An online monitoring method and system for the operating state of a magnetic drive pump

Abstract

The present invention provides an online monitoring method and system for the operating state of a magnetic drive pump, relating to the technical field of data monitoring. The method includes: generating a fault feature tree of the magnetic drive pump based on historical detection information, generating a temperature monitoring data set through a temperature acquisition unit, generating rotation monitoring data through a speed monitoring unit, synchronously inputting real-time control information into an anomaly detection model to call an anomaly matching database, completing the model initialization of the anomaly detection model, inputting the temperature monitoring data set and the rotation monitoring data into the anomaly detection model, comparing the anomaly recognition result with the fault feature tree after output, and generating an anomaly monitoring result based on the comparison result. The present invention solves the technical problem in the prior art that the monitoring during the operation of the magnetic pump is poor, resulting in low fault monitoring efficiency for the operating state of the magnetic pump, realizes reasonable and accurate monitoring of the operation of the magnetic pump, and further improves the fault monitoring efficiency for the operating state of the magnetic pump.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and particularly relates to an online monitoring method and system for the operating state of a magnetic drive pump. Background Art

[0002] With the rapid development of the petrochemical and chemical industries, magnetic drive pumps have been increasingly widely used due to their characteristics of no leakage, environmental protection, and safety. The magnetic drive pump generates a magnetic field through the coupling of an outer magnetic rotor and an inner magnetic rotor. The outer magnetic rotor drives the inner rotor to rotate through the magnetic field torque. In order to ensure that the magnetic drive pump operates without leakage during operation, it is very necessary to monitor and protect the magnetic pump against faults during operation.

[0003] However, the current monitoring of the magnetic pump during operation is poor, resulting in the technical problem of low efficiency in fault monitoring of the operating state of the magnetic pump. Summary of the Invention

[0004] This application provides an online monitoring method and system for the operating state of a magnetic drive pump, which is used to solve the technical problem that the monitoring of the magnetic pump during operation in the prior art is poor, resulting in low efficiency in fault monitoring of the operating state of the magnetic pump.

[0005] In view of the above problems, this application provides an online monitoring method and system for the operating state of a magnetic drive pump.

[0006] In a first aspect, this application provides an online monitoring method for the operating state of a magnetic drive pump. The method includes: connecting the magnetic drive pump and reading the historical detection information and real-time control information of the magnetic drive pump; generating a fault feature tree of the magnetic drive pump based on the historical detection information, where the horizontal axis of the trunk of the fault feature tree is the time axis, the vertical axis of the branches is the fault axis, and at least one abnormal source branch corresponds to the vertical axis of the branches; monitoring the temperature of the isolation sleeve through the temperature acquisition unit to generate a temperature monitoring data set; monitoring the rotation of the magnetic drive pump through the speed monitoring unit to generate rotation monitoring data; synchronously inputting the real-time control information into an anomaly detection model to call an anomaly matching database to complete the model initialization of the anomaly detection model; inputting the temperature monitoring data set and the rotation monitoring data into the anomaly detection model and outputting an anomaly recognition result; performing feature comparison based on the anomaly recognition result and the fault feature tree, and generating an anomaly monitoring result based on the comparison result.

[0007] Second aspect, the present application provides an online monitoring system for the operating state of a magnetic drive pump. The system includes: an information reading module, which is used to connect to the magnetic drive pump and read the historical detection information and real-time control information of the magnetic drive pump; a feature tree generation module, which is used to generate a fault feature tree of the magnetic drive pump based on the historical detection information. Wherein, the horizontal axis of the trunk of the fault feature tree is the time axis, the vertical axis of the branches is the fault axis, and at least one abnormal source branch corresponds to the vertical axis of the branches; a temperature monitoring module, which is used to monitor the temperature of the isolation sleeve through the temperature acquisition unit and generate a temperature monitoring data set; a rotation monitoring module, which is used to monitor the rotation of the magnetic drive pump through the speed monitoring unit and generate rotation monitoring data; a model initialization module, which is used to synchronously input the real-time control information into an anomaly detection model to call an anomaly matching database and complete the model initialization of the anomaly detection model; an input module, which is used to input the temperature monitoring data set and the rotation monitoring data into the anomaly detection model and output an anomaly recognition result; a feature comparison module, which is used to compare features according to the anomaly recognition result and the fault feature tree and generate an anomaly monitoring result based on the comparison result.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0009] An online monitoring method and system for the operating state of a magnetic drive pump provided in the present application relate to the technical field of data monitoring, solve the technical problem that the monitoring during the operation of a magnetic pump in the prior art is poor, resulting in low fault monitoring efficiency for the operating state of the magnetic pump, and realize reasonable and accurate monitoring of the operation of the magnetic pump, thereby improving the fault monitoring efficiency for the operating state of the magnetic pump. Description of the Drawings

