An intelligent noise reduction and heat dissipation system for PCS converters

Abstract

The present invention discloses a PCS converter intelligent noise reduction and heat dissipation system, which relates to the field of converter operation control technology, including collecting PCS converter operation data and real-time monitoring of temperature data, optimizing heat dissipation control based on real-time temperature data; acquiring sound data during the operation of the PCS converter to analyze the operation noise, and performing noise reduction control through an intelligent audio driver; integrating heat dissipation control and noise reduction control using an artificial intelligence algorithm to optimize the PCS converter operation parameters and evaluate the effects of the operation parameters; applying and displaying the optimized operation parameters evaluated, and synchronously generating adjustment records and storing them in a database. The present invention realizes dynamic optimization of heat dissipation of PCS converters, effectively solves the problem of local overheating, and realizes precise control of full-band noise, while realizing intelligent adjustment and effect evaluation of converter operation parameters.

Description

Technical Field

[0001] The invention relates to the technical field of converter operation control, and in particular to an intelligent noise reduction and heat dissipation system for a PCS converter. Background Art

[0002] With the rapid development of power electronics technology, power conversion equipment is increasingly used in industrial production, renewable energy utilization, and grid stability. Among them, PCS (Power Conversion System) converters, as core equipment, undertake the important task of DC and AC power conversion. While modern PCS converters pursue high conversion efficiency and high power density, their heat dissipation performance and operating noise issues are becoming increasingly prominent. On the one hand, the high power density design leads to a significant increase in the internal heat of the converter, and poor heat dissipation may cause power devices to overheat, performance degradation, and even equipment failure; on the other hand, the mechanical vibration noise and electromagnetic noise generated during operation not only interfere with the surrounding environment, but also may affect the long-term stability of the equipment. Traditional heat dissipation design mainly relies on fixed fan speed or passive heat dissipation devices, which cannot adapt to changes in dynamic heat loads, making it difficult to effectively solve local hot spot problems; while noise reduction control mainly relies on mechanical structure optimization or static noise shielding technology, which is insufficient to adapt to complex and changeable noise scenes. The existing technology still has obvious deficiencies in the integration and intelligence of heat dissipation control and noise reduction control. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a PCS converter intelligent noise reduction and heat dissipation system to solve the problem that the system cannot adapt to changes in dynamic heat load, resulting in difficulty in effectively solving local hot spot problems and insufficient adaptability to complex and changeable noise scenarios.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a PCS converter intelligent noise reduction and heat dissipation system, which comprises:

[0007] The heat dissipation control module is used to collect PCS converter operation data and monitor temperature data in real time, and optimize heat dissipation control based on real-time temperature data;

[0008] The noise reduction control module is used to obtain the sound data of the PCS converter during operation, analyze the operating noise, and perform noise reduction control through the intelligent audio driver;

[0009] Operation optimization module for comprehensive heat dissipation control and noise reduction control uses artificial intelligence algorithms to optimize PCS converter operating parameters and evaluate the effects of operating parameters;

[0010] A display and storage module is used to apply and display the optimized operating parameters that have passed the evaluation, and to simultaneously generate adjustment records and store them in a database;

[0011] The central control module is used to generate control commands and connect with the heat dissipation control module, the noise reduction control module, the operation optimization module and the display storage module through the network.

[0012] As a preferred solution of the PCS inverter intelligent noise reduction and heat dissipation system described in the present invention, the collecting of PCS inverter operation data and real-time monitoring of temperature data refers to installing current and voltage sensors in the PCS inverter to collect operation current and voltage data, installing NTC thermistors in the PCS inverter to monitor temperature data in real time, installing high-precision wind speed sensors at the inlet and outlet of the heat dissipation channel to record the airflow speed direction, pre-processing the collected operation current and voltage data, temperature data and airflow speed direction, and integrating them into a data set.

[0013] As a preferred solution of the PCS converter intelligent noise reduction and heat dissipation system of the present invention, the heat dissipation control optimization based on real-time temperature data refers to dividing the PCS converter into regions by grids, and using the Bernoulli equation to calculate the air pressure of region z in the heat dissipation channel. ;

[0014] Calculate the air pressure of the adjacent areas of area z respectively, and calculate the pressure difference between area z and the adjacent areas ;

[0015] Calculation of DC copper loss of PCS converter based on the relationship between current square and resistance ;

[0016] According to the DC copper loss Calculating AC Copper Losses :

[0017]

[0018] in is the correction coefficient, f is the switching frequency of the PCS converter;

[0019] Calculate the magnetic flux density B of the PCS converter using the magnetic flux density formula;

[0020] And calculate the total iron loss based on the magnetic flux density :

[0021] ;

[0022] in and are the hysteresis and eddy current loss coefficients, respectively;

[0023] The pressure difference , AC copper loss And the total iron loss Combine the data sets to form the feature matrix X, and define the preliminary temperature prediction model for region z through OLS linear regression:

[0024] ;

