Testing method and testing system for voltage filter of asynchronous generator for ship
By monitoring the environment and operating status, building abnormal density and optimizing knowledge graphs, reducing interference from asynchronous generators, ensuring the reliability and optimization effect of voltage filter testing, it solves the problems of unreliable test data and insufficient optimization guidance in the existing technology. , improves the performance and reliability of voltage filters.
Patent Information
- Application Number
- CN202410924147.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-11
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-11
AI Technical Summary
The existing voltage filter testing methods cannot effectively consider the abnormal interference of asynchronous generators, resulting in unreliable test data and insufficient optimization guidance, which affects the performance and reliability of the voltage filter.
By building exception density and optimizing knowledge graphs, monitoring the environment and operating status, optimizing test conditions, reducing asynchronous generator interference, building a digital twin model to verify optimization effects, ensuring the reliability of test data and the effectiveness of optimization solutions.
It realizes reliability guarantee during multiple tests of voltage filters, improves the accuracy and optimization efficiency of test data, and enhances the matching and reliability of voltage filters with asynchronous generators.
Smart Images

Figure CN118483598B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of voltage filters, and in particular to a testing method and a testing system for a voltage filter of an asynchronous generator for a ship. Background Art
[0002] The asynchronous generator used in ships is a special generator that uses the reversible principle of the electric motor to generate electrical energy. It is mainly achieved through electromagnetic induction. When the rotor starts to rotate, the magnet or electromagnet on it forms a rotating magnetic field. This magnetic field passes through the stator coil, causing the conductor to feel the induced electromotive force in the magnetic field, thereby forming a voltage difference, which is the output voltage of the generator. The output voltage of the generator can be controlled by adjusting the rotation speed of the rotor and the number of coils.
[0003] Marine asynchronous generators are usually used to meet the power requirements of various equipment and systems on board. It is suitable for driving ship auxiliary machines, such as engine room pumps, ventilators, air compressors, etc. At the same time, due to the advantages of simple structure and reliable operation, marine asynchronous generators have been widely used on ships.
[0004] Voltage filter is a device or circuit used to process voltage signals. Its main function is to filter useful signals to pass through without attenuation as much as possible, while attenuating useless signals as much as possible. Voltage filters are widely used in many fields. For example, they can effectively reduce the harmonic pollution caused by asynchronous generators and improve the operating efficiency of asynchronous generators.
[0005] The invention patent with application publication number CN111913039A provides a method and device for calculating the background harmonic voltage of an AC filter. The method includes obtaining the site voltage waveform, site current waveform and AC power grid data of each selected substation; analyzing the site voltage waveform and site current waveform of each selected substation by a harmonic analysis method to obtain each harmonic voltage and each harmonic current in each time period; calculating each equivalent harmonic impedance of each selected substation according to the AC power grid data; calculating each initial background harmonic voltage of each selected substation in each time period according to each harmonic voltage, each harmonic current and equivalent harmonic impedance; comparing each initial background harmonic voltage, and selecting the largest initial background harmonic voltage as the background harmonic voltage of the AC filter.
[0006] Combining the above content with the content in the prior art:
[0007] When the voltage filter is in operation, its reliability is usually affected by many factors. In particular, if the asynchronous generator is installed on a ship, the humidity and salt content in the air in the area where the ship is located are usually high, which will cause a certain degree of corrosion to the components in the asynchronous generator and the voltage filter, thereby affecting the actual performance of the voltage filter. Therefore, in order to ensure the availability of the voltage filter, it is usually necessary to perform a performance test on the voltage filter before installing the voltage filter to ensure that the voltage filter can play the desired effect after installation;
[0008] However, in the existing testing methods for voltage filters, the working environment of the voltage filter is usually simulated to obtain test data in various usage scenarios, and these test data are used to determine whether the voltage filter can meet the usage requirements. However, in actual use, the abnormal data output by the voltage filter may be due to abnormal operation of the asynchronous generator. In the existing testing methods for voltage filters, there is a lack of consideration for the interference caused by the abnormality of the asynchronous generator. At the same time, after the voltage filter is fully tested, the test data provided cannot provide guidance for the optimization of the voltage filter.
