Compressor lubrication state detection method and system, medium and program product

Abstract

The invention provides a compressor lubrication state detection method and system, a medium and a program product. The detection method comprises the following steps: acquiring a real-time sampling image of the window; determining oil level state information of the lubricating oil based on the real-time sampling image; determining a target image recognition model based on the fluctuation state information or the foam interference information of the oil surface; inputting the real-time sampling image of the window into the target image recognition model to obtain target oil level data of the compressor; and lubricating state information of the compressor is obtained based on the target oil level data. By eliminating interference factors in a sampling environment, determining an image recognition model matched with oil level state information and inputting an accurate real-time sampling image into the image recognition model, an accurate recognition result of the lubricating oil level in the real-time sampling image is obtained, corresponding target oil level data is obtained, and accurate detection of the lubricating state of the compressor is achieved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of compressor operating condition evaluation, and in particular to a method, system, compressor, medium and program product for detecting the lubrication state of a compressor. Background Art

[0002] Among the reliability issues of compressor equipment operation, the wear caused by lack of oil in the friction pair of the compressor is one of the most common reliability issues. Among them, the rolling rotor compressor relies on pressure difference and centrifugal action to supply oil, and the oil level has an important influence on the lubrication and heat dissipation of the whole machine. When the lubricating oil level is low, the friction pair may be partially lacking in oil, thus affecting the reliability of the compressor operation. Therefore, a window is usually opened at a specific position of the compressor to judge the lubrication status of the compressor by observing the oil level status and oil level height under different working conditions.

[0003] At present, the evaluation of the oil supply and lubrication status of the compressor through oil level observation test is an essential evaluation link in compressor development and one of the common means of compressor fault troubleshooting. However, the existing oil level observation test can only rely on manual recording of oil level height and status. The stability of manually recorded data is poor, and the data is difficult to quantify. It is difficult to achieve real-time correlation between oil level height and operating parameters such as temperature, pressure, and power, and lacks multi-dimensional judgment of the actual oil supply status of the compressor. Summary of the invention

[0004] The technical problem to be solved by the present disclosure is to overcome the defects of poor stability of compressor lubricating oil data and difficulty in data quantification in the prior art, and to provide a method, system, medium, equipment and program product for detecting the lubrication status of a compressor.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] In a first aspect, a method for detecting a lubrication state of a compressor is provided, wherein the compressor comprises a window, wherein the window is used to observe lubricating oil of the compressor, and the lubrication state evaluation method comprises:

[0007] Acquire a real-time sampling image of the window;

[0008] Determining the oil level status information of the lubricating oil based on the real-time sampling image;

[0009] Wherein, the oil level state information represents the fluctuation state information of the oil level or the foam interference information of the oil level;

[0010] Determining a target image recognition model based on the fluctuation state information or foam interference information of the oil surface;

[0011] Inputting the real-time sampling image of the window into the target image recognition model to obtain the target oil level data of the compressor;

[0012] Lubrication status information of the compressor is obtained based on the target oil level data.

[0013] Preferably, the step of determining the target image recognition model based on the oil surface fluctuation state information or foam interference information comprises:

[0014] In response to the fluctuation state information meeting the liquid level fluctuation abnormality condition, determining a first image recognition model as the target image recognition model;

[0015] Wherein, the first image recognition model is used to identify the liquid level of the lubricating oil from the dynamic liquid surface image;

[0016] or,

[0017] In response to the foam interference information meeting the oil surface foam abnormality condition, determining a second image recognition model as the target image recognition model;

[0018] The second image recognition model is used to distinguish oil from foam in an image and identify the liquid level of the lubricating oil.

[0019] Preferably, the abnormal liquid level fluctuation condition includes at least one of the following conditions:

[0020] The fluctuation amplitude of the oil level is greater than or equal to the fluctuation amplitude threshold;

[0021] The fluctuation frequency of the oil level is greater than or equal to a fluctuation frequency threshold;

[0022] The abnormal oil surface foam condition includes at least one of the following conditions:

[0023] The foam area of ​​the oil surface is greater than or equal to a foam area threshold;

[0024] The foam thickness of the oil surface is greater than or equal to a foam thickness threshold.

