Method and device for determining oxidation resistance, storage medium, electronic device and computer program product

The characteristic band data of lubricant oil is obtained through infrared spectrometer and analyzed using backpropagation neural network, which solves the problem of detecting the anti-oxidation properties of lubricant oil, and achieves efficient and accurate detection of lubricant oil performance.

CN118914124APending Publication Date: 2024-11-08HUANENG RENEWABLES CORPORATION LIMITED +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410961061.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The prior art cannot effectively detect the oxidation resistance of lubricating oil, resulting in increased oil viscosity, formation of non-oil-soluble polymers, and blockage of the engine system due to sediments.

Method used

The lubricant is scanned by infrared spectrometer, and the characteristic band data of the oxide is obtained, and the backpropagation neural network is used for analysis to determine the oxidation resistance of the lubricant.

Benefits of technology

It realizes accurate and efficient detection of the oxidation resistance of lubricant oil, solves the problem of not being able to better detect the oxidation resistance of lubricant oil, and improves the efficiency and accuracy of lubricant performance detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118914124A_ABST
    Figure CN118914124A_ABST
Patent Text Reader

Abstract

The invention discloses an oxidation resistance determination method and device, a storage medium, an electronic device and a computer program product, and relates to the field of computers.The oxidation resistance determination method comprises the steps that target lubricating oil is scanned through an infrared spectrometer, and a target infrared spectrogram is obtained; determining target characteristic wave band data of a target oxide from the target infrared spectrogram; the target characteristic wave band data are input into a target back-propagation neural network, the oxidation resistance of the target lubricating oil is obtained, the target back-propagation neural network is used for determining the oxidation resistance of the lubricating oil according to the characteristic wave band data of target oxide in the lubricating oil, and the lubricating oil comprises the target lubricating oil. The characteristic wave band data comprises the target characteristic wave band data. By adopting the technical scheme, the problem that the oxidation resistance of the lubricating oil cannot be well detected is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computers, and more specifically, to a method and device for determining antioxidant properties, a storage medium, an electronic device, and a computer program product. Background Art

[0002] Gearbox is an important transmission equipment of wind turbine. Most of them use gear lubricant as lubricant of gearbox. However, when the gearbox is working, the oil temperature in the oil tank is very high, and the lubricant is easy to oxidize. At the same time, accompanied by gear stirring, wear catalysis, water and impurities, the oxidation process of lubricant is further accelerated. In addition, there are many extreme pressure agents in lubricant, and the thermal oxidation stability is poor. It is easy to decompose or condense at high temperature, which increases the acid value corrosiveness and viscosity, reduces the cooling effect, and leads to the formation of sludge or precipitation, affecting the performance of lubricant. After the lubricant is oxidized, it will cause many problems, such as the increase of oil viscosity, the formation of paint film and sediment by non-oil-soluble polymers, and the blockage of engine system. Therefore, the lubricant should have good antioxidant ability.

[0003] In the related technologies, methods for evaluating the antioxidant properties of lubricating oils include the rotating oxygen bomb method, the high-pressure differential scanning calorimetry rapid experimental method and the infrared spectroscopy method, but most of the methods for detecting the antioxidant properties of lubricating oils have shortcomings such as long analysis cycles and cumbersome operation processes. Although the infrared spectroscopy method can identify the molecular structure of unknown substances or determine their chemical groups, and can also perform quantitative analysis and purity identification, due to the complex composition structure of lubricating oils, it is difficult for infrared spectroscopy technology to directly measure the antioxidant content in lubricating oils.

[0004] With regard to the problem in related technologies that the oxidation resistance of lubricating oil cannot be properly detected, no effective solution has been proposed so far.

[0005] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0006] The embodiments of the present application provide a method and device for determining antioxidant properties, a storage medium, an electronic device, and a computer program product to at least solve the problem of being unable to better detect the antioxidant properties of lubricating oil.