[0025] in is the preliminary predicted temperature of region z, is the regression coefficient;

[0026] Optimize regression coefficients by minimizing mean square error ;

[0027] Substitute the optimized regression coefficient into the preliminary temperature prediction model and input the feature matrix X to obtain the preliminary predicted temperature ;

[0028] At the same time, the verification temperature prediction model of area z is defined by the gray box model:

[0029] ;

[0030] in is the real-time temperature of area z, is the air pressure difference between area z and adjacent area j, is the real-time temperature of area j, is the air flow velocity in region j, is the heat retention factor, and are the proportionality coefficients of pressure and air velocity, respectively, Predict the temperature for verification of zone z;

[0031] Optimize and verify the temperature prediction model parameters based on historical data through the least squares method , and And update and verify the temperature prediction model;

[0032] The real-time temperature, regional pressure difference and airflow velocity are input into the verification temperature prediction model to obtain the verification prediction temperature ;

[0033] The preliminary predicted temperature and the verified predicted temperature of area z are weightedly fused to obtain the final predicted temperature of area z. The speed of the PCS converter cooling fan is adjusted according to the final predicted temperature:

[0034] ;

[0035] in is the current speed of the PCS converter fan, The total number of regions divided for the PCS converter, is the set temperature of zone z, is the final predicted temperature of region z, To adjust the gain factor, is the adjusted PCS inverter fan speed.

[0036] As a preferred solution of the PCS converter intelligent noise reduction and heat dissipation system of the present invention, wherein: the acquisition of the sound data of the PCS converter during operation and the analysis of the operating noise refers to arranging an acoustic sensor in the PCS converter to collect the sound data of the PCS converter during operation in real time, and storing the sound data collected by all acoustic sensors as a time domain signal matrix ;

[0037] For the time domain signal matrix Each row in the frequency domain signal matrix is ​​obtained by fast Fourier transform , from the frequency domain signal matrix Identify the main frequency of noise and harmonic frequencies , respectively extract the amplitude and phase corresponding to the main frequency and harmonic frequency of the noise:

[0038] ;

[0039] ;

[0040] in is the amplitude, is the phase, is the real part of frequency l, is the imaginary part of frequency l, which includes the main frequency of the noise and harmonic frequencies .

[0041] As a preferred solution of the PCS converter intelligent noise reduction and heat dissipation system of the present invention, the noise reduction control through the intelligent audio driver refers to obtaining the amplitude and phase of the noise main frequency and the harmonic frequency respectively, and then generating the anti-phase sound wave corresponding to the noise main frequency through the intelligent audio driver. :

[0042] ;

[0043] in is the amplitude of the main frequency of the noise, is the phase of the main frequency of the noise;

[0044] Synchronously superimpose all harmonic frequencies to generate inverse phase sound waves of all harmonic frequencies :

[0045] ;

[0046] in is the amplitude of the i-th harmonic frequency, is the phase of the i-th harmonic frequency, I is the total number of harmonic frequencies, It is an anti-phase sound wave for all harmonic frequencies;

[0047] Use intelligent audio drivers to respectively detect the inverted sound waves corresponding to the main frequency of the noise and all harmonic frequencies in anti-phase Send out corresponding sound signals for noise reduction control.

[0048] As a preferred solution of the PCS converter intelligent noise reduction and heat dissipation system of the present invention, wherein: the comprehensive heat dissipation control and noise reduction control use artificial intelligence algorithm to optimize the PCS converter operating parameters, which refers to randomly generating a candidate parameter set according to the PCS converter operating parameters. , where V is voltage, I is current, L is air flow velocity, G is fan speed, and S is noise. For each candidate parameter set, the operating energy consumption E of the PCS converter is calculated, and each candidate parameter set is defined as an initial population composed of genetic individuals. The inverse of the operating energy consumption E of each genetic individual is used as the fitness. The roulette algorithm is used to select genetic individuals with high fitness values ​​for crossover mutation operations to generate the next generation of genetic individuals. The update is iterated until the fitness value converges. The genetic individual with the highest fitness value in the initial population after convergence is taken as the optimal individual. The gradient descent algorithm is used to perform gradient descent optimization and update the optimal individual and output the updated optimal individual. The operating parameters in the optimal individual are extracted as the optimal parameters.

[0049] As a preferred solution of the PCS converter intelligent noise reduction and heat dissipation system of the present invention, the evaluation of the operating parameter effect refers to performing an operating simulation in a simulation environment according to the obtained optimal parameters, and setting the constraint conditions as follows:

[0050] ;

[0051] in The maximum operating temperature allowed for the PCS converter. is the current operating energy consumption of the PCS converter;

[0052] If the optimal parameters meet all constraints at the same time, the evaluation is passed. If the optimal parameters violate any constraint, the operating parameters are re-optimized. If the optimal parameters cannot pass the evaluation within three optimizations, the current PCS converter operating parameters are judged to be the optimal parameters.

