Device and system for monitoring and diagnosing state of active equipment lubricating system

Abstract

The invention relates to a device and a system for monitoring and diagnosing the state of a lubricating system of active equipment, and relates to the field of state monitoring of the active equipment, and the method comprises the following steps: after the active equipment is started, receiving the monitoring state of the lubricating system from a collector through a master collector, and calculating the deviation from the theoretical state of the lubricating system; obtaining a lubrication system state deviation time sequence matrix to carry out demand computing power prediction, and obtaining a demand computing power prediction value; obtaining an edge node task allocation state to perform edge node scheduling optimization, and obtaining an edge node scheduling scheme; activating a target edge node according to the edge node scheduling scheme, and performing equipment state prediction based on the lubrication system state deviation time sequence matrix to obtain equipment state identification information; and when the abnormal state type is included, sending the abnormal state type to the management end through the cloud, and performing synchronous display with the main collector. The technical problem that the state of the active equipment cannot be timely and comprehensively reflected due to one-sided monitoring state attributes and limited local computing power in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of active equipment status monitoring, and in particular to a device and system for monitoring and diagnosing the status of a lubrication system of active equipment. Background Art

[0002] With the development of industrial automation and intelligence, active equipment is increasingly used in various fields. The status monitoring and diagnosis of its lubrication system is crucial to ensure the stable operation of the equipment. The lubrication system is equivalent to the "blood vessels and blood" of active equipment. Its good operating status is the basis for the normal operation of the equipment. It can also effectively reflect the operating health of mechanical equipment.

[0003] There are two main modes for lubrication system detection: an offline detection mode of sampling and inspection and an online lubricant detection mode of online sampling. In the offline detection mode, samples are taken at sampling points of the lubrication system according to the set sampling and inspection frequency, and then sent to the company's own or outsourced analysis and inspection units for testing. However, this mode is inefficient and has poor timeliness, and it is impossible to grasp the status of the lubrication system in real time. Although the online detection mode can monitor the quality and contaminants of the lubricating oil in real time, and can perform preliminary diagnosis on oil performance, partial contamination and wear status, it cannot fully reflect the status of active equipment. Moreover, due to the strong nonlinear relationship between the analysis of the operating conditions of active equipment based on the status of the lubrication system, insufficient local computing power makes it difficult to support timely analysis of the operating conditions of active equipment. Summary of the invention

[0004] The present invention aims to solve the technical problem in the prior art that the status of active equipment cannot be fully and timely reflected due to the one-sided monitoring status attributes and limited local computing power, and provides a device and system for monitoring and diagnosing the status of the lubrication system of active equipment to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In the first aspect, the present invention provides a device for monitoring and diagnosing the state of a lubrication system of an active device, and a system for monitoring and diagnosing the state of a lubrication system of an active device is deployed. The system includes a collection end, a cloud end, and a management end. The collection end includes a master collector and a slave collector. The execution steps include: when the active device is started and the timer meets the preset time length, the master collector receives the lubrication system monitoring state from the slave collector, calculates the deviation from the theoretical state of the lubrication system, obtains the lubrication system state deviation timing matrix, and resets the timer to zero and restarts the timing, wherein the lubrication system monitoring state attributes include flow, viscosity, temperature, density, dielectric constant, water activity, water content, metal Chip density, particle distribution density, oil-water interface, oil-gas interface, pressure and emulsification degree; predict the demand computing power according to the lubrication system state deviation timing matrix to obtain the demand computing power prediction value; obtain the edge node task allocation state; optimize the edge node scheduling according to the demand computing power prediction value and the edge node task allocation state to obtain the edge node scheduling plan; activate the target edge node according to the edge node scheduling plan, predict the equipment state based on the lubrication system state deviation timing matrix, and obtain the equipment state identification information; when the equipment state identification information includes the abnormal state type, send the equipment state identification information to the management end through the cloud, and perform synchronous display with the main collector.

[0007] In a second aspect, the present invention provides a system for monitoring and diagnosing the state of a lubrication system of an active device, which is deployed in the device for monitoring and diagnosing the state of a lubrication system of an active device of the first aspect.