[0007] According to one aspect of an embodiment of the present application, a method for determining antioxidant properties is provided, comprising: scanning a target lubricant through an infrared spectrometer to obtain a target infrared spectrum; determining target characteristic band data of a target oxide from the target infrared spectrum; inputting the target characteristic band data into a target back propagation neural network to obtain the antioxidant properties of the target lubricant, wherein the target back propagation neural network is used to determine the antioxidant properties of the lubricant based on the characteristic band data of the target oxide in the lubricant, the lubricant includes the target lubricant, and the characteristic band data includes the target characteristic band data.

[0008] In an exemplary embodiment, before inputting the target characteristic band data into the target back propagation neural network, the method further includes: obtaining a training sample set, wherein each training sample in the training sample set includes: sample characteristic band data of target oxides in sample lubricating oil, sample antioxidant properties of the sample lubricating oil; using the training sample set to train the back propagation neural network to be trained until the value of the target loss function corresponding to the back propagation neural network to be trained meets a preset convergence condition, and determining the back propagation neural network to be trained at the end of the training as the target back propagation neural network, wherein, when the value of the target loss function does not meet the preset convergence condition, the parameters in the back propagation neural network to be trained are adjusted.

[0009] In an exemplary embodiment, the back propagation neural network to be trained is trained using the training sample set, comprising: performing the i-th round of training through the following steps, wherein i is a positive integer greater than or equal to 1, and the back propagation neural network that has undergone the 0th round of training is the untrained back propagation neural network to be trained; obtaining the training samples used in the i-th round from the training sample set, wherein the training samples used in the i-th round include the sample characteristic band data used in the i-th round, and the sample antioxidant properties corresponding to the sample characteristic band data used in the i-th round; inputting the sample characteristic band data used in the i-th round into the i-th round of training; In the back-propagation neural network obtained by the i-th round of training, the target antioxidant property obtained by the i-th round of training is obtained; the value of the target loss function of the i-th round of training is determined according to the sample antioxidant property corresponding to the sample characteristic band data used in the i-th round and the target antioxidant property obtained by the i-th round of training; when the value of the target loss function of the i-th round of training meets the preset convergence condition, the training is terminated; when the value of the target loss function of the i-th round of training does not meet the preset convergence condition, the parameters in the back-propagation neural network obtained by the i-1-th round of training are adjusted to obtain the back-propagation neural network obtained by the i-th round of training.

[0010] In an exemplary embodiment, the method further includes: determining the sample antioxidant property of the sample lubricant by: determining the rotational oxygen-nitrogen value of the sample lubricant by a target detection method; and determining the sample antioxidant property of the sample lubricant according to the rotational oxygen-nitrogen value.

[0011] In an exemplary embodiment, the back propagation neural network has an input layer, a hidden layer and an output layer, the number of neurons in the input layer is determined according to the sample characteristic band data, the number of neurons in the output layer is equal to 1, and the number of neurons in the hidden layer is equal to m is the number of neurons in the input layer.

[0012] In an exemplary embodiment, the target oxide includes at least one of the following: alcohol, aldehyde, ketone, acid, ester.

[0013] According to another aspect of an embodiment of the present application, there is also provided an antioxidant determination device, comprising: a scanning module, used to scan a target lubricant through an infrared spectrometer to obtain a target infrared spectrum; a first determination module, used to determine target characteristic band data of a target oxide from the target infrared spectrum; an input module, used to input the target characteristic band data into a target back propagation neural network to obtain the antioxidant property of the target lubricant, wherein the target back propagation neural network is used to determine the antioxidant property of the lubricant based on the characteristic band data of the target oxide in the lubricant, the lubricant includes the target lubricant, and the characteristic band data includes the target characteristic band data.

[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein the program is configured to execute the above-mentioned antioxidant determination method when running.

[0015] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, wherein the processor is configured to execute the above-mentioned antioxidant determination method through the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method for determining antioxidant properties is implemented.

