Intelligent control method and system for air compressor

Abstract

An intelligent control method and system for an air compressor. The method comprises: acquiring a plurality of pieces of real-time pipeline pressure data of a plurality of pipeline positions of a target air compressor pipe network, and electric motor data and noise detection data which correspond to each air compressor in the target air compressor pipe network; on the basis of the real-time pipeline pressure data, determining defect pipeline positions, where there may be air supply defects, in the target air compressor pipe network; on the basis of the electric motor data and the noise detection data of the air compressor corresponding to each defect pipeline position, determining a defect probability corresponding to each defect pipeline position; and on the basis of the defect probability corresponding to each defect pipeline position, and the electric motor data and the noise detection data, determining an air compressor control instruction. The method and system can use a plurality of pieces of sensing data to effectively monitor and control an air compressor pipe network, thereby reducing operating faults and errors of the air compressor pipe network, and improving the air supply effect.

Description

Air compressor intelligent control method and system Technical Field

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

[0002] As the air pressure and demand for large-scale processing equipment continue to increase, many processing companies have begun purchasing air compressor network systems consisting of multiple air compressors to meet these needs. However, these systems typically rely on simple controllers and pre-set algorithms for simple control. These systems fail to consider the use of sensor data to detect defects in the network and make further adjustments to the compressor control. This demonstrates the shortcomings of existing technologies, which urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an intelligent control method and system for an air compressor, which can effectively monitor and control the air compressor pipeline network by using multiple sensor data, reduce the working failures and errors of the air compressor pipeline network, and improve the air supply effect.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses an intelligent control method for an air compressor, the method comprising:

[0005] Acquire multiple real-time pipeline pressure data at multiple pipeline locations of a target air compressor pipeline network and motor data and noise detection data corresponding to each air compressor in the target air compressor pipeline network;

[0006] Determining, based on the real-time pipeline pressure data, a location of a defective pipeline in the target air compressor pipeline network where a gas supply defect may exist;

[0007] Determining the defect probability corresponding to each defective pipeline location based on the motor data and noise detection data of the air compressor corresponding to each defective pipeline location; the defect probability is used to send to a maintenance terminal for repairing the defective pipeline location;

[0008] An air compressor control instruction is determined based on the defect probability corresponding to each defective pipeline position, as well as the motor data and noise detection data; the air compressor control instruction is used to drive the air compressor to work to resolve the air supply defect.

[0009] As an optional embodiment, in the first aspect of the present invention, determining the location of a defective pipeline in the target air compressor pipeline network where a gas supply defect may exist based on the real-time pipeline pressure data includes:

[0010] Determine the location type and pipeline line corresponding to each pipeline location corresponding to the real-time pipeline pressure data;

[0011] Grouping all the real-time pipeline pressure data according to the location type to obtain a plurality of first data groups;

[0012] Grouping all the real-time pipeline pressure data according to the pipeline lines to which they belong to obtain a plurality of second data groups;

[0013] According to the multiple first data groups and the multiple second data groups, based on a probability weight algorithm, defective pipeline locations that may have gas supply defects are screened out from the multiple pipeline locations.

[0014] As an optional embodiment, in the first aspect of the present invention, the location type is a gas supply terminal location, a pipeline junction location, a gas supply starting location, or a single pipeline intermediate location; and all the real-time pipeline pressure data are grouped according to the location type to obtain multiple first data groups, including:

[0015] All the real-time pipeline pressure data belonging to the same location type are divided into the same first data group to obtain multiple first data groups corresponding to multiple location types.

[0016] As an optional embodiment, in the first aspect of the present invention, all the real-time pipeline pressure data are grouped according to the pipeline lines to which they belong to obtain a plurality of second data groups, including:

[0017] All the real-time pipeline pressure data belonging to the same pipeline line are divided into the same second data group to obtain multiple second data groups corresponding to multiple pipeline lines.

