Online monitoring method of electromagnetic valve and electronic equipment

Abstract

The invention discloses an on-line monitoring method of an electromagnetic valve and electronic equipment, and relates to an electromagnetic valve monitoring technology, and the method comprises the steps: a fault model construction step: collecting a historical abnormal data set of the electromagnetic valve, carrying out the weight analysis of the historical abnormal data set, and constructing an abnormal feature track set according to a weight analysis result; the online monitoring step is used for collecting real-time operation data of the electromagnetic valve, judging whether the real-time operation data is abnormal or not according to preset standard operation data, if yes, extracting abnormal parameters in the real-time operation data, and sending the abnormal parameters to a server; and according to the abnormal parameters, finding out an abnormal characteristic track corresponding to the abnormal parameters from an abnormal characteristic track set as a target abnormal characteristic track, predicting predicted operation data of the solenoid valve according to the target abnormal characteristic track, and generating abnormal processing information at the same time. According to the invention, the monitoring efficiency and the feedback speed are improved, so that a user can respond to and handle exceptions in time.

Description

Technical Field

[0001] The present invention relates to a solenoid valve monitoring technology, and in particular to an online monitoring method and electronic equipment for a solenoid valve. Background Art

[0002] A solenoid valve is a valve that uses electromagnetic force to control the flow of fluid (liquid or gas). It is an important automatic control component. Because the solenoid valve has a fast response speed, usually in milliseconds, and is small in size, simple in structure, high in control accuracy, good in sealing performance, long in service life, and easy to remotely control, it is widely used in industrial automation, building automation, automobiles, household appliances and other fields. The solenoid valve controls the opening and closing of the valve through the magnetic field generated by the electromagnetic coil. When the electromagnetic coil is energized, a magnetic field is generated, which attracts or releases the valve core to open or close the valve. When the electromagnetic coil is de-energized, the magnetic field disappears, the valve core is reset by the spring or other reset mechanism, and the valve is closed.

[0003] At present, the inspection of solenoid valves is basically carried out through manual experience. For example, the impedance of the solenoid valve solenoid is measured by a multimeter, the insulation performance is measured by an insulation meter, the valve core assembly is disassembled to check the mechanical wear, etc. For solenoid valves that are energized for a long time, since such solenoid valves do not operate frequently (mechanical wear is small), the reason for the failure of most solenoid valves is that the solenoid works with power for a long time and the high ambient temperature causes a short circuit between the winding turns (magnetism weakens), the solenoid coil terminals have poor contact, and it is inconvenient to test the wires and solenoids when the unit is running.

[0004] The existing technology mainly focuses on data analysis and research, by collecting the working performance parameters and characteristics of multiple abnormal solenoid valves to generate an information set, and then compares the data collected by tracking with the data information set to determine whether the solenoid valve is abnormal. However, in the actual implementation process, there are situations where all data collection conditions cannot be met, and the processing process is complicated and uses a large number of calculations, so most of them can only remain in the theoretical stage. Summary of the invention

[0005] The purpose of the present disclosure is to provide an online monitoring method and electronic equipment for a solenoid valve.

[0006] In order to achieve the above objectives, in a first aspect, the present disclosure provides an online monitoring method for a solenoid valve, the method comprising: A fault model building step is used to collect a historical abnormal data set of the solenoid valve, perform weight analysis on the historical abnormal data set, and construct an abnormal feature trajectory set according to the weight analysis result; The online monitoring step is used to collect the real-time operation data of the solenoid valve, and determine whether the real-time operation data has any abnormality based on the preset standard operation data. If there is an abnormality, the abnormal parameters in the real-time operation data are extracted, and the abnormal characteristic trajectory corresponding to the abnormal parameter is found from the abnormal characteristic trajectory set as the target abnormal characteristic trajectory, and the predicted operation data of the solenoid valve is predicted based on the target abnormal characteristic trajectory, and abnormal processing information is generated at the same time.

