Desulfurization fan room noise reduction optimization system based on sound field simulation

Abstract

The invention discloses a noise reduction optimization system for a desulfurization fan room based on sound field simulation. The noise reduction optimization system comprises a data acquisition module, a sound field simulation module, a noise analysis module, a noise reduction scheme optimization module and a scheme output and execution module. By integrating a sound field simulation technology and a modular optimization system, accurate prediction and active optimization of the noise of the desulfurization fan room are realized, and the system can perform high-precision sound field simulation and identify a main noise source and a propagation path on the basis of actual equipment parameters and a machine room structure, so that a targeted noise reduction scheme is generated; according to the method, the blindness of a traditional method is effectively avoided, the noise reduction effect is remarkably improved, the treatment cost is reduced, the long-term effectiveness of measures is guaranteed through real-time monitoring and dynamic optimization functions, meanwhile, the equipment operation efficiency and the machine room safety are both considered, and a scientific and intelligent solution is provided for industrial noise treatment.

Description

Technical Field

[0001] This invention relates to the field of noise optimization system technology, specifically to a noise reduction optimization system for desulfurization fan rooms based on sound field simulation. Background Technology

[0002] In industrial sectors such as thermal power plants and chemical plants, desulfurization fans are key equipment to ensure environmental compliance, but the loud noise they generate during operation seriously pollutes the working environment and endangers personnel health.

[0003] Currently, noise reduction measures for desulfurization fan rooms mainly rely on passive means such as installing soundproof walls and sound absorbers. These methods lack specificity, are often based on experience-based design, and are difficult to accurately predict and optimize the sound field distribution, resulting in limited noise reduction effects, high costs, and potential impact on equipment ventilation and heat dissipation.

[0004] With increasingly stringent environmental standards and the development of intelligent industry, there is an urgent need for a systematic solution that can accurately predict, analyze, and optimize noise control schemes. Summary of the Invention

[0005] To address this issue, the present invention provides a noise reduction optimization system for desulfurization fan rooms based on sound field simulation, in order to solve the problems in the prior art where it is difficult to accurately predict and optimize the sound field distribution, resulting in limited noise reduction effect, high cost, and potential impact on equipment ventilation and heat dissipation.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A noise reduction optimization system for desulfurization fan rooms based on sound field simulation includes the following modules:

[0008] The data acquisition module is used to acquire the physical parameters of the desulfurization fan room, the operating parameters of the fan equipment, and noise data. The physical parameters include the geometric dimensions of the fan room, the properties of the wall materials, and the layout of internal obstacles. The operating parameters of the fan equipment include the fan speed, power, and operating condition information. The noise data is acquired in real time by sound pressure sensors arranged at multiple measuring points in the fan room, and includes time domain and frequency domain characteristics.

[0009] The sound field simulation module receives the data output by the data acquisition module and uses it to construct an acoustic model of the computer room based on the acquired physical parameters and equipment operating parameters. It also uses acoustic simulation algorithms to simulate the sound field distribution within the computer room. The acoustic simulation algorithms include the finite element method or the boundary element method, which can calculate the sound pressure level distribution, sound energy flow, and reverberation time at different frequencies.

[0010] The noise analysis module receives data output from the sound field simulation module and uses it to identify the location, contribution, and propagation path of noise sources based on the simulated sound field distribution. The noise analysis module determines the noise influence weight of each sound source on the target area through acoustic contribution analysis and extracts frequency band features.

[0011] The noise reduction scheme optimization module receives the data output by the noise analysis module and generates a targeted noise reduction scheme based on the noise analysis results. It then determines the optimal scheme through iterative optimization. The noise reduction scheme optimization module integrates a noise reduction measures database, which includes sound-absorbing material configuration, sound insulation structure design, and active control strategies. The optimization objective is to minimize the noise level in the target area under a preset cost constraint.

[0012] The solution output and execution module receives the data output by the noise reduction solution optimization module, and outputs the optimal noise reduction solution in a three-dimensional visualization form and generates a construction guidance document. At the same time, the solution output and execution module can drive the execution mechanism to implement active noise reduction measures and integrate monitoring feedback to adjust the solution.