[0018] As an optional embodiment, in the first aspect of the present invention, screening out defective pipeline locations that may have gas supply defects from the multiple pipeline locations based on the multiple first data groups and the multiple second data groups based on a probability weight algorithm includes:

[0019] Inputting each of the first data sets into a trained first defect probability prediction neural network model to obtain a first defect probability corresponding to the location type corresponding to each of the first data sets; the first defect probability prediction neural network model is trained using a training data set including a plurality of training pressure data sets and corresponding pipeline defect annotations;

[0020] Inputting each of the second data groups into the first defect probability prediction neural network model to obtain a second defect probability corresponding to the pipeline line to which each of the second data groups belongs;

[0021] For each pipeline position, inputting the real-time pipeline pressure data corresponding to the pipeline position into the first defect probability prediction neural network model to obtain a third defect probability corresponding to the pipeline position;

[0022] Calculating the product of the third defect probability corresponding to the pipeline position, the first defect probability corresponding to the location type corresponding to the pipeline position, and the second defect probability corresponding to the pipeline line to which the pipeline position belongs, to obtain a defect parameter corresponding to the pipeline position;

[0023] All the pipeline positions where the defect parameter is greater than a preset parameter threshold are determined as defective pipeline positions where gas supply defects may occur.

[0024] As an optional embodiment, in the first aspect of the present invention, determining the defect probability corresponding to each defective pipeline location based on the motor data and noise detection data of the air compressor corresponding to each defective pipeline location includes:

[0025] For each defective pipeline location, all the air compressors whose distance to the defective pipeline location is less than a preset distance threshold are determined as associated air compressors corresponding to the defective pipeline location;

[0026] Inputting the motor data and noise detection data of each associated air compressor into a trained second defect probability prediction neural network model to obtain a fourth defect probability corresponding to each associated air compressor; the second defect probability prediction neural network model is trained by a training data set including a plurality of training motor data, training noise detection data, and corresponding motor defect annotations;

[0027] The probability average of the fourth probabilities of all the associated air compressors corresponding to the defective pipeline position is calculated, and the product of the probability average and the defect parameter corresponding to the defective pipeline position is calculated to obtain the defect probability corresponding to the defective pipeline position.

[0028] As an optional embodiment, in the first aspect of the present invention, determining the air compressor control instruction based on the defect probability corresponding to each defective pipe position, as well as the motor data and noise detection data, includes:

[0029] For each of the associated air compressors, determining whether the fourth probability corresponding to the associated air compressor is greater than a preset first probability threshold;

[0030] If not, it is determined that the control instruction of the associated air compressor is no instruction;

[0031] If so, determining whether an average value of the defect probabilities of all defective pipeline locations to which the associated air compressor is directly connected by a pipeline is greater than a preset second probability threshold;

[0032] If so, it is determined that the control instruction of the associated air compressor is no instruction;

[0033] If not, it is determined that the control instruction of the associated air compressor is to stop operation;

[0034] The associated air compressors whose control instructions are to stop operation are determined as defective air compressors, and the control instructions of the air compressors adjacent to each of the defective air compressors are determined to increase the air compression power.

[0035] A second aspect of the present invention discloses an intelligent control system for an air compressor, the system comprising:

[0036] an acquisition module, configured to acquire a plurality of real-time pipeline pressure data at a plurality of pipeline positions of a target air compressor pipeline network and motor data and noise detection data corresponding to each air compressor in the target air compressor pipeline network;

[0037] A first determining module is configured to determine a position of a defective pipeline in the target air compressor pipeline network where a gas supply defect may occur based on the real-time pipeline pressure data;

[0038] A second determination module is configured to determine a defect probability corresponding to each defective pipeline location based on the motor data and noise detection data of the air compressor corresponding to each defective pipeline location; the defect probability is used to send the defect probability to a maintenance terminal for repairing the defective pipeline location;

[0039] The third determination module is used to determine an air compressor control instruction based on the defect probability corresponding to each defective pipeline position, as well as the motor data and noise detection data; the air compressor control instruction is used to drive the air compressor to work to resolve the air supply defect.

[0040] As an optional embodiment, in the second aspect of the present invention, the first determination module determines, based on the real-time pipeline pressure data, a specific method for determining the location of a defective pipeline in the target air compressor pipeline network where an air supply defect may exist, including:

[0041] Determine the location type and pipeline line corresponding to each pipeline location corresponding to the real-time pipeline pressure data;

[0042] Grouping all the real-time pipeline pressure data according to the location type to obtain a plurality of first data groups;

[0043] Grouping all the real-time pipeline pressure data according to the pipeline lines to which they belong to obtain a plurality of second data groups;

[0044] According to the multiple first data groups and the multiple second data groups, based on a probability weight algorithm, defective pipeline locations that may have gas supply defects are screened out from the multiple pipeline locations.

[0045] As an optional embodiment, in the second aspect of the present invention, the location type is a gas supply terminal location, a pipeline junction location, a gas supply starting location, or a single pipeline intermediate location; and the first determination module groups all the real-time pipeline pressure data according to the location type to obtain a specific manner of multiple first data groups, including:

[0046] All the real-time pipeline pressure data belonging to the same location type are divided into the same first data group to obtain multiple first data groups corresponding to multiple location types.