[0053] As a preferred solution of the PCS inverter intelligent noise reduction and heat dissipation system described in the present invention, the application and display of the evaluated optimized operating parameters refers to applying the evaluated optimal operating parameters to the PCS inverter and visually displaying the optimal operating parameters.

[0054] As a preferred solution of the PCS inverter intelligent noise reduction and heat dissipation system described in the present invention, the generation of adjustment records and storage in the database refers to storing the optimal parameters of the PCS inverter and the adjustment records generated by the PCS inverter adjustment in the database, the database classifies the adjustment records according to timestamps, and regularly performs integrity checks on the stored adjustment records, and synchronously uploads them to the cloud for backup storage.

[0055] As a preferred solution of the PCS converter intelligent noise reduction and heat dissipation system described in the present invention, wherein: the generation of control commands and connecting with the heat dissipation control module, the noise reduction control module, the operation optimization module and the display storage module through the network refers to the central control module being connected with the heat dissipation control module, the noise reduction control module, the operation optimization module and the display storage module through the network, and generating control commands and sending them to the remaining modules through the network for comprehensive module control.

[0056] The beneficial effects of the present invention are as follows: the present invention obtains the operating data and temperature data of the PCS converter, performs temperature prediction according to the dual temperature prediction model, and thus controls the heat dissipation of the PCS converter, thereby realizing dynamic optimization of the heat dissipation of the PCS converter, and effectively solving the problem of local overheating. The present invention analyzes the sound data through an artificial intelligence algorithm to calculate the anti-phase sound wave for noise reduction processing to achieve precise control of the full-band noise. At the same time, the PCS operating parameters are optimized through a genetic algorithm, thereby realizing intelligent adjustment of the converter operating parameters and effect evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0058] Figure 1 This is a structural diagram of the intelligent noise reduction and heat dissipation system of the PCS converter in Example 1. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0062] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and provides a PCS converter intelligent noise reduction and heat dissipation system, including the following contents:

[0063] S1, heat dissipation control module, used to collect PCS converter operation data and monitor temperature data in real time, and optimize heat dissipation control based on real-time temperature data;

[0064] Specifically, collecting PCS converter operation data and real-time monitoring of temperature data means installing current and voltage sensors in the PCS converter to collect operation current and voltage data, installing NTC thermistors in the PCS converter to monitor temperature data in real time, installing high-precision wind speed sensors at the entrance and exit of the heat dissipation channel to record the airflow speed direction, pre-processing the collected operation current and voltage data, temperature data, and airflow speed direction, and integrating them into a data set. NTC thermistors have the characteristics of low power consumption and high precision, and their real-time monitoring can quickly capture temperature rise changes, especially in dynamic environments with large thermal load fluctuations.

[0065] The fluctuation of current and voltage directly affects the heat generated by power devices. By collecting these data in real time, the temperature rise trend of power devices can be predicted in advance, thereby providing prior data for fan speed adjustment to avoid overheating of power devices. By monitoring abnormal current and voltage fluctuations, the operating faults of the converter (such as short circuit, overload, etc.) can be quickly diagnosed, thereby reducing local hot spots caused by faults. Through temperature distribution data, local hot spots inside the converter can be identified, thereby guiding the cooling system to perform directional cooling or adjust the cooling air duct to effectively improve the cooling efficiency. Real-time airflow monitoring can determine whether there is airflow blockage, backflow or speed attenuation in the cooling channel. For example, if the outlet wind speed is significantly lower than the inlet wind speed, there may be dust accumulation or airflow disorder in the cooling channel, which can trigger maintenance reminders. By analyzing the wind speed change data, the fan speed or air guide angle can be intelligently adjusted to ensure the uniformity of airflow speed in the cooling channel and reduce local overheating problems. Data from different types of sensors have different sampling frequencies and data formats. The preprocessing process standardizes and synchronizes them to eliminate data deviations and ensure that all data are input with the same time reference.

[0066] Furthermore, the heat dissipation control optimization based on real-time temperature data refers to dividing the PCS converter into grids and using the Bernoulli equation to calculate the air pressure of area z in the heat dissipation channel. :

[0067] ;

[0068] in is the air density, and is the velocity component of the airflow in the heat dissipation channel direction, obtained by orthogonal decomposition;

[0069] Calculate the air pressure of the adjacent areas of area z respectively, and calculate the pressure difference between area z and the adjacent areas ;

[0070] Calculation of DC copper loss of PCS converter based on the relationship between current square and resistance :

[0071] ;

[0072] Where I is the operating current of the PCS converter;

[0073] According to the DC copper loss Calculating AC Copper Losses :

[0074] ;

[0075] in is the correction factor, which is related to the conductor thickness and the current frequency characteristics (determined or calibrated through experiments), and f is the switching frequency of the PCS converter;

[0076] The magnetic flux density B of the PCS converter is calculated using the magnetic flux density formula:

[0077] ;

[0078] Where n is the number of coil turns, I is the operating current of the PCS converter, and A is the cross-sectional area of ​​the magnetic core;

