Oilless air compressor running state detection method, electronic equipment and storage medium

Abstract

The invention provides an oilless air compressor running state detection method, electronic equipment and a storage medium, and the method comprises the following steps: determining a running data list according to a plurality of running data of an oilless air compressor; performing data speculation processing on operation data before any operation data in each operation data list to obtain first speculation data corresponding to the operation data; performing data speculation processing on the operation data after any operation data in each operation data list to obtain second speculation data corresponding to the operation data, and determining target speculation data corresponding to the operation data; if the difference value between any operation data and the target speculation data corresponding to the operation data is greater than a preset data difference threshold value, replacing the operation data with the target speculation data corresponding to the operation data; and the operation state of the oilless air compressor is determined according to each operation data list, so that the detection result, obtained through the state detection model, of the operation state of the oilless air compressor is more accurate.

Description

Technical Field

[0001] This invention relates to the field of air compressor testing technology, and in particular to a method, electronic device and storage medium for detecting the operating status of an oil-free air compressor. Background Technology

[0002] An oil-free air compressor is an air compressor that does not require lubrication. It can be used in home oxygen concentrators to compress air. Because it is generally used in equipment with relatively high requirements for operational safety, such as oxygen concentrators, it is necessary to perform real-time operational safety monitoring during the operation of the oil-free air compressor. This is to prevent abnormal malfunctions of the oil-free air compressor (such as poor oxygen production due to low air compression power, or unstable air output rate due to excessive internal temperature or pressure) from causing low oxygen production efficiency of the oxygen concentrator, which could then affect the user's health safety.

[0003] Current methods for detecting the operating status of oil-free air compressors involve either threshold range detection of individual operating data or inputting the operating data into a pre-trained data model. For example, a fixed threshold range is set for each type of operating data. During operation, changes in the internal operating data of the oil-free air compressor are monitored in real time. When the data falls outside the set threshold range, an operational abnormality is determined. However, in practical applications, the accuracy of this detection method is relatively low. If only one type of operating data experiences a momentary change, or if it falls outside the threshold range for a short period, it may be due to external environmental factors. The issue caused by this is not due to a malfunction in the oil-free air compressor itself, nor does it affect the compressor's efficiency. However, according to existing detection methods, this situation requires reporting an error in the compressor's operating status or performing model checks on the operating data. Because such instantaneous data may deviate significantly from normal data, the model's output may also be inaccurate. When such false alarms occur, personnel still need to perform maintenance and inspection on the oil-free air compressor. Therefore, this detection method for oil-free air compressors, which relies on judging a single factor or instantaneous data anomalies, has low accuracy, wastes manpower, and also affects user experience. Summary of the Invention

[0004] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows: According to one aspect of this application, a method for detecting the operating status of an oil-free air compressor is provided, comprising: Step S100: Based on the operating data corresponding to each detection position of the oil-free air compressor within the target time period, determine the operating data list corresponding to each detection position; the duration of the target time period is the preset duration, and the end time of the target time period is the current time. Step S200: Perform data inference processing on several running data before any running data in each running data list to obtain the first inferred data corresponding to the running data and several running data after the running data; Step S300: Perform data speculation processing on several running data following any running data in each running data list to obtain the second speculative data corresponding to the running data and several running data preceding the running data; Step S400: Determine the target predicted data corresponding to any running data based on the first predicted data and the second predicted data corresponding to any running data. Step S500: If the difference between any running data and the target inferred data corresponding to the running data is greater than a preset data difference threshold, then in the running data list where the running data is located, the running data is replaced with the target inferred data corresponding to the running data. Step S600: Input each running data list into the preset state detection model to obtain the running status of each detection position of the oil-free air compressor within the target time period; the state detection model is obtained by training on several historical running data of the oil-free air compressor within a historical time period.

[0005] In one exemplary embodiment of this application, step S100 includes: Step S110: Obtain several operating data points corresponding to each detection position of the oil-free air compressor within the target time period to obtain several operating data lists A1, A2, ..., A m ,...,A n Where m = 1, 2, ..., n; n is the number of detection positions of the oil-free air compressor; A m This is a list of operating data corresponding to the m-th detection position of the oil-free air compressor within the target time period; A m =(A m1 A m2 ,...,A mi ,...,A mj ); i=1,2,...,j; j is the number of data collection times included in the target time period; A mi This represents the operating data of the m-th detection position of the oil-free air compressor at the i-th data acquisition time within the target time period.