[0017] The present application, based on a target back-propagation neural network, uses the target characteristic band data of the target oxide in the infrared spectrum of the lubricant to determine the antioxidant property of the lubricant, thereby accurately and efficiently determining the antioxidant property of the lubricant, solving the problem of being unable to better detect the antioxidant property of the lubricant. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 It is a hardware structure block diagram of a mobile terminal of a method for determining antioxidant properties according to an embodiment of the present application;

[0021] Figure 2 is a flow chart of a method for determining antioxidant properties according to an embodiment of the present application;

[0022] Figure 3 is an overall flow chart of a method for determining antioxidant properties according to an embodiment of the present application;

[0023] Figure 4 It is a structural block diagram of an antioxidant determination device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a method for determining antioxidant properties according to an embodiment of the present application. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor (MP) or a programmable logic device (FPGA)) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for detecting pneumatic imbalance in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0028] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] In order to solve the above problems, a method for determining antioxidant properties is provided in this embodiment, including but not limited to being applied to the above mobile terminal. Figure 2 is a flow chart of a method for determining antioxidant properties according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps S202-S206:

[0030] Step S202: scanning the target lubricating oil by an infrared spectrometer to obtain a target infrared spectrum;

[0031] It should be noted that the target infrared spectrum includes full-band data.

[0032] It should be noted that infrared spectroscopy can not only identify the molecular structure of unknown substances or determine their chemical groups, but also perform quantitative analysis and purity identification. Moreover, the detection process is not limited by the phase state of the sample, and can directly measure solid, liquid or gaseous samples. Infrared spectroscopy requires less sample volume, has a fast analysis speed and is easy to operate. Therefore, in the detection of the antioxidant properties of lubricating oils, the antioxidant properties of the target lubricating oils can be analyzed by measuring the content of antioxidants in the lubricating oils by infrared spectroscopy.

[0033] Step S204: determining target characteristic band data of the target oxide from the target infrared spectrum;

[0034] In an exemplary embodiment, the target oxide includes at least one of the following: alcohol, aldehyde, ketone, acid, ester.

[0035] Optionally, the wavelength corresponding to the target characteristic band data is 1000-1800, and the corresponding peak is a dense peak in the target infrared spectrum.

[0036] Step S206: Input the target characteristic band data into the target back propagation neural network to obtain the antioxidant property of the target lubricant, wherein the target back propagation neural network is used to determine the antioxidant property of the lubricant based on the characteristic band data of the target oxide in the lubricant, the lubricant includes the target lubricant, and the characteristic band data includes the target characteristic band data.

[0037] The above steps, based on the target back propagation neural network, use the target characteristic band data of the target oxide in the infrared spectrum of the lubricant to determine the antioxidant property of the lubricant, and then accurately and efficiently determine the antioxidant property of the lubricant, solving the problem of being unable to better detect the antioxidant property of the lubricant.

[0038] In an exemplary embodiment, before the above step S206, the method further includes the following steps S11-S12:

[0039] Step S11: obtaining a training sample set, wherein each training sample in the training sample set includes: sample characteristic band data of target oxides in sample lubricating oil, and sample antioxidant properties of the sample lubricating oil;

[0040] Optionally, a sample lubricating oil is extracted from a gearbox that has been used for a certain period of time, and characteristic band data of a target oxide in the sample lubricating oil is determined, and the obtained characteristic band data is used as the sample characteristic band data.

[0041] In an exemplary embodiment, the method further includes: determining the sample antioxidant property of the sample lubricant by: determining the rotational oxygen-nitrogen value of the sample lubricant by a target detection method; and determining the sample antioxidant property of the sample lubricant according to the rotational oxygen-nitrogen value.

[0042] Optionally, the sample lubricating oil is placed in a rotational oxygen-nitrogen value tester for testing to measure its rotational oxygen-nitrogen value, and then the sample antioxidant property of the sample lubricating oil can be determined based on the rotational oxygen-nitrogen value.

[0043] It should be noted that the rotational oxygen-nitrogen value is an important indicator to measure the antioxidant properties of lubricants. It indicates the amount of oxygen-nitrogen compounds that the lubricant can withstand when it is oxidized. The antioxidant properties of the sample lubricant can be judged based on the obtained rotational oxygen-nitrogen value. The higher the rotational oxygen-nitrogen value, the better the antioxidant properties of the lubricant, and the ability to maintain its performance stability for a longer period of time during use, thereby extending the service life of the lubricant.