[0079] And calculate the total iron loss based on the magnetic flux density :

[0080] ;

[0081] in and are hysteresis and eddy current loss coefficients respectively (obtained through equipment parameters or calibration);

[0082] The pressure difference , AC copper loss And the total iron loss Combine the data sets to form the feature matrix X, and define the preliminary temperature prediction model for region z through OLS linear regression:

[0083] ;

[0084] in is the preliminary predicted temperature of region z, is the regression coefficient;

[0085] Optimize regression coefficients by minimizing mean square error :

[0086] ;

[0087] in is the actual temperature, obtained through training data, and Q is the transposition operation;

[0088] Substitute the optimized regression coefficient into the preliminary temperature prediction model and input the feature matrix X to obtain the preliminary predicted temperature ;

[0089] At the same time, the verification temperature prediction model of area z is defined by the gray box model:

[0090] ;

[0091] in is the real-time temperature of area z, obtained through real-time monitoring, is the air pressure difference between area z and adjacent area j, is the real-time temperature of area j, is the air flow velocity in region j, is the heat retention factor, reflecting the heat storage capacity of region z (obtained through calibration or experience), and are the proportional coefficients of pressure and air flow velocity, respectively, which are calibrated through experiments. Predict the temperature for verification of zone z;

[0092] Optimize and verify the temperature prediction model parameters based on historical data through the least squares method , and And update and verify the temperature prediction model;

[0093] The real-time temperature, regional pressure difference and airflow velocity are input into the verification temperature prediction model to obtain the verification prediction temperature ;

[0094] The preliminary predicted temperature and the verified predicted temperature of area z are weightedly fused to obtain the final predicted temperature of area z. The speed of the PCS converter cooling fan is adjusted according to the final predicted temperature:

[0095] ;

[0096] in is the current speed of the PCS converter fan, The total number of regions divided for the PCS converter, is the set temperature of zone z, is the final predicted temperature of region z, To adjust the gain factor, is the adjusted PCS inverter fan speed.

[0097] The pressure difference and air flow velocity directly reflect the resistance and efficiency of the heat dissipation path. When the pressure difference in a certain area increases significantly, it means that there may be airflow blockage or local overheating problems in the area. Based on this information, the heat dissipation channel structure or fan speed can be dynamically adjusted. Traditional heat dissipation solutions often rely on global fan speed increases, while the present invention achieves accurate local heat dissipation through regional pressure difference monitoring, reduces unnecessary energy consumption, and accurately calculates heat source losses (copper loss and iron loss) by real-time monitoring of current and magnetic flux density. Compared with traditional heat source assessment methods that rely on static calibration, the present invention achieves dynamic and accurate heat source prediction. Dynamic copper loss and iron loss data are used as the core input of the feature matrix, which improves the accuracy and robustness of the temperature prediction model. The OLS model uses historical data for prediction, while the gray box model corrects the predicted values ​​based on real-time data and physical mechanisms. The combination of the two ensures the accuracy of the prediction and enhances the physical interpretation of the temperature rise process. The gray box model introduces dynamic adjustment parameters of the heat retention factor and the pressure proportional coefficient, which significantly enhances the system's adaptability to environmental changes (such as load fluctuations or changes in heat dissipation channels). Based on the temperature prediction data, the fan speed is adjusted region by region to ensure accurate allocation of heat dissipation resources. For example, when the temperature in a certain area is higher than the set value, the fan speed will be increased first to meet the heat dissipation needs of the area. Compared with the traditional constant speed or global adjustment method, the present invention realizes distributed regulation through regional temperature weights, effectively reducing unnecessary fan power consumption.

[0098] S2, a noise reduction control module, used to obtain the sound data of the PCS converter during operation, analyze the operating noise, and perform noise reduction control through an intelligent audio driver;

[0099] Specifically, obtaining the sound data of the PCS converter during operation and analyzing the operating noise refers to arranging acoustic sensors in the PCS converter to collect the sound data of the PCS converter during operation in real time, and storing all the sound data collected by the acoustic sensors as a time domain signal matrix. :

[0100] ;

[0101] in is the sound data collected by the i-th acoustic sensor, and N is the number of acoustic sensors;

[0102] For the time domain signal matrix Each row in the frequency domain signal matrix is ​​obtained by fast Fourier transform , from the frequency domain signal matrix Identify the main frequency of noise and harmonic frequencies , where there are multiple harmonic frequencies, the amplitude and phase corresponding to the main frequency of the noise and the harmonic frequency are extracted respectively:

[0103] ;

[0104] ;

[0105] in is the amplitude, is the phase, is the real part of frequency l, is the imaginary part of frequency l, which includes the main frequency of the noise and harmonic frequencies .