[0008] The beneficial effects of the present invention are as follows: by setting flow rate, viscosity, temperature, density, dielectric constant, water activity, water content, metal chip density, particle distribution density, oil-water interface, oil-gas interface, pressure and emulsification degree as monitoring attributes, the state of the lubrication system can be comprehensively monitored, and the comprehensiveness of the monitoring state is improved, thereby solving the problem that the prior art cannot reflect the lubrication state of the equipment lubrication system as a whole. At the same time, the demand computing power is predicted by using the lubrication system state deviation timing matrix, and the edge node scheduling is performed according to the demand computing power prediction value to perform equipment state analysis. It can reasonably allocate tasks and optimize the use of computing power according to limited local computing power resources, thus solving the problem of insufficient local computing power and achieving the technical effect of efficiently predicting the state of active equipment according to the state of the lubrication system. It provides strong technical support for fault diagnosis and preventive maintenance of active equipment, and improves the reliability and stability of equipment operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of the execution steps of a device for monitoring and diagnosing the state of a lubrication system of an active equipment provided by the present invention;

[0010] Figure 2 A schematic diagram of the structure of a system for monitoring and diagnosing the state of a lubrication system of an active device provided by the present invention;

[0011] Figure 3 A schematic diagram of possible application deployment of a device for monitoring and diagnosing the state of a lubrication system of active equipment provided by the present invention. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0015] Embodiment 1:

[0016] like Figure 1 As shown, an embodiment of the present invention provides a device for monitoring and diagnosing the state of a lubrication system of an active device, and a system for monitoring and diagnosing the state of a lubrication system of an active device is deployed. The system includes a collection end, a cloud end, and a management end. The collection end includes a master collector and a slave collector. The execution steps include the following steps:

[0017] Specifically, the system for monitoring and diagnosing the state of the lubrication system of the active equipment is software, and the device for monitoring and diagnosing the state of the lubrication system of the active equipment is hardware, such as a storage medium. The acquisition end is a data acquisition interface for communicating with the lubrication system sensor and collecting the state data of the lubrication system; the cloud is a virtual medium for remote data interaction; the management end is a terminal for remote management of the active equipment, preferably including a PC terminal, a mobile terminal and a control room DCS system, etc.; the master collector is a functional module for receiving and storing data from the slave collector, and the slave collector is a functional module for directly receiving signals from the lubrication system sensor. Preferably, generally a set of "master and slave" collectors serves one active equipment; if necessary, multiple slave collectors can be set on different devices, and these slave collectors can be connected with a master collector, so that a set of "master and slave" collectors can serve multiple devices; the master and slave collectors can communicate with each other by wire or wirelessly; the display is divided into the master collector on-site display, the management end display, that is, the control room DCS system display, the PC terminal display, and the mobile terminal display, which correspond to local, wired communication, wireless communication or cloud platform respectively.

[0018] Further, such as Figure 3 The figure shows a possible deployment diagram of a device for monitoring and diagnosing the condition of the lubrication system of active equipment. The field collector is the "master and slave" collector, the DCS is the control room DCS system, the server is the cloud, and the management end and the application service are mobile terminals.

[0019] S10: After the active equipment is started and the timer meets the preset time length, the master collector receives the monitoring state of the lubrication system from the slave collector, calculates the deviation from the theoretical state of the lubrication system, obtains the lubrication system state deviation time series matrix, and resets the timer to zero and restarts the timing, wherein the monitoring state attributes of the lubrication system include flow, viscosity, temperature, density, dielectric constant, water activity, water content, metal chip density, particle distribution density, oil-water interface, oil-gas interface, pressure and emulsification degree;

[0020] Specifically, the start-up of the active equipment refers to the start of the operation of the active equipment; the timer meeting the preset time length refers to a preset timing mechanism. When the preset time threshold is reached, the subsequent collection and calculation operations are triggered, and the timer is reset to zero and the timing is restarted after each collection; the main collector is responsible for receiving the lubrication system monitoring status data sent by the slave collector; preferably, the slave collector is configured according to the data attributes to be monitored, including at least sensors corresponding to flow rate, viscosity, temperature, density, dielectric constant, water activity, water content, metal chip density, particle distribution density, oil-water interface, oil-gas interface, pressure and emulsification degree; the theoretical state of the lubrication system refers to the lubrication system monitoring status threshold value pre-configured by the user each time the active equipment is started.