[0010] Figure 1 It is a schematic flow chart of an online monitoring method for the operating state of a magnetic drive pump provided in the present application;

[0011] Figure 2 It is a schematic flow chart of outputting an anomaly monitoring result in an online monitoring method for the operating state of a magnetic drive pump provided in the present application;

[0012] Figure 3 It is a schematic flow chart of anomaly recognition of a magnetic drive pump in an online monitoring method for the operating state of a magnetic drive pump provided in the present application;

[0013] Figure 4 It is a schematic flow chart of fault feedback and update in an online monitoring method for the operating state of a magnetic drive pump provided in the present application;

[0014] Figure 5 This application provides a schematic structural diagram of an online monitoring system for the operating state of a magnetic drive pump.

[0015] Explanation of reference numerals: Information reading module 1, feature tree generation module 2, temperature monitoring module 3, rotation monitoring module 4, model initialization module 5, input module 6, feature comparison module 7. Detailed implementation manners

[0016] This application provides an online monitoring method and system for the operating state of a magnetic drive pump to solve the technical problem in the prior art that the monitoring during the operation of the magnetic pump is poor, resulting in low efficiency of fault monitoring of the operating state of the magnetic pump.

[0017] Embodiment 1

[0018] As Figure 1 shown, an embodiment of this application provides an online monitoring method for the operating state of a magnetic drive pump. This method is applied to an online monitoring system for the operating state, and the online monitoring system for the operating state is communicatively connected to a temperature acquisition unit and a speed monitoring unit. This method includes:

[0019] Step S100: Connect the magnetic drive pump and read the historical detection information and real-time control information of the magnetic drive pump;

[0020] Specifically, an online monitoring method for the operating state of a magnetic drive pump provided by an embodiment of this application is applied to an online monitoring system for the operating state. The online monitoring system for the operating state is communicatively connected to a temperature acquisition unit and a speed monitoring unit, and the temperature acquisition unit and the speed monitoring unit are used to acquire parameters of the magnetic drive pump during operation.

[0021] To ensure the accuracy of fault monitoring of the magnetic drive pump during operation in the later stage, it is necessary to connect the online monitoring system for the operating state to the target magnetic drive pump, and further read the historical monitoring information and real-time control information of the target magnetic drive pump. The historical detection information refers to the information obtained by detecting the motor, strong magnetic coupler, and centrifugal pump included in the target magnetic pump before the current moment, and the real-time control information refers to the information for real-time corresponding control of the motor, strong magnetic coupler, and centrifugal pump included in the target magnetic pump during operation, which serves as an important reference basis for fault monitoring of the magnetic drive pump during operation in the later stage.

[0022] Step S200: Generate a fault feature tree of the magnetic drive pump based on the historical detection information, where the horizontal axis of the trunk of the fault feature tree is the time axis, the vertical axis of the branches is the fault axis, and at least one abnormal source branch corresponds to the vertical axis of the branches;

[0023] Specifically, based on the historical detection information obtained above, a fault feature tree of the magnetic drive pump is constructed. The fault features in the fault feature tree are obtained by extracting fault features from the historical fault information contained in the historical detection information. At the same time, the trunk of the fault feature tree is taken as the horizontal axis with time as the unit, and the branches of the fault feature tree are taken as the vertical axis with faults as the unit. The fault feature tree is constructed based on the horizontal axis with time as the unit and the vertical axis with faults as the unit. The fault feature tree contains fault features, the faults corresponding to the fault features, the time corresponding to the faults, etc. And there should be at least one abnormal source branch in the numerical vertical axis of the fault feature tree, which means that there is at least one fault in the numerical vertical axis of the fault feature tree, thus providing a guarantee for realizing fault monitoring of the magnetic drive pump during operation.