[0106] The arrangement of acoustic sensors can fully cover the main noise sources of PCS converters, making noise collection global and targeted. Compared with single-point monitoring, multi-point arrangement can improve the ability to describe complex sound fields, especially the analysis of noise propagation paths. The sound signal recorded by each acoustic sensor has clear spatial position information, which is convenient for subsequent analysis of the distribution and time evolution characteristics of noise sources, thereby improving the accuracy of noise reduction processing. The time domain signal matrix normalizes the sound signals of multiple sensors into a unified structure, providing an efficient data input format for subsequent frequency domain analysis, avoiding the complexity of scattered data processing. The time domain signal matrix can ensure the temporal synchronization of data collected by different sensors, thereby improving High accuracy of noise characteristic analysis. Frequency domain signals can directly display the frequency components and intensity distribution of noise signals, avoiding the complex time domain analysis process. Especially for the frequently changing noise sources in the converter, frequency domain signals can significantly improve the analysis efficiency. The FFT algorithm can efficiently separate noise signals of different frequencies, making the extraction of main frequency and harmonics more accurate, which is especially important for multi-frequency noise sources (such as fan noise and electromagnetic noise). The extraction of amplitude and phase can fully reflect the intensity and propagation characteristics of the main frequency and harmonic frequencies, and provide input data for subsequent noise reduction algorithms. The real-time extraction of noise main frequency and harmonic frequencies can provide real-time updated noise characteristic data for dynamic noise reduction control, improving the real-time and accuracy of noise reduction effects.

[0107] Furthermore, the noise reduction control is performed by the intelligent audio driver, and then the amplitude and phase of the noise main frequency and the harmonic frequency are obtained respectively, and then the anti-phase sound wave corresponding to the noise main frequency is generated by the intelligent audio driver. :

[0108] ;

[0109] in is the amplitude of the main frequency of the noise, is the phase of the main frequency of the noise;

[0110] Synchronously superimpose all harmonic frequencies to generate inverse phase sound waves of all harmonic frequencies :

[0111] ;

[0112] in is the amplitude of the i-th harmonic frequency, is the phase of the i-th harmonic frequency, I is the total number of harmonic frequencies, It is an anti-phase sound wave for all harmonic frequencies;

[0113] Use intelligent audio drivers to respectively detect the inverted sound waves corresponding to the main frequency of the noise and all harmonic frequencies in anti-phase Send out corresponding sound signals for noise reduction control.

[0114] The accurate extraction of the amplitude and phase of the main frequency enables the generated anti-phase sound wave to achieve complete waveform oppositeness and phase matching with the noise main frequency signal, thereby achieving an ideal interference silencing effect. This method is significantly better than the signal generation relying on empirical estimation in the traditional noise reduction method. The main frequency is usually the frequency component with the strongest energy in the noise signal. Effective noise reduction of the main frequency can significantly reduce the overall intensity of the environmental noise and reduce the burden for subsequent harmonic noise reduction. The amplitude and phase of the harmonic frequency are important characteristics in complex noise scenes. The superimposed generated anti-phase sound waves can cover multi-frequency noise sources, which is particularly suitable for the complex harmonic components of fan noise and electromagnetic noise in PCS converters. The parameters of all harmonic frequencies are extracted one by one and superimposed for processing, so that the generated anti-phase sound waves can carefully match the noise signals of different frequencies. , significantly reducing the interference of harmonics on the noise reduction effect. Traditional noise reduction methods are often effective for single-frequency noise, but lack the processing capacity for multi-frequency harmonic noise. The present invention solves the technical difficulties of multi-frequency noise reduction by superimposing harmonics. The intelligent audio driver has efficient digital signal processing capabilities and can complete the generation and emission of anti-phase sound waves at the millisecond level, ensuring real-time synchronization with noise signals and avoiding failure caused by noise reduction signal lag. Through the regulation of the intelligent audio driver, the intensity and frequency coverage of the anti-phase sound waves can be dynamically adjusted to adapt to the complex noise change scenarios in the operation of the PCS converter. The intelligent audio driver can achieve targeted noise reduction in single-frequency and multi-frequency noise scenarios by separately controlling the generation and emission of main frequency anti-phase sound waves and harmonic anti-phase sound waves, thereby improving the overall noise reduction effect.

[0115] S3, operation optimization module, for comprehensive heat dissipation control and noise reduction control, uses artificial intelligence algorithms to optimize PCS converter operation parameters and evaluates the effects of operation parameters;

[0116] Specifically, the integrated heat dissipation control and noise reduction control use artificial intelligence algorithms to optimize the PCS converter operating parameters, which refers to randomly generating a candidate parameter set based on the PCS converter operating parameters. , where V is voltage, I is current, L is air flow velocity, G is fan speed, and S is noise. For each candidate parameter set, the operating energy consumption E of the PCS converter is calculated, and each candidate parameter set is defined as an initial population composed of genetic individuals. The inverse of the operating energy consumption E of each genetic individual is used as the fitness. The roulette algorithm is used to select genetic individuals with high fitness values ​​for crossover mutation operations to generate the next generation of genetic individuals. The update is iterated until the fitness value converges. The genetic individual with the highest fitness value in the initial population after convergence is taken as the optimal individual. The gradient descent algorithm is used to perform gradient descent optimization and update the optimal individual and output the updated optimal individual. The operating parameters in the optimal individual are extracted as the optimal parameters.