[0047] As an optional embodiment, in the second aspect of the present invention, the first determining module groups all the real-time pipeline pressure data according to the pipeline lines to which they belong to, to obtain a plurality of second data groups, including:

[0048] All the real-time pipeline pressure data belonging to the same pipeline line are divided into the same second data group to obtain multiple second data groups corresponding to multiple pipeline lines.

[0049] As an optional embodiment, in the second aspect of the present invention, the first determination module screens out defective pipeline locations that may have gas supply defects from the multiple pipeline locations based on the multiple first data groups and the multiple second data groups based on a probability weight algorithm, including:

[0050] Inputting each of the first data sets into a trained first defect probability prediction neural network model to obtain a first defect probability corresponding to the location type corresponding to each of the first data sets; the first defect probability prediction neural network model is trained using a training data set including a plurality of training pressure data sets and corresponding pipeline defect annotations;

[0051] Inputting each of the second data groups into the first defect probability prediction neural network model to obtain a second defect probability corresponding to the pipeline line to which each of the second data groups belongs;

[0052] For each pipeline position, inputting the real-time pipeline pressure data corresponding to the pipeline position into the first defect probability prediction neural network model to obtain a third defect probability corresponding to the pipeline position;

[0053] Calculating the product of the third defect probability corresponding to the pipeline position, the first defect probability corresponding to the location type corresponding to the pipeline position, and the second defect probability corresponding to the pipeline line to which the pipeline position belongs, to obtain a defect parameter corresponding to the pipeline position;

[0054] All the pipeline positions where the defect parameter is greater than a preset parameter threshold are determined as defective pipeline positions where gas supply defects may occur.

[0055] As an optional embodiment, in the second aspect of the present invention, the second determination module determines the specific manner in which the defect probability corresponding to each defective pipeline location is determined based on the motor data and noise detection data of the air compressor corresponding to each defective pipeline location, including:

[0056] For each defective pipeline location, all the air compressors whose distance to the defective pipeline location is less than a preset distance threshold are determined as associated air compressors corresponding to the defective pipeline location;

[0057] Inputting the motor data and noise detection data of each associated air compressor into a trained second defect probability prediction neural network model to obtain a fourth defect probability corresponding to each associated air compressor; the second defect probability prediction neural network model is trained by a training data set including a plurality of training motor data, training noise detection data, and corresponding motor defect annotations;

[0058] The probability average of the fourth probabilities of all the associated air compressors corresponding to the defective pipeline position is calculated, and the product of the probability average and the defect parameter corresponding to the defective pipeline position is calculated to obtain the defect probability corresponding to the defective pipeline position.

[0059] As an optional embodiment, in the second aspect of the present invention, the third determination module determines a specific manner of the air compressor control instruction based on the defect probability corresponding to each defective pipe position, as well as the motor data and the noise detection data, including:

[0060] For each of the associated air compressors, determining whether the fourth probability corresponding to the associated air compressor is greater than a preset first probability threshold;

[0061] If not, it is determined that the control instruction of the associated air compressor is no instruction;

[0062] If so, determining whether an average value of the defect probabilities of all defective pipeline locations to which the associated air compressor is directly connected by a pipeline is greater than a preset second probability threshold;

[0063] If so, it is determined that the control instruction of the associated air compressor is no instruction;

[0064] If not, it is determined that the control instruction of the associated air compressor is to stop operation;

[0065] The associated air compressors whose control instructions are to stop operation are determined as defective air compressors, and the control instructions of the air compressors adjacent to each of the defective air compressors are determined to increase the air compression power.

[0066] A third aspect of the present invention discloses another intelligent control system for an air compressor, the system comprising:

[0067] a memory storing executable program code;

[0068] a processor coupled to the memory;

[0069] The processor calls the executable program code stored in the memory to execute part or all of the steps in the air compressor intelligent control method disclosed in the first aspect of the present invention.

[0070] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the air compressor intelligent control method disclosed in the first aspect of the present invention.