[0025] Preferably, the step of acquiring the real-time sampling image of the window comprises:

[0026] said obtaining environmental data of said compressor;

[0027] Wherein, the environmental data is used to characterize interference information data for obtaining the lubricating oil image;

[0028] Determining corresponding image acquisition parameters based on the environmental data;

[0029] A real-time observation image of the window is acquired based on the image acquisition parameters.

[0030] Preferably, the step of obtaining the lubrication status information of the compressor based on the target oil level data comprises:

[0031] Acquiring operating data of the compressor;

[0032] Inputting the target oil level data and the operation data into a friction correlation model, and outputting a corresponding correlation coefficient of the friction pair loss of the compressor;

[0033] Wherein, the correlation coefficient corresponds one-to-one with the target oil level data or the operation data;

[0034] Lubrication status information of the compressor is obtained based on the correlation coefficient.

[0035] Preferably, the detection method further comprises:

[0036] The target oil level information, the operating data and the corresponding correlation coefficient are formed into a report image.

[0037] In a second aspect, a compressor lubrication status detection system is provided, wherein the compressor includes a window, and the window is used to observe the lubricating oil of the compressor. The lubrication status evaluation system includes a real-time image acquisition module, an oil level status determination module, an image recognition model determination module, a target oil level output module, and a lubrication status determination module:

[0038] The real-time image acquisition module is used to acquire the real-time sampling image of the window;

[0039] The oil level state determination module is used to determine the oil level state information of the lubricating oil based on the real-time sampling image;

[0040] Wherein, the oil level state information represents the fluctuation state information of the oil level or the foam interference information of the oil level;

[0041] The image recognition model determination module is used to determine the target image recognition model based on the fluctuation state information or foam interference information of the oil surface;

[0042] The target oil level output module is used to input the real-time observation image of the window into the target image recognition model to obtain the target oil level data of the compressor;

[0043] The lubrication status determination module is used to obtain the lubrication status information of the compressor based on the target oil level data.

[0044] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein when the processor executes the computer program, the method for detecting the lubrication status of the compressor as described in the first aspect is implemented.

[0045] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for detecting the lubrication status of the compressor according to the first aspect is implemented.

[0046] According to a fifth aspect, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method for detecting the lubrication status of the compressor as described in the first aspect is implemented.

[0047] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0048] The positive progressive effect of the present disclosure is that by eliminating interference factors in the sampling environment, determining an image recognition model that matches the oil level status information, inputting accurate real-time sampling images into the image recognition model, obtaining accurate recognition results of the lubricating oil level in the real-time sampling images, and obtaining corresponding target oil level data, accurate detection of the lubrication status of the compressor is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flow chart of a method for detecting the lubrication status of a compressor provided by an exemplary embodiment of the present disclosure;

[0050] Figure 2 A flowchart of step S103 in a method for detecting the lubrication status of a compressor provided by an exemplary embodiment of the present disclosure;

[0051] Figure 3 A flowchart of step S101 in a method for detecting the lubrication status of a compressor provided by an exemplary embodiment of the present disclosure;

[0052] Figure 4 A flowchart of step S105 in a method for detecting the lubrication status of a compressor provided by an exemplary embodiment of the present disclosure;

[0053] Figure 5 A module schematic diagram of a system for detecting the lubrication status of a compressor provided by an exemplary embodiment of the present disclosure;

[0054] Figure 6 A schematic diagram of the hardware structure of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0055] The present disclosure is further described below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0056] Prefixes such as "first" and "second" are used in the embodiments of the present disclosure only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present disclosure does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0057] Example 1

[0058] This embodiment provides a method for detecting the lubrication status of a compressor, wherein the compressor includes a window, and the window is used to observe the lubricating oil of the compressor, such as Figure 1 As shown, the lubrication state assessment method comprises:

[0059] S101, acquiring a real-time sampling image of the window;

[0060] S102, determining the oil level status information of the lubricating oil based on the real-time sampling image;

[0061] Wherein, the oil level state information represents the fluctuation state information of the oil level or the foam interference information of the oil level;

[0062] S103, determining a target image recognition model based on the oil surface fluctuation state information or foam interference information;

[0063] S104, inputting the real-time sampling image of the window into the target image recognition model to obtain target oil level data of the compressor;

[0064] S105. Obtain lubrication status information of the compressor based on the target oil level data.