[0117] By randomly generating candidate parameter sets, the combination space of candidate parameters can be fully explored, providing a sufficient data basis for global optimization and avoiding local optimal problems caused by over-concentration of initial parameter selection. The randomness of candidate parameters makes the algorithm more adaptable, especially when the operating environment of the PCS converter changes dynamically, it can quickly respond to new input conditions, and use the inverse of energy consumption as the fitness function to directly link the optimization goal with the energy-saving demand, ensuring that each generation of genetic algorithm evolution develops in the direction of minimizing energy consumption. The roulette algorithm uses a probabilistic selection mechanism to ensure the inheritance of high-fitness individuals and retain a certain probability of low-fitness individuals, providing diversity support for subsequent crossover mutations. The crossover operation can integrate the advantages of two high-fitness individuals and change The mutation operation effectively prevents the algorithm from falling into the local optimum, thereby improving the global search capability. The mutation operation increases the adaptability of the genetic algorithm to the dynamic changes of the operating parameters of the PCS converter, which is especially suitable for scenarios where the converter load fluctuates frequently. The genetic algorithm is good at global search, but it has shortcomings in local fine optimization. The gradient descent algorithm can further refine the optimal parameters by accurately calculating the energy consumption gradient, significantly improving the optimization accuracy. By combining the genetic algorithm with the gradient descent, the extracted operating parameters take into account the three major goals of heat dissipation, noise reduction and energy saving, reflecting the global optimal optimization effect. The optimal operating parameters not only significantly reduce the operating energy consumption of the PCS converter, but also provide a reliable guarantee for its long-term stable operation, avoiding heat dissipation or noise problems caused by improper parameter settings.

[0118] Furthermore, evaluating the effect of operating parameters refers to running simulation in a simulation environment according to the obtained optimal parameters, and setting the constraints as follows:

[0119] ;

[0120] in The maximum operating temperature allowed for the PCS converter. is the current operating energy consumption of the PCS converter;

[0121] If the optimal parameters meet all constraints at the same time, the evaluation is passed. If the optimal parameters violate any constraint, the operating parameters are re-optimized. If the optimal parameters cannot pass the evaluation within three optimizations, the current PCS converter operating parameters are judged to be the optimal parameters.

[0122] The operating temperature constraint ensures that the converter operates within the designed safety range and effectively avoids hardware failures caused by excessive temperature. This constraint is particularly important under high-power operating conditions. The current energy consumption constraint prompts the optimization algorithm to reduce energy consumption as much as possible while meeting other conditions, thereby improving the energy utilization of the converter and meeting the design goals of energy conservation and emission reduction. Evaluating the optimal parameters in a simulation environment can avoid the risk of damage that may be caused by direct testing on hardware devices. For example, if unverified parameters are run in actual equipment, it may cause temperature exceeding the limit or excessive energy consumption problems. The simulation environment can accurately output operating temperature and energy consumption data, providing a reliable feedback basis for parameter optimization. At the same time, the data can also be used as input for subsequent optimization to improve the scientific nature of parameter adjustment. Re-optimization is a further correction to the initial optimal solution, aiming to make up for the shortcomings of the algorithm in the initial optimization. Through multiple rounds of optimization, it can effectively eliminate In addition to the deviation caused by error accumulation, the three-time optimization limitation can not only prevent the time waste caused by too many iterations, but also ensure the practical feasibility of the results. Especially in complex operating scenarios, this mechanism can dynamically adapt to changing constraints and improve the robustness of the algorithm. Limiting the number of optimizations avoids infinite loops of the algorithm near the local optimal solution, significantly reducing the computing cost. This limitation is particularly critical in embedded systems with limited resources. By clearly limiting the number of optimizations, available solutions can be obtained faster without falling into the lengthy waiting of the optimization process, thereby meeting the efficiency requirements in actual industrial applications. Through the dual constraints on operating temperature and energy consumption, the final operating parameters can meet the heat dissipation requirements while avoiding the increase in energy consumption caused by excessive fan speed or other operating conditions. The operating parameters based on simulation evaluation have stronger stability and adaptability, thereby providing long-term and reliable operation support for PCS converters.

[0123] S4, a display storage module, used to apply and display the optimized operating parameters that have passed the evaluation, and simultaneously generate adjustment records and store them in a database;

[0124] Specifically, applying and displaying the evaluated optimized operating parameters refers to applying the evaluated optimal operating parameters to the PCS converter and visually displaying the optimal operating parameters.

[0125] Furthermore, generating adjustment records and storing them in a database means storing the optimal parameters of the PCS converter and the adjustment records generated by the PCS converter adjustment in the database. The database classifies the adjustment records according to timestamps, and regularly performs integrity checks on the stored adjustment records, and synchronously uploads them to the cloud for backup storage.