[0024] Step S300: Monitor the temperature of the isolation sleeve through the temperature acquisition unit to generate a temperature monitoring data set.

[0025] Specifically, the magnetic drive pump generates a magnetic field through the coupling of the outer magnetic rotor and the inner magnetic rotor. The outer magnetic rotor drives the inner rotor to rotate through the magnetic field torque. An isolation sleeve for enclosing the operating medium is provided in the magnetic field where the inner and outer rotors are coupled. The isolation sleeve and the pressure-bearing housing together form a static sealed cavity for enclosing the operating medium, thus realizing complete leakage-free of the magnetic drive pump. Since the isolation sleeve is in the coupling magnetic field of the inner and outer magnetic rotors, its thickness is affected by the sizes of the inner and outer magnetic rotors and the temperature rise of the coupling magnetic field. To keep the temperature of the magnetic drive pump within the normal range during operation, it is necessary to monitor the temperature of the isolation sleeve in the magnetic drive pump in real time through the temperature acquisition unit communicatively connected to the operation status online monitoring system, and record the real-time monitored temperature after summarization and integration as the temperature monitoring data set, laying a foundation for subsequent realizing fault monitoring of the magnetic drive pump during operation.

[0026] Step S400: Monitor the rotation of the magnetic drive pump through the speed monitoring unit to generate rotation monitoring data.

[0027] Specifically, since the magnetic drive pump is a centrifugal pump that uses magnetic force to transmit power, to ensure that the rotational speed of the magnetic drive pump is within the normal range during operation, it is necessary to monitor the rotational speed of the target magnetic drive pump through the speed monitoring unit communicatively connected to the operation status online monitoring system. And the rotational speed of the magnetic drive pump is about 2800 r / min. On this basis, the speed monitoring point unit conducts real-time monitoring and comparison of the rotational speed of the magnetic drive pump, and records the real-time monitored rotational data of the magnetic drive pump as the rotation monitoring data for output, which plays a role in improving the accuracy of realizing fault monitoring of the magnetic drive pump during operation.

[0028] Step S500: Synchronously input the real-time control information into the anomaly detection model to call the anomaly matching database and complete the model initialization of the anomaly detection model;

[0029] Specifically, for more accurate detection and extraction when a magnetic drive pump fails during operation, the obtained real-time control information is then synchronously input into the constructed anomaly detection model to call the anomaly matching database, which means

[0030] Input the real-time control information of each part of the magnetic drive pump in the real-time control information into the anomaly detection model, and adjust the output supervision of the anomaly detection model through the anomaly matching data corresponding to the input real-time control information. The anomaly matching data is extracted from the called anomaly matching database. When the output result of the anomaly detection model is consistent with the supervision data, the current group of training ends. When all the real-time control of each part of the magnetic drive pump in the real-time control information is trained, that is, the anomaly recognition of the magnetic drive pump in the real-time control information is completed, and the initialization of the anomaly detection model is completed, so as to be used as reference data for later fault monitoring of the magnetic drive pump during operation.

[0031] Step S600: Input the temperature monitoring data set and the rotation monitoring data into the anomaly detection model and output the anomaly recognition result;

[0032] Specifically, input the temperature monitoring data set generated by monitoring the temperature of the isolation sleeve through the temperature acquisition unit and the rotation monitoring data generated by monitoring the rotation of the magnetic drive pump by the speed monitoring unit into the above-mentioned constructed anomaly detection model, which means first extracting the fault records in the temperature monitoring data set and rotation monitoring data of the magnetic drive pump, and then corresponding to the anomaly matching database according to the fault records, and then outputting the anomaly recognition result of the magnetic drive pump. The anomaly recognition result includes the abnormal temperature data and abnormal rotation data of the target magnetic drive pump, improving the accuracy of later fault monitoring of the magnetic drive pump during operation.

[0033] Step S700: Compare the features according to the anomaly recognition result and the fault feature tree, and generate an anomaly monitoring result based on the comparison result.