[0009] To this end, the present invention provides a testing method and a testing system for a voltage filter of an asynchronous generator for a ship. Summary of the invention
[0010] 1. Technical issues to be resolved
[0011] In view of the deficiencies of the prior art, the present invention provides a test method and a test system for a voltage filter of an asynchronous generator for ships. By constructing an abnormal density, if the abnormal density exceeds the density threshold, the waveform similarity between load and no load is obtained under different load conditions, and the improvement of the waveform by the voltage filter is constructed from the similarity data. The improvement degree of the waveform distortion by the filter is evaluated based on the improvement degree. If the improvement degree is less than expected, a corresponding optimization scheme is given by the filter optimization knowledge map, and a digital twin model is constructed based on the voltage filter to verify the optimized voltage filter. The interference caused by the asynchronous generator when testing the voltage filter is reduced, and the reliability of the test data is guaranteed when multiple tests are performed on the voltage filter, thereby solving the technical problems raised in the background technology.
[0012] (II) Technical solution
[0013] To achieve the above objectives, the present invention is implemented through the following technical solutions:
[0014] Test methods for voltage filters of asynchronous generators for ships, including:
[0015] Periodically monitor the environmental conditions of the asynchronous generator, and construct a working condition data set from the acquired monitoring data, and construct an environmental condition coefficient from the working condition data. , if the environmental condition coefficient If the data exceeds the expected value, an abnormal monitoring instruction is issued to the outside; the working condition data set includes the obtained ambient humidity. And salt spray concentration ;
[0016] Monitor and obtain the working status data of the asynchronous generator, build a generator operating status data set, and build the operating abnormality of the asynchronous generator based on the data in the motor operating status data set. If the operation is abnormal If the error exceeds the expectation, a test instruction will be issued to the outside; among them, the abnormality of operation The construction method is as follows: and operating noise Perform linear normalization and map the corresponding data values to the interval Then follow the steps below:
[0017]
[0018] in, is the value of the power factor at the i-th monitoring node, is the value of the operating noise at the i-th monitoring node; , n is the number of monitoring nodes; weight coefficient: , ;
[0019] Pre-build the test conditions of the voltage filter, build the test data set from the test data after the test, and build the abnormal density of the waveform abnormality of the asynchronous generator from the acquired test data , if the abnormal density If the density threshold is exceeded, a load test instruction is issued to the outside.
[0020] Under different load conditions, the waveform similarity between loaded and unloaded is obtained, and the improvement of the waveform by the voltage filter is constructed based on the similarity data. , based on the improvement Evaluate the improvement of the filter on waveform distortion. If the voltage filter is lower than expected, an optimization instruction for the voltage filter is issued to the outside.
[0021] The corresponding optimization features are obtained by analyzing the test data under different test conditions. If the voltage filter is optimized, the filter optimization knowledge graph gives the corresponding optimization solution. After the optimization is completed, a digital twin model is built based on the voltage filter to verify the optimized voltage filter.
[0022] Furthermore, the environmental condition coefficient The construction method is as follows, for ambient humidity And salt spray concentration Perform linear normalization and map the corresponding data values to the interval Then follow the steps below:
[0023]
[0024] in, is the reference standard value of ambient humidity, is the value of ambient humidity at the i-th monitoring node, It is the reference standard value of ambient humidity; is the reference standard value of salt spray concentration, is the value of salt spray concentration at the i-th monitoring node, is the reference standard value of salt spray concentration; , k is the number of monitoring nodes; weight coefficient: , .
[0025] Furthermore, after receiving the abnormal monitoring instruction, the working status data of the asynchronous generator is monitored at each monitoring node, including: the power factor of the asynchronous generator and operating noise After the acquired monitoring data is aggregated, a generator operation status data set is constructed; the abnormality degree of the asynchronous generator under the current environmental conditions is constructed based on the data in the motor operation status data set. .