[0021] Taking the theoretical state of the lubrication system as the minuend and the monitoring state of the lubrication system as the subtrahend, the difference of the same attribute between the monitoring state of the lubrication system and the theoretical state of the lubrication system is calculated at each moment to obtain each attribute deviation vector at each moment; further, taking the time as the horizontal element of the matrix and the attribute as the vertical element of the matrix, each attribute deviation vector at each moment is stored to obtain the lubrication system state deviation time series matrix used to reflect the change of the lubrication system state over time.

[0022] S20: performing demand computing power prediction according to the lubrication system state deviation time series matrix to obtain a demand computing power prediction value;

[0023] Further, the required computing power is predicted according to the lubrication system state deviation time series matrix to obtain the required computing power prediction value, and step S20 includes:

[0024] Step S21: performing fuzzy deviation parameter analysis according to the lubrication system state deviation time series matrix to obtain a first monitoring attribute fuzzy deviation parameter up to an Nth monitoring attribute fuzzy deviation parameter;

[0025] Step S22: extracting a set of monitoring attributes whose fuzzy deviation parameters are greater than or equal to a fuzzy deviation threshold according to the first monitoring attribute fuzzy deviation parameter to the Nth monitoring attribute fuzzy deviation parameter;

[0026] Step S23: performing computing power demand forecasting according to the monitoring attribute set to obtain the computing power demand forecast value.

[0027] Further, the required computing power is predicted according to the monitoring attribute set to obtain the required computing power prediction value. Step S23 includes the following steps:

[0028] S231: Obtaining a device state prediction unit library, wherein the device state prediction unit library has a plurality of device state prediction units, and the plurality of device state prediction units have a plurality of monitoring attribute weight distribution results and a plurality of required computing power identifiers;

[0029] S232: Based on the monitoring attribute set, traverse the plurality of monitoring attribute weight distribution results to perform matching degree analysis to obtain a plurality of matching degrees;

[0030] S233: extracting a target device state prediction unit set having a matching degree greater than or equal to a matching degree threshold from the device state prediction unit library according to the plurality of matching degrees;

[0031] S234: Calculate the required computing power based on the target device state prediction unit set and the plurality of required computing power identifiers to obtain the required computing power prediction value.

[0032] Furthermore, the device state prediction unit library construction step includes:

[0033] Matching the active equipment operation log according to the active equipment model, wherein the active equipment operation log includes a lubrication system state deviation time series record matrix and active equipment state type record information;

[0034] Obtaining preset weight distribution information of monitoring attributes;

[0035] The input layer of the long short-term memory neural network is configured according to the preset weight distribution information of the monitoring attribute, the active equipment state type record information is used as supervision, and the lubrication system state deviation time series record matrix is ​​used as input to train the equipment state prediction unit and add it to the equipment state prediction unit library.

[0036] Further, a fuzzy deviation parameter analysis is performed according to the lubrication system state deviation time series matrix to obtain the first monitoring attribute fuzzy deviation parameter until the Nth monitoring attribute fuzzy deviation parameter. Step S21 includes the following steps:

[0037] S211: Obtaining a monitoring attribute deviation threshold set;

[0038] S212: extracting the first monitoring attribute deviation threshold value of the monitoring attribute deviation threshold value set until the Nth monitoring attribute deviation threshold value;

[0039] S213: Counting the proportion of moments when the deviation vector modulus in the first monitoring attribute deviation vector modulus time series information of the lubrication system state deviation time series matrix is ​​greater than or equal to the first monitoring attribute deviation threshold, and setting it as the first monitoring attribute fuzzy deviation parameter;

[0040] S214: until the proportion of moments when the deviation vector modulus in the Nth monitoring attribute deviation vector modulus time series information of the lubrication system state deviation time series matrix is ​​greater than or equal to the Nth monitoring attribute deviation threshold is counted and set as the Nth monitoring attribute fuzzy deviation parameter.

[0041] Further, based on the monitoring attribute set, the plurality of monitoring attribute weight distribution results are traversed to perform matching degree analysis to obtain a plurality of matching degrees. Step S233 includes the following steps:

[0042] S2331: traverse the plurality of monitoring attribute weight distribution results, sort the monitoring attributes according to the weight from large to small, and obtain a plurality of monitoring attribute sorting results;

[0043] S2332: Obtain the monitoring attribute set, traverse the plurality of monitoring attribute sequences, and extract a plurality of monitoring attribute sequence numbers;

[0044] S2333: Construct matching evaluation function:

[0045]

[0046] Among them, P(X i ) represents the matching degree of the i-th monitoring attribute sequence, n represents the number of monitoring attribute sets, X ij The jth number representing the i-th monitoring attribute number sequence, X i Characterizes the sequence of the i-th monitoring attribute number;

[0047] S2334: According to the matching evaluation function, traverse the plurality of monitoring attribute number sequences to perform matching analysis to obtain the plurality of matching degrees.