[0007] By constructing the fault model building steps, real-time online monitoring of the solenoid valve can be provided, the monitoring efficiency and feedback speed can be improved, the abnormality can be effectively prevented from further deteriorating, the damage rate of the solenoid valve can be reduced, and the life status of the solenoid valve can be effectively monitored.

[0008] As a further improvement, the principle for collecting the historical abnormal data set of the solenoid valve is: select an abnormal operating condition of the solenoid valve, and at the abnormal initial moment of the abnormal operating condition of the solenoid valve, collect the data at the abnormal initial moment as the first sample data, and at the same time collect the second sample data within several consecutive abnormal cycles after the abnormal initial moment, and use the collected first sample data and all the second sample data as a historical abnormal data set of the solenoid valve under the abnormal operating condition of the solenoid valve.

[0009] Furthermore, a weight analysis is performed on the historical abnormal data set, specifically: Parameters with the same parameter type in all sample data in the historical abnormal data set under the abnormal working condition of the solenoid valve are extracted as sample parameters, and the third sample data when the solenoid valve works normally is obtained, and the parameters in the third sample data are used as reference parameters; the parameter weight of each parameter type is calculated according to the sample parameters and the reference parameters, and the parameter weights are arranged from large to small to obtain a weight queue.

[0010] Furthermore, an abnormal feature trajectory set is constructed based on the weight analysis results, specifically: The weight queue is used as a sorting reference to sort the sample parameters, and then the sample parameters are expanded with a preset abnormal value range to form a sample parameter abnormal range to form an abnormal feature trajectory; and the combination of all abnormal feature trajectories is used as an abnormal feature trajectory set.

[0011] Furthermore, the parameter weight of each parameter type is calculated as follows: , In the formula, is the weight of the parameter type, n is the parameter type; For the m Sample parameters; is a reference parameter.

[0012] Furthermore, the number k of sample parameter abnormal ranges in the abnormal feature trajectory is obtained, a corresponding parameter type abnormal prompt is added to the first sample parameter abnormal range, a corresponding parameter type abnormal warning prompt is added to the k / 2th sample parameter abnormal range and a solution is displayed.

[0013] Furthermore, according to the abnormal parameter, the abnormal feature trajectory corresponding to the abnormal parameter is found from the abnormal feature trajectory set as the target abnormal feature trajectory, specifically: Obtain the parameter type of the abnormal parameter, and traverse the parameter type of the first sample parameter abnormal range of each abnormal feature trajectory in the abnormal feature trajectory set according to the parameter type of the abnormal parameter to see if they are consistent. If they are consistent, use the current abnormal feature trajectory as the target abnormal feature trajectory; if they are inconsistent, generate an alarm message to prompt that the current operation abnormality of the solenoid valve is not saved in the abnormal feature trajectory set, and at the same time traverse the sample parameter abnormal range of each abnormal feature trajectory in the abnormal feature trajectory set in turn until the abnormal feature trajectory whose parameter type is consistent with the sample parameter abnormal range is found first and used as the target abnormal feature trajectory.

[0014] Furthermore, the predicted operation data of the solenoid valve is predicted according to the target abnormal characteristic trajectory, specifically: All sample parameter abnormal ranges in the target abnormal feature trajectory are extracted, and the sample parameter abnormal ranges are used as predicted operation data of the solenoid valve. At the same time, abnormal prompts or abnormal warning prompts and solutions are displayed when displaying the corresponding sample parameter abnormal ranges.

[0015] As a further improvement, judging whether the real-time operation data is abnormal is performed according to the preset standard operation data, specifically: Determine whether the real-time operation data is equal to the standard operation data. If so, the solenoid valve is operating normally. If not, the real-time operation data currently collected is compared with the standard operation data again after a preset collection period. If the two are still not equal, it is determined that the solenoid valve is operating abnormally.

[0016] As a further improvement, the collected historical abnormal data set and real-time operation data need to be preprocessed to make the format of all data consistent.

[0017] In a second aspect, the present invention provides an electronic device, characterized in that it includes: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of the online monitoring method of the solenoid valve described in the first aspect above.