[0026] Further, after receiving the test instruction, the voltage filter is prepared for testing, and voltage waveform data is obtained at each test node, and a test data set is constructed after continuously obtaining several groups in combination with a preset standard reference image;
[0027] After presetting the tolerable interval, the waveform images in the test data set and the pre-prepared standard images are used to obtain the difference ratio between the current waveform and the standard waveform through difference analysis. Based on the relationship between the difference ratio and the tolerable interval, it is determined whether the current waveform is abnormal. If there is an abnormality, the difference ratio is used as the current waveform abnormality degree. , and obtain the time information of the corresponding abnormal waveform.
[0028] Furthermore, the abnormal density of the abnormal waveform is constructed based on the acquired waveform abnormality and the corresponding time information. , where the time center of each abnormal waveform is calculated by the time difference between any two abnormal waveforms ; The time center of each abnormal waveform is obtained and waveform abnormality Finally, the abnormal density constructed for the waveform abnormalities during the test , for time centrality and waveform abnormality After normalization, follow the following method:
[0029]
[0030] Where i is the abnormal waveform number, ; for The mean of the time centrality, for The mean value of the abnormality of the waveforms; For the The temporal center of the abnormal waveform, For the The waveform abnormality of an abnormal waveform; weight coefficient: , .
[0031] Furthermore, after receiving the load test instruction, different load conditions are set for the generator, and the generator is load tested under each load condition, and the output voltage and corresponding waveform under different load conditions are recorded. After obtaining the waveform image when the filter is not installed, similarity analysis is performed to analyze the waveform similarity between with load and without load. ; Aggregate the obtained waveform similarities to obtain a waveform similarity data set.
[0032] Furthermore, the improvement of the waveform by constructing a voltage filter based on the similarity data , as follows:
[0033]
[0034] in, , is the number of load conditions, weight coefficient: , and ; is the waveform similarity between the load and non-load conditions under the i-th load condition, is the mean value of waveform similarity, is the qualified standard value.
[0035] Furthermore, after receiving the optimization instruction, different test conditions are obtained through adjustments, and various data in the test are recorded under each test condition, including load size, voltage reading, waveform diagram, etc. The obtained test data are summarized to construct a test data set; after identifying and comparing the data, the corresponding optimization features are analyzed and obtained; with filter optimization as the target word, a filter optimization knowledge graph is constructed.
[0036] Furthermore, based on the correspondence between the optimization features and the optimization scheme, a corresponding optimization scheme is given by the filter optimization knowledge graph; the optimization scheme is executed to optimize the current voltage filter; a digital twin model of the voltage filter is constructed, and the optimized voltage filter is simulated and analyzed based on the digital twin model of the voltage filter, and corresponding test data is obtained; if the optimized voltage filter is feasible, the optimization of the voltage filter is terminated; if it is not feasible, the test and optimization process is repeated after the optimization.
[0037] The test system for voltage filter of asynchronous generator for ships includes:
[0038] The environmental condition evaluation unit periodically monitors the environmental conditions of the asynchronous generator environment, and constructs a working condition data set based on the acquired monitoring data, and constructs an environmental condition coefficient based on the working condition data. , if the environmental condition coefficient If it exceeds expectations, an abnormal monitoring instruction will be issued to the outside;
[0039] The abnormal state monitoring unit monitors and obtains the working state data of the asynchronous generator, constructs the generator operation state data set, and constructs the operation abnormality degree of the asynchronous generator from the data in the motor operation state data set. If the operation is abnormal Exceeded expectations and issued external testing instructions;
[0040] The load test unit constructs the test conditions of the voltage filter in advance, constructs the test data set from the test data after the test, and constructs the abnormal density of the waveform abnormality of the asynchronous generator from the acquired test data , if the abnormal density If the density threshold is exceeded, a load test instruction is issued to the outside.
