraint conditions;

[0141] For each motor with the optimal energy efficiency safety control instruction, set the corresponding control instruction;

[0142] For each iteration, for each motor, update its local variable by solving the minimization problem, and the expression is:

[0143]

[0144] Among them, f i (x i ) represents the cost function of the i-th motor, which is related to the energy efficiency and safety objectives, and x j represents the variable of the adjacent motor, which is determined by the network topology structure, is the Lagrange multiplier at the current iteration number;

[0145] Adjust the Lagrange multiplier by using the update rule, and optimize the interaction between motors by using the Nash equilibrium concept;

[0146] At the end of each iteration, check whether the Nash equilibrium is reached, that is, no motor can obtain better results by changing its own strategy alone;

[0147] When it satisfies a Nash equilibrium is reached, where is the current strategy and x i ′ is any possible alternative strategy;

[0148] Use the finally determined set of control instructions as input to generate the PWM regulation parameters for each motor;

[0149] It should be noted that the combination of the distributed algorithm ADMM and the Nash game equilibrium strategy can effectively coordinate the interactions between multiple motors, achieve the output of globally optimal PWM regulation parameters, ensure that each motor can operate under its optimal strategy, avoid the problem of local optimal solutions, not only improve the collaborative efficiency of the system, but also enhance the robustness and stability of the overall system by introducing Lagrange multipliers and penalty parameters, and checking whether the Nash equilibrium state is reached.

[0150] An execution module for sending the PWM regulation parameters to the motor driver to perform physical control;

[0151] Furthermore, adopt the communication protocol between the edge computing platform and the motor driver;

[0152] Convert the PWM regulation parameters into a form suitable for processing by the target driver;

[0153] Send the converted PWM regulation parameters to the motor driver using the selected communication protocol;

[0154] After receiving the data packet, the motor driver parses it to extract the PWM regulation parameters and adjusts the working state of the motor according to the parameters;

[0155] Use the motor driver to control the motor to run according to the new PWM signal;

[0156] It should be noted that sending the PWM regulation parameters to the motor driver to perform physical control through the communication protocol between the edge computing platform and the motor driver realizes the seamless connection from data analysis to actual operation. By converting the PWM regulation parameters into a form suitable for processing by the target driver and using the selected communication protocol for transmission, the accuracy and real-time performance of the control instructions are ensured, not only improving the accuracy of motor control, but also enhancing the flexibility and response speed of the system, which helps to achieve efficient motor management and maintenance.

[0157] This embodiment also provides a computer device applicable to the situation of an ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing as proposed in the above embodiment.

[0158] The computer device can be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through Wi-Fi, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0159] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0160] In summary, the present invention performs noise reduction processing on the original sensing data through a sliding window filtering method, extracts the characteristic frequency band of the vibration signal through a wavelet transform method, obtains standardized time-series data, effectively removes noise interference, and improves data quality. By using a spatio-temporal convolutional network (TCN) to model and analyze the standardized time-series data, an initial load prediction value is obtained. An advanced machine learning model is used to capture complex patterns in the time series, making the load prediction more accurate. This not only helps to identify potential load fluctuations in advance but also supports dynamic adjustment of the motor's operating state to optimize energy efficiency. Through recursive least squares (RLS), the initial load prediction value is corrected for residuals, obtaining a high-precision load prediction value. The RLS algorithm is used to continuously update the prediction model and correct the prediction error, further improving the accuracy of the load prediction. This can ensure highly accurate load prediction even in complex and changing actual operating environments, facilitating the implementation of more refined control strategies.