[0013] Preferably, the data acquisition module further includes an environmental parameter sensing unit, which is used to synchronously monitor the temperature, humidity and airflow speed in the computer room, and the sound field simulation module corrects the sound speed and air absorption effect according to the environmental parameters.

[0014] Preferably, when constructing the acoustic model, the sound field simulation module uses a multipole model to characterize the fan sound source and introduces the frequency dependence of the wall acoustic impedance to simulate solid sound propagation by coupling the structural vibration equation.

[0015] Preferably, the sound pressure sensor array of the data acquisition module is arranged in a non-uniform grid pattern, covering the near-field region and the high-noise expected region. The sound pressure sensor data is transmitted to the central processing unit through a wireless transmission unit, and a time synchronization algorithm is used to ensure data consistency.

[0016] Preferably, the noise analysis module further includes a machine learning unit, which trains a sound source identification model using historical noise data so that the sound source identification model can adaptively update the noise source contribution weights and predict the noise change trend caused by equipment degradation.

[0017] Preferably, the iterative optimization process of the noise reduction scheme optimization module includes the following steps:

[0018] First, based on the key frequency bands and sound source weights output by the noise analysis module, a set of noise reduction measures is initially selected.

[0019] Secondly, the expected noise reduction and cost of this combination are calculated using the sound field simulation module.

[0020] Then, a multi-objective genetic algorithm is used to perform Pareto optimization on the measure parameters to find the optimal balance between noise reduction effect and cost;

[0021] Finally, verify whether the optimal solution meets the target noise limit. If it does not, re-initialize the optimization process.

[0022] The noise reduction measures database includes sound-absorbing material configurations that combine porous materials with resonant structures, sound insulation structure designs that include acoustic metamaterial soundproof covers, which are parametrically designed based on simulated sound wave wavelengths, and active control strategies that include active noise control systems based on adaptive filters.

[0023] Preferably, the three-dimensional visualization output of the solution output and execution module includes a noise cloud map, a sound ray tracing map, and a noise reduction measure layout diagram, while the construction guidance document includes a material list, structural installation details, and an active control system wiring diagram.

[0024] Preferably, the scheme output and execution module is also connected to an online monitoring unit. The online monitoring unit continuously collects noise data after the noise reduction measures are implemented, and dynamically adjusts the noise reduction scheme by comparing the simulated predicted value with the measured value, thus forming a closed-loop control system.

[0025] This invention has the following advantages: By integrating sound field simulation technology with a modular optimization system, it achieves accurate prediction and proactive optimization of noise in desulfurization fan rooms. The system can perform high-precision sound field simulation based on actual equipment parameters and fan room structure, identify the main noise sources and propagation paths, and generate targeted noise reduction solutions. This effectively avoids the blindness of traditional methods, which not only significantly improves the noise reduction effect and reduces the treatment cost, but also ensures the long-term effectiveness of the measures through real-time monitoring and dynamic optimization functions. At the same time, it takes into account equipment operating efficiency and fan room safety, providing a scientific and intelligent solution for industrial noise control. Attached Figure Description

[0026] To more intuitively illustrate the prior art and this application, exemplary drawings are provided below. It should be understood that the specific shapes and structures shown in the drawings should not generally be regarded as limiting conditions for implementing this application; for example, based on the technical concept disclosed in this application and the exemplary drawings, those skilled in the art are able to easily make conventional adjustments or further optimizations to the addition / reduction / classification, specific shapes, positional relationships, connection methods, size ratios, etc. of certain units (components).

[0027] Figure 1 A block diagram of a noise reduction optimization system for a desulfurization fan room based on sound field simulation, provided in an embodiment of this application; Detailed Implementation

[0028] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. It should be understood that these embodiments are merely for further explanation of the present invention and should not be construed as limiting the scope of protection of the present invention. Technical engineers in the field can make some non-essential improvements and adjustments to the present invention based on the above-described content. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Please see Figure 1 A noise reduction optimization system for desulfurization fan rooms based on sound field simulation includes the following modules:

[0030] The data acquisition module is used to acquire the physical parameters of the desulfurization fan room, the operating parameters of the fan equipment, and noise data. The physical parameters include the geometric dimensions of the fan room, the properties of the wall materials, and the layout of internal obstacles. The operating parameters of the fan equipment include the fan speed, power, and operating condition information. The noise data is acquired in real time by sound pressure sensors arranged at multiple measuring points in the fan room, and includes time domain and frequency domain characteristics.