[0034] Specifically, to improve the accuracy of fault monitoring of the magnetic drive pump during operation, it is necessary to compare the abnormal recognition results with the fault feature tree for fault features. This refers to authenticating the abnormal rotation data and abnormal temperature data of the magnetic drive pump contained in the abnormal recognition results, and using the authenticated abnormalities to perform corresponding feedback updates on the fault features, fault events, and fault times contained in the fault feature tree. On this basis, the feature comparison between the abnormal recognition results and the fault feature tree is completed. Finally, based on the comparison abnormal results obtained from the comparison, the abnormal detection results of the magnetic drive pump are improved, realizing reasonable and accurate monitoring of the operation of the magnetic pump, and further improving the fault monitoring efficiency of the operation state of the magnetic pump.

[0035] Furthermore, as Figure 2 shown, step S800 of this application further includes:

[0036] Step S810: Set N of the vibration monitoring devices and record the device coordinates of the vibration monitoring devices, where N is an integer greater than 2;

[0037] Step S820: Collect the vibration data of the magnetic drive pump through N of the vibration monitoring devices and output the vibration data collection result;

[0038] Step S830: Generate auxiliary verification information according to the vibration data collection result;

[0039] Step S840: Auxiliary authenticate the comparison result through the auxiliary verification information and output the abnormal monitoring result.

[0040] Specifically, the vibration monitoring devices communicatively connected through the operation state online monitoring system are used to monitor the vibration of the magnetic drive pump during operation. Further, N vibration detection devices are correspondingly set in the magnetic drive pump, and the position coordinates of the N vibration monitoring devices set in the magnetic drive pump are recorded at the same time. At the same time, the vibration data of the magnetic drive pump is collected through the N vibration monitoring devices. The vibration data of the magnetic drive pump can be that the magnetic drive pump is driven by an electric motor, and due to the imbalance of the electromagnetic force, the stator is subjected to a changing electromagnetic force, thereby causing periodic vibration. Thus, the collected vibration data collection result is output. Further, the vibration characteristics are extracted from the vibration data collection result respectively, and the vibration positioning result is determined according to the coordinates of the vibration monitoring device where the vibration extraction data comes from. Auxiliary verification information is correspondingly generated according to the extracted vibration characteristics and vibration positioning result, and the comparison result obtained by comparing the abnormal recognition result with the fault feature tree is auxiliary authenticated through the auxiliary verification information, so as to output the abnormal monitoring result including the auxiliary authentication.

[0041] Furthermore, step S830 of this application includes:

[0042] Step S831: Set the synchronization authentication tolerance interval for vibration;

[0043] Step S832: Extract vibration features from the vibration data acquisition results respectively to generate vibration extraction data;

[0044] Step S833: Perform data source node authentication on the vibration extraction data through the synchronization authentication tolerance interval;

[0045] Step S834: Determine the vibration positioning result according to the node authentication result and the device coordinates, and generate the auxiliary verification information according to the vibration extraction data and the vibration positioning result.

[0046] Specifically, in order to generate the auxiliary verification information based on the obtained vibration data acquisition results, first, the synchronization authentication tolerance interval for vibration is set. The synchronization authentication tolerance interval is a time interval. Then, the vibration features are extracted from the vibration data acquisition results respectively. The vibration features can be that the vibration frequency of the magnetic drive pump is the product of the rotational speed and the number of poles or a multiple of it. If this frequency is consistent with the natural frequency of the motor base in the magnetic drive pump, the vibration will increase, and the vibration of the magnetic drive pump will also increase accordingly due to the influence of the motor. Thus, the data source node authentication of the vibration extraction data is performed through the set synchronization authentication tolerance interval, that is, the specific corresponding source devices of different vibration extraction data in N vibration monitoring devices are authenticated. Finally, the vibration positioning of the magnetic drive pump is determined according to the node authentication result and the current coordinates of the device, and at the same time, the auxiliary verification information when the magnetic drive pump fails during operation is generated according to the vibration extraction data and the vibration positioning result, achieving the technical effect of providing an important basis for realizing fault monitoring of the magnetic drive pump during operation in the later stage.

