A screw compressor control method and system

Abstract

The present invention provides a screw compressor control method and system, which relates to the field of intelligent control technology. Within the power and noise requirement thresholds, multiple performance index influencing parameters affecting the air compression power and noise of the screw compressor are analyzed and obtained, and the multiple performance index influencing parameters are input into the optimization amplitude analysis module to obtain multiple power optimization amplitude information and noise optimization amplitude information; based on the multiple power optimization amplitude information and noise optimization amplitude information, the index parameter optimization is optimized, and the power index parameter optimization results and the noise index parameter optimization results are obtained for comprehensive calculation to obtain the optimal index parameter set. The technical problem in the prior art that the adjustment of screw compressor control index parameters is highly dependent on manual experience and difficult to balance noise and drive power output is solved. The technical effect of quickly and efficiently obtaining screw compressor performance index parameters that meet the requirements of the drive device and reducing the dependence of screw compressor performance adjustment on manual experience is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a screw compressor control method and system. Background Art

[0002] As a type of compressor with relatively advanced production technology at this stage, screw compressors are widely used as driving devices because of their high operational reliability, simple components and fewer vulnerable parts, and their advantages of reliable operation and long service life. Screw compressors are widely used in the field of aerodynamics.

[0003] While screw compressors offer operational advantages, the air dynamic devices they drive often have higher output power precision and noise level requirements. Manually adjusting control parameters often results in insufficient adjustment to meet the air dynamic device's operational requirements or is time-consuming. Therefore, rapidly and accurately adjusting screw compressor operation has become a bottleneck hindering their widespread use.

[0004] In the prior art, there is a technical problem that the adjustment of screw compressor control index parameters is highly dependent on manual experience and it is difficult to balance noise and drive power output, resulting in low compatibility between the control adjustment of the screw compressor and the drive device. Summary of the Invention

[0005] The present application provides a screw compressor control method and system, which is used to solve the technical problems in the prior art that the adjustment of screw compressor control index parameters is highly dependent on manual experience and it is difficult to balance noise and drive power output, resulting in low adaptability between the control adjustment of the screw compressor and the drive device.

[0006] In view of the above problems, the present application provides a screw compressor control method and system.

[0007] The first aspect of the present application provides a screw compressor control method, the method comprising: obtaining multiple performance indicators that affect the power and noise of the screw compressor for air compression; collecting the power requirements and noise requirements of the screw compressor for air compression in the current environment, and obtaining a power requirement threshold and a noise requirement threshold; within the power requirement threshold and the noise requirement threshold, analyzing the influencing parameters of the multiple performance indicators affecting the power and noise of the screw compressor for air compression, and obtaining multiple power influencing parameters and multiple noise influencing parameters; constructing an optimization amplitude analysis model, wherein the optimization amplitude analysis model includes a power optimization amplitude analysis module and a noise optimization amplitude analysis module; respectively inputting the multiple power impact parameters into the power optimization amplitude analysis module to obtain multiple power optimization amplitude information, and respectively inputting the multiple noise impact parameters into the noise optimization amplitude analysis module to obtain multiple noise optimization amplitude information; respectively using the multiple power optimization amplitude information and the multiple noise optimization amplitude information to perform index parameter optimization on the multiple performance indicators to obtain power index parameter optimization results and noise index parameter optimization results; according to the power index parameter optimization results and the noise index parameter optimization results, the optimal index parameter set is calculated to control the screw compressor.

[0008] The second aspect of the present application provides a screw compressor control system, the system comprising: a performance index acquisition module for acquiring a plurality of performance indicators that affect the power and noise of the screw compressor for air compression; a compression requirement acquisition module for acquiring the power requirement and noise requirement of the screw compressor for air compression in the current environment, and obtaining a power requirement threshold and a noise requirement threshold; an impact parameter analysis module for analyzing the impact parameters of the plurality of performance indicators on the power and noise of the screw compressor for air compression within the power requirement threshold and the noise requirement threshold, and obtaining a plurality of power impact parameters and a plurality of noise impact parameters; an analysis model construction module for constructing an optimization amplitude analysis model, wherein the optimization amplitude analysis model includes a power optimization amplitude degree analysis module and noise optimization amplitude analysis module; an optimization amplitude acquisition module, used to input the multiple power impact parameters into the power optimization amplitude analysis module respectively to obtain multiple power optimization amplitude information, and input the multiple noise impact parameters into the noise optimization amplitude analysis module respectively to obtain multiple noise optimization amplitude information; an optimization execution module, used to respectively use the multiple power optimization amplitude information and the multiple noise optimization amplitude information to perform index parameter optimization on the multiple performance indicators, and obtain power index parameter optimization results and noise index parameter optimization results; an optimization result processing module, used to calculate and obtain the optimal index parameter set based on the power index parameter optimization results and the noise index parameter optimization results, and control the screw compressor.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The method provided in the embodiment of the present application obtains multiple performance indicators that affect the power and noise of the screw compressor for air compression; collects the power requirements and noise requirements of the screw compressor for air compression in the current environment, obtains the power requirement threshold and the noise requirement threshold, and provides a data optimization range for subsequent optimization to obtain control parameters with optimal power output and low noise; within the power requirement threshold and the noise requirement threshold, analyzes the influencing parameters of the multiple performance indicators that affect the power and noise of the screw compressor for air compression, obtains multiple power influencing parameters and multiple noise influencing parameters, and provides a reference for the degree of performance indicator adjustment for subsequent adaptive adjustment of the power and noise of the screw compressor; constructs an optimization amplitude analysis model, wherein the optimization amplitude analysis model includes a power optimization amplitude analysis module and a noise optimization amplitude analysis module, and by constructing the optimization amplitude analysis model, it is possible to accurately obtain the optimization amplitude information corresponding to the influencing parameters based on the power / noise influencing parameters, thereby improving the optimization adjustment of performance indicators. The scientific nature and efficiency of amplitude generation reduce the reliance on manual experience in determining the performance index optimization adjustment amplitude. The multiple power impact parameters are input into the power optimization amplitude analysis module to obtain multiple power optimization amplitude information, and the multiple noise impact parameters are input into the noise optimization amplitude analysis module to obtain multiple noise optimization amplitude information. The multiple power optimization amplitude information and the multiple noise optimization amplitude information are used to optimize the multiple performance index parameters, respectively, to obtain power index parameter optimization results and noise index parameter optimization results, thereby obtaining optimal performance index adjustment parameters for controlling the power and noise of the screw compressor. Based on the power index parameter optimization results and the noise index parameter optimization results, an optimal index parameter set is calculated and the screw compressor is controlled to obtain multiple performance index parameter optimization results that meet both power and noise adjustment requirements, thereby balancing the noise and power output during the operation of the screw compressor. This achieves the technical effect of quickly and efficiently obtaining screw compressor performance index parameters that meet the requirements of the drive device and reducing the reliance on manual experience in screw compressor performance adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of a screw compressor control method provided in this application;

[0012] Figure 2 A schematic diagram of a flow chart for obtaining a noise requirement threshold value in a screw compressor control method provided in this application;

[0013] Figure 3A schematic diagram of a flow chart for obtaining air compression power and noise influencing parameters in a screw compressor control method provided in this application;

[0014] Figure 4 This is a structural diagram of a screw compressor control system provided in this application.