[0041] Improve the evaluation unit, obtain the waveform similarity between loaded and unloaded under different load conditions, and construct the improvement degree of the voltage filter on the waveform based on the similarity data , based on the improvement Evaluate the improvement of the filter on waveform distortion. If the voltage filter is lower than expected, an optimization instruction for the voltage filter is issued to the outside.
[0042] The optimization unit obtains the corresponding optimization features by analyzing the test data under different test conditions. If the voltage filter is optimized, the filter optimization knowledge graph gives the corresponding optimization plan. After the optimization is completed, a digital twin model is built based on the voltage filter to verify the optimized voltage filter.
[0043] (III) Beneficial effects
[0044] The present invention provides a testing method and a testing system for a voltage filter of an asynchronous generator for a ship, which have the following beneficial effects:
[0045] 1. Based on environmental condition coefficient The value of determines whether the current environment of the asynchronous generator is abnormal. If there is an abnormality, the performance of the asynchronous generator and the corresponding voltage filter will be affected to a certain extent. By monitoring and processing the abnormal environment, the use environment of the asynchronous generator and the corresponding voltage filter can be adjusted and improved to ensure its safe use.
[0046] 2. Based on the degree of abnormal operation The value of is used to judge whether the asynchronous generator currently has an operating abnormality. If there is an operating abnormality, refer to linear regression analysis or correlation analysis. If there is a correlation between the operating abnormality and the current environment, the use environment of the asynchronous generator can be adjusted first. If the correlation is not high, the working status and corresponding parameters of the asynchronous generator itself need to be adjusted. Based on abnormal monitoring and corresponding judgment results, it can be timely judged whether the asynchronous generator can still be used normally, thereby ensuring the availability of the asynchronous generator.
[0047] 3. Pre-set different test conditions, conduct tests and obtain corresponding test data. Since there is a certain tolerance for abnormalities of asynchronous generators, screen out the abnormal situations and build the abnormal density according to the abnormal degree and distribution of the abnormal situations. , according to the abnormal density Further judgment can be made on whether the asynchronous generator is still in normal use, which can supplement the preliminary judgment to a certain extent, realize comprehensive evaluation of the abnormality of the asynchronous generator, and also realize the test of the voltage filter.
[0048] 4. Test the waveform of the asynchronous generator output under different load conditions and the waveform difference when the voltage filter is not installed, and build the improvement degree based on the waveform difference. When the asynchronous generator itself has an abnormality, confirm whether the installed voltage filter has the desired effect and realize the performance test of the voltage filter; by pre-setting different test conditions and obtaining corresponding test data under the corresponding test conditions, it can also reduce the interference caused by the asynchronous generator when testing the voltage filter, and realize the reliability of the test data when performing multiple tests on the voltage filter.
[0049] 5. According to the actual usage scenarios of the asynchronous generator, the test data of the corresponding usage scenarios are obtained for the voltage filter, so that the test data is more comprehensive and complete; according to the pre-set judgment criteria, the corresponding optimization features are identified and analyzed to determine the corresponding optimization goals when optimizing the voltage filter.
[0050] 6. By pre-building a filter optimization knowledge graph, when the voltage filter needs to be optimized, the corresponding optimization plan can be quickly obtained as a reference plan. After testing the voltage filter, the voltage filter can be optimized to improve the reliability of the voltage filter and the matching between the voltage filter and the asynchronous generator.