[0047] Furthermore, step S800 of this application includes:

[0048] Step S850: Set the regular maintenance period of the magnetic drive pump, where each time node within the regular maintenance period corresponds to a node integral;

[0049] Step S860: Perform integral matching for anomaly detection based on the anomaly monitoring results to generate additional integrals;

[0050] Step S870: Accumulate the maintenance integrals through the node integrals and the additional integrals. When the accumulated result of the maintenance integrals within any regular maintenance period meets the integral threshold, a maintenance instruction is generated;

[0051] Step S880: Control the equipment maintenance of the magnetic drive pump through the maintenance instruction.

[0052] Specifically, in order to detect the faults of the magnetic drive pump in a timely manner, it is necessary to perform regular maintenance on the magnetic drive pump. Therefore, a regular maintenance cycle is set accordingly, and the regular maintenance cycle can be set to 7 days. At the same time, each time node within the regular maintenance cycle corresponds to a node integral. The larger the node integral, the more the magnetic drive pump should be maintained at the corresponding time node. Further, based on the abnormal monitoring results output by the auxiliary verification information comparison for auxiliary authentication of the results, the integral of the abnormal detection is matched, and the successfully matched integral is recorded as the new integral. At the same time, the node integral corresponding to each time node within each cycle and the new integral are used together for the accumulation of the maintenance integral. If the cumulative result of the maintenance integral within any one cycle of the regular maintenance cycle meets the set integral threshold, a maintenance instruction for the magnetic drive pump is generated in the system. The obtained integral threshold is preset by relevant technical personnel according to the data when the magnetic drive pump needs to be maintained. Finally, the equipment maintenance operation of the magnetic drive pump is controlled according to the generated maintenance instruction, so as to ensure better monitoring of the faults of the magnetic drive pump during its operation in the later stage.

[0053] Furthermore, step S880 of the present application includes:

[0054] Step S881: Generate a reset maintenance node when any equipment maintenance of the magnetic drive pump is executed;

[0055] Step S882: Perform maintenance management of the magnetic drive pump according to the reset maintenance node and the regular maintenance cycle.

[0056] Specifically, when controlling the equipment maintenance operation of the magnetic drive pump according to the generated maintenance instruction, on the basis of performing maintenance on any equipment in the magnetic drive pump, a reset maintenance node is generated. The reset maintenance node means that after the maintenance of any one equipment in the target magnetic drive pump is completed, when performing maintenance on any other equipment in the target magnetic drive pump, the maintenance node needs to be reset. Further, based on the reset maintenance node and the regular maintenance cycle, regular maintenance management of the magnetic drive pump is performed to achieve fault monitoring of the magnetic drive pump during its operation based on the maintenance management.

[0057] Furthermore, as Figure 3 shown, step S600 of the present application further includes:

[0058] Step S610: Continuously record the real-time control information and match the continuous recognition database;

[0059] Step S620: Reset the model of the anomaly detection model through the continuous recognition database, summarize the continuously collected data, and input the summarized data into the reset anomaly detection model;

[0060] Step S630: Output the continuous anomaly recognition result, and perform anomaly recognition on the magnetic drive pump according to the anomaly recognition result and the continuous anomaly recognition result.

[0061] Specifically, continuously record the real-time control information read from the connected magnetic drive pump for a fixed time period, and match the continuous recognition database according to the obtained continuous recorded control information. The continuous recognition database collects information from the continuously recorded control information, and the information collected from the continuously recorded control information includes but is not limited to the information for real-time corresponding control of the motor, strong magnetic coupler, and centrifugal pump included in the target magnetic pump during operation, etc. On this basis, the construction of the continuous recognition database is completed. Further, the above anomaly detection model is updated and reset through the constructed continuous recognition database. The update and reset of the anomaly detection model refer to updating and replacing the real-time control information originally constructed in the anomaly detection model with the currently collected continuous recorded data, so as to obtain the reset anomaly detection model. At the same time, the continuously collected data is summarized and input into the reset anomaly detection model. If there is an anomaly in the current magnetic drive pump, the corresponding continuous anomaly recognition result is output. Finally, the magnetic drive pump is anomaly-recognized according to the anomaly recognition result and the continuous anomaly recognition result to ensure the efficiency of fault monitoring during the operation of the magnetic drive pump.