[0044] It should be noted that due to the influence of tester errors, drastic environmental changes, etc., certain data deviations are likely to occur. Abnormal data points with obvious large deviations must be removed, and the training sample set must be initialized with the initial error set to 0.

[0045] Step S12: using the training sample set to train the back propagation neural network to be trained until the value of the target loss function corresponding to the back propagation neural network to be trained meets the preset convergence condition, and determining the back propagation neural network to be trained at the end of the training as the target back propagation neural network, wherein, when the value of the target loss function does not meet the preset convergence condition, the parameters in the back propagation neural network to be trained are adjusted.

[0046] It should be noted that the topological structure of the back propagation neural network (BP neural network for short) includes an input layer, an output layer and a hidden layer.

[0047] In an exemplary embodiment, the back propagation neural network has an input layer, a hidden layer and an output layer, the number of neurons in the input layer is determined according to the sample characteristic band data, the number of neurons in the output layer is equal to 1, and the number of neurons in the hidden layer is equal to m is the number of neurons in the input layer.

[0048] In an exemplary embodiment, the step S12 includes: performing the i-th round of training through the following steps S21-S24, wherein i is a positive integer greater than or equal to 1, and the back propagation neural network trained in the 0th round is the untrained back propagation neural network to be trained:

[0049] Step S21: acquiring the training sample used in the i-th round from the training sample set, wherein the training sample used in the i-th round includes the sample characteristic band data used in the i-th round, and the sample antioxidant properties corresponding to the sample characteristic band data used in the i-th round;

[0050] Step S22: inputting the sample characteristic band data used in the i-th round into the back propagation neural network obtained through the i-1-th round of training to obtain the target antioxidant capacity obtained through the i-th round of training;

[0051] Optionally, the sample characteristic band data used in the i-th round is input into the hidden layer of the back propagation neural network obtained through the i-1-th round of training through the input layer, and the corresponding target antioxidant capacity is obtained by activating the transfer function of each layer. The number of neurons in the hidden layer is related to the number of neurons in the input layer and the output layer. The formula is as follows:

[0052]

[0053] Here, k is the number of neurons in the hidden layer, m is the number of neurons in the input layer, and n is the number of neurons in the output layer.

[0054] Optionally, in the embodiment of the present application, the back propagation neural network is connected to the external data through the input layer, and the number of neurons in the input layer is determined by the dimension of the input vector, that is, the number of neurons in the input layer is determined according to the sample characteristic band data in the training sample set. The output layer is the target antioxidant property of the sample lubricant, and the number of neurons in the output layer is 1.

[0055] Optionally, the information of the output layer of the back propagation neural network (i.e., the target antioxidant property of the sample lubricant) needs to be calculated through the information of the input layer (i.e., the sample characteristic band data) through a transfer function. In the embodiment of the present application, a Sigmoid function is used:

[0056] The analytical expression of the transfer function of the input layer is:

[0057]

[0058] The analytical expression of the transfer function of the output layer is:

[0059] f(x) = x;

[0060] Step S23: determining the value of the target loss function of the i-th round of training according to the sample antioxidant capacity corresponding to the sample characteristic band data used in the i-th round and the target antioxidant capacity obtained by the i-th round of training;

[0061] Step S24: When the value of the target loss function in the i-th round of training meets the preset convergence condition, the training is terminated; when the value of the target loss function in the i-th round of training does not meet the preset convergence condition, the parameters in the back propagation neural network obtained after the i-1-th round of training are adjusted to obtain the back propagation neural network obtained after the i-th round of training.

[0062] Optionally, during the back-propagation process of the back-propagation neural network, the gradient of the loss function with respect to each weight is calculated, and then the weights in the network are updated according to the principle of gradient descent to reduce the value of the loss function.

