Method and system for monitoring hydraulic oil

Abstract

The present application discloses a method for monitoring hydraulic oil. The method comprises steps of: capturing real-time images of hydraulic oil flowing through a sampling pipeline by means of an imaging system and detecting oil parameters of the hydraulic oil by means of an oil sensor; determining contaminant information based on the real-time images, wherein the contaminant information describes characteristics of contaminants in the hydraulic oil; and determining a current health state of the hydraulic oil according to the contaminant information and the oil parameters. The multi-sensor and multi-modal detection according to the present application provides more comprehensive and accurate oil parameters and information of granular contaminants, whereby the health state of the hydraulic oil can be determined more accurately.

Description

[0001] Description

[0002] METHOD AND SYSTEM FOR MONITORING HYDRAULIC OIL

[0003] Technical Field

[0004] The present application relates to the technical field of construction machinery monitoring, and more particularly to a method and system for monitoring hydraulic oil.

[0005] Background Art

[0006] A hydraulic system is an important part of a construction machine, in which hydraulic oil is used as working fluid to transmit power or control the movement of various mechanical parts. The working environment of construction machinery is usually very harsh. Particles such as dust and debris will contaminate the hydraulic system, and the working environment such as high temperature and high pressure will lead to the decline of oil quality. If left unchecked, the hydraulic components such as pumps, cylinders and valves may be eventually damaged. Therefore, it is necessary to monitor and evaluate the health state of hydraulic oil in the construction machine in real time.

[0007] At present, the dominant method for detecting hydraulic oil in a construction machine is to detect contamination online by installing a particle size sensor. The mainstream particle size sensors nowadays detect in a photoresist method. However, the photoresist method is inept in distinguishing between bubbles and particles, making the output contamination level inaccurate, and it is inapplicable to detection of other oil parameters, such as viscosity, moisture and dielectric constant.

[0008] Therefore, there is a demand for improving the existing method and system for monitoring hydraulic oil. Summary of the Invention

[0009] The present application proposes a method and a corresponding system for monitoring hydraulic oil, aiming at overcoming one or more technical problems and / or other technical problems in the prior art.

[0010] According to one aspect of the present application, a method for monitoring hydraulic oil is proposed. The method comprises steps of: capturing real-time images of hydraulic oil flowing through a sampling pipeline by means of an imaging system and detecting oil parameters of the hydraulic oil by means of an oil sensor; determining contaminant information based on the real-time images, wherein the contaminant information describes characteristics of granular contaminants in the hydraulic oil; determining a current health state of the hydraulic oil according to the contaminant information and the oil parameters.

[0011] According to another aspect of the present application, a hydraulic oil health monitoring system is proposed. The hydraulic oil health monitoring system comprises a signal acquisition module and a signal processing module. The signal acquisition module comprises an oil sensor and an imaging system, wherein the imaging system comprises light sources and cameras oppositely arranged on both radial sides of a sampling pipeline, and the signal processing module and the signal acquisition module are in communication and are designed to implement the method according to the present application.

[0012] In the method for monitoring hydraulic oil proposed in the present application, an imaging system and an oil sensor are used to acquire contaminant information and parameters of hydraulic oil. The contaminant information refers to the parameters of granular contaminants in hydraulic oil, including, for example, particle number, particle size, particle type, and particle shape, and the contaminant information also includes contaminant levels determined by these parameters. The parameters of hydraulic oil include temperature, viscosity, moisture and dielectric constant of hydraulic oil. By analyzing and evaluating the acquired parameters and contaminant information, the present application can give a more accurate estimation of the health state of hydraulic oil based on multiple eigenvalues. In addition, the method according to the present application helps manage and predict the life cycle of the hydraulic oil, making the whole life cycle of the hydraulic oil visualized and the current health state of the hydraulic oil informed to the user in time, telling the user in advance when the hydraulic oil needs to be replaced. The method of the present application can also trace the contamination according to particle characteristics and locate the worn key parts, thus facilitating earlier repair and maintenance if necessary. At the same time, the accumulated fault information may form fault information bases of target parts, whereby the R&D personnel can optimize the design of certain parts easily.