[0126] S5, a central control module, used to generate control commands and connect with the heat dissipation control module, the noise reduction control module, the operation optimization module and the display storage module through the network;

[0127] Specifically, generating control commands and connecting with the heat dissipation control module, the noise reduction control module, the operation optimization module and the display storage module through the network means that the central control module is connected with the heat dissipation control module, the noise reduction control module, the operation optimization module and the display storage module through the network, and generating control commands and sending them to the remaining modules through the network for comprehensive module control.

[0128] This embodiment also provides a computer device, which is suitable for the case of a PCS converter intelligent noise reduction and heat dissipation system, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the PCS converter intelligent noise reduction and heat dissipation system proposed in the above embodiment.

[0129] The computer device may be a terminal, and the computer device 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 achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0130] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the intelligent noise reduction and heat dissipation system of the PCS converter is implemented 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 (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0131] In summary, the present invention obtains the operating data and temperature data of the PCS inverter, performs temperature prediction according to the dual temperature prediction model, and thus controls the heat dissipation of the PCS inverter, thereby realizing dynamic optimization of the heat dissipation of the PCS inverter and effectively solving the problem of local overheating. The sound data is analyzed by an artificial intelligence algorithm to calculate the anti-phase sound wave for noise reduction processing to achieve precise control of the noise in the entire frequency band. At the same time, the PCS operating parameters are optimized through a genetic algorithm, thereby realizing intelligent adjustment of the inverter operating parameters and effect evaluation.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A PCS converter intelligent noise reduction and heat dissipation system, characterized by: include, The heat dissipation control module is used to collect PCS converter operation data and monitor temperature data in real time, and optimize heat dissipation control based on real-time temperature data; The noise reduction control module is used to obtain the sound data of the PCS converter during operation, analyze the operating noise, and perform noise reduction control through the intelligent audio driver; Operation optimization module for comprehensive heat dissipation control and noise reduction control uses artificial intelligence algorithms to optimize PCS converter operating parameters and evaluate the effects of operating parameters; A display and storage module is used to apply and display the optimized operating parameters that have passed the evaluation, and to simultaneously generate adjustment records and store them in a database; A central control module, used for generating control commands and connecting with the heat dissipation control module, the noise reduction control module, the operation optimization module and the display storage module through a network; The heat dissipation control optimization based on real-time temperature data refers to dividing the PCS converter into regions by grids and calculating the air pressure of region z in the heat dissipation channel using the Bernoulli equation. , and calculate the pressure difference between area z and the adjacent area ; The pressure difference , AC copper loss And the total iron loss Combine the data sets to form a feature matrix X, and define a preliminary temperature prediction model for region z through OLS linear regression; The preliminary temperature prediction model is: ； in is the preliminary predicted temperature of region z, is the regression coefficient; Optimize regression coefficients by minimizing mean square error ; Substitute the optimized regression coefficient into the preliminary temperature prediction model and input the feature matrix X to obtain the preliminary predicted temperature ; At the same time, the verification temperature prediction model of area z is defined by the gray box model: ； in is the real-time temperature of area z, is the air pressure difference between area z and adjacent area j, is the real-time temperature of area j, is the air flow velocity in region j, is the heat retention factor, and are the proportionality coefficients of pressure and air velocity, Predict the temperature for verification of zone z; The real-time temperature, regional pressure difference and airflow velocity are input into the verification temperature prediction model to obtain the verification prediction temperature ; The preliminary predicted temperature and the verified predicted temperature of area z are weightedly fused to obtain the final predicted temperature of area z, and the speed of the PCS converter cooling fan is adjusted according to the final predicted temperature.

2. The PCS converter intelligent noise reduction and heat dissipation system according to claim 1, characterized in that: The collecting of PCS inverter operation data and real-time monitoring of temperature data refers to installing current and voltage sensors in the PCS inverter to collect operation current and voltage data, installing NTC thermistors in the PCS inverter to monitor temperature data in real time, installing high-precision wind speed sensors at the inlet and outlet of the heat dissipation channel to record the airflow speed direction, pre-processing the collected operation current and voltage data, temperature data and airflow speed direction, and integrating them into a data set.

3. The PCS converter intelligent noise reduction and heat dissipation system according to claim 2, characterized in that: The heat dissipation control optimization based on real-time temperature data refers to dividing the PCS converter into regions by grids and calculating the air pressure of region z in the heat dissipation channel using the Bernoulli equation. ; Calculate the air pressure of the adjacent areas of area z respectively, and calculate the pressure difference between area z and the adjacent areas ; Calculation of DC copper loss of PCS converter based on the relationship between current square and resistance ; According to the DC copper loss Calculating AC Copper Losses : ； in is the correction coefficient, f is the switching frequency of the PCS converter; Calculate the magnetic flux density B of the PCS converter using the magnetic flux density formula; And calculate the total iron loss based on the magnetic flux density : ； in and are the hysteresis and eddy current loss coefficients, respectively; The validation temperature prediction model of region z is defined by the grey box model; Optimize and verify the temperature prediction model parameters based on historical data through the least squares method , and And update and verify the temperature prediction model; The real-time temperature, regional pressure difference and airflow velocity are input into the verification temperature prediction model to obtain the verification prediction temperature ; The PCS converter cooling fan speed is adjusted according to the final predicted temperature: ； in is the current speed of the PCS converter fan, The total number of regions divided for the PCS converter, is the set temperature of zone z, is the final predicted temperature of region z, To adjust the gain factor, is the adjusted PCS inverter fan speed.