[0018] The advantages of the present invention are: 1. The abnormal feature trajectory set constructed through the fault model construction step contains all the historical abnormalities of the solenoid valve, so that in the subsequent monitoring, it is only necessary to extract the corresponding historical data based on the historical abnormalities of the solenoid valve to predict the operation of the solenoid valve when an abnormality occurs, and provide users with real-time online reference data and response strategies, which can effectively prevent the abnormality from further deteriorating, reduce the damage rate of the solenoid valve, and effectively monitor the life status of the solenoid valve.

[0019] 2. By performing weight analysis on historical abnormal data sets, the parameters most likely to have abnormalities can be extracted from multiple sample parameters of the solenoid valve, and the abnormal parameters can be weighted and ranked, making the abnormal development of the solenoid valve clearer and providing users with a more intuitive reference.

[0020] 3. When monitoring the solenoid valve, it is only necessary to compare and judge the real-time operation data with the standard operation data, and in case of an abnormality, the target abnormal feature trajectory can be found from the abnormal feature trajectory set by traversal to obtain the predicted operation data and abnormality handling information. This greatly improves the monitoring efficiency and feedback speed, allowing users to respond and handle abnormalities in a timely manner.

[0021] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. The accompanying drawings are as follows.

[0023] Figure 1 It is a schematic diagram of the process flow of the fault model construction steps of the present invention.

[0024] Figure 2 It is a schematic flow chart of the online monitoring steps of the present invention.

[0025] Figure 3 A block diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0026] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0027] See also Figure 1-Figure 2The present invention provides an online monitoring method for a solenoid valve, which includes a fault model building step and an online monitoring step. By building the fault model building step, real-time performance can be provided for online monitoring of the solenoid valve, the monitoring efficiency and feedback speed can be improved, and the abnormality can be effectively prevented from further deteriorating, the damage rate of the solenoid valve can be reduced, and the life status of the solenoid valve can be effectively monitored.

[0028] Among them, the fault model construction step is used to collect the historical abnormal data set of the solenoid valve, perform weight analysis on the historical abnormal data set, and construct an abnormal feature trajectory set according to the weight analysis result. The constructed abnormal feature trajectory set contains all the historical abnormalities of the solenoid valve, so that in the subsequent monitoring, only the corresponding historical data can be extracted according to the historical abnormalities of the solenoid valve to predict the operation of the solenoid valve when an abnormality occurs, providing users with real-time online reference data and response strategies, so that users can respond and handle abnormalities in a timely manner.

[0029] Specifically, in the fault model building step, the principles for collecting the historical abnormal data set of the solenoid valve are as follows: Select an abnormal working condition of a solenoid valve, collect the data at the abnormal initial moment of the abnormal working condition of the solenoid valve as the first sample data, and collect the second sample data within a number of continuous abnormal cycles after the abnormal initial moment, and use the collected first sample data and all the second sample data as the historical abnormal data set of the solenoid valve under the abnormal working condition of the solenoid valve. That is, each abnormal working condition of the solenoid valve corresponds to a historical abnormal data set.

[0030] In this embodiment, the sample data mainly includes the magnetic field intensity E, the working voltage V of the solenoid valve, the working current I of the solenoid valve, the power consumption P of the solenoid valve and the working temperature T. Therefore, the measuring device mainly includes a magnetic field sensor, a temperature sensor and an electrical parameter sensor. Among them, the magnetic field sensor is used to measure the current magnetic field of the field solenoid valve coil. The HX695 high-performance linear Hall sensor is used. The output signal is determined by the magnetic field intensity applied to the sensitive surface of the device and changes proportionally with the magnetic field intensity. The static output voltage of the sensor is 50% of the power supply voltage and the sensitivity is 6mV / Gauss. The sensor integrates a Hall circuit, a temperature compensation circuit to reduce the Hall element, a small signal high-gain amplifier and a proportional low-impedance output. The temperature sensor is used to measure the body working temperature of the field solenoid valve coil. It uses PT100 and infrared laser temperature measurement principles for simultaneous measurement. The measurement temperature range is 20℃-150℃, the accuracy is less than 0.5%, and the nonlinear distortion is less than 0.5%. The electrical parameter sensing device is used to measure the current working current, working voltage, power consumption and other parameters of the on-site solenoid valve coil. The sensor output signal has good linearity with the input current, that is, within the entire measurement range, the output signal should be linearly related to the input current, with a deviation of no more than 0.5%FS and an accuracy level of ≤0.5%FS.