[0071] Compared with the prior art, the present invention has the following beneficial effects:

[0072] The present invention can utilize real-time pipeline pressure data and the motor data and noise monitoring data of each air compressor to effectively determine the location of defective pipelines and the corresponding defect probability in the pipeline network composed of multiple air compressors, and further determine the control instructions of the air compressors, thereby being able to utilize multiple sensor data to effectively monitor and control the air compressor pipeline network, reduce working failures and errors in the air compressor pipeline network, and improve the air supply effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0074] FIG1 is a schematic flow chart of an air compressor intelligent control method disclosed in an embodiment of the present invention;

[0075] FIG2 is a schematic structural diagram of an air compressor intelligent control system disclosed in an embodiment of the present invention;

[0076] FIG3 is a schematic structural diagram of another air compressor intelligent control system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0077] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0078] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or end comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or end.

[0079] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0080] The present invention discloses an intelligent air compressor control method and system. These methods utilize real-time pipeline pressure data, motor data, and noise monitoring data from each air compressor to effectively determine the locations and corresponding defect probabilities of defective pipelines within a pipeline network comprised of multiple air compressors. Furthermore, these methods determine control instructions for the air compressors. This allows for effective monitoring and control of the air compressor pipeline network using multiple sensor data, reducing operational failures and errors within the network and improving air supply efficiency. These are described in detail below.

[0081] Example 1

[0082] Please refer to Figure 1, which is a flow chart of an air compressor intelligent control method disclosed in an embodiment of the present invention. The method described in Figure 1 can be applied to corresponding data processing equipment, data processing terminals, and data processing servers, and the server can be a local server or a cloud server. The embodiment of the present invention is not limited to this. As shown in Figure 1, the air compressor intelligent control method may include the following operations:

[0083] 101. Acquire multiple real-time pipeline pressure data at multiple pipeline locations of a target air compressor pipeline network and motor data and noise detection data corresponding to each air compressor in the target air compressor pipeline network.

[0084] 102. Based on real-time pipeline pressure data, determine the location of defective pipelines in the target air compressor pipeline network where air supply defects may exist.

[0085] 103. Determine the defect probability corresponding to each defective pipeline location based on the motor data and noise detection data of the air compressor corresponding to each defective pipeline location.

[0086] Specifically, the defect probability is used to send to a maintenance terminal to inspect the defective pipeline location.

[0087] 104. Determine the air compressor control instruction based on the defect probability corresponding to each defective pipeline position, as well as the motor data and noise detection data.

[0088] Specifically, the air compressor control instruction is used to drive the air compressor to work to solve the air supply defect.

[0089] It can be seen that the method described in the embodiment of the present invention can utilize real-time pipeline pressure data and the motor data and noise monitoring data of each air compressor to effectively determine the location of defective pipelines and the corresponding defect probability in the pipeline network composed of multiple air compressors, and further determine the control instructions of the air compressor, so that multiple sensor data can be used to effectively monitor and control the air compressor pipeline network, reduce the working failures and errors of the air compressor pipeline network, and improve the air supply effect.

[0090] As an optional embodiment, in the above step, determining the location of a defective pipeline in the target air compressor pipeline network where a gas supply defect may exist based on the real-time pipeline pressure data includes:

[0091] Determine the location type and pipeline line corresponding to each pipeline location corresponding to real-time pipeline pressure data;

[0092] Grouping all real-time pipeline pressure data according to location type to obtain a plurality of first data groups;

[0093] Grouping all real-time pipeline pressure data according to the pipeline lines to which they belong to obtain a plurality of second data groups;

[0094] According to the multiple first data groups and the multiple second data groups, based on a probability weight algorithm, defective pipeline locations that may have gas supply defects are screened out from the multiple pipeline locations.

[0095] Through the above embodiment, it is possible to group all real-time pipeline pressure data according to information such as location type and pipeline line to which they belong, so as to obtain multiple data groups, and based on the probability weight algorithm, screen out defective pipeline locations that may have gas supply defects from multiple pipeline locations, thereby accurately determining the defective pipeline locations, facilitating subsequent monitoring and control of the air compressor pipeline network, reducing operating failures and errors in the air compressor pipeline network, and improving the gas supply effect.

[0096] As an optional embodiment, the location type is a gas supply terminal location, a pipeline junction location, a gas supply starting location, or a single pipeline intermediate location; in the above steps, all real-time pipeline pressure data are grouped according to the location type to obtain multiple first data groups, including:

[0097] All real-time pipeline pressure data belonging to the same location type are divided into the same first data group to obtain multiple first data groups corresponding to multiple location types.

[0098] Through the above embodiment, it is possible to group all real-time pipeline pressure data according to location type to obtain multiple data groups, which is helpful for subsequent accurate determination of the location of defective pipelines, facilitates subsequent monitoring and control of the air compressor pipeline network, reduces working failures and errors of the air compressor pipeline network, and improves the air supply effect.