[0013] Brief Description of the Drawings

[0014] The above and other features and advantages of the present application will become more apparent by describing in detail the exemplary embodiments with reference to the accompanying drawings.

[0015] Fig. l is a flow chart of one embodiment of the method according to the present application.

[0016] Fig. 2 is a partial schematic view of the hydraulic oil health monitoring system according to the present application.

[0017] Fig. 3 is a schematic diagram showing the architecture of a preferred embodiment of the hydraulic oil health monitoring system according to the present application.

[0018] Detailed Description of the Embodiments

[0019] The exemplary embodiments are described comprehensively below with reference to the drawings. However, they can be implemented in many forms and the present application should not be construed as limited to the embodiments set forth herein. On the contrary, the embodiments are provided to make the content of the present application comprehensive and complete, and make the concepts therein fully conveyed to those skilled in the art. For the sake of clarity, some components in the drawings may be dimensionally exaggerated or changed in shape. The same reference numerals in the drawings denote the same or similar structures, which will not be described in detail below.

[0020] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present application. However, it will be appreciated that the technical solution of the present application can be implemented without one or more of the specific details, or other methods, components, etc. can be adopted. In other instances, well-known structures, methods or operations are not shown or described in detail to avoid obscuring other aspects of the present application.

[0021] In the present application, "hydraulic oil" should be understood as hydraulic oil circulating in a hydraulic circuit, which is a hydraulic oil mixture that may contain one or more contaminants such as granular contaminants, moisture, air bubbles, etc. For the sake of simplicity, the hydraulic oil mixture that may contain one or more contaminants such as granular contaminants, moisture, air bubbles, etc. is referred to as "hydraulic oil" in the present application.

[0022] Fig. l is a flowchart of a preferred embodiment of the hydraulic oil health monitoring method according to the present application. The method comprises the following steps:

[0023] SI : capturing real-time images of hydraulic oil flowing through a sampling pipeline by means of cameras and detecting oil parameters of the hydraulic oil by means of an oil sensor;

[0024] S2: determining contaminant information based on the real-time images, wherein the contaminant information describes characteristics of granular contaminants in the hydraulic oil;

[0025] S3 : determining a current health state of the hydraulic oil according to the contaminant information and the oil parameters.

[0026] The sampling pipeline is in communication with a hydraulic oil circulation pipeline. In other words, at least part of the hydraulic oil flows through the sampling pipeline during circulation. Generally speaking, one sampling pipeline is enough to fulfill the sampling function, but still multiple sampling pipelines may be arranged. It can be considered to set up multiple sampling pipelines at different positions of the hydraulic oil circulation pipeline for sampling, thus the influence of the hydraulic oil at different flow rates, pressures, heights, etc. can be considered. For example, there may be more large particles in a lower position with slower flow. An imaging system, i.e., light sources and cameras are oppositely arranged on both radial sides of each sampling pipeline, wherein the cameras can capture real-time images of the hydraulic oil flowing through the sampling pipeline. Here, the light sources are preferably LED light sources, and the cameras are preferably micro cameras. The photoelectric signals acquired by the micro-cameras are processed and converted into image data by the signal processing module.

[0027] The contaminant information is determined based on the real-time images, and it describes the characteristics of granular contaminants in the hydraulic oil. The image information acquired by the cameras is further processed by the signal processing module. So-called further processing can include preprocessing such as noise reduction and filtering, as well as image recognition for recognizing granular contaminants, air bubbles, etc. in the image. The contaminant information of granular contaminants in the hydraulic oil can be determined through image recognition. The contaminant information includes, for example, the size, quantity, type, shape, etc. of granular contaminants, and the level of contaminants determined based on these characteristics (ISO 4406:2021).