[0063] Optionally, when the value E of the objective loss function is less than the preset error value 10 -6 When the training is finished.

[0064] Optionally, the performance of the back propagation neural network can be evaluated by cross-validation. In each validation, a subset of the training sample set is selected as the test set, and the remaining subsets are used as the training sample set. The accuracy, standard deviation and other indicators on the test set are calculated to evaluate the diagnostic performance of the back propagation neural network.

[0065] Optionally, once the back propagation neural network training is completed, it can be used for actual antioxidant detection tasks. For new test samples, the same feature band data extraction process as in the training phase is first performed, and then the trained back propagation neural network is used to predict the antioxidant properties of the sample.

[0066] Obviously, the above-described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. In order to better understand the above method, the above process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present invention. Figure 3 The overall flow chart of a method for determining antioxidant properties of an embodiment of the application is shown, specifically:

[0067] 1. For the lubricating oil sample to be tested, an infrared spectrometer is used to test it and obtain the full-band information in the infrared spectrum;

[0068] 2. Select characteristic spectral points of antioxidants and establish a database, and remove outliers in the data set through data cleaning;

[0069] Optionally, characteristic band data of a certain oxidation product of the gearbox lubricating oil (i.e., the above-mentioned target oxide) can be extracted for analysis, and the anti-oxidation performance of the oil can be judged by the content of the oxidation product of the lubricating oil, thereby establishing a characteristic spectral point database (i.e., the above-mentioned training sample set);

[0070] 3. After preprocessing the data, create a large number of training samples and a small number of test samples;

[0071] 4. Input the training samples into the BP neural network (i.e. the above-mentioned back propagation neural network) through the input layer, and obtain the corresponding predicted output value (i.e. the above-mentioned target antioxidant property) by activating the transfer function of each layer;

[0072] 5. Calculate the error E by subtracting the expected value set from the predicted value obtained in step 4;

[0073] 6. If the error accuracy does not reach the preset value, the required error value is transmitted to the neurons of each layer in the reverse direction to modify the corresponding weights and thresholds, and then return to step 4 to repeat the training;

[0074] 7. If the error accuracy reaches the preset value, the neural network training is terminated.

[0075] It should be noted that the effectiveness and accuracy of the method can be further evaluated based on the validation samples.

[0076] It should be noted that this application also has the following advantages:

[0077] 1. Under the premise of knowing the types of antioxidants, the BP neural network algorithm is used to measure the content of a certain oxidation product in the gear oil in use to evaluate the antioxidant performance of the oil. The BP neural network can learn and store a large number of input-output pattern mapping relationships, and has good nonlinear modeling, function approximation pattern classification and other capabilities. By learning the training sample set, it can well reflect the complex nonlinear relationship between the input and output of the object, that is, it can better reflect the antioxidant properties of the sample lubricant, and improve the accuracy of the antioxidant detection of the lubricant.

[0078] 2. By analyzing the changes in the content of oxidation products generated during the oxidation process of the gear oil in use, and establishing a functional relationship between the content of lubricant oxidation products and the anti-oxidation property of the lubricant, it is possible to quantitatively judge the changes in the anti-oxidation performance of the oil, effectively grasp the health status of the lubricant in the gearbox of the wind turbine, improve the efficiency of the anti-oxidation detection of the lubricant, and facilitate the staff to replace the lubricant in the gearbox in real time, so as to maximize the economic benefits.

[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0080] In this embodiment, a device for determining antioxidant properties is also provided, which is used to implement the above embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0081] Figure 4 : is a structural block diagram of a device for determining antioxidant properties according to an embodiment of the present application, the device comprising:

[0082] A scanning module 402 is used to scan the target lubricating oil through an infrared spectrometer to obtain a target infrared spectrum;

[0083] A first determination module 404 is used to determine target characteristic band data of a target oxide from the target infrared spectrum;

[0084] The input module 406 is used to input the target characteristic band data into the target back propagation neural network to obtain the antioxidant property of the target lubricant, wherein the target back propagation neural network is used to determine the antioxidant property of the lubricant based on the characteristic band data of the target oxide in the lubricant, the lubricant includes the target lubricant, and the characteristic band data includes the target characteristic band data.