[0099] As an optional embodiment, in the above step, all real-time pipeline pressure data are grouped according to the pipeline lines to which they belong to obtain multiple second data groups, including:

[0100] All real-time pipeline pressure data belonging to the same pipeline line are divided into the same second data group to obtain multiple second data groups corresponding to multiple pipeline lines.

[0101] Through the above embodiment, it is possible to group all real-time pipeline pressure data according to the pipeline lines to which they belong to obtain multiple data groups, which helps to accurately determine the location of defective pipelines in the subsequent process, facilitates the subsequent monitoring and control of the air compressor pipeline network, reduces operating failures and errors in the air compressor pipeline network, and improves the air supply effect.

[0102] As an optional embodiment, in the above step, screening out defective pipeline locations that may have gas supply defects from multiple pipeline locations based on the multiple first data groups and the multiple second data groups based on a probability weight algorithm includes:

[0103] Inputting each first data set into a trained first defect probability prediction neural network model to obtain a first defect probability corresponding to a location type corresponding to each first data set; the first defect probability prediction neural network model is trained using a training data set including a plurality of training pressure data sets and corresponding pipeline defect annotations;

[0104] Inputting each second data group into the first defect probability prediction neural network model to obtain a second defect probability corresponding to the pipeline line corresponding to each second data group;

[0105] For each pipeline location, inputting the real-time pipeline pressure data corresponding to the pipeline location into the first defect probability prediction neural network model to obtain a third defect probability corresponding to the pipeline location;

[0106] Calculate the product of a third defect probability corresponding to the pipeline position, a first defect probability corresponding to the location type corresponding to the pipeline position, and a second defect probability corresponding to the pipeline line to which the pipeline position belongs, to obtain a defect parameter corresponding to the pipeline position;

[0107] All pipeline locations with defect parameters greater than a preset parameter threshold are determined as defective pipeline locations that may have gas supply defects.

[0108] Through the above embodiments, it is possible to determine the defect probabilities of different aspects based on different data groups and pipeline sensor data according to the first defect probability prediction neural network model, and further calculate the defect parameters to accurately screen and determine the location of the defective pipeline, so as to facilitate the subsequent monitoring and control of the air compressor pipeline network, reduce the working failures and errors of the air compressor pipeline network, and improve the air supply effect.

[0109] As an optional embodiment, in the above step, determining the defect probability corresponding to each defective pipeline location based on the motor data and noise detection data of the air compressor corresponding to each defective pipeline location includes:

[0110] For each defective pipeline location, all air compressors whose distance to the defective pipeline location is less than a preset distance threshold are determined as associated air compressors corresponding to the defective pipeline location;

[0111] Inputting the motor data and noise detection data of each associated air compressor into a trained second defect probability prediction neural network model to obtain a fourth defect probability corresponding to each associated air compressor; the second defect probability prediction neural network model is trained using a training data set including a plurality of training motor data, training noise detection data, and corresponding motor defect annotations;

[0112] The probability average of the fourth probabilities of all associated air compressors corresponding to the defective pipeline position is calculated, and the product of the probability average and the defect parameter corresponding to the defective pipeline position is calculated to obtain the defect probability corresponding to the defective pipeline position.

[0113] Through the above embodiment, it is possible to calculate the probability average of the fourth probability of all associated air compressors corresponding to the defective pipeline position according to the second defect probability prediction neural network model, and calculate the product between the probability average and the defect parameter corresponding to the defective pipeline position to obtain the defect probability, so as to accurately calculate the defect probability of the defective pipeline position. On the one hand, it helps the monitoring end to monitor and subsequently repair it, and on the other hand, it facilitates the subsequent monitoring and control of the air compressor pipeline network, reduces the working failures and errors of the air compressor pipeline network, and improves the air supply effect.

[0114] As an optional embodiment, in the above steps, determining the air compressor control instruction based on the defect probability corresponding to each defective pipe position, as well as the motor data and noise detection data, includes:

[0115] For each associated air compressor, determining whether the fourth probability corresponding to the associated air compressor is greater than a preset first probability threshold;

[0116] If not, it is determined that the control instruction of the associated air compressor is no instruction;

[0117] If so, determining whether the average defect probability of all defective pipeline locations to which the associated air compressor has a direct pipeline connection is greater than a preset second probability threshold;

[0118] If so, it is determined that the control instruction of the associated air compressor is no instruction;

[0119] If not, it is determined that the control instruction of the associated air compressor is to stop operation;

[0120] The associated air compressors whose control instructions are to stop operation are determined as defective air compressors, and the control instructions of the air compressors adjacent to each defective air compressor are determined to increase the air compression power.