[0048] Specifically, in the embodiment of the present application, different lubrication system state deviation timing matrices may require different computing power due to different models for scheduling equipment state prediction. Therefore, each time the lubrication system state deviation timing matrix is ​​obtained, it is necessary to perform a required computing power prediction to obtain the required computing power prediction value, thereby providing a reference for the subsequent task allocation of edge nodes.

[0049] The following is a specific method for implementing demand computing power prediction in the embodiment of this application:

[0050] The fuzzy deviation parameter of the first monitoring attribute represents the overall deviation of the first monitoring attribute calculated based on the lubrication system state deviation time series matrix. The detailed calculation method is:

[0051] Through the management end, each monitoring attribute deviation threshold set is obtained, and then the first monitoring attribute deviation threshold is extracted; the first monitoring attribute deviation vector modulus time series information is extracted from the lubrication system state deviation time series matrix; further, the number of moments in the first monitoring attribute deviation vector modulus time series information when the deviation vector modulus is greater than or equal to the first monitoring attribute deviation threshold is calculated, and the ratio of the number of moments to the total number of moments in the first monitoring attribute deviation vector modulus time series information is calculated, and set as the first monitoring attribute fuzzy deviation parameter; the second monitoring attribute up to the Nth monitoring attribute is analyzed in the same way, thereby obtaining the first monitoring attribute fuzzy deviation parameter up to the Nth monitoring attribute fuzzy deviation parameter.

[0052] Furthermore, based on the fuzzy deviation parameter of the first monitoring attribute to the Nth monitoring attribute fuzzy deviation parameter, a set of monitoring attributes whose fuzzy deviation parameters are greater than or equal to the fuzzy deviation threshold is extracted, where the fuzzy deviation threshold refers to a fuzzy deviation characteristic value preset by the user, which defaults to 0.3; the monitoring attribute set refers to monitoring attributes that satisfy the fuzzy deviation parameter being greater than or equal to the fuzzy deviation threshold. When the fuzzy deviation parameter is greater than or equal to the fuzzy deviation threshold, it means that the corresponding monitoring attribute has a large overall deviation in this monitoring and therefore needs to be taken seriously. Therefore, it is stored as a monitoring attribute set and awaits subsequent calls.

[0053] Furthermore, the device state prediction unit library is used to store the functional unit library for device state prediction. Any device state prediction unit is based on a long short-term memory neural network and is trained as a prediction model under different monitoring attribute weight distributions. Preferably, any device state prediction unit is trained as follows:

[0054] Through the management end, configure the preset weight distribution information of the monitoring attributes; then match the active equipment operation log according to the active equipment model, where any active equipment operation log includes the lubrication system state deviation time series record matrix and the active equipment state type record information, the active equipment state type record information is the coding information, and any active equipment state type corresponds to a unique code. Using the preset weight distribution information of the monitoring attributes, the input layer of the long short-term memory neural network is constructed, and the lubrication system state deviation time series record matrix can be weighted predicted.

[0055] Furthermore, the operation logs of active equipment are divided into 8 training data sets and 2 validation data sets. At the same time, the loss function of the multi-classification model is constructed. Among them, X i0 Characterizes the type of record information of the active equipment status, X i Characterize the prediction information of the state type of active equipment, X i ∩X i0Characterize the active equipment state type record information and the intersection of the active equipment state type record information; configure the convergence loss threshold. During specific training, 8 training data sets are scheduled, and the active equipment state type record information is used as supervision, and the lubrication system state deviation time series record matrix is ​​used as input to train the long short-term memory neural network that has been configured with weights. When the LOSS value of the preset number of consecutive trainings is less than or equal to the convergence loss threshold, 2 verification data sets are scheduled, and the active equipment state type record information is used as supervision, and the lubrication system state deviation time series record matrix is ​​used as input to train the long short-term memory neural network that has been configured with weights. When the LOSS value is less than or equal to the convergence loss threshold for at least 50 times, it is considered that the long short-term memory neural network has converged and is stored as an equipment state prediction unit. The preset weight distribution information of the monitoring attributes is stored as the weight distribution result of the monitoring attributes. Furthermore, the computing power requirement values ​​of at least 500 times when the equipment state prediction unit is working are counted and the average is calculated, which is set as the required computing power identifier; the monitoring attribute weight distribution result, the required computing power identifier and the equipment state prediction unit are associated and stored in the equipment state prediction unit library. Preferably, the monitoring attribute weight distribution result is enumerated and combined. The enumeration combination here refers to the enumeration combination of the monitoring attributes sorted from large to small according to the weight. The resulting processing unit set can call different equipment state prediction units for analysis when facing different deviation states to improve the accuracy of the analysis.