[0015] Explanation of the accompanying symbols: performance indicator collection module 11, compression requirement collection module 12, influencing parameter analysis module 13, analysis model construction module 14, optimization range acquisition module 15, optimization execution module 16, optimization result processing module 17. DETAILED DESCRIPTION

[0016] This application provides a screw compressor control method and system designed to address the existing technical issues of high reliance on manual experience for screw compressor control parameter adjustment, difficulty balancing noise and drive power output, and poor compatibility between the screw compressor control adjustment and the drive device. This method achieves the technical effect of quickly and efficiently obtaining screw compressor performance parameter indicators that meet the drive device's requirements, reducing the reliance on manual experience for screw compressor performance adjustment.

[0017] The acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of national laws and regulations.

[0018] Below, the technical solutions of the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention, rather than all, are shown in the accompanying drawings.

[0019] Example 1

[0020] like Figure 1 As shown, the present application provides a screw compressor control method, the method comprising:

[0021] S100: Acquiring multiple performance indicators that affect the power and noise of the screw compressor during air compression;

[0022] Specifically, a screw compressor is a mechanical device that compresses gas by rotating helical rotors in two housings that mesh with each other at a specific transmission ratio to produce a change in working volume. Screw compressors are widely used in the aerodynamics field to drive various types of pneumatic tools.

[0023] It should be understood that the operating power and noise generated by the screw compressor are mainly determined by the input current and voltage, and the amount of oil injected into the screw compressor.

[0024] Therefore, in this embodiment, multiple performance indicators that affect the power and noise of air compression during the operation of the screw compressor are collected and acquired. The multiple performance indicators include an input current indicator, an input voltage indicator, and an oil injection amount indicator.

[0025] S200: Collecting the power requirement and noise requirement of the screw compressor for air compression in the current environment, and obtaining a power requirement threshold and a noise requirement threshold;

[0026] Further, such as Figure 2 As shown, the power requirement and noise requirement of the screw compressor for air compression in the current environment are collected, and the method step S200 provided in the present application also includes:

[0027] S210: Collecting the power requirement standard value of air compression in the current environment;

[0028] S220: Performing forward compensation on the power requirement standard value to obtain the power requirement threshold;

[0029] S230: Collecting the required standard value of noise of air compression in the current environment;

[0030] S240: Perform negative compensation on the noise requirement standard value to obtain the noise requirement threshold.

[0031] Specifically, the screw compressor is used to drive a pneumatic tool. Therefore, in this embodiment, the pneumatic tool represents the operating environment of the screw compressor. The power requirement standard value represents the output power requirement for normal operation of the pneumatic tool in which the screw compressor is located. The noise requirement standard value represents the maximum noise intensity permitted by the operating environment of the screw compressor.

[0032] In this embodiment, based on the pneumatic tool operation requirements, the power requirement standard value of the air compression in the current environment and the noise requirement standard value of the air compression in the current environment are obtained.

[0033] Based on the screw compressor model data and the adjustable ranges of the multiple performance indicators, a power output threshold and a noise intensity threshold for the operation of the screw compressor are obtained. Based on the power output threshold of the screw compressor, the power requirement standard value is positively compensated to obtain the power requirement threshold. The power requirement threshold represents the adjustable power range when the screw compressor is operating as a driving device for the pneumatic tool. Based on the noise intensity threshold of the screw compressor, the noise requirement standard value is negatively compensated to obtain the noise requirement threshold. The noise requirement threshold represents the range of noise intensity that can be generated when the screw compressor is operating as a driving device for the pneumatic tool.

[0034] This embodiment obtains the noise requirements and driving power requirements of the current environment of the pneumatic tool by obtaining a specific pneumatic tool that uses a screw compressor as a driving device, and combines it with the driving power and noise output intensity that can actually be generated by the screw compressor to generate a power requirement threshold and noise intensity threshold that meet the driving power requirements and noise decibel requirements of the pneumatic tool, thereby providing a technical effect of a data optimization range for subsequent optimization to obtain control parameters with optimal power output and lower noise.

[0035] S300: Within the power requirement threshold and the noise requirement threshold, analyzing the influencing parameters of the multiple performance indicators affecting the power and noise of the screw compressor during air compression, and obtaining multiple power influencing parameters and multiple noise influencing parameters;

[0036] Further, such as Figure 3 As shown, within the power requirement threshold and the noise requirement threshold, the influencing parameters of the multiple performance indicators affecting the power and noise of the screw compressor for air compression are analyzed. The method step S300 provided in this application also includes:

[0037] S310: Acquire multiple sample power parameters of the screw compressor within the power requirement threshold;

[0038] S320: Obtain index parameters of the multiple performance indicators of the screw compressor under the multiple sample power parameters to obtain multiple power index parameter sets;

[0039] S330: Based on the multiple sample power parameters and the multiple power index parameter sets, analyzing the influencing parameters of the multiple performance indicators affecting the power of the screw compressor for air compression, and obtaining the multiple power influencing parameters;

[0040] S340: Acquire multiple sample noise parameters of the screw compressor within the noise requirement threshold;

[0041] S350: Obtain index parameters of the multiple performance indicators of the screw compressor under the multiple sample noise parameters to obtain multiple noise index parameter sets;

[0042] S360: Based on the multiple sample noise parameters and the multiple noise index parameter sets, analyze and obtain the influencing parameters of the multiple performance indicators affecting the noise of the screw compressor performing air compression, and obtain the multiple noise influencing parameters.

[0043] Specifically, in this embodiment, the power requirement threshold is used as a benchmark for the operating drive power that can be provided by the screw compressor, and a plurality of sample power parameters of the screw compressor operation are obtained; based on the power output characteristics of the sample power parameters depending on a plurality of performance indicators for controlling the operation of the screw compressor, the index parameters of the plurality of performance indicators of the screw compressor corresponding to the plurality of sample power parameters are obtained, and a plurality of power index parameter sets are obtained.

[0044] Based on the multiple sample power parameters and the multiple power index parameter sets, a method including but not limited to grey correlation analysis is adopted to analyze the influence parameters of the index parameter adjustment of the multiple performance indicators on the power of the screw compressor for air compression, and obtain the multiple power influence parameters. The multiple power influence parameters have a corresponding relationship with the multiple performance indicators, and the larger the power influence parameter value, the higher the degree of influence of the corresponding performance index adjustment on the change in the output power value of the screw compressor.