[0031] In addition, we also need a signal acquisition device, through which it can be connected to the back-end data analysis platform. The signal acquisition device is used to receive various parameters of the measuring device of the on-site solenoid valve, including signals such as magnetic field strength E, working voltage V, working current I, power consumption P, and working temperature T, and display and transmit them locally. The working power supply of the signal acquisition device is 24VDC, the power consumption is ≤20W, and it has its own lithium battery. When the external power supply is lost, it can work continuously for no less than 24 hours. There are 8 input channels, that is, up to 8 solenoid valve data can be monitored at the same time. For different solenoid valve models, the input channel can be set to adapt to the sensor type that measures the parameters of the solenoid valve. The acquisition device configures acquisition modules according to the channels, that is, one acquisition module and one channel, and they are independent of each other to avoid individual channel abnormalities affecting the overall data acquisition. The external analog input uses 16-bit A / D, all channels work in parallel and synchronously, the sampling frequency (all sensors collect synchronously) ≥100KS / S, and it has a self-test function to quickly know the current status of the channel. The acquisition device can collect multi-channel signals in real time and uninterruptedly for a long time. The data source management of the data analysis platform supports multiple data source collection and upload methods, such as communication data packets, local CSV files, and database files. It supports data preservation function, and supports storage for up to 10 years; you can choose to save the corresponding data points or time periods, and save them in CSV or EXCEL format. The data analysis platform has the function of intelligent data analysis. According to the model parameters of each solenoid valve, the relevant test data at the factory, the test data before installation, and the data trend of the data changes during normal use, it compares the current collected real-time data, conducts trend tracking analysis, and triggers corresponding alarm information when necessary. It supports different data files for indicator construction, and provides construction methods such as original data, four arithmetic grouping aggregation, screening, and SQL scripting to achieve the effect of data indicator construction.

[0032] The above is an introduction to the data collection principles, measurement devices and supporting platforms. Based on the above introduction, this paper introduces in detail how to implement weight analysis and abnormal feature trajectory set construction in the fault model construction step.

[0033] First, a weight analysis is performed on the historical abnormal data set. The specific analysis method is as follows: Extract parameters of the same parameter type from all sample data in the historical abnormal data set under the abnormal working condition of the solenoid valve as sample parameters. For example, there are four groups of sample data collected, and each group of sample data has five parameter types, namely magnetic field intensity E, working voltage V, working current I, power consumption P and working temperature T. Therefore, the extracted sample parameters are [E1, E2, E3, E4], [V1, V2, V3, V4], [I1, I2, I3, I4], [P1, P2, P3, P4], [T1, T2, T3, T4]. Obtain the third sample data when the solenoid valve is working normally, and use the parameters in the third sample data as reference parameters. The third sample data can use standard operating data. The reference parameters are [E0, V0, I0, P0, T0]. Calculate the parameter weight of each parameter type based on the sample parameters and the reference parameters, and arrange the parameter weights from large to small to obtain a weight queue.

[0034] The following formula is used to calculate the parameter weight of each parameter type: , In the formula, is the weight of the parameter type, n is the parameter type; For the m Sample parameters; is a reference parameter.

[0035] Taking the working voltage V as an example, the parameter weight of the working voltage V is: .

[0036] In this way, the parameter weight of each parameter type can be calculated as: , , , , . Assume that among these five parameter weights, The largest, and their order of arrangement is: > > > > It can be seen that under the abnormal working condition of the solenoid valve, the working current I of the solenoid valve is the first to show abnormality or the most serious abnormality, such as short circuit, open circuit, poor contact and other faults of the control circuit of the solenoid valve.