[0056] In specific applications, the matching degree of each device state prediction unit in the device state prediction unit library is calculated according to the monitoring attribute set. Preferably, the matching degree is calculated as follows:

[0057] Traverse several monitoring attribute weight distribution results of several equipment status prediction units, sort the monitoring attributes according to the weight from large to small based on each monitoring attribute weight distribution result, and obtain several monitoring attribute sorting results; further, traverse several monitoring attribute sorting results, respectively extract the sequence number parameters of the monitoring attribute set in each sorting, and store them as several monitoring attribute sequence numbers; further, use the matching evaluation function: A plurality of monitoring attribute number sequences are processed respectively, so as to obtain a plurality of matching degrees corresponding to a plurality of equipment state prediction units one by one.

[0058] Through the management end, configure the matching degree threshold; then, based on the several matching degrees, extract the target device state prediction unit set whose matching degree is greater than or equal to the matching degree threshold from the device state prediction unit library. At this time, the target device state prediction unit set is the functional component that needs to perform device state prediction in the next step. The required computing power is added up according to several required computing power identifiers of the target device state prediction unit set to obtain the required computing power prediction value.

[0059] S30: Obtaining edge node task allocation status;

[0060] S40: performing edge node scheduling optimization according to the demand computing power prediction value and the edge node task allocation state to obtain an edge node scheduling solution;

[0061] Further, according to the demand computing power prediction value and the edge node task allocation state, edge node scheduling optimization is performed to obtain an edge node scheduling solution. Step S40 includes the following steps:

[0062] S41: Obtaining a redundant computing power list of an edge node list according to the edge node task allocation state;

[0063] S42: According to the demand computing power prediction value and based on the redundant computing power list, the target edge node is matched and added into the edge node scheduling scheme.

[0064] Specifically, the edge node task allocation state refers to the occupancy state of the current edge node. In detail, the edge node task allocation state includes a redundant computing power list of the edge node list at the current moment, and the redundant computing power refers to the idle computing power that can be scheduled.

[0065] In one implementation, the redundant computing power list is traversed and compared with the predicted value of the required computing power, edge nodes whose redundant computing power is greater than the predicted value of the required computing power are extracted, and the aforementioned target device state prediction unit set is downloaded to the corresponding edge node to obtain an edge node scheduling plan;

[0066] In another embodiment, when there is no edge node in the redundant computing power list that is greater than the predicted value of the required computing power, the target device state prediction unit set is split into multiple independent units according to the required computing power identification set, and then a scheduling plan is constructed based on the redundant computing power list, and the edge node scheduling plan is obtained by optimizing the edge node scheduling number as the fitness function;

[0067] In a third implementation, when the above two methods cannot meet the required computing power forecast value, a forecast warning message is generated and fed back to the management end.

[0068] S50: activating the target edge node according to the edge node scheduling scheme, performing equipment state prediction based on the lubrication system state deviation time series matrix, and obtaining equipment state identification information;

[0069] S60: When the device status identification information includes an abnormal status type, the device status identification information is sent to the management end through the cloud, and is displayed synchronously with the main collector.

[0070] Specifically, according to the edge node scheduling plan, the target edge node is configured, and the target edge node downloads the target device state prediction unit for device state prediction. At this time, the lubrication system state deviation timing matrix is ​​input into the target device state prediction unit to output the device state identification information.

[0071] When the equipment status identification information includes the abnormal status type, for example, when the codes of abnormal operating conditions such as liquid level, interface change, filter failure, emulsification, etc. are included, the equipment status identification information is sent to the management end through the cloud, and the abnormal status type is synchronously displayed on the main collector, as well as the DCS system, PC and mobile end of the management end.