[0028] Common oil sensors can be capacitive, resistive or acoustic sensors, but other suitable sensors such as photoelectric sensors can also be considered. Oil parameters acquired by oil sensors include, for example, temperature, viscosity, moisture, and dielectric constant of hydraulic oil. The current health state of hydraulic oil can be determined according to the contaminant information and oil parameters. The correspondence between the contaminant information & oil parameters and the health state of hydraulic oil can be determined by algorithm models, such as the neural network algorithm model. Of course, we can also consider using tables or characteristic curve families to determine the health state of hydraulic oil.

[0029] According to the health state of the hydraulic oil, the hydraulic oil can be classified into a healthy state, a sub-healthy state and a dangerous state. Thus, a hydraulic oil health indicator can be provided to the user on the display interface of the construction machine. For example, a green display screen in the cab of the construction machine shows the health state, a yellow display screen shows the sub-health state, and a red display screen shows the dangerous state. Alternatively, an alarm device, such as an alarm light can be set in the cab of the construction machine, which can visually present the current state of hydraulic oil to the user with different colors and / or sounds.

[0030] Image recognition can be realized by artificial intelligence algorithms, such as neural networks and / or deep learning. There exist many artificial intelligence algorithms for image recognition, such as Convolutional Neural Network (CNN), Regional Convolutional Neural Network (RCNN), YOLO (You Only Look Once), SSD (Single Shot Multi Box Detector) and so on. The CNN algorithm can be preferred here to process the real-time images of hydraulic oil. As a mainstream algorithm in the field of image recognition, the CNN algorithm has grown to be very mature and reliable. CNN usually consists of three parts: a convolution layer, a pooling layer, and a fully connected layer. The convolution layer is responsible for extracting local and global features in the image; the pooling layer is provided to greatly reduce the magnitude, i.e. dimensions, of parameters; and the fully connected layer is provided to process "compressed image information" and output the results. In the current application scenario, the CNN algorithm mainly includes the following steps: image preprocessing, binarization, feature extraction, classification, contamination level mapping and so on.

[0031] Further, the whole life cycle of the hydraulic oil can be managed according to the contaminant information, oil parameters and the current health state of the hydraulic oil. Managing the whole life cycle of the hydraulic oil comprises predicting a remaining life of the hydraulic oil and / or tracing the contaminants and diagnosing faults of parts based on the contaminant information of the hydraulic oil.

[0032] The remaining life of the hydraulic oil can be predicted by, for example, a hydraulic oil remaining life prediction model. The hydraulic oil remaining life prediction model is preferably an algorithm model based on the Long Short-Term Memory (LSTM) neural network. The LSTM neural network is a kind of recurrent neural network (RNN), which is suitable for processing and predicting important events with long interruptions and delays in time series. As a long-term accumulation process, the monitoring of hydraulic oil depends highly on long-term data. Therefore, it is very advantageous to use the LSTM neural network here. The input parameters of the hydraulic oil remaining life prediction model include, for example, the contaminant information, oil parameters, the current health state of hydraulic oil, the last time to replace hydraulic oil, and so on. For a specific type of hydraulic oil, its theoretical service life and reference oil-changing interval are usually known to the users, and taking them as input parameters of the hydraulic oil remaining life prediction model is particularly beneficial to the prediction of the remaining life of hydraulic oil. In order to improve the accuracy of the remaining life prediction of hydraulic oil, the hydraulic oil remaining life prediction model can be combined with the deep learning (DL) algorithm.

[0033] The contaminants in hydraulic oil are mainly sourced from residual contaminants in the system, contaminants invading the system from the outside, and contaminants generated within the system. The residual contaminants in the system mainly refer to the contaminants existing in the hydraulic system before the hydraulic oil is filled, mainly the remnants left in the system after hydraulic components are produced, such as casting sand, welding slag, chips, iron sheets, cotton yarn ends, paint peelings, sealing fragments, dust, etc. The contaminants invading the system from the outside refer to the contaminants invading the system from the outside of the hydraulic system during the assembly, use and maintenance of the system, such as air, moisture, dust, sand and other impurities in the environment, which may enter the hydraulic oil through the gaps such as air holes in the oil tank, piston rods, and oil fillers. In addition, when the hydraulic system is working, the parts will rub during operation, and the residual rust, wear particles, corrosive substances, etc. generated thereby may enter the hydraulic oil to cause contamination.