[0037] The weight queue is used as a sorting reference to sort the sample parameters, and then the sample parameters are expanded with a preset abnormal value range to form a sample parameter abnormal range to form an abnormal feature trajectory; and the combination of all abnormal feature trajectories is used as an abnormal feature trajectory set.

[0038] From the above assumptions, it is known that the working current I is the earliest to show abnormalities or the most serious in terms of abnormal manifestations. Therefore, the key abnormal type is the working current I of the solenoid valve. The final sorted order of the sample parameters obtained is: [I1, I2, I3, I4], [V1, V2, V3, V4], [P1, P2, P3, P4], [E1, E2, E3, E4], [T1, T2, T3, T4]. Since the initial abnormal parameters of the solenoid valve are not consistent each time an abnormality occurs and there are或多或少 some deviations, in this embodiment, these sample parameters are amplified and compared with the operating parameters obtained during online monitoring in the form of parameter ranges. This can effectively reduce the amount of the data set and at the same time help with rapid prediction and finding of abnormalities. For example, the abnormal range of the sample parameters of the working current after range amplification is [I10~I11, I20~I21, I30~I31, I40~I41], where I10 < I1 < I11, and the same applies to the others. Finally, the completed abnormal feature trajectory consists of the abnormal ranges of the sample parameters of five parameters: magnetic field strength E, working voltage V, working current I, power consumption P, and working temperature T.

[0039] After constructing the abnormal feature trajectory, we also need to give corresponding prompts based on past abnormal handling experiences to facilitate the user's quick response to handle abnormalities. Specifically, obtain the number k of the abnormal ranges of the sample parameters in the abnormal feature trajectory. In this embodiment, k = 4. Add a corresponding prompt message for the abnormal occurrence of the parameter type to the first abnormal range of the sample parameters, that is, generate a prompt message when the parameter shows an abnormality to remind the user. Add a corresponding abnormal warning prompt message for the parameter type and display the solution to the k / 2-th abnormal range of the sample parameters. After the first abnormal parameter appears, the solenoid valve may return to normal or continue to be abnormal during subsequent operation. Therefore, when the parameter shows an abnormality, that is, when the abnormal parameter is within the first abnormal range of the sample parameters, only a prompt is given to prevent the problem that the solenoid valve may return to normal during subsequent operation. However, when the operating parameter of the solenoid valve appears within the k / 2-th abnormal range of the sample parameters, it indicates that the abnormality continues. At this time, an abnormal warning prompt message for the parameter type can be given and the solution can be displayed. When k is an odd number, k / 2 is rounded.

[0040] The online monitoring step is used to collect the real-time operation data of the solenoid valve, for example, the real-time operation data is [E5, V5, I5, P5, T5]. It is judged whether the real-time operation data is abnormal according to the preset standard operation data. Among them, the abnormal judgment method is: judge whether the real-time operation data is equal to the standard operation data. If it is equal, the solenoid valve is operating normally. If it is not equal, the real-time operation data currently collected is compared with the standard operation data again after a preset collection period. If the two are still not equal, it is judged that the solenoid valve is operating abnormally. In this way, the problem of parameter abnormality caused by external interference can be prevented. The collection period is generally small and can be set to more than 1 / 10 of the abnormal period. If the solenoid valve is abnormal, the abnormal parameters in the real-time operation data are extracted. For example, if the working current I5 is inconsistent with I0, I5 is extracted. Then, according to the abnormal parameters, the corresponding abnormal characteristic trajectory is found from the abnormal characteristic trajectory set as the target abnormal characteristic trajectory, and finally the predicted operation data of the solenoid valve is predicted according to the target abnormal characteristic trajectory, and abnormal processing information is generated at the same time.

[0041] From the above online monitoring steps, it can be seen that when monitoring the solenoid valve, it is only necessary to compare and judge the real-time operation data with the standard operation data, and in the event of an abnormality, the target abnormal feature trajectory is found from the abnormal feature trajectory set by traversal to obtain the predicted operation data and abnormality handling information. This greatly improves the monitoring efficiency and feedback speed, allowing users to respond and handle abnormalities in a timely manner.