[0072] An embodiment of the present invention provides a device for monitoring and diagnosing the state of a lubrication system of an active device, which has at least the following technical effects:

[0073] By setting flow, viscosity, temperature, density, dielectric constant, water activity, water content, metal chip density, particle distribution density, oil-water interface, oil-gas interface, pressure and emulsification degree as monitoring attributes, the state of the lubrication system can be fully monitored, which improves the comprehensiveness of the monitoring state, thereby solving the problem that the existing technology cannot reflect the lubrication state of the equipment lubrication system as a whole. At the same time, the demand computing power is predicted by using the lubrication system state deviation timing matrix, and the edge node scheduling is performed according to the demand computing power prediction value. Equipment state analysis can be performed, which can reasonably allocate tasks and optimize computing power usage based on limited local computing power resources, thus solving the problem of insufficient local computing power and achieving the technical effect of efficiently predicting the state of active equipment based on the state of the lubrication system. It provides strong technical support for fault diagnosis and preventive maintenance of active equipment, and improves the reliability and stability of equipment operation.

[0074] Embodiment 2:

[0075] like Figure 2 As shown, an embodiment of the present invention further provides a system for monitoring and diagnosing the state of a lubrication system of an active device, which is deployed in a device for monitoring and diagnosing the state of a lubrication system of an active device provided in the first embodiment, and the execution steps include:

[0076] When the active equipment is started and the timer meets the preset time length, the master collector receives the monitoring status of the lubrication system from the slave collector, and calculates the deviation from the theoretical state of the lubrication system to obtain the lubrication system state deviation time series matrix, and at the same time resets the timer to zero and restarts the timing, wherein the monitoring status attributes of the lubrication system include flow, viscosity, temperature, density, dielectric constant, water activity, water content, metal chip density, particle distribution density, oil-water interface, oil-gas interface, pressure and emulsification degree;

[0077] Performing demand computing power forecasting according to the lubrication system state deviation time series matrix to obtain a demand computing power forecast value;

[0078] Get the edge node task allocation status;

[0079] Perform edge node scheduling optimization according to the demand computing power prediction value and the edge node task allocation status to obtain an edge node scheduling solution;

[0080] activating the target edge node according to the edge node scheduling scheme, performing equipment state prediction based on the lubrication system state deviation time series matrix, and obtaining equipment state identification information;

[0081] When the device status identification information includes an abnormal status type, the device status identification information is sent to the management end through the cloud and displayed synchronously with the main collector.

[0082] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as devices, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0084] The present invention is described with reference to flowcharts and / or block diagrams of apparatuses, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0087] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0088] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A device for monitoring and diagnosing the state of a lubrication system of an active equipment, characterized in that: A system for monitoring and diagnosing the state of a lubrication system of an active device is deployed. The system includes a collection terminal, a cloud terminal, and a management terminal. The collection terminal includes a master collector and a slave collector. The execution steps include: When the active equipment is started and the timer meets the preset time length, the master collector receives the monitoring status of the lubrication system from the slave collector, and calculates the deviation from the theoretical state of the lubrication system to obtain the lubrication system state deviation time series matrix, and at the same time resets the timer to zero and restarts the timing, wherein the monitoring status attributes of the lubrication system include flow, viscosity, temperature, density, dielectric constant, water activity, water content, metal chip density, particle distribution density, oil-water interface, oil-gas interface, pressure and emulsification degree; Performing demand computing power forecasting according to the lubrication system state deviation time series matrix to obtain a demand computing power forecast value; Get the edge node task allocation status; Perform edge node scheduling optimization according to the demand computing power prediction value and the edge node task allocation status to obtain an edge node scheduling solution; activating the target edge node according to the edge node scheduling scheme, performing equipment state prediction based on the lubrication system state deviation time series matrix, and obtaining equipment state identification information; When the device status identification information includes an abnormal status type, the device status identification information is sent to the management end through the cloud and displayed synchronously with the main collector.