[0062] Furthermore, as Figure 4 shown, step S700 of this application further includes:

[0063] Step S710: Perform anomaly authentication on the anomaly monitoring result;

[0064] Step S720: Perform fault feedback update on the fault feature tree based on the anomaly authentication result.

[0065] Specifically, to ensure real-time and accurate fault monitoring of the magnetic drive pump, it is necessary to perform anomaly authentication on the comparison result obtained by comparing the anomaly recognition result with the fault feature tree, that is, to confirm the anomalies in the abnormal rotation data and abnormal temperature data of the magnetic drive pump included in the anomaly recognition result, which means to determine that there are indeed abnormal rotations and abnormal temperatures and other anomalies in the magnetic drive pump, and use the confirmed anomalies to perform feedback updates on the fault features, fault events, and fault times included in the fault feature tree for corresponding abnormal situations such as abnormal rotations and abnormal temperatures. According to the feedback update result, the technical effect of fault monitoring during the operation of the magnetic drive pump is achieved.

[0066] Embodiment 2

[0067] Based on the same inventive concept as the online monitoring method for the operating state of a magnetic drive pump in the foregoing embodiment, as Figure 5 shown, the present application provides an online monitoring system for the operating state of a magnetic drive pump, the system comprising:

[0068] An information reading module 1, which is used to connect to the magnetic drive pump and read the historical detection information and real-time control information of the magnetic drive pump;

[0069] A feature tree generation module 2, which is used to generate a fault feature tree of the magnetic drive pump based on the historical detection information, wherein the horizontal axis of the trunk of the fault feature tree is the time axis, the vertical axis of the branches is the fault axis, and at least one abnormal source branch corresponds to the vertical axis of the branches;

[0070] A temperature monitoring module 3, which is used to monitor the temperature of the isolation sleeve through the temperature acquisition unit and generate a temperature monitoring data set;

[0071] A rotation monitoring module 4, which is used to monitor the rotation of the magnetic drive pump through the speed monitoring unit and generate rotation monitoring data;

[0072] A model initialization module 5, which is used to synchronously input the real-time control information into an anomaly detection model to call an anomaly matching database and complete the model initialization of the anomaly detection model;

[0073] An input module 6, which is used to input the temperature monitoring data set and the rotation monitoring data into the anomaly detection model and output an anomaly recognition result;

[0074] A feature comparison module 7, which is used to compare features according to the anomaly recognition result and the fault feature tree and generate an anomaly monitoring result based on the comparison result.

[0075] Furthermore, the system further comprises:

[0076] A device coordinate module, which is used to set N vibration monitoring devices and record the device coordinates of the vibration monitoring devices, where N is an integer greater than 2;

[0077] A vibration data acquisition module, which is used to acquire the vibration data of the magnetic drive pump through N vibration monitoring devices and output a vibration data acquisition result;

[0078] An auxiliary verification information module, which is used to generate auxiliary verification information according to the vibration data acquisition result;

[0079] An output module, which is used to perform auxiliary authentication on the comparison result through the auxiliary verification information and output the abnormal monitoring result.

[0080] Furthermore, the system further includes:

[0081] An interval module, which is used to set a synchronous authentication tolerance interval for vibration;

[0082] A feature extraction module, which is used to perform vibration feature extraction on the vibration data acquisition result respectively to generate vibration extraction data;

[0083] A node authentication module, which is used to perform data source node authentication on the vibration extraction data through the synchronous authentication tolerance interval;

[0084] A result determination module, which is used to determine the vibration positioning result according to the node authentication result and the device coordinates, and generate the auxiliary verification information according to the vibration extraction data and the vibration positioning result.

[0085] Furthermore, the system further includes:

[0086] An overhaul period module, which is used to set the regular overhaul period of the magnetic drive pump, wherein each time node in the regular overhaul period corresponds to a node integral;

[0087] An integral matching module, which is used to perform integral matching for abnormal detection based on the abnormal monitoring result to generate new integrals;

[0088] An instruction generation module, which is used to accumulate overhaul integrals through the node integral and the new integral. When the accumulated result of the overhaul integrals in any regular overhaul period meets the integral threshold, an overhaul instruction is generated;

[0089] An equipment overhaul module, which is used to control the equipment overhaul of the magnetic drive pump through the overhaul instruction.