[0006] In one exemplary embodiment of this application, step S200 includes: Step S210, A m1 ,...,A m(i-1) The input is fed into a preset first prediction model to obtain the B output by the first prediction model. mi ,...,Bmj B mi For A mi The corresponding first inferred data; The first inference model is determined according to the following steps: Step S211: Obtain several historical operating data points corresponding to several historical time periods for several detection locations of the oil-free air compressor, to obtain several historical operating data lists C1, C2, ..., C p ,...,C q Where p = 1, 2, ..., q; q is the number of historical time periods; the duration of each historical time period is equal to the duration of the target time period; the end time of each historical time period is before the start time of the target time period; the number of data collection moments included in each historical time period is equal to the number of data collection moments included in the target time period, and the duration between two adjacent data collection moments included in each historical time period is equal to the duration between two corresponding data collection moments included in the target time period; C p This is a list of historical operating data for the oil-free air compressor within the p-th historical time period. C p =(C p1 C p2 ,...,C pi ,...,C pj );C pi This refers to the historical operating data of the oil-free air compressor at the i-th data acquisition time in the p-th historical time period; Step S212, C p1 To C p(i-1) As input sample, C pi To C pj As the output label, a pre-defined neural network model is subjected to supervised training to obtain the first inference model.

[0007] In one exemplary embodiment of this application, step S300 includes: Step S310, Place A m(i+1) ,...,A mj The input is fed into a preset second prediction model to obtain the C output by the second prediction model. m1 ,...,C mi C mi For A mi The corresponding second inferred data; The second inference model is determined according to the following steps: Step S311, place C p(i+1) To C pj As input sample, C p1 To Cpi As the output label, a pre-defined neural network model is subjected to supervised training to obtain a second inference model.

[0008] In one exemplary embodiment of this application, the loss functions of the first speculation model and the second speculation model are determined according to the following steps: Step S001, C p1 ,...,C p(i-1) Input into the first inference model to obtain the first validation data list E=(E pi ,...,E pj ); where E pi C pi The corresponding first verification data; Step S002, C p(i+1) ,...,C pj Input into the second prediction model to obtain the second validation data list F = (F p1 ,...,F pi ); where F pi C pi The corresponding second verification data; Step S003: Based on the first verification data list E and the second verification data list F, obtain the target verification data list H1 = (F p1 ,...,F p(i-1) E p(i+1) ,...,E pj ); Step S004, according to C p The first original data list I1=(C) is obtained. p1 ,...,C pi ), Second original data list I2=(C pi ,...,C pj ), Target original data list H2=(C p1 ,...,C p(i-1) C p(i+1) ,...,C pj ); Step S005: Based on the target validation data list H1 and the target original data list H2, determine the loss function Loss1 corresponding to the first speculation model and the loss function Loss2 corresponding to the second speculation model; Where Loss1=dist(H1,H2)+|E pi -F pi | / C pi +dist(E,I2)+|C pi -E pi |; Loss2=dist(H1,H2)+|E pi -F pi | / C pi +dist(F,I1)+|C pi -F pi |; In the formula, dist() is a preset Euclidean distance calculation function.

[0009] In one exemplary embodiment of this application, step S400 includes: Step S410, according to B m(i+1) ,...,B mj and A m(i+1) ,...,A mj The first predicted coefficient D1 was determined to be (∑ j g=i+1 (B mg -A mg ) 2 ) 1 / 2 ; Step S420, according to C m1 ,...,C m(i-1) and A m1 ,...,A m(i-1) The second predicted coefficient D2 was determined to be (∑ i-1 g=1 (C mg -A mg ) 2 ) 1 / 2 ; Step S430: Determine A based on the first prediction coefficient D1 and the second prediction coefficient D2. mi Corresponding target prediction data T mi =(D1 / (D1+D2))×B mi +(D2 / (D1+D2))×C mi .

[0010] In one exemplary embodiment of this application, step S500 includes: Step S510, Traverse A m For each running data, if |A mi -T mi |>G, then A m A in mi Replace with T mi Where G is the preset data difference threshold.

[0011] In one exemplary embodiment of this application, the state detection model is determined according to the following steps: Step S601: Obtain the status identifier N corresponding to the operating status of the oil-free air compressor in the p-th historical time period. p ; Step S602, C p As input samples, N p As output labels, supervised training is performed on a pre-defined neural network model to obtain a state detection model.

[0012] According to another aspect of this application, a non-transitory computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored in the storage medium, the at least one instruction or the at least one program being loaded and executed by a processor to implement the aforementioned method for detecting the operating status of an oil-free air compressor.