[0034] Preferably, the contaminants can be traced and the faults of parts can be diagnosed according to the contaminant information. For example, the contaminants can be traced through a traceability model trained by means of empirical data or experimental data, wherein the traceability model is preferably based on the CNN algorithm. By analyzing the size, type, quantity, shape, etc. of granular contaminants in the traceability model, we can infer where the contaminants come from, which is called traceability. The worn parts can be located by tracing the contaminants.

[0035] It is also beneficial to determine wear degrees of parts in the hydraulic system according to the contaminant tracing results, thereby diagnosing the faults of parts, predicting the service life of related parts, and sending out a maintenance or replacement reminder when necessary. For example, it is known that a certain granular contaminant in the hydraulic oil is mainly caused by the wear of meshing gears in the oil pump. If the amount of such granular contaminants in the hydraulic oil reaches a certain threshold or the average size of such granular contaminants exceeds a certain threshold, it means that the gears are seriously worn and need to be repaired or replaced.

[0036] In addition, the wear information of parts in the hydraulic system and the information of their changing over time are stored in the database. In other words, the wear information or fault information of a target part throughout its whole life cycle from putting to use to failure or fault will all be recorded in the database. With the fault or wear information of parts accumulated, a fault / wear information base of target parts can be formed, which can facilitate the R&D personnel to optimize the design of the parts. For example, if big data analysis shows that the wear rate of a component is significantly higher than that of other components in the hydraulic system, it means that the component should be optimized in future research and development design to improve its wear resistance and prolong its service life.

[0037] It is also preferable to send the predicted remaining life and / or the estimated current health state of the hydraulic oil to a mobile terminal or a remote control terminal and present them to the user in a visual form or an active warning form. This is especially beneficial for unmanned construction machinery or construction machinery that can be remotely controlled. For example, a remote operator can view the current health state and the predicted remaining life of the hydraulic oil in a visual form on a mobile terminal or a remote control terminal, such as a smart phone, a PAD, or a remote management device for unmanned construction machinery.

[0038] Fig. 2 is a partial schematic view of a hydraulic oil health monitoring system according to the present application, and specifically, it is a schematic diagram of a signal acquisition module for sampling the hydraulic oil. In fig. 2, the sampling pipeline 1 is shown by an arrow, which indicates the flow direction of the hydraulic oil. The hydraulic oil contains air bubbles 2 and other granular contaminants 3. For the sake of clarity, only one air bubble 2 and one granular contaminant 3 are schematically shown in the figure, but obviously there may be more air bubbles and granular contaminants in an actual situation. The sampling pipeline 1 is designed as an at least partially transparent pipeline, which can be in the shape of a cylinder, a cuboid, etc. At least part of the hydraulic oil will flow through the sampling pipeline during circulation. It can also be considered to set up multiple sampling pipelines at multiple locations.