[0031] The sound field simulation module receives the data output by the data acquisition module and uses it to construct an acoustic model of the computer room based on the acquired physical parameters and equipment operating parameters. It also uses acoustic simulation algorithms to simulate the sound field distribution within the computer room. The acoustic simulation algorithms include the finite element method or the boundary element method, which can calculate the sound pressure level distribution, sound energy flow, and reverberation time at different frequencies.

[0032] The noise analysis module receives data output from the sound field simulation module and uses it to identify the location, contribution, and propagation path of noise sources based on the simulated sound field distribution. The noise analysis module determines the noise influence weight of each sound source on the target area through acoustic contribution analysis and extracts frequency band features.

[0033] The noise reduction scheme optimization module receives the data output by the noise analysis module and generates targeted noise reduction schemes based on the noise analysis results. It then determines the optimal scheme through iterative optimization. This module integrates a noise reduction measures database, including sound-absorbing material configuration, sound insulation structure design, and active control strategies. The optimization objective is to minimize the noise level in the target area under preset cost constraints.

[0034] The solution output and execution module receives the data output by the noise reduction solution optimization module, and outputs the optimal noise reduction solution in a three-dimensional visualization form and generates a construction guidance document. At the same time, this module can drive the execution mechanism to implement active noise reduction measures and integrate monitoring feedback to adjust the solution.

[0035] When implementing this invention, the data acquisition module first comprehensively acquires the geometric dimensions of the computer room, the properties of the wall materials, and the operating parameters of the equipment. At the same time, it collects the noise spectrum characteristics in real time through a distributed sound pressure sensor network. This multi-dimensional data acquisition provides an accurate input basis for subsequent analysis, ensuring that the entire system is built on real and reliable data.

[0036] The sound field simulation module establishes a high-fidelity acoustic model based on the collected data. It uses the finite element method to simulate the propagation, reflection, and interference effects of sound waves in a complex computer room environment. By calculating the sound pressure level distribution in different frequency bands, it accurately reproduces the actual sound field conditions in the computer room. This simulation method based on physical models breaks through the limitations of traditional empirical design and can predict the noise distribution under different operating conditions.

[0037] The noise analysis module performs in-depth analysis of the simulation results, identifies the main noise sources and their impact on sensitive areas through acoustic contribution analysis, and extracts key noise frequency band features. This precise source analysis enables noise reduction measures to be targeted and avoids waste of resources.

[0038] Based on the analysis results, the noise reduction scheme optimization module intelligently matches sound absorption, sound insulation and active control measures from the integrated database. Through multi-objective optimization algorithms, it seeks the optimal balance between noise reduction effect and cost constraints. This systematic optimization process ensures the economy and efficiency of the governance scheme.

[0039] Finally, the solution output and execution module outputs the optimization results in a visual form and guides on-site implementation. At the same time, it forms a closed-loop control through monitoring and feedback. This end-to-end solution not only significantly improves the noise reduction effect, but also achieves standardization and replicability of the governance process.

[0040] The data acquisition module also includes an environmental parameter sensing unit for synchronously monitoring the temperature, humidity and airflow speed in the computer room. The sound field simulation module corrects the sound speed and air absorption effect based on the environmental parameters.

[0041] Building upon basic data acquisition, environmental parameter monitoring was added. By integrating temperature, humidity, and airflow velocity sensors, the sound field simulation more closely resembles actual working conditions. Since the speed of sound propagation in air is closely related to temperature, and humidity and airflow affect the attenuation characteristics of sound waves, the above solution significantly improves the accuracy of the sound field simulation through environmental parameter correction. For example, in high-temperature summer environments, increased sound speed leads to changes in sound wave wavelength, which in turn affects standing wave distribution and resonant frequency; an uncorrected model would produce significant errors.