[0013] According to another aspect of this application, an electronic device is provided, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0014] The present invention has at least the following beneficial effects: The oil-free air compressor operating status detection method of the present invention first determines an operating data list corresponding to each detection position based on several operating data corresponding to each detection position of the oil-free air compressor within a target time period. Then, it performs data estimation processing on several operating data preceding any given operating data in each operating data list to obtain first estimated data corresponding to that operating data and several operating data following it. It also performs data estimation processing on several operating data following any given operating data in each operating data list to obtain second estimated data corresponding to that operating data and several operating data preceding it. Finally, based on the first and second estimated data corresponding to any given operating data, it determines the target estimated data corresponding to that operating data. The target inferred data is the data that is comprehensively inferred from other related operational data. If the difference between any operational data and the target inferred data corresponding to that operational data is greater than a preset data difference threshold, it indicates that the operational data may be abnormal, there may be a detection problem, or a momentary change has occurred. In this case, the operational data in the operational data list is replaced with the target inferred data corresponding to that operational data, so that the operational data tends to be the data for normal detection. Each operational data list is then input into the state detection model to obtain the operational status of each detection position of the oil-free air compressor within the target time period, so that the detection results of the operational status of the oil-free air compressor obtained by the state detection model are more accurate and the possibility of false alarms is reduced. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart of the oil-free air compressor operation status detection method provided in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] This application proposes a method for detecting the operating status of an oil-free air compressor, such as... Figure 1 As shown, it includes: Step S100: Based on the operating data corresponding to each detection position of the oil-free air compressor within the target time period, determine the operating data list corresponding to each detection position. The target time period has a preset duration, and the end time of the target time period is the current time.

[0019] The inspection points for oil-free air compressors can be locations where abnormalities are likely to occur during operation, such as the piston, screw, and worm gear, or locations set by the operator.

[0020] The acquired operational data at the detection location can be data that affects the safe operation of the detection location, such as pressure data, temperature data, vibration data, noise data, etc. Several data sensors can be set at the detection location to detect operational data of different types.

[0021] Furthermore, step S100 includes step S110: Step S110: Obtain several operating data points corresponding to each detection position of the oil-free air compressor within the target time period to obtain several operating data lists A1, A2, ..., A m ,...,A n Where m = 1, 2, ..., n; n is the number of detection positions of the oil-free air compressor; A m This is a list of operating data corresponding to the m-th detection position of the oil-free air compressor within the target time period; A m=(A m1 A m2 ,...,A mi ,...,A mj ); i=1,2,...,j; j is the number of data collection times included in the target time period; A mi This represents the operating data of the m-th detection position of the oil-free air compressor at the i-th data acquisition time within the target time period.

[0022] Step S200: Perform data inference processing on several running data before any running data in each running data list to obtain the first inferred data corresponding to the running data and several running data after the running data; Furthermore, step S200 includes step S210: Step S210, A m1 ,...,A m(i-1) The input is fed into a preset first prediction model to obtain the B output by the first prediction model. mi ,...,B mj B mi For A mi The corresponding first inferred data; The first prediction model is determined according to steps S211-S212: Step S211: Obtain several historical operating data points corresponding to several historical time periods for several detection locations of the oil-free air compressor, to obtain several historical operating data lists C1, C2, ..., C p ,...,C q Where p = 1, 2, ..., q; q is the number of historical time periods; C p This is a list of historical operating data for the oil-free air compressor within the p-th historical time period. C p =(C p1 C p2 ,...,C pi ,...,C pj );C pi This refers to the historical operating data of the oil-free air compressor at the i-th data acquisition time in the p-th historical time period; The duration of each historical time period is equal to the duration of the target time period; the end time of each historical time period is before the start time of the target time period; the number of data collection moments included in each historical time period is equal to the number of data collection moments included in the target time period, and the duration between two adjacent data collection moments included in each historical time period is equal to the duration between two corresponding data collection moments included in the target time period.

[0023] Step S212, C p1 To C p(i-1) As input sample, C pi To C pj As the output label, a pre-defined neural network model is subjected to supervised training to obtain the first inference model.

[0024] The existing sample training methods can be used to train the neural network model. The neural network model can be an LSTM (Long Short-Term Memory) model.