[0065] In step S101, currently, the oil level data collection of the compressor is still manually observed, and the compressor is affected by factors such as poor ambient light, insufficient lighting, poor illumination of the observation window, and reflective background. In this embodiment, an adaptive automatic lighting device is used to adjust the environmental conditions of the compressor based on real-time monitoring of the environmental conditions of the oil level in the sight glass, eliminate interference factors in the sampling environment, and improve the accuracy of the real-time sampling image.

[0066] In step S102, while improving the accuracy of oil surface image sampling, the oil surface state is also an important factor in oil level identification, among which the liquid surface fluctuation of the oil surface and the distribution of oil and foam in the oil surface are particularly significant.

[0067] For example, when using an optical liquid level sensor, the presence of foam will interfere with the propagation path of light, thereby affecting the accurate measurement of the liquid level; for non-contact sensors such as ultrasonic and radar, foam will absorb and scatter signals, causing the signal strength to weaken or even fail to penetrate the foam layer to reach the actual liquid surface; and the presence of foam may cause the liquid level indicator to display a false liquid level.

[0068] For example, fluctuations in the liquid surface will cause fluctuations in the liquid level readings, making the image recognition measurement value unstable and difficult to obtain accurate liquid level information; fluctuations will increase the measurement error in the image recognition result, especially when the liquid level fluctuation amplitude is large, the accuracy of the measurement result will be seriously affected.

[0069] In step S103, based on the oil level status information, the pre-trained image recognition model is matched, and the parameters of the image recognition model are adaptively adjusted. Through the intelligent algorithm selection and adjustment mechanism, high-precision liquid level detection can be achieved under various complex working conditions.

[0070] In one embodiment, through machine learning and deep learning technology, historical oil level status data is used as training data to optimize the parameter selection and algorithm adjustment strategy of the image recognition model to adapt to the changing working conditions. The model can use YOLOv5 (a target detection model) model, Deep Convolutional Neural Network (DCNN) and / or RNN (Recurrent Neural Network) / LSTM (Long Short-Term Memory) model to achieve high accuracy and high stability in long-term operation.

[0071] In step S104, by eliminating interference factors in the sampling environment, an image recognition model that matches the oil level status information is determined, and the accurate real-time sampling image is input into the image recognition model to obtain an accurate recognition result of the lubricating oil level in the real-time sampling image, and obtain the corresponding target oil level data.

[0072] In step S105, the target oil level data can be used to accurately understand the state of the lubricating oil in the compressor. For example, when the lubricating oil level is too low, it is determined that the lubrication state of the compressor is abnormal.

[0073] In this scheme, by eliminating interference factors in the sampling environment, determining the image recognition model that matches the oil level status information, and inputting the accurate real-time sampling image into the image recognition model, the accurate recognition result of the lubricating oil level in the real-time sampling image is obtained, and the corresponding target oil level data is obtained, thereby realizing accurate detection of the lubrication status of the compressor.

[0074] As a feasible approach, Figure 2 As shown, step S103 includes:

[0075] S1031, in response to the fluctuation state information meeting the liquid level fluctuation abnormality condition, determining a first image recognition model as the target image recognition model;

[0076] Wherein, the first image recognition model is used to identify the liquid level of the lubricating oil from the dynamic liquid surface image;

[0077] or,

[0078] S1032, in response to the foam interference information meeting the oil surface foam abnormality condition, determining a second image recognition model as the target image recognition model;

[0079] The second image recognition model is used to distinguish oil from foam in an image and identify the liquid level of the lubricating oil.