[0039] On a radial side of the sampling pipeline 1, there is provided an LED light source 4, which is preferably integrated in an LED panel 5. The LED panel 5 is provided with a circuit for supplying power to the LED light source 4 and controlling the LED light source 4. Opposite to the LED light source 4, a camera 6 is arranged on the other radial side of the sampling pipeline 1. The LED light source 4 provides auxiliary light. The camera 6 is designed as a micro camera integrated in a circuit board 7. The circuit board 7 is preferably an image signal processing circuit board including an image signal processor (ISP). The image signal processing circuit board 7 converts photoelectric signals acquired by the camera 6 into image data. At least one oil sensor 8 is arranged at the sampling pipeline 1. Although only one oil sensor 8 is schematically shown in the figure, it is available to arrange a plurality of oil sensors with different functions or one or more oil sensors embracing multiple functions. The oil sensor 8 is provided to detect oil parameters of the hydraulic oil flowing through the sampling pipeline 1, such as temperature, viscosity, moisture and dielectric constant of the hydraulic oil. A detection end of the oil sensor 8 particularly extends into the sampling pipeline 1, and the other end, which is opposite to the detection end, is preferably integrated in the LED panel 5 to power the oil sensor 8. The oil sensor 8 is also preferably in communication with the image signal processing circuit board 7. That is, signals of the oil sensor 8 can be processed or preprocessed by the image signal processing circuit board 7. A compact configuration is created by integrating the oil sensor 8 and the LED light source 4 in the LED panel 5 and integrating the micro-camera in the image signal processing circuit board 7, which makes the power supply, signal transmission and control more reliable. It is also advantageous that the image signal processing circuit board 7 is embedded with the aforementioned algorithms, such as the image recognition algorithm, including algorithms for image preprocessing, binarization, feature extraction, classification and contamination level mapping.

[0040] Fig. 3 is a schematic diagram showing the architecture of a preferred embodiment of the hydraulic oil health monitoring system according to the present application. Generally speaking, the hydraulic oil health monitoring system includes a signal acquisition module 12, a signal processing module 13 and a cloud platform 10. Although the cloud platform 12 and the programs deployed thereon are shown here, it is obvious that a local computing mode rather than the cloud platform can be used. That is, all the programs are deployed locally, e.g. on a computing device of the construction machine, on which relevant calculations and storage are performed. However, it should be pointed out that the cloud platform 12 has obvious advantages in terms of computing power and storage space. For the detailed structure of the signal acquisition module 12, reference can be made to, for example, the embodiment shown in Fig. 2, which mainly includes an oil sensor and an imaging system, wherein the imaging system includes a light source and a camera. The signal processing module 13 may be a microprocessor integrated in the image signal processing (ISP) circuit board 7, or a controller separately constructed from the signal acquisition module 12. Of course, other computing devices on the construction machine can also be used as signal processing modules. The signal processing module 13 is in communication with the signal acquisition module 12. To be specific, it is in direct or indirect communication with the oil sensor and camera of the signal acquisition module 12, acquires signals from the oil sensor and camera, and processes the acquired signals, for example, by the aforementioned built-in algorithms.

[0041] The signal processing module 13 is in communication with a control device 9 of the construction machine via a CAN bus, and the construction machine is provided with a display and / or an alarm lamp for indicating the health state of the hydraulic oil. The result acquired from the signal processing module 13 can be transmitted to the control device 9 of the construction machine, e.g. the control device in the cab, via the CAN bus of the construction machine. A display can be arranged in the cab to display, on the display interface, the real-time state of the hydraulic oil and the estimated remaining life and oil-changing time to the user. It is preferable to use different colors to denote different health states of the hydraulic oil. For example, green denotes a healthy state, yellow denotes a sub- healthy state, and red denotes a dangerous state. An alarm device, such as an alarm light, can also be arranged in the cab of the construction machine, which can vividly present the current state of the hydraulic oil to the user with different colors and / or sounds.

[0042] On the other hand, the data from the signal acquisition module 12 and the signal processing module 13 can be transmitted to a remote server or the cloud platform 10 through a remote communication network, such as Ethernet or a mobile communication network. These data are stored in a database 11 on the remote server or the cloud platform 10. The database 11, the hydraulic oil remaining life prediction model, and the contaminants-targeted traceability model are deployed on the remote server or the cloud platform. The hydraulic oil remaining life prediction model and the traceability model are both artificial intelligence analysis models based on neural network algorithms. For example, the hydraulic oil remaining life prediction model is an algorithm model based on long-term and short-term memory neural network, and the traceability model is an algorithm model based on the convolutional neural network. The traceability model can be trained by means of empirical data or experimental data.