[0025] Step S300: Perform data speculation processing on several running data following any running data in each running data list to obtain the second speculative data corresponding to the running data and several running data preceding the running data; Furthermore, step S300 includes step S310: Step S310, Place A m(i+1) ,...,A mj The input is fed into a preset second prediction model to obtain the C output by the second prediction model. m1 ,...,C mi C mi For A mi The corresponding second inferred data; The second prediction model is determined according to step S311: Step S311, place C p(i+1) To C pj As input sample, C p1 To C pi As the output label, a pre-defined neural network model is subjected to supervised training to obtain a second inference model.

[0026] Furthermore, the loss functions of the first and second prediction models are determined according to steps S001-S005: Step S001, C p1 ,...,C p(i-1) Input into the first inference model to obtain the first validation data list E=(E pi ,...,E pj ); where E pi C pi The corresponding first verification data; Step S002, C p(i+1) ,...,C pj Input into the second prediction model to obtain the second validation data list F = (F p1 ,...,Fpi ); where F pi C pi The corresponding second verification data; Step S003: Based on the first verification data list E and the second verification data list F, obtain the target verification data list H1 = (F p1 ,...,F p(i-1) E p(i+1) ,...,E pj ); Step S004, according to C p The first original data list I1=(C) is obtained. p1 ,...,C pi ), Second original data list I2=(C pi ,...,C pj ), Target original data list H2=(C p1 ,...,C p(i-1) C p(i+1) ,...,C pj ); Step S005: Based on the target validation data list H1 and the target original data list H2, determine the loss function Loss1 corresponding to the first speculation model and the loss function Loss2 corresponding to the second speculation model; Where Loss1=dist(H1,H2)+|E pi -F pi | / C pi +dist(E,I2)+|C pi -E pi |; Loss2=dist(H1,H2)+|E pi -F pi | / C pi +dist(F,I1)+|C pi -F pi |; In the formula, dist() is a preset Euclidean distance calculation function.

[0027] dist(H1,H2)+|E pi -F pi | / C pi Let dist(E,I2)+|C be the joint loss function of the first and second prediction models. pi -E pi | represents the single loss function of the first inference model, dist(F,I1)+|C pi -F pi| is the single loss function of the second speculation model. By determining the joint loss function and the single loss function of the first speculation model and the second speculation model, and by training the first speculation model and the second speculation model with samples based on the same set of historical running data, the first speculation model and the second speculation model are jointly and synchronously trained so that the obtained first speculation model and the second speculation model can influence each other, thereby improving the accuracy of the obtained first speculation data and second speculation data.

[0028] Step S400: Determine the target predicted data corresponding to any running data based on the first predicted data and the second predicted data corresponding to any running data. Furthermore, step S400 includes steps S410-S430: Step S410, according to B m(i+1) ,...,B mj and A m(i+1) ,...,A mj The first predicted coefficient D1 was determined to be (∑ j g=i+1 (B mg -A mg ) 2 ) 1 / 2 ; Step S420, according to C m1 ,...,C m(i-1) and A m1 ,...,A m(i-1) The second predicted coefficient D2 was determined to be (∑ i-1 g=1 (C mg -A mg ) 2 ) 1 / 2 ; Step S430: Determine A based on the first prediction coefficient D1 and the second prediction coefficient D2. mi Corresponding target prediction data T mi =(D1 / (D1+D2))×B mi +(D2 / (D1+D2))×C mi .

[0029] The target inferred data is determined by comprehensively processing the first and second inferred data. It is determined by comprehensively judging the operational data that is related to it (i.e., operational data at the same detection location in the same time period) so that the determined target inferred data can better reflect the authenticity of the corresponding operational data.

[0030] Step S500: If the difference between any running data and the target inferred data corresponding to the running data is greater than a preset data difference threshold, then in the running data list where the running data is located, the running data is replaced with the target inferred data corresponding to the running data. Furthermore, step S500 includes step S510: Step S510, Traverse A m For each running data, if |A mi -T mi |>G, then A m A in mi Replace with T mi Where G is the preset data difference threshold.

[0031] If the difference between any running data and the corresponding target inferred data is greater than a preset data difference threshold, it indicates that the running data may be abnormal (this abnormality does not refer to data abnormality, but rather to an anomaly that may be caused by the running data being abruptly or suddenly changing, leading to false alarms in subsequent running detection results). Therefore, in order to make the detection results of the subsequently determined running status more accurate, the corresponding target inferred data is replaced with the running data so that the running data can better reflect the normal detection data before the detection anomaly occurs.