[0121] Through the above embodiment, it is possible to determine the air compressor control instructions based on the defect probability corresponding to each defective pipeline position and the defect probability of each associated air compressor, so as to accurately stop the associated air compressor with a determined fault, and increase the power of the air compressor near the stopped air compressor to supplement its lack of air supply output. This can achieve more intelligent monitoring and control of the air compressor pipeline network, reduce working failures and errors in the air compressor pipeline network, and improve the air supply effect.

[0122] Example 2

[0123] Please refer to Figure 2, which is a schematic diagram of the structure of an air compressor intelligent control system disclosed in an embodiment of the present invention. The system described in Figure 2 can be applied to corresponding data processing equipment, data processing terminals, and data processing servers. The server can be a local server or a cloud server, which is not limited by the embodiment of the present invention. As shown in Figure 2, the system may include:

[0124] An acquisition module 201 is configured to acquire a plurality of real-time pipeline pressure data at a plurality of pipeline positions of a target air compressor pipeline network and motor data and noise detection data corresponding to each air compressor in the target air compressor pipeline network;

[0125] The first determining module 202 is configured to determine the location of a defective pipeline in the target air compressor pipeline network that may have an air supply defect based on the real-time pipeline pressure data;

[0126] The second determination module 203 is configured to determine the defect probability corresponding to each defective pipeline location based on the motor data and noise detection data of the air compressor corresponding to each defective pipeline location; the defect probability is used to send to the maintenance terminal for repairing the defective pipeline location;

[0127] The third determination module 204 is used to determine an air compressor control instruction based on the defect probability corresponding to each defective pipe position, as well as the motor data and noise detection data; the air compressor control instruction is used to drive the air compressor to work to solve the air supply defect.

[0128] As an optional embodiment, the first determining module 202 determines the specific location of a defective pipeline in the target air compressor pipeline network that may have an air supply defect based on the real-time pipeline pressure data, including:

[0129] Determine the location type and pipeline line corresponding to each pipeline location corresponding to real-time pipeline pressure data;

[0130] Grouping all real-time pipeline pressure data according to location type to obtain a plurality of first data groups;

[0131] Grouping all real-time pipeline pressure data according to the pipeline lines to which they belong to obtain a plurality of second data groups;

[0132] According to the multiple first data groups and the multiple second data groups, based on a probability weight algorithm, defective pipeline locations that may have gas supply defects are screened out from the multiple pipeline locations.

[0133] As an optional embodiment, the location type is a gas supply terminal location, a pipeline junction location, a gas supply starting location, or a single pipeline intermediate location; the first determination module 202 groups all real-time pipeline pressure data according to the location type to obtain a plurality of first data groups, including:

[0134] All real-time pipeline pressure data belonging to the same location type are divided into the same first data group to obtain multiple first data groups corresponding to multiple location types.

[0135] As an optional embodiment, the first determining module 202 groups all the real-time pipeline pressure data according to the pipeline lines to which they belong to, to obtain a plurality of second data groups, including:

[0136] All real-time pipeline pressure data belonging to the same pipeline line are divided into the same second data group to obtain multiple second data groups corresponding to multiple pipeline lines.

[0137] As an optional embodiment, the first determining module 202 selects defective pipeline locations that may have gas supply defects from multiple pipeline locations based on the multiple first data groups and the multiple second data groups and a probability weighting algorithm, including:

[0138] Inputting each first data set into a trained first defect probability prediction neural network model to obtain a first defect probability corresponding to a location type corresponding to each first data set; the first defect probability prediction neural network model is trained using a training data set including a plurality of training pressure data sets and corresponding pipeline defect annotations;

[0139] Inputting each second data group into the first defect probability prediction neural network model to obtain a second defect probability corresponding to the pipeline line corresponding to each second data group;

[0140] For each pipeline location, inputting the real-time pipeline pressure data corresponding to the pipeline location into the first defect probability prediction neural network model to obtain a third defect probability corresponding to the pipeline location;

[0141] Calculate the product of a third defect probability corresponding to the pipeline position, a first defect probability corresponding to the location type corresponding to the pipeline position, and a second defect probability corresponding to the pipeline line to which the pipeline position belongs, to obtain a defect parameter corresponding to the pipeline position;

[0142] All pipeline locations with defect parameters greater than a preset parameter threshold are determined as defective pipeline locations that may have gas supply defects.