[0161] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An ultra-efficient intelligent explosion-proof motor dynamic regulation system based on edge computing, characterized in that: Including: Edge data acquisition module, data preprocessing module, real-time load prediction module, dynamic compensation module, energy efficiency and safety game control module, cluster collaborative optimization module, and execution module; The edge data acquisition module is used to collect the motor operating state parameters and environmental safety parameters by using multi-sensor fusion technology to obtain the original sensing data; The data preprocessing module is used to perform noise reduction processing on the original sensing data by using a sliding window filtering method, and extract the vibration signal characteristic frequency band by using a wavelet transform method to obtain the standardized time series data; The real-time load prediction module is used to perform modeling analysis on the standardized time series data by using a temporal convolutional network (TCN) to obtain the initial load prediction value; The dynamic compensation module is used to perform residual correction on the initial load prediction value by using the recursive least squares (RLS) method to obtain the high-precision load prediction value; The energy efficiency and safety game control module is used to optimize the high-precision load prediction value and environmental parameters by using a multi-objective reinforcement learning algorithm, and generate the optimal energy efficiency and safety control instruction by dynamically calculating the critical safety threshold; The cluster collaborative optimization module is used to perform collaborative calculation on the optimal energy efficiency and safety control instruction by using the distributed algorithm (ADMM), introduce the Nash game equilibrium strategy, and output the PWM regulation parameters of each motor; The execution module is used to send the PWM regulation parameters to the motor driver to execute physical control.

2. The ultra - efficient intelligent explosion - proof motor dynamic regulation system based on edge computing according to claim 1, characterized in that: The specific steps of collecting the motor operating state parameters and environmental safety parameters by using multi-sensor fusion technology to obtain the original sensing data are as follows: Three groups of high-precision industrial-grade sensor arrays are used for data collection; The three groups of high-precision industrial-grade sensors include a motor status monitoring group, an environmental monitoring group, and a mechanical monitoring group; The motor status monitoring group includes a Hall current sensor, a differential voltage sensor, and a MEMS vibration sensor; The environmental monitoring group includes an infrared methane sensor and a PT100 temperature sensor; The mechanical monitoring group includes a six-axis inertial measurement unit and an acoustic emission sensor; Design a hard synchronization acquisition scheme based on timestamps, and generate a 10 MHz synchronous clock signal through a field programmable gate array (FPGA), distribute it to each sensor node, collect the motor operating state parameters and environmental safety parameters, and obtain the original sensing data; The motor operating state parameters include the current, voltage, speed, and temperature of the motor; The environmental safety parameters include methane concentration and vibration spectrum.

3. The ultra-high efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing according to claim 2, characterized in that: The specific steps of performing noise reduction processing on the original sensing data by using a sliding window filtering method and extracting the vibration signal characteristic frequency band by using a wavelet transform method to obtain the standardized time series data are as follows: Define the sliding window size, and for the data at each time point, calculate the arithmetic mean of the points by using all the data points within the sliding window; Select the Morlet wavelet as the mother wavelet function for time-frequency analysis, apply wavelet transform to the denoised time series data, and obtain the wavelet coefficients at different scales and translations; By analyzing the results of the wavelet transform, determine the specific frequency band closely related to motor faults or operating states; Standardize the wavelet coefficients of the extracted characteristic frequency bands to obtain standardized time series data.

4. The ultra-high efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing according to claim 3, characterized in that: Use the spatio-temporal convolutional network TCN to model and analyze the standardized time series data to obtain the initial load prediction value. The specific steps are as follows: Based on the characteristics of the motor operating state parameters, the convolution kernel size and the number of network layers are defined, and the output of each layer is defined as representing the hidden state at the l-th layer and time point t; Introduce residual connections between each layer so that information can be directly transmitted from the previous layer to several subsequent layers. The expression is: Among them, is the hidden state of the l-th layer and the time point t in the TCN model, ReLU is the activation function, and Conv is the one-dimensional convolution operation; Use the mean squared error loss function L to evaluate the model performance. The expression is: Among them, y i represents the actual load value, which is the load value predicted by the TCN model; Select the Adam optimization algorithm to adjust the model parameters to minimize the above loss function. The expression is: where θ t is a model parameter, α is the learning rate, and are the first and second moment estimates of the gradient, respectively; Input the standardized time series data into the trained TCN model to obtain the load prediction value corresponding to each time point.