[0045] The same data analysis and processing method is adopted to obtain power impact parameters, and multiple sample noise parameters of the screw compressor are obtained within the noise requirement threshold. The index parameters of the multiple performance indicators of the screw compressor under the multiple sample noise parameters are obtained to obtain multiple noise index parameter sets.

[0046] Based on the multiple sample noise parameters and the multiple noise index parameter sets, a method including but not limited to grey correlation analysis is used to analyze and obtain the influencing parameters of the multiple performance indicators affecting the noise of the screw compressor performing air compression, and obtain the multiple noise influencing parameters. Similarly, the multiple noise influencing parameters have a corresponding relationship with the multiple performance indicators, and the larger the value of the noise influencing parameter, the higher the degree of influence of the corresponding performance indicator adjustment on the change in the output noise intensity of the screw compressor.

[0047] This embodiment analyzes and determines the degree of influence of multiple performance indicators on the change of the output power of the screw compressor and the degree of influence of multiple performance indicators on the change of the output noise intensity of the screw compressor, thereby achieving the technical effect of scientifically and accurately obtaining the influence intensity data of different performance indicators on the output power and noise changes of the screw compressor, and providing a reference for the degree of adjustment of the performance indicators for subsequent adaptive adjustment of the power and noise of the screw compressor.

[0048] S400: Constructing an optimization amplitude analysis model, wherein the optimization amplitude analysis model includes a power optimization amplitude analysis module and a noise optimization amplitude analysis module;

[0049] Furthermore, the construction of the optimization amplitude analysis model includes constructing the power optimization amplitude analysis module and constructing the noise optimization amplitude analysis module. To construct the power optimization amplitude analysis module, the method step S400 provided in this application further includes:

[0050] S410: Collecting sample power impact parameters of the multiple performance indicators to obtain multiple sample power impact parameter sets;

[0051] S420: Obtaining sample optimization amplitude information of the multiple performance indicators according to the sample power impact parameters in the multiple sample power impact parameter sets, to obtain multiple sample optimization amplitude information sets;

[0052] S430: Randomly select a sample power impact parameter from a first sample power impact parameter set to construct a partition root node of a first power optimization amplitude analysis unit, wherein the first sample power impact parameter set is included in the multiple sample power impact parameter sets;

[0053] S440: Randomly select a sample power impact parameter from the first sample power impact parameter set again to construct a partitioning node of the first power optimization amplitude analysis unit;

[0054] S450: Continue to construct the multi-level division nodes of the power optimization amplitude analysis module, and obtain multiple final division results according to the multi-level division nodes;

[0055] S460: Using the multiple sample optimization amplitude information in the first sample optimization amplitude information set, marking the multiple final division results, and obtaining the constructed first power optimization amplitude analysis unit;

[0056] S470: Continue to construct multiple power optimization amplitude analysis units of other multiple performance indicators to obtain the constructed power optimization amplitude analysis module.

[0057] Specifically, in this embodiment, the optimization amplitude analysis model is preferably constructed based on a decision tree, and the optimization amplitude analysis model is used to perform data analysis according to power / noise impact parameters and output parameter adjustment amplitudes corresponding to performance indicators.

[0058] The optimization amplitude analysis model includes a power optimization amplitude analysis module and a noise optimization amplitude analysis module. The module construction method of the power optimization amplitude analysis module is consistent with that of the noise amplitude optimization analysis module. Therefore, this embodiment takes the construction of the power optimization amplitude analysis module as an example to elaborate on the technical solution in detail.

[0059] Specifically, in an embodiment, multiple sample screw compressors having the same signal specifications as the screw compressor, including but not limited to differences in service life, are obtained. Based on the multiple sample screw compressors, the method of step S300 is used to obtain sample power impact parameters of the multiple performance indicators of the multiple sample screw compressors, thereby generating multiple sample power impact parameter sets.

[0060] Based on the sample power influence parameters within the plurality of sample power influence parameter sets, sample optimization amplitude information for adjusting the plurality of performance indicators is obtained based on the technical experience of screw compressor design and maintenance personnel, thereby obtaining a plurality of sample optimization amplitude information sets. For example, the sample influence parameter for the fuel injection quantity performance indicator is 0.95, and the corresponding sample optimization amplitude information is 20 ml based on manual experience evaluation.

[0061] In this embodiment, each performance indicator corresponds to a sample power impact parameter set, and the first sample power impact parameter set is randomly selected from multiple sample power impact parameter sets. A sample power impact parameter is randomly selected from the first sample power impact parameter set to construct a partition root node of the first power optimization amplitude analysis unit. Another sample power impact parameter is randomly selected from the first sample power impact parameter set to construct a partition trunk node of the first power optimization amplitude analysis unit. Multi-level partition nodes of the power optimization amplitude analysis module are continuously constructed, and multiple final partition results are obtained based on the multi-level partition nodes. The multiple sample optimization amplitude information within the first sample optimization amplitude information set are used to identify the multiple final partition results, thereby obtaining the completed first power optimization amplitude analysis unit.

[0062] The same decision tree construction method as steps S410 to S460 is used to continue constructing multiple power optimization amplitude analysis units for multiple other performance indicators to obtain the constructed power optimization amplitude analysis module. The same decision tree construction method as steps S410 to S470 is used to construct the module of the noise amplitude optimization analysis module. The power optimization amplitude analysis module and the noise optimization amplitude analysis module constitute the optimization amplitude analysis model.

[0063] This embodiment obtains multiple sample screw compressors and obtains the power / noise influencing parameters of the sample screw compressor performance indicators, combines them with manual experience evaluation to obtain power / noise optimization amplitude information, and constructs a power optimization amplitude analysis module and a noise optimization amplitude analysis module based on a decision tree. It is achieved that based on the power / noise influencing parameters, the optimization amplitude information corresponding to the influencing parameters can be accurately obtained, thereby achieving the technical effect of improving the scientific nature and efficiency of generating the performance indicator optimization adjustment amplitude and reducing the dependence of the determination of the performance indicator optimization adjustment amplitude on manual experience.

[0064] S500: Inputting the multiple power impact parameters into the power optimization amplitude analysis module respectively to obtain multiple power optimization amplitude information; inputting the multiple noise impact parameters into the noise optimization amplitude analysis module respectively to obtain multiple noise optimization amplitude information;

[0065] Specifically, in this embodiment, multiple power influencing parameters having a mapping relationship with multiple performance indicators are respectively input into the power optimization amplitude analysis module to obtain multiple power optimization amplitude information for adjusting multiple performance indicators when adjusting the output drive power of the screw compressor.