[0042] This system dynamically adjusts the physical parameters in the sound field simulation by collecting environmental data in real time, making the prediction results more reflective of the actual acoustic environment of the computer room. This environmentally adaptive sound field simulation method is particularly suitable for areas with large diurnal temperature differences or significant seasonal climate changes, effectively avoiding the failure of noise reduction solutions due to changes in environmental factors and expanding the system's applicability.

[0043] When constructing the acoustic model, the sound field simulation module uses a multipole model to characterize the fan sound source and introduces the frequency dependence of the wall acoustic impedance to simulate solid sound propagation by coupling the structural vibration equation.

[0044] By refining the sound source modeling and propagation mechanism, a multipole model was adopted to accurately characterize the noise source characteristics of the fan. Compared with the traditional monopole model, the multipole model can better describe the directional noise characteristics of rotating machinery, especially for complex equipment such as desulfurization fans that simultaneously contain monopole, dipole, and quadrupole sound sources. Furthermore, this scheme considers the frequency dependence of wall acoustic impedance and achieves accurate simulation of solid-borne sound propagation by coupling the structural vibration equations.

[0045] In practical applications, the walls and ceilings of wind turbine rooms exhibit different acoustic characteristics at different frequencies. At low frequencies, vibration radiation may dominate, while at high frequencies, sound wave reflection is the primary mode of propagation. This refined modeling method can accurately predict the sound transmission path of the structure, providing a theoretical basis for the design of subsequent vibration isolation measures. It is particularly suitable for solving the problem of low-frequency noise propagating through building structures.

[0046] The sound pressure sensor array of the data acquisition module is arranged in a non-uniform grid pattern, focusing on covering the near-field area and the high-noise expected area. The sensor data is sent to the central processing unit through the wireless transmission unit, and a time synchronization algorithm is used to ensure data consistency.

[0047] The above scheme optimizes the sensor network deployment strategy by employing a non-uniform grid layout, increasing the density of measurement points in the near-field region and areas expected to experience high noise. This deployment method is based on acoustic measurement principles; the sound pressure gradient in the near-field region is relatively large, requiring higher spatial resolution to accurately capture sound field details. Simultaneously, this scheme utilizes wireless transmission and time synchronization technologies, solving the problems of complex wiring and susceptibility to interference inherent in traditional wired measurements. In practical implementation, the system optimizes sensor utilization efficiency while maintaining measurement accuracy by densely deploying sensors at key locations such as fan inlets and outlets and pipe connections, and appropriately reducing measurement points in areas with gentle sound field changes. The time synchronization algorithm ensures that all measurement point data has a unified time reference, providing a reliable data foundation for subsequent sound source localization and propagation path analysis. This intelligent sensor network design significantly improves the convenience of on-site implementation and data reliability.

[0048] The noise analysis module also includes a machine learning unit, which trains a sound source identification model using historical noise data, and can adaptively update the noise source contribution weights and predict the noise change trend caused by equipment degradation.

[0049] Traditional acoustic analysis methods are often based on fixed physical models, making it difficult to adapt to dynamic factors such as equipment aging and changes in operating conditions. This system, through its machine learning unit, continuously learns from historical noise data, automatically updating the contribution weights of each noise source and establishing a correlation model between equipment status and noise characteristics. For example, when fan bearings wear, noise in specific frequency bands gradually increases; the machine learning model can identify this trend and issue an early warning. This intelligent analysis approach not only improves the accuracy of noise source identification but also provides technical support for predictive maintenance, enabling the system to shift from passive noise control to proactive equipment condition management, extending equipment lifespan and reducing maintenance costs.

[0050] The iterative optimization process of the noise reduction scheme optimization module includes the following steps: First, based on the key frequency band and sound source weights output by the noise analysis module, a set of noise reduction measures is initially selected; second, the expected noise reduction amount and cost under this combination are calculated through the sound field simulation module; then, a multi-objective genetic algorithm is used to perform Pareto optimization on the measure parameters to find the optimal balance between noise reduction effect and cost; finally, it is verified whether the optimal scheme meets the target noise limit. If it does not meet the limit, the optimization process is re-initialized; the sound-absorbing material configuration in the noise reduction measure database includes the composite application of porous materials and resonant structures, the sound insulation structure design includes acoustic metamaterial soundproof covers, whose unit structures are parametrically designed according to the simulated sound wave wavelength, the active control strategy includes an active noise control system based on an adaptive filter, and the secondary sound source layout is guided by the sound energy flow analysis results of the sound field simulation module.