5. The ultra-high-efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing according to claim 4, characterized in that: Use the recursive least squares method RLS to correct the residuals of the initial load prediction value to obtain a high-precision load prediction value. The specific steps are as follows: Set the initial parameters for the RLS algorithm; Set the initially estimated weight vector as a zero vector, indicating no prior knowledge, and set the initial covariance matrix; Use the initial load prediction value obtained after processing the standardized time series data by the TCN model as the input of the RLS algorithm; Use the RLS algorithm to correct the residuals of the initial load prediction value. For each time point t, calculate its residual e(t). The expression is: where \(y(t)\) is the actual load value, \(\varphi(t)\) is the regression vector containing current and past load information, is the weight vector estimated at the previous moment; According to the update rule of the RLS algorithm, first calculate the gain vector, then update the weight vector, and finally update the covariance matrix; Adopt the updated weight vector Predict the new input data to obtain a high-precision load prediction value.

6. The ultra-high efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing according to claim 5, characterized in that: Use the multi-objective reinforcement learning algorithm to optimize the high-precision load prediction value and environmental parameters, and generate the optimal energy efficiency safety control instruction by dynamically calculating the critical safety threshold. The specific steps are as follows: Use the multi-objective reinforcement learning algorithm MORL to optimize the high-precision load prediction value and environmental parameters; The environmental parameters include methane concentration C(t) and temperature T(t); Define the multi-objective function. The expression is: J(θ) = w1R eff (θ) + w2R safe (θ); Among them, R eff (θ) represents the energy efficiency return, and R safe (θ) represents the safety return, where w1 and w2 are weight coefficients; Determine the critical safety threshold S th (t) using a dynamic calculation method, with the expression: S th (t) = αC(t) + βT(t) + γ; Among them, α, β, and γ are constants obtained based on experimental data and historical analysis, and are used to adjust the influence degree of different factors on the safety threshold; Use the MORL algorithm to generate the optimal control instruction.

7. The ultra-high efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing according to claim 6, characterized in that: Use the distributed algorithm ADMM to perform collaborative calculation on the optimal energy efficiency safety control instruction, introduce the Nash game equilibrium strategy, and output the PWM regulation parameters of each motor. The expression is: Define the state set S of all motors; Set the initial Lagrange multiplier in the ADMM algorithm as a zero vector, and the penalty parameter, which is used to adjust the strictness of the constraint conditions; Use the optimal energy efficiency safety control instruction to set the corresponding control instruction for each motor; For each iteration, for each motor, update its local variable by solving the minimization problem. The expression is: Among them, f i (x i ) represents the cost function of the i-th motor, which is related to the energy efficiency and safety objectives. x j represents the variables of adjacent motors, which are determined by the network topology structure, is the Lagrange multiplier at the current iteration; Use the update rule to adjust the Lagrange multiplier, and use the Nash equilibrium concept to optimize the interaction between motors; At the end of each iteration, check whether the Nash equilibrium is reached, that is, no motor can obtain better results by changing its own strategy alone; When the following condition is met a Nash equilibrium is reached, where is the current strategy, and x i ′ is any possible alternative strategy; Use the finally determined set of control instructions as the input to generate the PWM regulation parameters of each motor.

8. The ultra-high efficiency intelligent explosion-proof motor dynamic regulation system based on edge computing according to claim 7, characterized in that: Send the PWM regulation parameters to the motor driver to execute physical control. The expression is: Use the communication protocol between the edge computing platform and the motor driver; Convert the PWM control parameters into a form suitable for processing by the target driver; Send the converted PWM control parameters to the motor driver using the selected communication protocol; After receiving the data packet, the motor driver parses it to extract the PWM control parameters and adjusts the operating state of the motor according to the parameters; Use the motor driver to control the motor to run according to the new PWM signal.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the edge computing-based ultra-high efficiency intelligent explosion-proof motor dynamic regulation system according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the edge computing-based ultra-high efficiency intelligent explosion-proof motor dynamic regulation system according to any one of claims 1 to 7.

Images