[0066] Multiple power impact parameters having a mapping relationship with multiple performance indicators are respectively input into the noise optimization amplitude analysis module to obtain multiple power optimization amplitude information for adjusting multiple performance indicators when adjusting the output noise intensity of the screw compressor.

[0067] S600: Optimizing the parameters of the multiple performance indicators by using the multiple power optimization amplitude information and the multiple noise optimization amplitude information respectively, and obtaining power indicator parameter optimization results and noise indicator parameter optimization results;

[0068] Furthermore, the plurality of power optimization amplitude information and the plurality of noise optimization amplitude information are respectively used to perform parameter optimization on the plurality of performance indicators. Step S600 of the method provided in the present application further includes:

[0069] S610: Acquire multiple preset index parameters of the multiple current performance indicators of the screw compressor;

[0070] S620: Using the multiple power optimization amplitude information, randomly adjust and combine the multiple preset index parameters to obtain multiple power index parameter sets;

[0071] S630: Randomly select a power index parameter set from the multiple power index parameter sets as a first power index parameter set, and use it as the current optimization result;

[0072] S640: Obtain a first power optimization score of the first power indicator parameter;

[0073] S650: Randomly select a power index parameter set from the multiple power index parameter sets again as a second power index parameter set;

[0074] S660: Obtain a second power optimization score of the second power indicator parameter set;

[0075] S670: Determine whether the second power optimization score is greater than the first power score. If so, use the second power index parameter set as the current optimization result. If not, use the second power index parameter set as the current optimization result according to probability, where the probability is calculated by the following formula:

[0076]

[0077] Where e is the natural logarithm, G2 is the second power optimization score, G1 is the first power optimization score, and C is the optimization rate parameter;

[0078] S680: Continue iterating the optimization until a preset number of iterations is reached, output the final current optimization result, and obtain the power index parameter optimization result;

[0079] S690: Using the multiple noise optimization amplitude information, optimize the index parameters of the multiple performance indicators to obtain the noise index parameter optimization results.

[0080] Specifically, it should be understood that the multiple power optimization amplitude information and multiple noise optimization amplitude information obtained in step S500 are single-dimensional optimization amplitudes for the purpose of power regulation or noise regulation alone. Therefore, this embodiment performs optimization processing based on multiple power optimization amplitude information to obtain the power index optimization result corresponding to the maximum driving power that can be output by the screw compressor, and performs optimization processing based on multiple noise optimization amplitude information to obtain the noise index optimization result corresponding to the minimum intensity noise generated by the screw compressor.

[0081] The data processing logic of the power index optimization result is consistent with that of the noise index optimization result, so this embodiment takes the acquisition of the power index optimization result as an example to elaborate on the technical solution in detail.

[0082] Specifically, multiple preset indicator parameters of the current multiple performance indicators of the screw compressor are obtained, and the multiple preset indicator parameters are randomly adjusted with reference to the multiple power optimization amplitude information. The multiple indicator parameters after random adjustment are randomly arranged and combined to obtain multiple power indicator parameter sets consisting of multiple performance indicators.

[0083] A power index parameter set is randomly selected from the multiple power index parameter sets as a first power index parameter set, and as the current optimization result, a first power optimization score of the first power index parameter is obtained by adopting methods including but not limited to expert evaluation method and model analysis method. The first power optimization score is used to evaluate the power intensity evaluation of the output power of the screw compressor when the corresponding power index set is used to control the operation of the screw compressor.

[0084] Using the same data processing method, a power index parameter set is randomly selected from the multiple power index parameter sets again as a second power index parameter set, and a second power optimization score of the second power index parameter set is obtained.

[0085] Determine whether the second power optimization score is greater than the first power score. If so, use the second power index parameter set as the current optimization result. If not, use the second power index parameter set as the current optimization result according to probability, where the probability is calculated by the following formula:

[0086]

[0087] Where e is the natural logarithm, G2 is the second power optimization score, G1 is the first power optimization score, and C is the optimization rate parameter, which is a constant that decreases gradually as the optimization progresses. In the early stages of the optimization, C is large, which increases P, improving optimization efficiency and avoiding local optimality. As C decreases, P gradually decreases, improving optimization accuracy.

[0088] A power index parameter set is randomly selected from the multiple power index parameter sets, and iterative optimization is continued until a preset number of iterations is reached, and a final current optimization result is output to obtain the power index parameter optimization result.

[0089] The same data processing method as that for optimizing power index parameters is adopted, and the plurality of noise optimization amplitude information is used to perform index parameter optimization on the plurality of performance indexes to obtain the noise index parameter optimization result.

[0090] This embodiment generates an indicator parameter set by using power / noise optimization amplitude information as a reference for performance indicator parameter adjustment, and evaluates the power output and noise output intensity of the screw compressor controlled based on the indicator parameter set, for optimizing the performance indicator parameter set. This achieves the goal of obtaining a performance indicator parameter set that meets the power indicator parameter optimization result for the highest power output purpose and a performance indicator parameter set that meets the noise indicator parameter optimization result for the lowest noise intensity output purpose, achieving the technical effect of obtaining the optimal performance indicator adjustment parameters for screw compressor power control and noise control. Furthermore, it provides a technical effect of providing a data reference basis for the subsequent determination of comprehensive performance indicator parameters that meet both power output and noise output purposes.

[0091] S700: Based on the optimization results of the power index parameters and the noise index parameters, an optimal index parameter set is calculated to control the screw compressor.

[0092] Furthermore, according to the power index parameter optimization result and the noise index parameter optimization result, an optimal index parameter set is calculated and obtained. The method step S700 provided in the present application further includes:

[0093] S710: Obtain multiple optimal power index parameters according to the power index parameter optimization result;

[0094] S720: Obtain multiple optimal noise index parameters according to the noise index parameter optimization result;

[0095] S730: Calculate the mean values ​​of the index parameters of the multiple performance indicators according to the multiple power optimal index parameters and the multiple noise optimal index parameters, and obtain the optimal index parameters of the multiple performance indicators as the optimal index parameter set.

[0096] Specifically, it should be understood that the multiple power optimization amplitude information and multiple noise optimization amplitude information obtained in step S600 are single-dimensional optimization amplitudes for the purpose of power regulation or noise regulation alone. However, in actual applications, the power and noise of screw compressors are simultaneously affected by the regulation of multiple performance indicators. Therefore, in this embodiment, the multiple performance indicator optimization amplitude information is secondary optimized to obtain multiple performance indicator parameter optimization results that meet both power regulation requirements and noise regulation requirements.

[0097] In this embodiment, based on the optimization results of the power index parameters, multiple optimal power index parameters are obtained; based on the optimization results of the noise index parameters, multiple optimal noise index parameters are obtained; based on the multiple optimal power index parameters and the multiple optimal noise index parameters, the index parameter means of the multiple performance indicators are calculated to obtain the optimal index parameters of the multiple performance indicators as the optimal index parameter set.