[0032] Step S600: Input each running data list into the preset state detection model to obtain the running status of each detection position of the oil-free air compressor within the target time period; The state detection model is trained based on historical operating data of the oil-free air compressor over a historical period. Specifically, the state detection model is determined according to steps S601-S602: Step S601: Obtain the status identifier N corresponding to the operating status of the oil-free air compressor in the p-th historical time period. p ; Step S602, C p As input samples, N p As output labels, supervised training is performed on a pre-defined neural network model to obtain a state detection model.

[0033] Each running data list is input into a preset state detection model. The state detection model will output a state identifier corresponding to each running data list. The running state corresponding to this state identifier is the running state of the detection position corresponding to that running data list within the target time period.

[0034] The oil-free air compressor operating status detection method of the present invention first determines an operating data list corresponding to each detection position based on several operating data corresponding to each detection position of the oil-free air compressor within a target time period. Then, it performs data estimation processing on several operating data preceding any given operating data in each operating data list to obtain first estimated data corresponding to that operating data and several operating data following it. It also performs data estimation processing on several operating data following any given operating data in each operating data list to obtain second estimated data corresponding to that operating data and several operating data preceding it. Finally, based on the first and second estimated data corresponding to any given operating data, it determines the target estimated data corresponding to that operating data. The target inferred data is the data that is comprehensively inferred from other related operational data. If the difference between any operational data and the target inferred data corresponding to that operational data is greater than a preset data difference threshold, it indicates that the operational data may be abnormal, there may be a detection problem, or a momentary change has occurred. In this case, the operational data in the operational data list is replaced with the target inferred data corresponding to that operational data, so that the operational data tends to be the data for normal detection. Each operational data list is then input into the state detection model to obtain the operational status of each detection position of the oil-free air compressor within the target time period, so that the detection results of the operational status of the oil-free air compressor obtained by the state detection model are more accurate and the possibility of false alarms is reduced.

[0035] Embodiments of the present invention also provide a computer program product including program code, which, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described above in various exemplary embodiments of the present invention.

[0036] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0037] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0038] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0039] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as “circuit,” “module,” or “system.”

[0040] An electronic device according to this embodiment of the invention. The electronic device is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the invention.

[0041] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).

[0042] The storage device stores program code that can be executed by the processor to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of the present invention.

[0043] The storage may include readable media in the form of volatile storage, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0044] The storage may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more applications, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0045] A bus can represent one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus architectures.

[0046] Electronic devices can also communicate with one or more external devices (such as keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable users to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (such as routers, modems, etc.). This communication can be performed through input / output (I / O) interfaces. Furthermore, electronic devices can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapters.

[0047] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0048] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the invention described in the "Exemplary Methods" section of this specification.

[0049] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0050] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0051] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0052] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0053] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0054] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0055] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for detecting the operating status of an oil-free air compressor, characterized in that, include: Step S100: Based on several operating data corresponding to each detection position of the oil-free air compressor within the target time period, determine the operating data list corresponding to each detection position; the duration of the target time period is a preset duration, and the end time of the target time period is the current time; Step S200: Perform data estimation processing on several running data preceding any running data in each of the running data lists to obtain the running data and the first estimated data corresponding to several running data following the running data; Step S300: Perform data estimation processing on several running data following any running data in each of the running data lists to obtain the running data and the second estimated data corresponding to the running data and several running data preceding the running data. Step S400: Determine the target predicted data corresponding to any of the running data based on the first predicted data and the second predicted data corresponding to the running data; Step S500: If the difference between any of the running data and the target inferred data corresponding to the running data is greater than a preset data difference threshold, then the running data in the running data list where the running data is located is replaced with the target inferred data corresponding to the running data. Step S600: Input each of the aforementioned operating data lists into the preset state detection model to obtain the operating state of each detection position of the oil-free air compressor within the target time period; The state detection model is obtained by training on several historical operating data of the oil-free air compressor within a historical time period.

2. The method according to claim 1, characterized in that, Step S100 includes: Step S110: Obtain several operating data points corresponding to each detection position of the oil-free air compressor within the target time period to obtain several operating data lists A1, A2, ..., A m ,...,A n Where m = 1, 2, ..., n; n is the number of detection positions of the oil-free air compressor; A m This is a list of operating data corresponding to the m-th detection position of the oil-free air compressor within the target time period; A m =(A m1 A m2 ,...,A mi ,...,A mj ); i = 1, 2, ..., j; j is the number of data collection times included in the target time period; A mi The data refers to the operating data of the m-th detection position of the oil-free air compressor at the i-th data acquisition time within the target time period.