[0042] Regarding the determination of target abnormal characteristic trajectory and the prediction of operation data, the following methods are specifically adopted: First, obtain the parameter type of the abnormal parameter. Taking the above as an example, the abnormal parameter is the working current I5, and its parameter type is current. According to the parameter type of the abnormal parameter, traverse the parameter type of the first sample parameter abnormal range of each abnormal feature trajectory in the abnormal feature trajectory set to see if it is consistent. If it is consistent, the current abnormal feature trajectory is used as the target abnormal feature trajectory, that is, the abnormal feature trajectory composed of the sample parameter abnormal range of the working current I, working voltage V, power consumption P, magnetic field strength E and working temperature T. If it is inconsistent, an alarm message is generated to prompt that the current operation abnormality of the solenoid valve is not saved in the abnormal feature trajectory set, and at the same time, the sample parameter abnormal range of each abnormal feature trajectory in the abnormal feature trajectory set is traversed in turn until the abnormal feature trajectory with the parameter type of the sample parameter abnormal range that is consistent with it is found first as the target abnormal feature trajectory. Assume that there is no abnormal characteristic trajectory consisting of abnormal ranges of sample parameters of working current I, working voltage V, power consumption P, magnetic field strength E and working temperature T in the abnormal characteristic trajectory set, but there are abnormal characteristic trajectories consisting of abnormal ranges of sample parameters of working voltage V, working current I, power consumption P, magnetic field strength E and working temperature T, and abnormal characteristic trajectories consisting of abnormal ranges of sample parameters of working voltage V, working current I, power consumption P, working current I, magnetic field strength E and working temperature T. Through the above execution method, the abnormal characteristic trajectory consisting of abnormal ranges of sample parameters of working voltage V, working current I, power consumption P, magnetic field strength E and working temperature T should be used as the target abnormal characteristic trajectory.

[0043] All sample parameter abnormal ranges in the target abnormal feature trajectory are extracted, and the sample parameter abnormal ranges are used as predicted operation data of the solenoid valve. At the same time, abnormal prompts or abnormal warning prompts and solutions are displayed when displaying the corresponding sample parameter abnormal ranges, thereby realizing abnormal early warning of the operation of the solenoid valve.

[0044] In addition, in this embodiment, the collected historical abnormal data set and real-time operation data need to be preprocessed to make the format of all data consistent, which is conducive to data processing.

[0045] Figure 3 3 is a block diagram of an electronic device 300 of the present invention. For example, the electronic device 300 may be provided as a server. Figure 3 The electronic device 300 includes a processor 322, which may be one or more, and a memory 332 for storing a computer program executable by the processor 322. The computer program stored in the memory 332 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 322 may be configured to execute the computer program to perform the above-mentioned online monitoring method of the solenoid valve.

[0046] In addition, the electronic device 300 may further include a power supply component 326 and a communication component 350, wherein the power supply component 326 may be configured to perform power management of the electronic device 300, and the communication component 350 may be configured to implement communication, for example, wired or wireless communication, of the electronic device 300. In addition, the electronic device 300 may further include an input / output interface 358. The electronic device 300 may operate based on an operating system stored in the memory 332.

[0047] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned online monitoring method of the solenoid valve are implemented. For example, the non-transitory computer-readable storage medium can be the above-mentioned memory 332 including program instructions, and the above-mentioned program instructions can be executed by the processor 322 of the electronic device 300 to complete the above-mentioned online monitoring method of the solenoid valve.

[0048] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device. The computer program has a code portion for executing the above-mentioned online monitoring method of a solenoid valve when executed by the programmable device.

[0049] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0050] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0051] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. An online monitoring method for a solenoid valve, characterized in that: The method comprises: A fault model building step is used to collect a historical abnormal data set of the solenoid valve, perform weight analysis on the historical abnormal data set, and construct an abnormal feature trajectory set according to the weight analysis result; The online monitoring step is used to collect the real-time operation data of the solenoid valve, and determine whether the real-time operation data has any abnormality based on the preset standard operation data. If there is an abnormality, the abnormal parameters in the real-time operation data are extracted, and the abnormal characteristic trajectory corresponding to the abnormal parameter is found from the abnormal characteristic trajectory set as the target abnormal characteristic trajectory, and the predicted operation data of the solenoid valve is predicted based on the target abnormal characteristic trajectory, and abnormal processing information is generated at the same time.