[0143] As an optional embodiment, the second determination module 203 determines the defect probability corresponding to each defective pipeline location based on the motor data and noise detection data of the air compressor corresponding to each defective pipeline location, including:

[0144] For each defective pipeline location, all air compressors whose distance to the defective pipeline location is less than a preset distance threshold are determined as associated air compressors corresponding to the defective pipeline location;

[0145] Inputting the motor data and noise detection data of each associated air compressor into a trained second defect probability prediction neural network model to obtain a fourth defect probability corresponding to each associated air compressor; the second defect probability prediction neural network model is trained using a training data set including a plurality of training motor data, training noise detection data, and corresponding motor defect annotations;

[0146] The probability average of the fourth probabilities of all associated air compressors corresponding to the defective pipeline position is calculated, and the product of the probability average and the defect parameter corresponding to the defective pipeline position is calculated to obtain the defect probability corresponding to the defective pipeline position.

[0147] As an optional embodiment, the third determination module 204 determines a specific method of the air compressor control instruction based on the defect probability corresponding to each defective pipe position, as well as the motor data and the noise detection data, including:

[0148] For each associated air compressor, determining whether the fourth probability corresponding to the associated air compressor is greater than a preset first probability threshold;

[0149] If not, it is determined that the control instruction of the associated air compressor is no instruction;

[0150] If so, determining whether the average defect probability of all defective pipeline locations to which the associated air compressor has a direct pipeline connection is greater than a preset second probability threshold;

[0151] If so, it is determined that the control instruction of the associated air compressor is no instruction;

[0152] If not, it is determined that the control instruction of the associated air compressor is to stop operation;

[0153] The associated air compressors whose control instructions are to stop operation are determined as defective air compressors, and the control instructions of the air compressors adjacent to each defective air compressor are determined to increase the air compression power.

[0154] The module details and technical effects in the embodiment of the present invention can be referred to the description in the first embodiment and will not be repeated here.

[0155] Example 3

[0156] Please refer to Figure 3, which is a schematic diagram of the structure of another air compressor intelligent control system disclosed in an embodiment of the present invention. As shown in Figure 3, the system may include:

[0157] A memory 301 storing executable program code;

[0158] a processor 302 coupled to the memory 301;

[0159] The processor 302 calls the executable program code stored in the memory 301 to execute part or all of the steps in the air compressor intelligent control method disclosed in the first embodiment of the present invention.

[0160] Example 4

[0161] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all steps of the air compressor intelligent control method disclosed in the first embodiment of the present invention.

[0162] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present embodiment without inventive effort.

[0163] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0164] Finally, it should be noted that the air compressor intelligent control method and system disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An intelligent control method for an air compressor, characterized in that: The method comprises: Acquire multiple real-time pipeline pressure data of multiple pipeline positions of the target air compressor pipeline network and motor data and noise detection data corresponding to each air compressor in the target air compressor pipeline network; Determine the position of a defective pipeline in the target air compressor pipeline network where a gas supply defect may exist according to the real-time pipeline pressure data; Determine the defect probability corresponding to each defective pipeline position according to the motor data and noise detection data of the air compressor corresponding to each defective pipeline position; the defect probability is used to send to the maintenance terminal to repair the defective pipeline position; An air compressor control instruction is determined according to the defect probability corresponding to each defective pipeline position, as well as the motor data and noise detection data; the air compressor control instruction is used to drive the air compressor to work to solve the air supply defect.

2. The air compressor intelligent control method according to claim 1, characterized in that: The step of determining the position of a defective pipeline in the target air compressor pipeline network where a gas supply defect may exist according to the real-time pipeline pressure data includes: Determine the location type and pipeline line corresponding to each pipeline location corresponding to the real-time pipeline pressure data; According to the location type, grouping all the real-time pipeline pressure data to obtain a plurality of first data groups; Grouping all the real-time pipeline pressure data according to the pipeline lines to which they belong, to obtain a plurality of second data groups; According to the multiple first data groups and the multiple second data groups, based on a probability weight algorithm, defective pipeline locations that may have gas supply defects are screened out from the multiple pipeline locations.

3. The air compressor intelligent control method according to claim 2 is characterized in that: The location type is a gas supply terminal location, a pipeline junction location, a gas supply starting location, or a single pipeline middle location; and according to the location type, all the real-time pipeline pressure data are grouped to obtain a plurality of first data groups, including: All the real-time pipeline pressure data belonging to the same location type are divided into the same first data group to obtain multiple first data groups corresponding to multiple location types.