[0051] The system first selects a combination of noise reduction measures based on noise analysis results. This step fully considers the effective frequency bands and applicable scenarios of different measures. For example, porous sound-absorbing materials are mainly effective against mid-to-high frequency noise, while resonant structures are significantly effective against low-frequency peak noise. During the optimization process, the system employs a multi-objective genetic algorithm for Pareto optimization. This algorithm can simultaneously handle multiple conflicting objective functions, finding the optimal solution set under constraints such as noise reduction effect, cost, and construction complexity. In practical implementation, the system generates several candidate solutions, each including different types of sound-absorbing material configurations, sound insulation structure parameters, and active control system settings. The expected effects of each solution are evaluated through a sound field simulation module, and finally, a set of non-dominated solutions is output for the user to choose from.

[0052] This solution proposes the application of acoustic metamaterials in desulfurization fan rooms. The unit structure is customized based on the target frequency band's acoustic wavelength, achieving sound insulation performance that is difficult to achieve with traditional materials within a specific frequency range. Simultaneously, the secondary sound source layout of the active noise control system is directly determined based on acoustic energy flow analysis results, ensuring effective intervention along critical propagation paths. This refined design, combined with a systematic optimization process, ensures that the final solution is both technically feasible and economically sound.

[0053] The three-dimensional visualization output of the solution output and execution module includes noise cloud map, sound ray tracing map and noise reduction measure layout diagram. The construction guidance document includes material list, structural installation details and active control system wiring diagram.

[0054] Noise cloud maps can clearly display the sound pressure level distribution in various areas of the computer room, helping engineers to quickly identify noise hotspots.

[0055] Sound tracing diagrams can visually display the main propagation paths of noise, providing a basis for selecting the location of sound insulation measures;

[0056] The noise reduction measures layout diagram details the installation locations and parameter requirements of various treatment facilities.

[0057] The construction guidance documents further refined the implementation plan, the materials list ensured the accuracy of procurement, the structural installation details guided on-site construction, and the active control system wiring diagram ensured the standardization of electrical connections. This standardized output format significantly lowered the technical threshold for implementation, enabling even construction personnel without a professional acoustics background to accurately execute the noise reduction plan, thus improving project implementation efficiency and success rate.

[0058] The scheme output and execution module is also connected to an online monitoring unit. This unit continuously collects noise data after the noise reduction measures are implemented, and dynamically adjusts the noise reduction scheme by comparing the simulated predicted values ​​with the measured values, thus forming a closed-loop control system.

[0059] In practical engineering, due to factors such as construction errors and material performance deviations, the actual noise reduction effect may differ from the design target. This system, through a monitoring and feedback mechanism, can promptly detect such deviations and initiate adjustment procedures. For example, when the measured noise in a certain area is higher than expected, the system will reanalyze the sound field characteristics of that area and suggest adding auxiliary noise reduction measures or adjusting the parameters of existing measures. This dynamic optimization mechanism ensures the long-term stability of the noise reduction effect, adapting to changes in equipment operating conditions, material performance degradation, and other actual conditions. This gives the system the ability to self-improve and continuously optimize, providing industrial enterprises with full life-cycle noise control assurance.