[0080] In this solution, the fluctuation state information includes at least the fluctuation amplitude and / or fluctuation frequency of the oil level. Among them, when the fluctuation amplitude of the oil level is large, the rapid movement of the liquid surface will cause motion blur during the image acquisition process, resulting in unclear edges of the oil surface and difficulty in accurately identifying the oil level; and the fluctuation of the oil level will cause changes in the reflection and refraction paths of light, thereby affecting the brightness and color distribution of the oil surface in the image. Interfering with the image processing algorithm's recognition of the oil surface. When the fluctuation frequency of the oil level increases, high-frequency oil level fluctuations will generate noise signals, interfere with the signal processing process of the image acquisition device, and cause the quality of the acquired image to deteriorate; and when continuously acquiring oil surface images, high-frequency fluctuations will cause the oil surface position in the image sequence to change frequently, resulting in increased instability of the image sequence, affecting the accuracy of the oil level tracking and recognition algorithm based on the image sequence.

[0081] The foam interference information includes at least the foam area and / or foam thickness of the oil surface. When the foam area is large, the larger foam area will block the actual position of the oil surface, resulting in unclear boundaries of the oil surface in the image, making it difficult to accurately identify the oil level; and when the foam area is large, more complex logic is required to distinguish between the foam and the actual oil surface, increasing the difficulty and amount of calculation in image processing, and the accuracy of general image processing algorithms is difficult to guarantee; when the foam thickness is large, the thicker foam layer will absorb and scatter light, resulting in a weakening of the image signal intensity received by the sensor, thereby affecting the accurate measurement of the oil level.

[0082] For the fluctuation amplitude and frequency of the oil surface, models with strong time series analysis capabilities can be selected, such as recurrent neural networks (RNN) or long short-term memory networks (LSTM). Alternatively, based on the fact that the changes in fluctuation amplitude and frequency are dynamic processes, models such as RNN / LSTM can be used to effectively extract the dynamic characteristics of the oil surface, thereby improving the accuracy of recognition. For the recognition of foam area and thickness, convolutional neural networks (CNN), especially deep convolutional neural networks (such as YOLOv5), can be used, which can accurately identify the size, shape and distribution of foam, can adapt to complex oil surface conditions, and improve the accuracy and reliability of recognition.

[0083] In one embodiment, a scoring function of light source, working condition, and camera parameters is defined to evaluate the performance of different models under specific conditions. Specifically, L is the light source score, W is the working condition score, C is the camera parameter score, and M is the model performance score.

[0084] The light source score is based on the stability, uniformity and adaptability of the light source. A scoring coefficient is assigned to each characteristic, for example: L = 0.3 × SLS + 0.3 × SLU + 0.4 × SLA; SLS: light source stability score, full score is 10 points; SLU: light source uniformity score, full score is 10 points; SLA: light source adaptability score, full score is 10 points.

[0085] The working condition score takes into account factors such as environmental light changes, temperature and humidity, for example: W = 0.4×SWE+0.3×SWT+0.3×SWH; SWE: environmental light change score, with a full score of 10 points; SWT: temperature condition score, with a full score of 10 points; SWH: humidity condition score, with a full score of 10 points.

[0086] The camera parameter score is based on resolution, frame rate and dynamic range, for example: C = 0.4×SCR+0.3×SCF+0.3×SCD; SCR: resolution score, full score is 10 points; SCF: frame rate score, full score is 10 points; SCD: dynamic range score, full score is 10 points.

[0087] The model performance score is based on accuracy, processing speed and generalization ability, for example: M = 0.5×SMA+0.3×SMS+0.2×SMG; SMA: accuracy score, full score is 10 points; SMS: processing speed score, full score is 10 points; SMG: generalization ability score, full score is 10 points.