4. The PCS converter intelligent noise reduction and heat dissipation system according to claim 3, characterized in that: The acquisition of the sound data of the PCS converter during operation and the analysis of the operating noise refers to arranging an acoustic sensor in the PCS converter to collect the sound data of the PCS converter during operation in real time, and storing the sound data collected by all the acoustic sensors as a time domain signal matrix. ; For the time domain signal matrix Each row in the frequency domain signal matrix is ​​obtained by fast Fourier transform , from the frequency domain signal matrix Identify the main frequency of noise and harmonic frequencies , respectively extract the amplitude and phase corresponding to the main frequency and harmonic frequency of the noise: ； ； in is the amplitude, is the phase, is the real part of frequency l, is the imaginary part of frequency l, which includes the main frequency of the noise and harmonic frequencies .

5. The PCS converter intelligent noise reduction and heat dissipation system according to claim 4, characterized in that: The noise reduction control by the intelligent audio driver refers to obtaining the amplitude and phase of the noise main frequency and the harmonic frequency respectively, and then generating the anti-phase sound wave corresponding to the noise main frequency by the intelligent audio driver. : ； in is the amplitude of the main frequency of the noise, is the phase of the main frequency of the noise; Synchronously superimpose all harmonic frequencies to generate inverse phase sound waves of all harmonic frequencies : ； in is the amplitude of the i-th harmonic frequency, is the phase of the i-th harmonic frequency, I is the total number of harmonic frequencies, It is an anti-phase sound wave for all harmonic frequencies; Use intelligent audio drivers to respectively detect the inverted sound waves corresponding to the main frequency of the noise and all harmonic frequencies in anti-phase Send out corresponding sound signals for noise reduction control.

6. The PCS converter intelligent noise reduction and heat dissipation system according to claim 5, characterized in that: The integrated heat dissipation control and noise reduction control uses an artificial intelligence algorithm to optimize the PCS converter operating parameters, which refers to randomly generating a candidate parameter set according to the PCS converter operating parameters. , where V is voltage, I is current, L is air flow velocity, G is fan speed, and S is noise. For each candidate parameter set, the operating energy consumption E of the PCS converter is calculated, and each candidate parameter set is defined as an initial population composed of genetic individuals. The inverse of the operating energy consumption E of each genetic individual is used as the fitness. The roulette algorithm is used to select genetic individuals with high fitness values ​​for crossover mutation operations to generate the next generation of genetic individuals. The update is iterated until the fitness value converges. The genetic individual with the highest fitness value in the initial population after convergence is taken as the optimal individual. The gradient descent algorithm is used to perform gradient descent optimization and update the optimal individual and output the updated optimal individual. The operating parameters in the optimal individual are extracted as the optimal parameters.

7. The PCS converter intelligent noise reduction and heat dissipation system according to claim 6, characterized in that: Evaluating the effect of operating parameters means running simulation in a simulation environment based on the obtained optimal parameters, and setting the constraints as follows: ； in The maximum operating temperature allowed for the PCS converter. is the current operating energy consumption of the PCS converter; If the optimal parameters meet all constraints at the same time, the evaluation is passed. If the optimal parameters violate any constraint, the operating parameters are re-optimized. If the optimal parameters cannot pass the evaluation within three optimizations, the current PCS converter operating parameters are judged to be the optimal parameters.

8. The PCS converter intelligent noise reduction and heat dissipation system according to claim 7, characterized in that: The applying and displaying the evaluated optimized operating parameters refers to applying the evaluated optimal operating parameters to the PCS converter and visually displaying the optimal operating parameters.

9. The PCS converter intelligent noise reduction and heat dissipation system according to claim 8, characterized in that: The generating and storing the adjustment records in the database refers to storing the optimal parameters of the PCS converter and the adjustment records generated by the PCS converter in the database. The database classifies the adjustment records according to timestamps, and regularly performs integrity checks on the stored adjustment records, and synchronously uploads them to the cloud for backup storage.

10. The PCS converter intelligent noise reduction and heat dissipation system according to claim 9, characterized in that: The generating control command and connecting with the heat dissipation control module, the noise reduction control module, the operation optimization module and the display storage module through the network means that the central control module is connected with the heat dissipation control module, the noise reduction control module, the operation optimization module and the display storage module through the network, and the generating control command is sent to the remaining modules through the network to perform comprehensive module control.

Images