2. The method according to claim 1, characterized in that The principle for collecting the historical abnormal data set of the solenoid valve is as follows: select an abnormal working condition of the solenoid valve, and at the abnormal initial moment of the abnormal working condition of the solenoid valve, collect the data at the abnormal initial moment as the first sample data, and at the same time collect the second sample data within several consecutive abnormal cycles after the abnormal initial moment, and use the collected first sample data and all the second sample data as a historical abnormal data set of the solenoid valve under the abnormal working condition of the solenoid valve.

3. The method according to claim 2, characterized in that The weight analysis of the historical abnormal data set is performed as follows: Parameters with the same parameter type in all sample data in the historical abnormal data set under the abnormal working condition of the solenoid valve are extracted as sample parameters, and the third sample data when the solenoid valve works normally is obtained, and the parameters in the third sample data are used as reference parameters; the parameter weight of each parameter type is calculated according to the sample parameters and the reference parameters, and the parameter weights are arranged from large to small to obtain a weight queue.

4. The method according to claim 3, characterized in that According to the weight analysis results, an abnormal feature trajectory set is constructed, specifically: The weight queue is used as a sorting reference to sort the sample parameters, and then the sample parameters are expanded with a preset abnormal value range to form a sample parameter abnormal range to form an abnormal feature trajectory; and the combination of all abnormal feature trajectories is used as an abnormal feature trajectory set.

5. The method according to claim 3, characterized in that: The following formula calculates the parameter weight for each of the parameter types: ； In the formula, is the weight of the parameter type, and n is the parameter type; is the mth sample parameter; is a reference parameter.

6. The method according to claim 4, characterized in that The number k of sample parameter abnormal ranges in the abnormal feature trajectory is obtained, a corresponding parameter type abnormal prompt is added to the first sample parameter abnormal range, a corresponding parameter type abnormal warning prompt is added to the k / 2th sample parameter abnormal range and a solution is displayed.

7. The method according to claim 4, characterized in that According to the abnormal parameter, the abnormal feature trajectory corresponding to the abnormal parameter is found from the abnormal feature trajectory set as the target abnormal feature trajectory, specifically: Obtain the parameter type of the abnormal parameter, and traverse the parameter type of the first sample parameter abnormal range of each abnormal feature trajectory in the abnormal feature trajectory set according to the parameter type of the abnormal parameter to see if they are consistent. If they are consistent, use the current abnormal feature trajectory as the target abnormal feature trajectory; if they are inconsistent, generate an alarm message to prompt that the current operation abnormality of the solenoid valve is not saved in the abnormal feature trajectory set, and at the same time traverse the sample parameter abnormal range of each abnormal feature trajectory in the abnormal feature trajectory set in turn until the abnormal feature trajectory whose parameter type is consistent with the sample parameter abnormal range is found first and used as the target abnormal feature trajectory.

8. The method according to claim 6, characterized in that The predicted operation data of the solenoid valve is predicted according to the target abnormal characteristic trajectory, specifically: All sample parameter abnormal ranges in the target abnormal feature trajectory are extracted, and the sample parameter abnormal ranges are used as predicted operation data of the solenoid valve. At the same time, abnormal prompts or abnormal warning prompts and solutions are displayed when displaying the corresponding sample parameter abnormal ranges.

9. The method according to claim 1, characterized in that: Judging whether the real-time operation data is abnormal according to the preset standard operation data is as follows: Determine whether the real-time operation data is equal to the standard operation data. If so, the solenoid valve is operating normally. If not, the real-time operation data currently collected is compared with the standard operation data again after a preset collection period. If the two are still not equal, it is determined that the solenoid valve is operating abnormally.

10. The method according to claim 1, characterized in that The collected historical abnormal data set and real-time operation data need to be preprocessed to make the format of all data consistent.

11. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 10.

Images