[0088] Let's use a specific example to explain. Assume that the compressor is in strong outdoor light. The detailed data of the implementation case is as follows:

[0089] Light source rating: stability (8 / 10), uniformity (7 / 10), adaptability (9 / 10), L=8.1.

[0090] Working condition rating: light change (6 / 10), temperature (7 / 10), humidity (8 / 10), W = 6.9.

[0091] Camera parameter scoring: resolution (9 / 10), frame rate (8 / 10), dynamic range (7 / 10), and C=8.1.

[0092] The matrix vector composed of light source, working condition and camera parameter score can be obtained as follows:

[0093]

[0094] Assume that the historical detection environment light source, working conditions, and camera parameter scoring matrix are as follows:

[0095]

[0096] In scenario B, the performance score of model 1 is M1 = 8.8, the performance score of model 2 is M2 = 8.0, and the performance score of model 3 is M3 = 7.

[0097] In scenario C, the performance score of model 1 is M1 = 7.8, the performance score of model 2 is M2 = 7.0, and the performance score of model 3 is M3 = 6.

[0098] In scenario D, the performance score of model 1 is M1 = 6.8, the performance score of model 2 is M2 = 7.6, and the performance score of model 3 is M3 = 9.

[0099] In scenario E, the performance score of model 1 is M1=5.8, the performance score of model 2 is M2=9.0, and the performance score of model 3 is M3=7.5.

[0100] Calculate the Euclidean distance between matrix A and matrix B, C, D, and E respectively, and select the model with the highest score in the closest similar scene as the model for the visual task. If the scene is a new scene, you can re-evaluate the existing model and save the scene matrix parameters and model score.

[0101] As an achievable manner, the abnormal liquid level fluctuation condition includes at least one of the following conditions:

[0102] The fluctuation amplitude of the oil level is greater than or equal to the fluctuation amplitude threshold;

[0103] The fluctuation frequency of the oil level is greater than or equal to a fluctuation frequency threshold;

[0104] The abnormal oil surface foam condition includes at least one of the following conditions:

[0105] The foam area of ​​the oil surface is greater than or equal to a foam area threshold;

[0106] The foam thickness of the oil surface is greater than or equal to a foam thickness threshold.

[0107] In this scheme, a judgment method is provided for comparing the fluctuation amplitude, fluctuation frequency, foam area and foam thickness of the oil level with the corresponding threshold values. This judgment method can quickly judge the fluctuation of the oil level and accurately reflect the foam state of the oil surface. It is suitable for real-time monitoring and rapid response, easy to implement, low cost and high reliability.

[0108] As a feasible approach, Figure 3 As shown, step S101 includes:

[0109] S1011, obtaining environmental data of the compressor;

[0110] Wherein, the environmental data is used to characterize interference information data for obtaining the lubricating oil image;

[0111] S1012, determining corresponding image acquisition parameters based on the environmental data;

[0112] S1013. Acquire a real-time observation image of the window based on the image acquisition parameters.

[0113] In this solution, an image acquisition device with adaptive lighting is used, which can automatically adjust the intensity and color of the light source based on the actual environment of the compressor, including the ambient light intensity and / or the oil surface color, so as to reduce the interference of reflections and oil stains on the back panel.

[0114] In one embodiment, the adaptively-lit image acquisition device includes an intelligent focus module, which can automatically adjust the focal length to adapt to the distance between the image acquisition device and the oil surface and environmental changes, thereby ensuring the clarity of the image.

[0115] In one embodiment, the adaptive lighting image acquisition device includes a light source steering fixture, a light source bracket, a light source, a photoelectric sensor, a connecting line, a light source controller, a controller power supply, a camera fine-tuning bracket, a pan / tilt, a camera, a network cable, a power supply line and other parts. By receiving the photoelectric sensor signal and combining the actual environment and color of the oil surface of the mirror, the intensity and color of the light source are automatically adjusted to reduce the interference of reflections and backboard oil stains. The camera can automatically adjust the focal length to adapt to different oil surface distances and environmental changes to ensure the clarity of the image.