[0043] Based on the data of the signal acquisition module 12 and the signal processing module 13, the hydraulic oil remaining life prediction model can predict the remaining life of the hydraulic oil. The prediction of the remaining life can remind the user to replace the hydraulic oil in time, thus preventing the hydraulic oil from damaging the parts due to excessive contamination. Here, the health state and remaining life of the hydraulic oil are evaluated or predicted by considering not only the contaminant information presented on the image of the hydraulic oil but also the parameters detected by the oil sensor. On the one hand, multi-sensor and multi-modal detection leads to high detection accuracy, and on the other hand, the captured multi-modal, multifeature and multi-sensor information can help give an accurate evaluation and prediction of the health state and remaining life of the hydraulic oil. It is also preferable to send the predicted remaining life and / or the estimated health state of the hydraulic oil to the control device 9 of the construction machine, and present them to the user in a visual form on the display interface of the construction machine. It is also available to send the predicted remaining life and / or the estimated health state to a mobile terminal or remote control terminal, such as a smart phone of the construction machine driver or administrator, a PAD, or a remote management device for unmanned construction machinery, and present them to the user in a visual form or an active warning form.

[0044] All contaminant information, health state information and timevarying data about the hydraulic oil are stored in the database. A different key part will produce a different type of particles when it wears, thus the wear state of the parts can be indirectly obtained by means of neural network models by deeply exploring the information of the granular contaminants, thereby tracing the contaminants and locating the worn parts. The information of granular contaminants includes, for example, particle size, type, shape, and quantity. The information of the same type of hydraulic oil in different construction machines will be collected and stored. Thereby it is available to get the big wear data of the same type of parts in the construction machinery. Based on the big wear data, all parts can be diagnosed and analyzed, and the easily damaged parts can be better designed in the subsequent research and development process to prolong their service life. Alternatively, the sturdy and robust parts can be redesigned by, for example, producing them with cheaper materials to shorten their service life and reduce the costs under the condition of not affecting normal use.

[0045] Generally speaking, the multi-sensor and multi-modal detection according to the present application provides more comprehensive and accurate oil parameters and information of granular contaminants, whereby the current health state of the hydraulic oil can be determined more accurately. In addition, with the help of the algorithm model based on the LSTM neural network, the remaining life of the hydraulic oil can be predicted reliably by taking oil parameters and granular contaminant information as input parameters. Given advance warning, the user can replace the hydraulic oil in time to avoid damage to the parts. Contaminant information and health state information of the hydraulic oil throughout its whole life cycle are collected and saved, and presented in a visual form. On the other hand, worn parts in the hydraulic system are located by the traceability model and / or wear degrees of related parts are determined based on the contaminant information to diagnose the faults of the parts, predict the service life of the related parts and send out a maintenance or replacement reminder when necessary. Preferably, the CNN-based traceability model is used to analyze the size, type, shape, quantity, etc. of granular contaminants, and trace and locate the worn parts, thereby tracing the contaminants and diagnosing the faults of the parts. Furthermore, all monitoring and prediction data are updated in real time; therefore, they can reflect the latest real state of the hydraulic oil and fulfill the whole life cycle management.

[0046] After considering the Specification and practice disclosed herein, those skilled in the art would readily conceive of other embodiments of the present application. The present application is intended to cover any variation, use or adaptation of the present application, which follow the general principles of the present application and include common knowledge or conventional technical means in the technical field that are not disclosed in the present application. The Specification and embodiments are considered to be illustrative only, and the true scope and spirit of the present application are determined by the appended claims.

Claims

Claims1. A method for monitoring hydraulic oil, comprising steps of: capturing real-time images of hydraulic oil flowing through a sampling pipeline by means of an imaging system and detecting oil parameters of the hydraulic oil by means of an oil sensor; determining contaminant information based on the real-time images, wherein the contaminant information describes characteristics of contaminants in the hydraulic oil; determining a current health state of the hydraulic oil according to the contaminant information and the oil parameters.