[0098] This embodiment obtains multiple power optimal index parameters for screw compressor power control and multiple noise optimal index parameters for screw compressor noise control, decomposes and obtains multiple optimal performance index parameters of multiple performance indicators for mean calculation, thereby achieving the goal of obtaining multiple performance index parameter optimization results that meet both power regulation requirements and noise regulation requirements, and realizing the technical effect of balancing the noise and power output during the operation of the screw compressor.

[0099] The method provided in this embodiment obtains multiple performance indicators that affect the power and noise of the screw compressor for air compression; collects the power requirements and noise requirements of the screw compressor for air compression in the current environment, obtains the power requirement threshold and the noise requirement threshold, and provides a data optimization range for subsequent optimization to obtain control parameters with optimal power output and low noise; within the power requirement threshold and the noise requirement threshold, analyzes the influencing parameters of the multiple performance indicators that affect the power and noise of the screw compressor for air compression, obtains multiple power influencing parameters and multiple noise influencing parameters, and provides a reference for the degree of adjustment of performance indicators for subsequent adaptive adjustment of the power and noise of the screw compressor; constructs an optimization amplitude analysis model, wherein the optimization amplitude analysis model includes a power optimization amplitude analysis module and a noise optimization amplitude analysis module, and by constructing the optimization amplitude analysis model, it is possible to accurately obtain the optimization amplitude information corresponding to the influencing parameters based on the power / noise influencing parameters, thereby improving the optimization adjustment amplitude of the performance indicators. The scientific nature and efficiency of degree generation are improved, and the reliance on manual experience in determining the optimization adjustment range of performance indicators is reduced; the multiple power impact parameters are respectively input into the power optimization range analysis module to obtain multiple power optimization range information, and the multiple noise impact parameters are respectively input into the noise optimization range analysis module to obtain multiple noise optimization range information; the multiple power optimization range information and the multiple noise optimization range information are respectively used to optimize the index parameters of the multiple performance indicators, obtain power index parameter optimization results and noise index parameter optimization results, and achieve optimal performance index adjustment parameters for power control and noise control of the screw compressor; based on the power index parameter optimization results and the noise index parameter optimization results, the optimal index parameter set is calculated and the screw compressor is controlled to obtain multiple performance index parameter optimization results that meet both power adjustment requirements and noise adjustment requirements, thereby balancing the noise and power output during the operation of the screw compressor. The technical effect of quickly and efficiently obtaining screw compressor performance index parameters that meet the requirements of the drive device and reducing the reliance on manual experience in screw compressor performance adjustment is achieved.

[0100] Furthermore, based on the multiple sample power parameters and the multiple power index parameter sets, the influencing parameters of the multiple performance indicators affecting the power of the screw compressor for air compression are analyzed to obtain the multiple power influencing parameters. Step S330 of the method provided in this application also includes:

[0101] S331: performing normalization processing on the data in the multiple sample power parameters and the multiple power index parameter sets;

[0102] S332: Sorting based on the result of the normalization process to obtain a first basic sequence and multiple first impact sequences;

[0103] S333: Calculate, based on the first basic sequence and the plurality of first impact sequences, correlation coefficients of the plurality of performance indicators affecting the power of the screw compressor for air compression, and obtain a set of correlation coefficients, using the following formula:

[0104]

[0105] A=min i min j |x0(j)-x i (j)|

[0106] B=max i max j |x0(j)-x i (j)|

[0107] Among them, i (j) is the correlation coefficient between the jth data in the i-th first influence sequence and the jth data in the first basic sequence, ρ is the adjustable calculation coefficient, x0(j) is the jth data in the first basic sequence, x i (j) is the jth data in the i-th first impact sequence;

[0108] S334: Calculate and obtain the multiple power impact parameters based on the correlation coefficient set.

[0109] Specifically, it should be understood that the sample power parameter depends on the index parameters of multiple performance indicators, and different performance indicators have different degrees of influence on the numerical changes of the power parameters. Therefore, in this embodiment, the influence parameters of multiple performance indicators on the output power of the screw compressor are obtained by analysis, so as to refer to the asynchronous and equal degree adjustment of the performance indicators in the subsequent screw compressor power regulation process.

[0110] Specifically, normalization processing is performed on the multiple sample power parameters and the data in the multiple power index parameter sets to obtain normalized data of the multiple sample power parameters and the multiple power index sets having a mapping relationship with the sample power parameters.

[0111] Based on the result of the normalization processing, the data size of the normalization processing results of multiple power index numbers are sorted to obtain a first basic sequence and multiple first impact sequences, where the first basic sequence has a mapping relationship with multiple sample power parameters, and the multiple first impact sequences are data sorting of multiple power index data corresponding to the multiple power indices.

[0112] According to the first basic sequence and the plurality of first influence sequences, correlation coefficients of the plurality of performance indicators affecting the power of the screw compressor for air compression are calculated to obtain a set of correlation coefficients, which are obtained by the following formula:

[0113]

[0114] A=min i min j |x0(j)-x i (j)|

[0115] B=max i max j |x0(j)-x i (j)|

[0116] Among them, i (j) is the correlation coefficient between the jth data in the i-th first influence sequence and the jth data in the first basic sequence, ρ is the adjustable calculation coefficient, x0(j) is the jth data in the first basic sequence, x i (j) represents the jth data in the i-th first impact sequence. The data in the correlation coefficient set are substituted one by one into the power impact parameter calculation formula to calculate the multiple power impact parameters. The numerical values ​​of the power impact parameters reflect the degree of impact of the corresponding performance indicator adjustment on the output drive power of the screw compressor.

[0117] This embodiment introduces a grey correlation analysis method to construct a power influence parameter calculation formula, normalizes the data in multiple sample power parameters and multiple power index parameter sets, and sorts the normalization results to obtain a first basic sequence and multiple first influence sequences. The power influence parameters of multiple performance indicators are calculated based on the power influence parameter calculation formula, achieving the technical effect of accurately knowing the degree of influence of the adjustment of multiple performance indicators on the output power of the screw compressor based on the calculation, thereby providing an adjustment reference for the asynchronous and equal degree adjustment of multiple performance indicators in the subsequent screw compressor power adjustment process.

[0118] Furthermore, the method step S640 of obtaining the first power optimization score of the first power indicator parameter provided in this application further includes:

[0119] S641: Perform data identification on the multiple sample power parameters and the multiple power index parameter sets to obtain a constructed data set;

[0120] S642: Constructing a power optimization scoring analysis model based on a BP neural network;

[0121] S643: Using the constructed data set to perform iterative supervised training, verification and testing on the power optimization scoring analysis model until the accuracy of the power optimization scoring analysis model meets the preset requirements, thereby obtaining the constructed power optimization scoring analysis model.