[0116] By adjusting the light intensity, color and / or focal length of the image acquisition device with adaptive lighting, not only the oil level observation is automated, but also the observation error caused by environmental factors is significantly reduced. The clarity of the image and the capture of details are ensured, providing accurate image information for subsequent data analysis.

[0117] As a feasible approach, Figure 4 As shown, step S105 includes:

[0118] S1051, obtaining the operating data of the compressor;

[0119] S1052, inputting the target oil level data and the operation data into a friction correlation model, and outputting a corresponding correlation coefficient of the friction pair loss of the compressor;

[0120] Wherein, the correlation coefficient corresponds one-to-one with the target oil level data or the operation data;

[0121] S1053. Obtain lubrication status information of the compressor based on the correlation coefficient.

[0122] In this solution, the operating data at least includes the operating time of the compressor, lubricating oil viscosity, oil temperature and friction pair pressure. By integrating commonly used correlation mathematical models such as the Pearson correlation coefficient, the Spearman rank correlation coefficient or the TOPSIS method, the correlation coefficient between each data and the friction pair is determined to obtain the corresponding lubrication status information of the compressor.

[0123] As an achievable manner, the detection method further includes:

[0124] The target oil level information, the operating data and the corresponding correlation coefficient are formed into a report image.

[0125] In this solution, by forming a report image such as a visual chart, the target oil level information, operating data and the corresponding correlation coefficient, linear or nonlinear analysis of each data can be performed to facilitate users to identify key factors affecting equipment loss, reduce equipment loss and increase service life.

[0126] Specifically, the compressor operation data is shown in Table 1:

[0127] Table 1

[0128]

[0129] As shown in Table 2, the Pearson correlation coefficient is integrated to obtain the correlation coefficients of the liquid level, operating time, lubricating oil viscosity and friction pair loss respectively:

[0130] Table 2

[0131] Data Types Correlation coefficient with friction pair loss Liquid level 0.85 Run time 0.90 Lubricating oil viscosity 0.75

[0132] The method for detecting the lubrication status of the compressor provided in this embodiment eliminates interference factors in the sampling environment, determines an image recognition model that matches the oil level status information, inputs the accurate real-time sampling image into the image recognition model, obtains a precise recognition result of the lubricating oil level in the real-time sampling image, and obtains the corresponding target oil level data, thereby realizing accurate detection of the lubrication status of the compressor.

[0133] Example 2

[0134] This embodiment provides a system 100 for detecting the lubrication status of a compressor. The compressor includes a window for observing the lubricating oil of the compressor. Figure 5 As shown, the lubrication state evaluation system 100 includes a real-time image acquisition module 101, an oil level state determination module 102, an image recognition model determination module 103, a target oil level output module 104 and a lubrication state determination module 105:

[0135] The real-time image acquisition module 101 is used to acquire the real-time sampling image of the window;

[0136] The oil level state determination module 102 is used to determine the oil level state information of the lubricating oil based on the real-time sampling image;

[0137] Wherein, the oil level state information represents the fluctuation state information of the oil level or the foam interference information of the oil level;

[0138] The image recognition model determination module 103 is used to determine the target image recognition model based on the fluctuation state information or foam interference information of the oil surface;

[0139] The target oil level output module 104 is used to input the real-time observation image of the window into the target image recognition model to obtain the target oil level data of the compressor;

[0140] The lubrication state determination module 105 is used to obtain lubrication state information of the compressor based on the target oil level data.

[0141] As an implementable manner, the image recognition model determination module 103 includes a fluctuation state determination unit and a foam interference determination unit;

[0142] a fluctuation state determining unit, configured to determine a first image recognition model as the target image recognition model in response to the fluctuation state information satisfying a liquid level fluctuation abnormality condition;

[0143] Wherein, the first image recognition model is used to identify the liquid level of the lubricating oil from the dynamic liquid surface image;

[0144] or,

[0145] a foam interference determination unit, configured to determine a second image recognition model as the target image recognition model in response to the foam interference information meeting an oil surface foam abnormality condition;

[0146] The second image recognition model is used to distinguish oil from foam in an image and identify the liquid level of the lubricating oil.