[0090] Furthermore, the system further includes:

[0091] A node generation module, which is used to generate a reset overhaul node when any equipment overhaul of the magnetic drive pump is executed;

[0092] An overhaul management module, which is used to perform overhaul management of the magnetic drive pump according to the reset overhaul node and the regular overhaul period.

[0093] Furthermore, the system further includes:

[0094] A matching module, which is used to continuously record the real-time control information and match the continuous recognition database;

[0095] A model reset module, which is used to reset the anomaly detection model through the continuous recognition database, summarize the continuously collected data, and input the reset anomaly detection model;

[0096] An anomaly recognition module, which is used to output continuous anomaly recognition results and perform anomaly recognition of the magnetic drive pump according to the anomaly recognition results and the continuous anomaly recognition results.

[0097] Furthermore, the system further includes:

[0098] An anomaly authentication module, which is used to authenticate the anomaly monitoring results;

[0099] A feedback update module, which is used to perform fault feedback update of the fault feature tree based on the anomaly authentication results.

[0100] Through the foregoing detailed description of a method for online monitoring of the operating state of a magnetic drive pump in this specification, those skilled in the art can clearly know an online monitoring system for the operating state of a magnetic drive pump in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, refer to the description in the method part.

[0101] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An on-line monitoring method for the operating state of a magnetic drive pump, characterized in that, The method is applied to an on-line monitoring system for operating status, which is communicatively connected to a temperature acquisition unit and a speed monitoring unit. The method includes: Connect the magnetic drive pump and read the historical detection information and real-time control information of the magnetic drive pump; Generate a fault feature tree of the magnetic drive pump based on the historical detection information. Among them, the horizontal axis of the trunk of the fault feature tree is the time axis, and the vertical axis of the branches is the fault axis. And there is at least one abnormal source branch corresponding to the vertical axis of the branches. Specifically, it includes constructing the fault feature tree of the magnetic drive pump based on the historical detection information. The fault features are obtained by extracting fault features from the historical fault information contained in the historical detection information. Take the trunk of the fault feature tree as the horizontal axis in units of time and the branches of the fault feature tree as the vertical axis in units of faults. Construct the fault feature tree based on the horizontal axis in units of time and the vertical axis in units of faults. The fact that there is at least one abnormal source branch corresponding to the vertical axis of the branches means that there is at least one fault in the vertical axis of the branches of the fault feature tree; Monitor the temperature of the isolation sleeve through the temperature acquisition unit and generate a temperature monitoring data set; Monitor the rotation of the magnetic drive pump through the speed monitoring unit and generate rotation monitoring data; Synchronously input the real-time control information into the anomaly detection model to call the anomaly matching database and complete the model initialization of the anomaly detection model. Specifically, it includes inputting the real-time control information of each part of the magnetic drive pump in the real-time control information into the anomaly detection model, and adjusting the output supervision of the anomaly detection model through the anomaly matching data corresponding to the input real-time control information. The anomaly matching data is obtained by extracting from the called anomaly matching database. When the output result of the anomaly detection model is consistent with the supervision data, the current group of training ends. When all the real-time control information of each part of the magnetic drive pump in the real-time control information is trained, the anomaly recognition of the magnetic drive pump in the real-time control information is completed, and the initialization of the anomaly detection model is completed; Input the temperature monitoring data set and the rotation monitoring data into the anomaly detection model and output an anomaly recognition result; Perform feature comparison according to the anomaly recognition result and the fault feature tree, and generate an anomaly monitoring result based on the comparison result.

2. The method according to claim 1, characterized in that, The on-line monitoring system for operating status is communicatively connected to a vibration monitoring device. The method further includes: Set N vibration monitoring devices and record the device coordinates of the vibration monitoring devices, where N is an integer greater than 2; Collect vibration data of the magnetic drive pump through N vibration monitoring devices and output a vibration data collection result; Generate auxiliary verification information according to the vibration data collection result; Auxiliary authenticate the comparison result through the auxiliary verification information and output the anomaly monitoring result.