[0122] Specifically, this embodiment does not limit the method of power optimization scoring based on power index parameters. Preferably, this embodiment constructs the power optimization scoring analysis model based on BP neural network. To improve the accuracy of the model output, the power optimization scoring analysis model is trained using a large amount of data.

[0123] In order to improve the effectiveness of model training, multiple sets of power indicator parameter sets and power optimization score sets with mapping relationships therewith are collected as model training data.

[0124] The multiple groups of power indicator parameter sets and the power optimization score sets having a mapping relationship therewith are divided and identified. Specifically, the multiple groups of power indicator parameter sets are divided into input parameters of the power optimization score analysis model and identified, and the power optimization score sets are divided into output parameters to generate the constructed sample set.

[0125] Based on the constructed sample set, supervised training, verification and testing are performed on the power optimization score analysis model until the accuracy of the power optimization score analysis model reaches a preset requirement, thereby obtaining the trained power optimization score analysis model.

[0126] This embodiment uses multiple sets of power indicator parameter sets and power optimization score sets with a mapping relationship therewith, and divides and labels them according to data types to facilitate computer recognition and processing. As training data for the power optimization score analysis model, effective training data that is convenient for the model to recognize and process is obtained. Based on the effective training data, the power optimization score analysis model is supervised for training, verification and testing, achieving the technical effect of obtaining a power optimization score analysis model that can output an optimization score with high credibility.

[0127] Example 2

[0128] Based on the same inventive concept as the screw compressor control method in the above embodiment, Figure 4 As shown, the present application provides a screw compressor control system, wherein the system includes:

[0129] The performance index acquisition module 11 is used to obtain multiple performance indicators that affect the power and noise of the screw compressor during air compression;

[0130] The compression requirement collection module 12 is used to collect the power requirement and noise requirement of the screw compressor for air compression in the current environment, and obtain the power requirement threshold and the noise requirement threshold;

[0131] an influencing parameter analysis module 13, configured to analyze, within the power requirement threshold and the noise requirement threshold, influencing parameters of the multiple performance indicators affecting the power and noise of the screw compressor during air compression, and obtain multiple power influencing parameters and multiple noise influencing parameters;

[0132] An analysis model construction module 14 is used to construct an optimization amplitude analysis model, wherein the optimization amplitude analysis model includes a power optimization amplitude analysis module and a noise optimization amplitude analysis module;

[0133] The optimization amplitude obtaining module 15 is configured to input the plurality of power impact parameters into the power optimization amplitude analysis module to obtain a plurality of power optimization amplitude information, and input the plurality of noise impact parameters into the noise optimization amplitude analysis module to obtain a plurality of noise optimization amplitude information;

[0134] An optimization execution module 16 is configured to respectively use the multiple power optimization amplitude information and the multiple noise optimization amplitude information to perform parameter optimization on the multiple performance indicators to obtain power indicator parameter optimization results and noise indicator parameter optimization results;

[0135] The optimization result processing module 17 is used to calculate and obtain an optimal index parameter set based on the power index parameter optimization result and the noise index parameter optimization result, and control the screw compressor.

[0136] Furthermore, the compression requirement acquisition module 12 further includes:

[0137] Power standard acquisition unit, used to collect the power requirement standard value of air compression in the current environment;

[0138] a requirement threshold obtaining unit, configured to perform forward compensation on the power requirement standard value to obtain the power requirement threshold;

[0139] Standard value acquisition unit, used to collect the standard value of noise requirement of air compression in the current environment;

[0140] The noise threshold obtaining unit is configured to perform negative compensation on the noise requirement standard value to obtain the noise requirement threshold.

[0141] Furthermore, the impact parameter analysis module 13 also includes:

[0142] a sample parameter obtaining unit, configured to obtain a plurality of sample power parameters of the screw compressor within the power requirement threshold;

[0143] an index parameter acquisition unit, configured to acquire index parameters of the plurality of performance indicators of the screw compressor under the plurality of sample power parameters, and obtain a plurality of power index parameter sets;

[0144] an influencing parameter analysis unit, configured to analyze, based on the multiple sample power parameters and the multiple power index parameter sets, influencing parameters of the multiple performance indicators affecting the power of the screw compressor for air compression, and obtain the multiple power influencing parameters;

[0145] a sample parameter acquisition unit, configured to acquire a plurality of sample noise parameters of the screw compressor within the noise requirement threshold;

[0146] a performance index analysis unit, configured to obtain index parameters of the plurality of performance indicators of the screw compressor under the plurality of sample noise parameters, and obtain a plurality of noise index parameter sets;

[0147] The influencing parameter analysis unit is used to analyze and obtain the influencing parameters of the noise of the screw compressor performing air compression based on the multiple sample noise parameters and the multiple noise index parameter sets, so as to obtain the multiple noise influencing parameters.

[0148] Furthermore, the impact parameter analysis module 13 also includes:

[0149] a normalization processing unit, configured to perform normalization processing on the data in the plurality of sample power parameters and the plurality of power index parameter sets;

[0150] a processing result sorting unit, configured to perform sorting based on the normalization processing result to obtain a first basic sequence and a plurality of first impact sequences;

[0151] A correlation coefficient calculation unit is configured to calculate, based on the first basic sequence and the plurality of first influence sequences, correlation coefficients of the plurality of performance indicators affecting the power of the screw compressor for air compression, and obtain a set of correlation coefficients, using the following formula:

[0152]

[0153] A=min i min j |x0(j)-x i (j)|

[0154] B=max i max j |x0(j)-x i (j)|

[0155] Among them,i (j) is the correlation coefficient between the jth data in the i-th first influence sequence and the jth data in the first basic sequence, ρ is the adjustable calculation coefficient, x0(j) is the jth data in the first basic sequence, x i (j) is the jth data in the i-th first impact sequence;

[0156] The influence parameter calculation unit is used to calculate and obtain the multiple power influence parameters according to the correlation coefficient set.

[0157] Furthermore, the analysis model building module 14 also includes:

[0158] An impact parameter collection unit, configured to collect sample power impact parameters of the plurality of performance indicators to obtain a plurality of sample power impact parameter sets;

[0159] an optimization amplitude acquisition unit, configured to acquire sample optimization amplitude information of the plurality of performance indicators according to the sample power impact parameters in the plurality of sample power impact parameter sets, and obtain a plurality of sample optimization amplitude information sets;

[0160] an influence parameter selection unit, configured to randomly select a sample power influence parameter from a first sample power influence parameter set to construct a partition root node of a first power optimization amplitude analysis unit, wherein the first sample power influence parameter set is included in the multiple sample power influence parameter sets;

[0161] an influence parameter selection unit, configured to randomly select a sample power influence parameter from the first sample power influence parameter set again to construct a division trunk node of the first power optimization amplitude analysis unit;

[0162] A division node construction unit, configured to continue constructing multi-level division nodes of the power optimization amplitude analysis module and obtain a plurality of final division results according to the multi-level division nodes;

[0163] a division result identification unit, configured to identify the multiple final division results using the multiple sample optimization amplitude information in the first sample optimization amplitude information set, and obtain the constructed first power optimization amplitude analysis unit;

[0164] The analysis module construction unit is used to continue to construct multiple power optimization amplitude analysis units of other multiple performance indicators to obtain the constructed power optimization amplitude analysis module.