[0060] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A noise reduction optimization system for desulfurization fan rooms based on sound field simulation, characterized in that, Includes the following modules: The data acquisition module is used to acquire the physical parameters of the desulfurization fan room, the operating parameters of the fan equipment, and noise data. The physical parameters include the geometric dimensions of the fan room, the properties of the wall materials, and the layout of internal obstacles. The operating parameters of the fan equipment include the fan speed, power, and operating condition information. The noise data is acquired in real time by sound pressure sensors arranged at multiple measuring points in the fan room, and includes time domain and frequency domain characteristics. The sound field simulation module receives the data output by the data acquisition module and uses it to construct an acoustic model of the computer room based on the acquired physical parameters and equipment operating parameters. It also uses acoustic simulation algorithms to simulate the sound field distribution within the computer room. The acoustic simulation algorithms include the finite element method or the boundary element method, which can calculate the sound pressure level distribution, sound energy flow, and reverberation time at different frequencies. The noise analysis module receives data output from the sound field simulation module and uses it to identify the location, contribution, and propagation path of noise sources based on the simulated sound field distribution. The noise analysis module determines the noise influence weight of each sound source on the target area through acoustic contribution analysis and extracts frequency band features. The noise reduction scheme optimization module receives the data output by the noise analysis module and uses it to generate a targeted noise reduction scheme based on the noise analysis results, and determines the optimal scheme through iterative optimization. The noise reduction scheme optimization module integrates a noise reduction measures database, which includes sound-absorbing material configuration, sound insulation structure design and active control strategies. The optimization goal is to minimize the noise level in the target area under preset cost constraints. The solution output and execution module receives the data output by the noise reduction solution optimization module, and outputs the optimal noise reduction solution in a three-dimensional visualization form and generates a construction guidance document. At the same time, the solution output and execution module can drive the execution mechanism to implement active noise reduction measures and integrate monitoring feedback to adjust the solution.

2. The noise reduction optimization system for desulfurization fan room based on sound field simulation according to claim 1, characterized in that, The data acquisition module also includes an environmental parameter sensing unit, which is used to synchronously monitor the temperature, humidity and airflow speed in the computer room. The sound field simulation module corrects the sound speed and air absorption effect according to the environmental parameters.

3. The noise reduction optimization system for desulfurization fan room based on sound field simulation according to claim 1, characterized in that, When constructing the acoustic model, the sound field simulation module uses a multipole model to characterize the fan sound source and introduces the frequency dependence of the wall acoustic impedance to simulate solid sound propagation by coupling the structural vibration equation.

4. The noise reduction optimization system for desulfurization fan room based on sound field simulation according to claim 2, characterized in that, The sound pressure sensor array of the data acquisition module is arranged in a non-uniform grid pattern, covering the near-field region and the high-noise expected region. The sound pressure sensor data is sent to the central processing unit through the wireless transmission unit, and a time synchronization algorithm is used to ensure data consistency.

5. The noise reduction optimization system for desulfurization fan room based on sound field simulation according to claim 4, characterized in that, The noise analysis module also includes a machine learning unit, which trains a sound source identification model using historical noise data so that the sound source identification model can adaptively update the noise source contribution weights and predict the noise change trend caused by equipment degradation.

6. The noise reduction optimization system for desulfurization fan room based on sound field simulation according to claim 5, characterized in that, The iterative optimization process of the noise reduction scheme optimization module includes the following steps: First, based on the key frequency bands and sound source weights output by the noise analysis module, a set of noise reduction measures is initially selected. Secondly, the expected noise reduction and cost of this combination are calculated using the sound field simulation module. Then, a multi-objective genetic algorithm is used to perform Pareto optimization on the measure parameters to find the optimal balance between noise reduction effect and cost; Finally, verify whether the optimal solution meets the target noise limit. If it does not, re-initialize the optimization process. The noise reduction measures database includes sound-absorbing material configurations that combine porous materials with resonant structures, sound insulation structure designs that include acoustic metamaterial soundproof covers, which are parametrically designed based on simulated sound wave wavelengths, and active control strategies that include active noise control systems based on adaptive filters.

7. The noise reduction optimization system for desulfurization fan room based on sound field simulation according to claim 1, characterized in that, The three-dimensional visualization output of the solution output and execution module includes noise cloud map, sound ray tracing map and noise reduction measure layout diagram. The construction guidance document includes material list, structural installation details and active control system wiring diagram.

8. The noise reduction optimization system for desulfurization fan room based on sound field simulation according to claim 7, characterized in that, The output and execution module of the solution is also connected to an online monitoring unit. After the noise reduction measures are implemented, the online monitoring unit continuously collects noise data and dynamically adjusts the noise reduction scheme by comparing the simulated predicted value with the measured value, thus forming a closed-loop control system.

Images