[0085] The above-mentioned device, based on the target back-propagation neural network, uses the target characteristic band data of the target oxide in the infrared spectrum of the lubricating oil to determine the antioxidant property of the lubricating oil, and can then accurately and efficiently determine the antioxidant property of the lubricating oil, thus solving the problem of being unable to better detect the antioxidant property of the lubricating oil.

[0086] In an exemplary embodiment, the above-mentioned device also includes: an acquisition module, which is used to acquire a training sample set before inputting the target characteristic band data into the target back propagation neural network, wherein each training sample in the training sample set includes: sample characteristic band data of target oxides in sample lubricating oil, sample antioxidant properties of the sample lubricating oil; a training module, which is used to use the training sample set to train the back propagation neural network to be trained until the value of the target loss function corresponding to the back propagation neural network to be trained meets the preset convergence condition, and the back propagation neural network to be trained at the end of training is determined as the target back propagation neural network, wherein, when the value of the target loss function does not meet the preset convergence condition, the parameters in the back propagation neural network to be trained are adjusted.

[0087] In an exemplary embodiment, the training module is further used to perform the i-th round of training through the following steps, wherein i is a positive integer greater than or equal to 1, and the back propagation neural network that has undergone the 0th round of training is the untrained back propagation neural network to be trained: obtaining the training samples used in the i-th round from the training sample set, wherein the training samples used in the i-th round include the sample characteristic band data used in the i-th round, and the sample antioxidant properties corresponding to the sample characteristic band data used in the i-th round; inputting the sample characteristic band data used in the i-th round into the back propagation neural network obtained after the i-1th round of training to obtain the target antioxidant properties obtained after the i-th round of training; determining the value of the target loss function of the i-th round of training according to the sample antioxidant properties corresponding to the sample characteristic band data used in the i-th round and the target antioxidant properties obtained after the i-th round of training; terminating the training if the value of the target loss function of the i-th round of training meets the preset convergence condition; adjusting the parameters in the back propagation neural network obtained after the i-1th round of training if the value of the target loss function of the i-th round of training does not meet the preset convergence condition to obtain the back propagation neural network obtained after the i-th round of training.

[0088] In an exemplary embodiment, the above-mentioned device also includes: a second determination module, which is used to determine the sample antioxidant property of the sample lubricant in the following manner: determining the rotational oxygen-nitrogen value of the sample lubricant through a target detection method; determining the sample antioxidant property of the sample lubricant based on the rotational oxygen-nitrogen value.

[0089] In an exemplary embodiment, the back propagation neural network has an input layer, a hidden layer and an output layer, the number of neurons in the input layer is determined according to the sample characteristic band data, the number of neurons in the output layer is equal to 1, and the number of neurons in the hidden layer is equal to m is the number of neurons in the input layer.

[0090] In an exemplary embodiment, the target oxide includes at least one of the following: alcohol, aldehyde, ketone, acid, ester.

[0091] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0092] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0093] S1, scanning the target lubricating oil by infrared spectrometer to obtain the target infrared spectrum;

[0094] S2, determining target characteristic band data of a target oxide from the target infrared spectrum;

[0095] S3, inputting the target characteristic band data into a target back propagation neural network to obtain the antioxidant property of the target lubricant, wherein the target back propagation neural network is used to determine the antioxidant property of the lubricant based on the characteristic band data of the target oxide in the lubricant, the lubricant includes the target lubricant, and the characteristic band data includes the target characteristic band data.

[0096] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0097] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0098] An embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in any one of the above method embodiments are performed.

[0099] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0100] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0101] S1, scanning the target lubricating oil by infrared spectrometer to obtain the target infrared spectrum;

[0102] S2, determining target characteristic band data of a target oxide from the target infrared spectrum;

[0103] S3, inputting the target characteristic band data into a target back propagation neural network to obtain the antioxidant property of the target lubricant, wherein the target back propagation neural network is used to determine the antioxidant property of the lubricant based on the characteristic band data of the target oxide in the lubricant, the lubricant includes the target lubricant, and the characteristic band data includes the target characteristic band data.