[0165] Furthermore, the optimization execution module 16 further includes:

[0166] A preset index obtaining unit, configured to obtain a plurality of preset index parameters of the plurality of current performance indicators of the screw compressor;

[0167] A preset indicator adjustment unit, configured to randomly adjust and combine the plurality of preset indicator parameters using the plurality of power optimization amplitude information to obtain a plurality of power indicator parameter sets;

[0168] an optimization result obtaining unit, configured to randomly select a power index parameter set from the plurality of power index parameter sets as a first power index parameter set and as a current optimization result;

[0169] an optimization score obtaining unit, configured to obtain a first power optimization score of the first power indicator parameter;

[0170] a power index selection unit, configured to randomly select a power index parameter set from the plurality of power index parameter sets again as a second power index parameter set;

[0171] a power score obtaining unit, configured to obtain a second power optimization score of the second power indicator parameter set;

[0172] A power score judgment unit is configured to determine whether the second power optimization score is greater than the first power score. If so, the second power index parameter set is used as the current optimization result. If not, the second power index parameter set is used as the current optimization result according to probability, wherein the probability is calculated by the following formula:

[0173]

[0174] Where e is the natural logarithm, G2 is the second power optimization score, G1 is the first power optimization score, and C is the optimization rate parameter;

[0175] The optimization iterative processing unit is used to continue iterative optimization until a preset number of iterations is reached, output the final current optimization result, and obtain the power index parameter optimization result;

[0176] The optimization execution unit is used to use the multiple noise optimization amplitude information to perform parameter optimization on the multiple performance indicators to obtain the noise indicator parameter optimization results.

[0177] Furthermore, the optimization score acquisition unit further includes:

[0178] A data identification execution unit, configured to perform data identification on the plurality of sample power parameters and the plurality of power index parameter sets to obtain a constructed data set;

[0179] An analysis model building unit, used to build a power optimization scoring analysis model based on a BP neural network;

[0180] The analysis model training unit is used to use the constructed data set to iteratively supervise the training, verification and testing of the power optimization score analysis model until the accuracy of the power optimization score analysis model meets the preset requirements, thereby obtaining the constructed power optimization score analysis model.

[0181] Furthermore, the optimization result processing module 17 further includes:

[0182] An optimization result analysis unit, configured to obtain a plurality of optimal power index parameters according to the power index parameter optimization result;

[0183] An optimal index obtaining unit, configured to obtain a plurality of noise optimal index parameters according to the noise index parameter optimization result;

[0184] A parameter set obtaining unit is used to calculate the index parameter mean of the multiple performance indicators based on the multiple power optimal index parameters and the multiple noise optimal index parameters, and obtain the optimal index parameters of the multiple performance indicators as the optimal index parameter set.

[0185] Any of the methods or steps described above may be stored as computer instructions or programs in various types of computer memories, and the computer instructions or programs may be recognized by various types of computer processors to implement any of the methods or steps described above.

[0186] Based on the above specific embodiments of the present invention, any improvements and modifications made to the present invention by those skilled in the art without departing from the principles of the present invention shall fall within the scope of patent protection of the present invention.

Claims

1. A screw compressor control method, characterized in that: The method comprises: Obtain multiple performance indicators that affect the power and noise of screw compressors for air compression; Collecting the power requirement and noise requirement of the screw compressor for air compression in the current environment, and obtaining a power requirement threshold and a noise requirement threshold; Within the power requirement threshold and the noise requirement threshold, analyzing the influencing parameters of the multiple performance indicators affecting the power and noise of the screw compressor in air compression, and obtaining multiple power influencing parameters and multiple noise influencing parameters; Constructing an optimization amplitude analysis model, wherein the optimization amplitude analysis model includes a power optimization amplitude analysis module and a noise optimization amplitude analysis module. Constructing the power optimization amplitude analysis module includes: Collecting sample power impact parameters of the multiple performance indicators to obtain multiple sample power impact parameter sets; acquiring, based on the sample power impact parameters in the plurality of sample power impact parameter sets, sample optimization amplitude information of the plurality of performance indicators, and obtaining a plurality of sample optimization amplitude information sets; Randomly selecting a sample power impact parameter from a first sample power impact parameter set to construct a partition root node of a first power optimization amplitude analysis unit, wherein the first sample power impact parameter set is included in the multiple sample power impact parameter sets; Randomly selecting a sample power impact parameter from the first sample power impact parameter set again to construct a division trunk node of the first power optimization amplitude analysis unit; Continuing to construct a multi-level division node of the power optimization amplitude analysis module, and obtaining a plurality of final division results according to the multi-level division node; Using multiple sample optimization amplitude information in the first sample optimization amplitude information set, marking the multiple final division results, and obtaining the constructed first power optimization amplitude analysis unit; Continue to construct multiple power optimization amplitude analysis units for other multiple performance indicators to obtain the constructed power optimization amplitude analysis module; Inputting the multiple power impact parameters into the power optimization amplitude analysis module respectively to obtain multiple power optimization amplitude information, and inputting the multiple noise impact parameters into the noise optimization amplitude analysis module respectively to obtain multiple noise optimization amplitude information; respectively using the plurality of power optimization amplitude information and the plurality of noise optimization amplitude information to perform index parameter optimization on the plurality of performance indicators, and obtain power index parameter optimization results and noise index parameter optimization results; According to the optimization results of the power index parameter and the noise index parameter, an optimal index parameter set is calculated to control the screw compressor.

2. The method according to claim 1, characterized in that Collect the power and noise requirements of the screw compressor for air compression in the current environment, including: Collect the power requirement standard value of air compression in the current environment; Performing forward compensation on the power requirement standard value to obtain the power requirement threshold; Collect the required standard value of noise for air compression in the current environment; Negative compensation is performed on the noise requirement standard value to obtain the noise requirement threshold value.