3. The method according to claim 2, wherein The method further includes: Set a synchronous authentication tolerance interval for vibration, where the synchronous authentication tolerance interval is a time interval; Extract vibration features from the vibration data collection results respectively to generate vibration extraction data; Perform data source node authentication on the vibration extraction data through the synchronization authentication tolerance interval; Determine the vibration positioning result according to the node authentication result and the device coordinates, and generate the auxiliary verification information according to the vibration extraction data and the vibration positioning result.

4. The method according to claim 1, wherein The method further includes: Set the regular maintenance period of the magnetic drive pump, wherein each time node in the regular maintenance period corresponds to a node integral; Perform integral matching for anomaly detection based on the anomaly monitoring result to generate additional integrals; Accumulate maintenance integrals through the node integrals and the additional integrals. When the accumulated result of the maintenance integrals in any regular maintenance period meets the integral threshold, a maintenance instruction is generated; Control the equipment maintenance of the magnetic drive pump through the maintenance instruction.

5. The method according to claim 4, wherein The method further includes: Generate a reset maintenance node when any equipment maintenance of the magnetic drive pump is executed; Perform maintenance management of the magnetic drive pump according to the reset maintenance node and the regular maintenance period.

6. The method according to claim 1, characterized in that, The method further includes: Continuously record the real-time control information and match the continuous recognition database; Reset the anomaly detection model through the continuous recognition database, summarize the continuously collected data, and input the reset anomaly detection model; Output the continuous anomaly recognition result, and perform anomaly recognition of the magnetic drive pump according to the anomaly recognition result and the continuous anomaly recognition result.

7. The method according to claim 1, characterized in that, The method further includes: Perform anomaly authentication on the anomaly monitoring result; Perform fault feedback update of the fault feature tree based on the anomaly authentication result.

8. An online monitoring system for the operating state of a magnetic drive pump, characterized in that, The operation status online monitoring system is communicatively connected to a temperature acquisition unit and a speed monitoring unit, and the system includes: An information reading module, which is used to connect to the magnetic drive pump and read the historical detection information and real-time control information of the magnetic drive pump; A feature tree generation module, which is used to generate a fault feature tree of the magnetic drive pump based on the historical detection information. The horizontal axis of the trunk of the fault feature tree is the time axis, and the vertical axis of the branches is the fault axis, and at least one anomaly source branch corresponds to the vertical axis of the branches. Specifically, it includes constructing the fault feature tree of the magnetic drive pump based on the historical detection information. The fault feature is obtained by extracting the fault feature from the historical fault information contained in the historical detection information. The trunk of the fault feature tree is used as the horizontal axis in units of time, and the branches of the fault feature tree are used as the vertical axis in units of faults. The fault feature tree is constructed based on the horizontal axis in units of time and the vertical axis in units of faults. The fact that at least one anomaly source branch corresponds to the vertical axis of the branches of the fault feature tree means that there is at least one fault in the vertical axis of the branches of the fault feature tree; A temperature monitoring module, which is used to monitor the temperature of the isolation sleeve through the temperature acquisition unit to generate a temperature monitoring data set; A rotation monitoring module, which is used to monitor the rotation of the magnetic drive pump through the speed monitoring unit to generate rotation monitoring data; Model initialization module, which is used to synchronously input the real-time control information into the anomaly detection model to call the anomaly matching database and complete the model initialization of the anomaly detection model. Specifically, it includes inputting the real-time control information of each part of the magnetic drive pump in the real-time control information into the anomaly detection model, and performing output supervision adjustment of the anomaly detection model through the anomaly matching data corresponding to the input real-time control information. The anomaly matching data is obtained by extracting from the called anomaly matching database. When the output result of the anomaly detection model is consistent with the supervision data, the current group of training ends. When all the real-time control of each part of the magnetic drive pump in the real-time control information is trained, that is, the anomaly recognition of the magnetic drive pump in the real-time control information is completed, then the initialization of the anomaly detection model is completed; Input module, which is used to input the temperature monitoring data set and the rotation monitoring data into the anomaly detection model and output the anomaly recognition result; Feature comparison module, which is used to compare features according to the anomaly recognition result and the fault feature tree and generate an anomaly monitoring result based on the comparison result.

Images