4. The air compressor intelligent control method according to claim 3 is characterized in that: The step of grouping all the real-time pipeline pressure data according to the pipeline line to which they belong to, so as to obtain a plurality of second data groups, comprises: All the real-time pipeline pressure data belonging to the same pipeline line are divided into the same second data group to obtain multiple second data groups corresponding to multiple pipeline lines.

5. The air compressor intelligent control method according to claim 4, characterized in that: The method of screening out defective pipeline locations that may have gas supply defects from the multiple pipeline locations based on the multiple first data groups and the multiple second data groups and based on a probability weight algorithm includes: Inputting each of the first data groups into a trained first defect probability prediction neural network model to obtain a first defect probability corresponding to the location type corresponding to each of the first data groups; the first defect probability prediction neural network model is trained by a training data set including a plurality of training pressure data sets and corresponding pipeline defect annotations; Inputting each of the second data groups into the first defect probability prediction neural network model to obtain a second defect probability corresponding to the pipeline line to which each of the second data groups belongs; For each of the pipeline positions, inputting the real-time pipeline pressure data corresponding to the pipeline position into the first defect probability prediction neural network model to obtain a third defect probability corresponding to the pipeline position; Calculate the product of the third defect probability corresponding to the pipeline position, the first defect probability corresponding to the position type corresponding to the pipeline position, and the second defect probability corresponding to the pipeline line corresponding to the pipeline position, to obtain a defect parameter corresponding to the pipeline position; All the pipeline positions where the defect parameter is greater than a preset parameter threshold are determined as defective pipeline positions where gas supply defects may exist.

6. The air compressor intelligent control method according to claim 5, characterized in that: Determining the defect probability corresponding to each defective pipeline position according to the motor data and noise detection data of the air compressor corresponding to each defective pipeline position includes: For each defective pipeline position, all the air compressors whose distances to the defective pipeline position are less than a preset distance threshold are determined as associated air compressors corresponding to the defective pipeline position; Input the motor data and noise detection data of each of the associated air compressors into the trained second defect probability prediction neural network model to obtain a fourth defect probability corresponding to each of the associated air compressors; the second defect probability prediction neural network model is trained by a training data set including a plurality of training motor data and training noise detection data and corresponding motor defect annotations; The probability average of the fourth probabilities of all the associated air compressors corresponding to the defective pipeline position is calculated, and the product of the probability average and the defect parameter corresponding to the defective pipeline position is calculated to obtain the defect probability corresponding to the defective pipeline position.

7. The air compressor intelligent control method according to claim 6, characterized in that: The method of determining the air compressor control instruction according to the defect probability corresponding to each defective pipeline position, the motor data and the noise detection data, comprises: For each of the associated air compressors, determining whether the fourth probability corresponding to the associated air compressor is greater than a preset first probability threshold; If not, it is determined that the control instruction of the associated air compressor is no instruction; If so, determine whether the average value of the defect probabilities of all the defective pipeline locations with direct pipeline connection of the associated air compressor is greater than a preset second probability threshold; If yes, it is determined that the control instruction of the associated air compressor is no instruction; If not, it is determined that the control instruction of the associated air compressor is to stop operation; The associated air compressor whose control instruction is to stop operation is determined as a defective air compressor, and the control instruction of the air compressors adjacent to each of the defective air compressors is determined to increase the air compression power.

8. An intelligent control system for an air compressor, characterized in that: The system comprises: An acquisition module, used to acquire a plurality of real-time pipeline pressure data of a plurality of pipeline positions of a target air compressor pipeline network and motor data and noise detection data corresponding to each air compressor in the target air compressor pipeline network; A first determination module is used to determine the position of a defective pipeline in the target air compressor pipeline network where a gas supply defect may exist according to the real-time pipeline pressure data; A second determination module is used to determine the defect probability corresponding to each defective pipeline position according to the motor data and noise detection data of the air compressor corresponding to each defective pipeline position; the defect probability is used to send to the maintenance terminal to repair the defective pipeline position; The third determination module is used to determine the air compressor control instruction according to the defect probability corresponding to each defective pipeline position, as well as the motor data and the noise detection data; the air compressor control instruction is used to drive the air compressor to work to solve the air supply defect.

9. An intelligent control system for an air compressor, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the air compressor intelligent control method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the air compressor intelligent control method according to any one of claims 1-7.

Images