3. The method according to claim 1, characterized in that Within the power requirement threshold and the noise requirement threshold, analyzing the influencing parameters of the multiple performance indicators affecting the power and noise of the screw compressor in air compression, including: acquiring a plurality of sample power parameters of the screw compressor within the power requirement threshold; Obtaining index parameters of the multiple performance indicators of the screw compressor under the multiple sample power parameters to obtain multiple power index parameter sets; Based on the multiple sample power parameters and the multiple power index parameter sets, analyzing the influencing parameters of the multiple performance indicators affecting the power of the screw compressor for air compression to obtain the multiple power influencing parameters; obtaining a plurality of sample noise parameters of the screw compressor within the noise requirement threshold; Acquire index parameters of the multiple performance indicators of the screw compressor under the multiple sample noise parameters to obtain multiple noise index parameter sets; Based on the multiple sample noise parameters and the multiple noise index parameter sets, the influencing parameters of the multiple performance indicators affecting the noise of the screw compressor during air compression are analyzed to obtain the multiple noise influencing parameters.

4. The method according to claim 3, characterized in that Analyzing, based on the multiple sample power parameters and the multiple power index parameter sets, the influencing parameters of the multiple performance indicators affecting the power of the screw compressor for air compression to obtain the multiple power influencing parameters, includes: Normalizing the data in the plurality of sample power parameters and the plurality of power index parameter sets; Sorting is performed based on the results of the normalization process to obtain a first basic sequence and a plurality of first impact sequences; According to the first basic sequence and the plurality of first influence sequences, correlation coefficients of the plurality of performance indicators affecting the power of the screw compressor for air compression are calculated to obtain a set of correlation coefficients, which are obtained by the following formula: A min i min j |x0(j)-x i (j)| B=max i max j |x0(j)-x i (j)| Among them, i (j) is the correlation coefficient between the jth data in the i-th first influence sequence and the jth data in the first basic sequence, ρ is the adjustable calculation coefficient, x0(j) is the jth data in the first basic sequence, x i (j) is the jth data in the i-th first impact sequence; The multiple power impact parameters are obtained by calculation according to the correlation coefficient set.

5. The method according to claim 3, characterized in that The plurality of power optimization amplitude information and the plurality of noise optimization amplitude information are respectively used to perform parameter optimization on the plurality of performance indicators, including: Acquiring a plurality of preset index parameters of the plurality of current performance indicators of the screw compressor; Using the multiple power optimization amplitude information, randomly adjusting and combining the multiple preset index parameters to obtain multiple power index parameter sets; Randomly selecting a power index parameter set from the multiple power index parameter sets as a first power index parameter set and as a current optimization result; Obtaining a first power optimization score of the first power indicator parameter; randomly selecting a power index parameter set from the multiple power index parameter sets as a second power index parameter set; Obtaining a second power optimization score for the second power indicator parameter set; Determine whether the second power optimization score is greater than the first power optimization score. If so, use the second power index parameter set as the current optimization result. If not, use the second power index parameter set as the current optimization result according to probability, where the probability is calculated by the following formula: Where e is the natural logarithm, G2 is the second power optimization score, G1 is the first power optimization score, and C is the optimization rate parameter; Continue iterating and optimizing until the preset number of iterations is reached, output the final current optimization result, and obtain the optimization result of the power index parameter; The plurality of noise optimization amplitude information is used to perform parameter optimization on the plurality of performance indicators to obtain the noise indicator parameter optimization result.

6. The method according to claim 5, characterized in that The obtaining of a first power optimization score of the first power indicator parameter includes: Performing data identification on the multiple sample power parameters and the multiple power index parameter sets to obtain a constructed data set; Based on BP neural network, a power optimization scoring analysis model is constructed; The power optimization scoring analysis model is iteratively supervised trained, verified, and tested using the constructed data set until the accuracy of the power optimization scoring analysis model meets preset requirements, thereby obtaining the constructed power optimization scoring analysis model.

7. The method according to claim 1, characterized in that Calculating and obtaining an optimal index parameter set based on the power index parameter optimization result and the noise index parameter optimization result includes: Obtaining multiple optimal power index parameters according to the power index parameter optimization result; Obtaining multiple optimal noise index parameters according to the noise index parameter optimization result; The indicator parameter means of the multiple performance indicators are calculated according to the multiple power optimal indicator parameters and the multiple noise optimal indicator parameters, and the optimal indicator parameters of the multiple performance indicators are obtained as the optimal indicator parameter set.

8. A screw compressor control system, characterized in that: The system comprises: A performance index collection module is used to obtain multiple performance indicators that affect the power and noise of the screw compressor during air compression; A compression requirement collection module is used to collect the power requirement and noise requirement of the screw compressor for air compression in the current environment, and obtain a power requirement threshold and a noise requirement threshold; an influencing parameter analysis module, configured to analyze, within the power requirement threshold and the noise requirement threshold, influencing parameters of the multiple performance indicators affecting the power and noise of the screw compressor in air compression, and obtain multiple power influencing parameters and multiple noise influencing parameters; An analysis model construction module is used to construct an optimization amplitude analysis model, wherein the optimization amplitude analysis model includes a power optimization amplitude analysis module and a noise optimization amplitude analysis module, and constructing the power optimization amplitude analysis module includes: collecting sample power impact parameters of the multiple performance indicators to obtain multiple sample power impact parameter sets; obtaining sample optimization amplitude information of the multiple performance indicators based on the sample power impact parameters in the multiple sample power impact parameter sets to obtain multiple sample optimization amplitude information sets; randomly selecting a sample power impact parameter from the first sample power impact parameter set to construct a partition root node of the first power optimization amplitude analysis unit, wherein the first sample power impact parameter The power optimization amplitude analysis unit comprises a plurality of sample power impact parameter sets, a sample power impact parameter set is randomly selected from the first sample power impact parameter set again, and a division trunk node of the first power optimization amplitude analysis unit is constructed; a multi-level division node of the power optimization amplitude analysis module is continued to be constructed, and a plurality of final division results are obtained according to the multi-level division node; a plurality of sample optimization amplitude information in the first sample optimization amplitude information set is used to identify the plurality of final division results, and a constructed first power optimization amplitude analysis unit is obtained; a plurality of power optimization amplitude analysis units of other plurality of performance indicators are continued to be constructed, and a constructed power optimization amplitude analysis module is obtained; an optimization amplitude obtaining module, configured to input the plurality of power impact parameters into the power optimization amplitude analysis module respectively to obtain a plurality of power optimization amplitude information, and input the plurality of noise impact parameters into the noise optimization amplitude analysis module respectively to obtain a plurality of noise optimization amplitude information; an optimization execution module, configured to respectively use the multiple power optimization amplitude information and the multiple noise optimization amplitude information to perform parameter optimization on the multiple performance indicators, and obtain power indicator parameter optimization results and noise indicator parameter optimization results; The optimization result processing module is used to calculate the optimal index parameter set according to the power index parameter optimization result and the noise index parameter optimization result, and control the screw compressor.

Images