[0104] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0105] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0106] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0107] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining antioxidant activity, It is characterized in that include: Scanning the target lubricating oil by an infrared spectrometer to obtain a target infrared spectrum; Determining target characteristic band data of a target oxide from the target infrared spectrum; The target characteristic band data is input into a target back propagation neural network to obtain the antioxidant property of the target lubricant, wherein the target back propagation neural network is used to determine the antioxidant property of the lubricant based on the characteristic band data of the target oxide in the lubricant, the lubricant includes the target lubricant, and the characteristic band data includes the target characteristic band data.

2. The method according to claim 1, It is characterized in that Before inputting the target characteristic band data into the target back propagation neural network, the method further includes: Acquire a training sample set, wherein each training sample in the training sample set includes: sample characteristic band data of target oxides in sample lubricating oil, and sample antioxidant properties of the sample lubricating oil; The back propagation neural network to be trained is trained using the training sample set until the value of the target loss function corresponding to the back propagation neural network to be trained meets the preset convergence condition, and the back propagation neural network to be trained at the end of the training is determined as the target back propagation neural network, wherein, when the value of the target loss function does not meet the preset convergence condition, the parameters in the back propagation neural network to be trained are adjusted.

3. The method according to claim 2, It is characterized in that Using the training sample set to train the back propagation neural network to be trained includes: The i-th round of training is performed by the following steps, wherein i is a positive integer greater than or equal to 1, and the back propagation neural network that has undergone the 0th round of training is the untrained back propagation neural network to be trained: Acquire the training samples used in the i-th round from the training sample set, wherein the training samples used in the i-th round include the sample characteristic band data used in the i-th round, and the sample antioxidant properties corresponding to the sample characteristic band data used in the i-th round; Input the characteristic band data of the samples used in the i-th round into the back propagation neural network trained in the i-1th round to obtain the target antioxidant activity obtained in the i-th round of training; Determine the value of the target loss function of the i-th round of training according to the sample antioxidant capacity corresponding to the sample characteristic band data used in the i-th round and the target antioxidant capacity obtained in the i-th round of training; When the value of the target loss function in the i-th round of training meets the preset convergence condition, the training is terminated; when the value of the target loss function in the i-th round of training does not meet the preset convergence condition, the parameters in the back-propagation neural network obtained after the i-1-th round of training are adjusted to obtain the back-propagation neural network obtained after the i-th round of training.

4. The method according to claim 2, It is characterized in that The method further comprises: The sample oxidation resistance of the sample lubricating oil was determined by: Determining the rotational oxygen and nitrogen value of the sample lubricating oil by a target detection method; The sample anti-oxidation property of the sample lubricating oil is determined according to the rotational oxygen and nitrogen value.

5. The method according to claim 2, It is characterized in that The back propagation neural network has an input layer, a hidden layer and an output layer, the number of neurons in the input layer is determined according to the sample characteristic band data, the number of neurons in the output layer is equal to 1, and the number of neurons in the hidden layer is equal to m is the number of neurons in the input layer.

6. The method according to claim 1, It is characterized in that The target oxide includes at least one of the following: alcohol, aldehyde, ketone, acid, and ester.

7. A device for determining antioxidant properties, It is characterized in that include: A scanning module is used to scan the target lubricating oil through an infrared spectrometer to obtain a target infrared spectrum; A first determination module is used to determine target characteristic band data of a target oxide from the target infrared spectrum; An input module is used to input the target characteristic band data into a target back propagation neural network to obtain the antioxidant property of the target lubricant, wherein the target back propagation neural network is used to determine the antioxidant property of the lubricant based on the characteristic band data of the target oxide in the lubricant, the lubricant includes the target lubricant, and the characteristic band data includes the target characteristic band data.

8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 6 when executed.

9. An electronic device comprising a memory and a processor, It is characterized in that A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.