2. The method according to claim 1, characterized in that the oil parameters include temperature, viscosity, moisture and dielectric constant of the hydraulic oil, and contaminant information includes size, type, quantity, shape and contaminant level of granular contaminants.

3. The method according to claim 1 or 2, characterized in that the hydraulic oil is classified into a healthy state, a sub-healthy state and a dangerous state according to the current health state of the hydraulic oil, wherein the current health state of the hydraulic oil is presented to users by diversified colors and / or sounds.

4. The method according to claim 1 or 2, characterized in that image information captured by the imaging system is further processed, and further processing includes preprocessing in the form of noise reduction, filtering and image recognition.

5. The method according to claim 4, characterized in that image recognition algorithms include image preprocessing, binarization, feature extraction, classification and contamination level mapping.

6. The method according to claim 1 or 2, characterized by further comprising a step of managing a whole life cycle of the hydraulic oil according to the contaminant information, the oil parameters and the current health state of the hydraulic oil.

7. The method according to claim 6, characterized in that managing the whole life cycle of the hydraulic oil comprises predicting a remaining life of the hydraulic oil and / or tracing the contaminants and diagnosing faults of parts based on the contaminant information of the hydraulic oil.

8. The method according to claim 7, characterized in that predicting the remaining life of the hydraulic oil by means of a hydraulic oil remaining life prediction model, which is an algorithm model based on long-term and short-term memory neural networks.

9. The method according to claim 7, characterized in that the contaminants are traced through a traceability model trained by means of empirical data or experimental data, wherein the traceability model is an algorithm model based on convolutional neural networks.

10. The method according to claim 7, characterized in that worn parts in the hydraulic system are located according to sources of contaminants, and / or wear degrees of related parts are determined based on the contaminant information to diagnose the faults of parts, predict service life of related parts and send out a maintenance or replacement reminder when necessary.

11. The method according to claim 7, characterized in that the predicted remaining life and / or estimated health state of the hydraulic oil are sent to a mobile terminal or a remote control terminal and presented to a user in a visual form or an active warning form.

12. A hydraulic oil health monitoring system, comprising a signal acquisition module and a signal processing module, wherein the signal acquisition module comprises an oil sensor and an imaging system, characterized in that the imaging system comprises light sources and cameras oppositely arranged on both radial sides of a sampling pipeline, and the signal processing module and the signal acquisition module are in communication and are designed to implement the method according to any one of claims 1 to 11.

13. The hydraulic oil health monitoring system according to claim 12, characterized in that the camera is designed as a micro camera integrated in an image signal processing circuit board, and the signal processing module is designed as a microprocessor integrated in the image signal processing circuit board.

14. The hydraulic oil health monitoring system according to claim 12, characterized in that the camera is designed as a micro-camera, and the signal processing module is designed as a microprocessor independently constructed relative to the signal acquisition module.

15. The hydraulic oil health monitoring system according to claim 12, characterized in that the signal processing module is in communication with a control device of a construction machine via a CAN bus, and the construction machine is provided with a display and / or an alarm lamp for indicating the health state of the hydraulic oil.

16. The hydraulic oil health monitoring system according to any one of claims 12 to 15, characterized in that the light source is an LED light source, and the oil sensor and the LED light source are integrated in an LED panel.

17. The hydraulic oil health monitoring system according to any one of claims 12 to 15, characterized by further comprising a cloud platform or a remote server, on which a database, a hydraulic oil remaining life prediction model and a contaminants-targeted traceability model are deployed, and the signal acquisition module and signal processing module are in communication with the cloud platform or remote server by means of Ethernet or a mobile communication network.

18. The hydraulic oil health monitoring system according to claim 17, characterized in that the cloud platform or remote server is in communication with the control device of the construction machine or the mobile terminal of the user.

19. The hydraulic oil health monitoring system according to claim 17, characterized in that worn parts in the hydraulic system are located by the traceability model and / or wear degrees of related parts are determined based on the contaminant information to diagnose the faults of parts, predict service life of related parts and send out a maintenance or replacement reminder when necessary.

Images