[0147] As an achievable manner, the abnormal liquid level fluctuation condition includes at least one of the following conditions:

[0148] The fluctuation amplitude of the oil level is greater than or equal to the fluctuation amplitude threshold;

[0149] The fluctuation frequency of the oil level is greater than or equal to a fluctuation frequency threshold;

[0150] The abnormal oil surface foam condition includes at least one of the following conditions:

[0151] The foam area of ​​the oil surface is greater than or equal to a foam area threshold;

[0152] The foam thickness of the oil surface is greater than or equal to a foam thickness threshold.

[0153] As an implementable manner, the real-time image acquisition module 101 includes an environmental data acquisition unit, an acquisition parameter determination unit and an image acquisition unit:

[0154] An environmental data acquisition unit, used to acquire environmental data of the compressor;

[0155] Wherein, the environmental data is used to characterize interference information data for obtaining the lubricating oil image;

[0156] An acquisition parameter determination unit, configured to determine corresponding image acquisition parameters based on the environmental data;

[0157] An image acquisition unit is used to acquire a real-time observation image of the window based on the image acquisition parameters.

[0158] As an implementable manner, the lubrication state determination module 105 includes an operation data acquisition unit, a correlation coefficient output unit and a lubrication state output unit:

[0159] An operation data acquisition unit, used to acquire operation data of the compressor;

[0160] A correlation coefficient output unit, used for inputting the target oil level data and the operation data into a friction correlation model, and outputting a corresponding correlation coefficient of the friction pair loss of the compressor;

[0161] Wherein, the correlation coefficient corresponds one-to-one with the target oil level data or the operation data;

[0162] A lubrication status output unit is used to obtain lubrication status information of the compressor based on the correlation coefficient.

[0163] As an implementable manner, the compressor lubrication status detection system 100 further includes a report generation module:

[0164] A report generation module is used to form a report image with the target oil level information, the operation data and the corresponding correlation coefficient.

[0165] As for the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, in which the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution.

[0166] The compressor lubrication status detection system provided in this embodiment eliminates interference factors in the sampling environment, determines an image recognition model that matches the oil level status information, inputs accurate real-time sampling images into the image recognition model, obtains accurate recognition results of the lubricating oil level in the real-time sampling images, and obtains corresponding target oil level data, thereby realizing accurate detection of the compressor lubrication status.

[0167] Example 3

[0168] Figure 6 This is a schematic diagram of the structure of an electronic device showing an example embodiment of the present disclosure, the electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor, and when the processor executes the computer program, the method for detecting the lubrication status of the compressor of any of the above embodiments is implemented. Figure 6 The electronic device 90 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0169] like Figure 6 As shown, the electronic device 90 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 90 may include, but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 connecting different system components (including the memory 92 and the processor 91).

[0170] The bus 93 includes a data bus, an address bus, and a control bus.

[0171] The memory 92 may include a volatile memory, such as a random access memory (RAM) 921 and / or a cache memory 922 , and may further include a read-only memory (ROM) 923 .

[0172] The memory 92 may also include a program tool 925 (or utility) having a set (at least one) of program modules 924, such program modules 924 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0173] The processor 91 executes various functional applications and data processing by running the computer program stored in the memory 92, such as the method for detecting the lubrication status of the compressor provided in any of the above embodiments.

[0174] The electronic device 90 may also communicate with one or more external devices 94 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 95. Furthermore, the electronic device 90 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 96. As shown, the network adapter 96 communicates with other modules of the electronic device 90 via a bus 93. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0175] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0176] Example 4

[0177] The embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the method for detecting the lubrication status of the compressor provided in any of the above embodiments is implemented.

[0178] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0179] Example 5

[0180] The embodiments of the present disclosure further provide a computer program product, including a computer program, which implements any of the above methods for detecting the lubrication status of a compressor when the computer program is executed by a processor.