3. The method according to claim 2, characterized in that, Step S200 includes: Step S210, A m1 ,...,A m(i-1) The input is fed into a preset first inference model to obtain the B output by the first inference model. mi ,...,B mj B mi For A mi The corresponding first inferred data; The first inference model is determined according to the following steps: Step S211: Obtain several historical operating data corresponding to several detection positions of the oil-free air compressor within several historical time periods, so as to obtain several historical operating data lists C1, C2, ..., C p ,...,C q Where p = 1, 2, ..., q; q is the number of historical time periods; the duration of each historical time period is equal to the duration of the target time period; the end time of each historical time period is before the start time of the target time period; the number of data collection moments included in each historical time period is equal to the number of data collection moments included in the target time period, and the duration between two adjacent data collection moments included in each historical time period is equal to the duration between two corresponding data collection moments included in the target time period; C p This is a list of historical operating data for the oil-free air compressor during the p-th historical time period. C p =(C p1 C p2 ,...,C pi ,...,C pj ); C pi The data represents the historical operating data of the oil-free air compressor at the i-th data acquisition time in the p-th historical time period. Step S212, C p1 To C p(i-1) As input sample, C pi To C pj As the output label, a pre-defined neural network model is subjected to supervised training to obtain the first inference model.

4. The method according to claim 3, characterized in that, Step S300 includes: Step S310, Place A m(i+1) ,...,A mj The input is fed into a preset second prediction model to obtain the C output by the second prediction model. m1 ,...,C mi C mi For A mi The corresponding second inferred data; The second inference model is determined according to the following steps: Step S311, place C p(i+1) To C pj As input sample, C p1 To C pi As the output label, a pre-defined neural network model is subjected to supervised training to obtain a second inference model.

5. The method according to claim 4, characterized in that, The loss functions of the first prediction model and the second prediction model are determined according to the following steps: Step S001, C p1 ,...,C p(i-1) The data is input into the first inference model to obtain the first verification data list E = (E... pi ,...,E pj ); where E pi C pi The corresponding first verification data; Step S002, C p(i+1) ,...,C pj The data is input into the second inference model to obtain the second verification data list F = (F... p1 ,...,F pi ); where F pi C pi The corresponding second verification data; Step S003: Based on the first verification data list E and the second verification data list F, obtain the target verification data list H1 = (F p1 ,...,F p(i-1) E p(i+1) ,...,E pj ); Step S004, according to C p The first original data list I1=(C) is obtained. p1 ,...,C pi ), Second original data list I2=(C pi ,...,C pj ), Target original data list H2=(C p1 ,...,C p(i-1) C p(i+1) ,...,C pj ); Step S005: Based on the target verification data list H1 and the target original data list H2, determine the loss function Loss1 corresponding to the first inference model and the loss function Loss2 corresponding to the second inference model; Where Loss1=dist(H1,H2)+|E pi -F pi | / C pi +dist(E,I2)+|C pi -E pi |; Loss2=dist(H1,H2)+|E pi -F pi | / C pi +dist(F,I1)+|C pi -F pi |; In the formula, dist() is a preset Euclidean distance calculation function.

6. The method according to claim 5, characterized in that, Step S400 includes: Step S410, according to B m(i+1) ,...,B mj and A m(i+1) ,...,A mj The first predicted coefficient D1 was determined to be (∑ j g=i+1 (B mg -A mg ) 2 ) 1 / 2 Step S420, according to C m1 ,...,C m(i-1) and A m1 ,...,A m(i-1) The second predicted coefficient D2 was determined to be (∑ i-1 g=1 (C mg -A mg ) 2 ) 1 / 2 Step S430: Determine A based on the first prediction coefficient D1 and the second prediction coefficient D2. mi Corresponding target prediction data T mi =(D1 / (D1+D2))×B mi +(D2 / (D1+D2))×C mi .

7. The method according to claim 6, characterized in that, Step S500 includes: Step S510, Traverse A m For each running data, if |A mi -T mi |>G, then A m A in mi Replace with T mi Where G is the preset data difference threshold.

8. The method according to claim 7, characterized in that, The state detection model is determined according to the following steps: Step S601: Obtain the status identifier N corresponding to the operating status of the oil-free air compressor in the p-th historical time period. p ; Step S602, C p As input samples, N p As output labels, supervised training is performed on a pre-defined neural network model to obtain a state detection model.

9. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores at least one instruction or at least one program segment, characterized in that the at least one instruction or the at least one program segment is loaded and executed by a processor to implement the method as described in any one of claims 1-8.

10. An electronic device, characterized in that, Includes a processor and the non-transitory computer-readable storage medium as described in claim 9.

Images