2. The device according to claim 1, characterized in that The demand computing power prediction is performed according to the lubrication system state deviation time series matrix to obtain the demand computing power prediction value, including: Perform fuzzy deviation parameter analysis according to the lubrication system state deviation time series matrix to obtain a first monitoring attribute fuzzy deviation parameter up to an Nth monitoring attribute fuzzy deviation parameter; Extracting a set of monitoring attributes whose fuzzy deviation parameters are greater than or equal to a fuzzy deviation threshold according to the first monitoring attribute fuzzy deviation parameter to the Nth monitoring attribute fuzzy deviation parameter; The computing power demand forecast is performed according to the monitoring attribute set to obtain the computing power demand forecast value.

3. The device according to claim 2, characterized in that Performing a demand computing power forecast according to the monitoring attribute set to obtain the demand computing power forecast value includes: Obtaining a device state prediction unit library, wherein the device state prediction unit library has a plurality of device state prediction units, and the plurality of device state prediction units have a plurality of monitoring attribute weight distribution results and a plurality of required computing power identifiers; Based on the monitoring attribute set, traverse the plurality of monitoring attribute weight distribution results to perform matching degree analysis to obtain a plurality of matching degrees; According to the plurality of matching degrees, extracting a target device state prediction unit set having a matching degree greater than or equal to a matching degree threshold from the device state prediction unit library; According to the target device state prediction unit set, the required computing power is calculated based on the plurality of required computing power identifiers to obtain the required computing power prediction value.

4. The device according to claim 2, characterized in that Performing fuzzy deviation parameter analysis according to the lubrication system state deviation time series matrix to obtain the first monitoring attribute fuzzy deviation parameter to the Nth monitoring attribute fuzzy deviation parameter includes: Obtaining a set of monitoring attribute deviation thresholds; Extracting the first monitoring attribute deviation threshold value of the monitoring attribute deviation threshold value set until the Nth monitoring attribute deviation threshold value; Counting the proportion of moments when the deviation vector modulus in the first monitoring attribute deviation vector modulus time series information of the lubrication system state deviation time series matrix is ​​greater than or equal to the first monitoring attribute deviation threshold, and setting it as the first monitoring attribute fuzzy deviation parameter; The proportion of moments when the deviation vector modulus in the Nth monitoring attribute deviation vector modulus time series information of the lubrication system state deviation time series matrix is ​​greater than or equal to the Nth monitoring attribute deviation threshold is counted and set as the Nth monitoring attribute fuzzy deviation parameter.

5. The device according to claim 3, characterized in that Based on the monitoring attribute set, the plurality of monitoring attribute weight distribution results are traversed to perform matching degree analysis to obtain a plurality of matching degrees, including: Traversing the plurality of monitoring attribute weight distribution results, sorting the monitoring attributes according to the weight from large to small, and obtaining a plurality of monitoring attribute sorting results; Obtain the monitoring attribute set, traverse the plurality of monitoring attribute sequences, and extract a plurality of monitoring attribute sequence numbers; Construct a matching evaluation function: Among them, P(X i ) represents the matching degree of the i-th monitoring attribute sequence, n represents the number of monitoring attribute sets, X ij The jth number representing the i-th monitoring attribute number sequence, X i Characterizes the sequence of the i-th monitoring attribute number; According to the matching evaluation function, the plurality of monitoring attribute number sequences are traversed to perform matching analysis to obtain the plurality of matching degrees.

6. The device according to claim 3, characterized in that The device state prediction unit library construction step includes: Matching the active equipment operation log according to the active equipment model, wherein the active equipment operation log includes a lubrication system state deviation time series record matrix and active equipment state type record information; Obtaining preset weight distribution information of monitoring attributes; The input layer of the long short-term memory neural network is configured according to the preset weight distribution information of the monitoring attribute, the active equipment state type record information is used as supervision, and the lubrication system state deviation time series record matrix is ​​used as input to train the equipment state prediction unit and add it to the equipment state prediction unit library.

7. The device according to claim 1, characterized in that Performing edge node scheduling optimization according to the demand computing power prediction value and the edge node task allocation state to obtain an edge node scheduling solution includes: Obtaining a redundant computing power list of an edge node list according to the edge node task allocation state; According to the demand computing power prediction value and based on the redundant computing power list, the target edge node is matched and added into the edge node scheduling scheme.

8. A system for monitoring and diagnosing the state of a lubrication system of an active device, characterized in that: A device for monitoring and diagnosing the condition of a lubrication system of a dynamic device as described in any one of claims 1 to 7.

Images