[0181] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0182] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A method for detecting the lubrication status of a compressor, characterized in that: The compressor includes a window for observing lubricating oil of the compressor, and the lubrication state assessment method includes: Acquire a real-time sampling image of the window; Determining the oil level status information of the lubricating oil based on the real-time sampling image; Wherein, the oil level state information represents the fluctuation state information of the oil level or the foam interference information of the oil level; Determining a target image recognition model based on the fluctuation state information or foam interference information of the oil surface; Inputting the real-time sampling image of the window into the target image recognition model to obtain the target oil level data of the compressor; Lubrication status information of the compressor is obtained based on the target oil level data.

2. The method for detecting the lubrication status of a compressor according to claim 1, characterized in that: The step of determining the target image recognition model based on the oil surface fluctuation state information or foam interference information comprises: In response to the fluctuation state information meeting the liquid level fluctuation abnormality condition, determining a first image recognition model as the target image recognition model; Wherein, the first image recognition model is used to identify the liquid level of the lubricating oil from the dynamic liquid surface image; or, In response to the foam interference information meeting the oil surface foam abnormality condition, determining a second image recognition model as the target image recognition model; The second image recognition model is used to distinguish oil from foam in an image and identify the liquid level of the lubricating oil.

3. The method for detecting the lubrication status of a compressor according to claim 2, characterized in that: The abnormal liquid level fluctuation condition includes at least one of the following conditions: The fluctuation amplitude of the oil level is greater than or equal to the fluctuation amplitude threshold; The fluctuation frequency of the oil level is greater than or equal to a fluctuation frequency threshold; The abnormal oil surface foam condition includes at least one of the following conditions: The foam area of ​​the oil surface is greater than or equal to a foam area threshold; The foam thickness of the oil surface is greater than or equal to a foam thickness threshold.

4. The method for detecting the lubrication status of a compressor according to claim 1, characterized in that: The step of acquiring the real-time sampling image of the window comprises: said obtaining environmental data of said compressor; Wherein, the environmental data is used to characterize interference information data for obtaining the lubricating oil image; Determining corresponding image acquisition parameters based on the environmental data; A real-time observation image of the window is acquired based on the image acquisition parameters.

5. The method for detecting the lubrication status of a compressor according to any one of claims 1 to 4, characterized in that: The step of obtaining the lubrication status information of the compressor based on the target oil level data comprises: Acquiring operating data of the compressor; Inputting the target oil level data and the operation data into a friction correlation model, and outputting a corresponding correlation coefficient of the friction pair loss of the compressor; Wherein, the correlation coefficient corresponds one-to-one with the target oil level data or the operation data; Lubrication status information of the compressor is obtained based on the correlation coefficient.

6. The method for detecting the lubrication status of a compressor according to claim 5, characterized in that: The detection method further comprises: The target oil level information, the operating data and the corresponding correlation coefficient are formed into a report image.

7. A compressor lubrication status detection system, characterized in that: The compressor includes a window for observing the lubricating oil of the compressor, and the detection system includes a real-time image acquisition module, an oil level state determination module, an image recognition model determination module, a target oil level output module and a lubrication state determination module: The real-time image acquisition module is used to acquire the real-time sampling image of the window; The oil level state determination module is used to determine the oil level state information of the lubricating oil based on the real-time sampling image; Wherein, the oil level state information represents the fluctuation state information of the oil level or the foam interference information of the oil level; The image recognition model determination module is used to determine the target image recognition model based on the fluctuation state information or foam interference information of the oil surface; The target oil level output module is used to input the real-time observation image of the window into the target image recognition model to obtain the target oil level data of the compressor; The lubrication status determination module is used to obtain the lubrication status information of the compressor based on the target oil level data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, characterized in that: When the processor executes the computer program, the method for detecting the lubrication state of the compressor according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting the lubrication state of a compressor according to any one of claims 1 to 6 is implemented.

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

Images