[0051] 7. After optimizing the power filter, in order to improve the efficiency of subsequent testing and optimization, a digital twin model of the voltage filter is constructed to perform simulation tests on the optimized voltage filter. Based on the data obtained from the simulation test, it is determined whether the current optimized voltage filter is usable, thereby improving the efficiency of subsequent optimization and testing. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Figure 1 It is a flow chart of a method for testing a voltage filter of an asynchronous generator according to the present invention;
[0053] Figure 2 The figure is a schematic diagram of the structure of the test system of the asynchronous generator voltage filter of the present invention. DETAILED DESCRIPTION
[0054] 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0055] See also Figure 1 This embodiment provides a method for testing a voltage filter of an asynchronous generator for a ship, comprising:
[0056] Step 1: Periodically monitor the environmental conditions of the asynchronous generator, and construct a working condition data set from the acquired monitoring data, and construct an environmental condition coefficient from the working condition data. , if the environmental condition coefficient If it exceeds expectations, an abnormal monitoring instruction will be issued to the outside;
[0057] The step 1 includes the following contents:
[0058] Step 101: After determining the use area of the filter, use the use area as the monitoring area; set a monitoring cycle including several monitoring nodes, monitor the working environment of the generator in each monitoring cycle, and obtain corresponding environmental condition data; including the humidity at each monitoring node in the monitoring area and the salt content in the air, and obtain the environmental humidity respectively. And salt spray concentration , after aggregation, a working condition data set is constructed;
[0059] Step 102: Construct environmental condition coefficients from working condition data , the method is as follows, for the ambient humidity And salt spray concentration Perform linear normalization and map the corresponding data values to the interval Then follow the steps below:
[0060]
[0061] in, is the reference standard value of ambient humidity, is the value of ambient humidity at the i-th monitoring node, It is the reference standard value of ambient humidity; is the reference standard value of salt spray concentration, is the value of salt spray concentration at the i-th monitoring node, is the reference standard value of salt spray concentration; , k is the number of monitoring nodes; weight coefficient: , , where the weight coefficient can be obtained by referring to the hierarchical analysis method;
[0062] Based on historical data and the expected use and management of the generator, the condition threshold is set in advance; if the environmental condition coefficient Exceeding expectations, that is, the environmental condition coefficient If the condition threshold is exceeded, it means that the asynchronous generator has certain abnormalities in the current environment. The use status of the generator and the corresponding filter may also cause certain abnormalities under the influence of environmental conditions. Therefore, it is necessary to deal with it in time, for example, adjust the current working conditions of the asynchronous generator. At this time, send an abnormal monitoring instruction to the outside;
[0063] When using, combine the contents in steps 101 and 102:
[0064] When the asynchronous generator is running on a ship, the environmental conditions in which it is running are first monitored and analyzed, and the corresponding environmental condition coefficients are constructed based on the analysis results. , according to the environmental condition coefficient The value of can be used to judge whether the current environment of the asynchronous generator is abnormal. If there is an abnormality, the performance of the asynchronous generator and the corresponding voltage filter will be affected to a certain extent under the abnormal environment. Therefore, by monitoring and processing the abnormal environment, the use environment of the asynchronous generator and the corresponding voltage filter can be adjusted and improved to ensure its safe use.
[0065] Combining the above content with the content in the prior art:
[0066] When the voltage filter is in operation, its reliability is usually affected by many factors. In particular, if the asynchronous generator is installed on a ship, the humidity and salt content in the air in the area where the ship is located are usually high, which will cause a certain degree of corrosion to the components in the asynchronous generator and the voltage filter, thereby affecting the actual performance of the voltage filter. Therefore, in order to ensure the availability of the voltage filter, it is usually necessary to perform a performance test on the voltage filter before installing the voltage filter to ensure that the voltage filter can play the desired effect after installation;
[0067] However, in the existing testing methods for voltage filters, the working environment of the voltage filter is usually simulated to obtain test data in various usage scenarios, and these test data are used to determine whether the voltage filter can meet the usage requirements. However, in actual use, the abnormal data output by the voltage filter may be due to abnormal operation of the asynchronous generator. In the existing testing methods for voltage filters, there is a lack of consideration for the interference caused by the abnormality of the asynchronous generator. At the same time, after the voltage filter is fully tested, the test data provided cannot provide guidance for the optimization of the voltage filter.
[0068] It should be noted that the operating parameters of asynchronous generators include several key indicators, which are crucial to understanding the performance and operating status of the generator. The following are some of the main operating parameters:
[0069] Rated current: The current consumed by the motor at rated voltage and rated frequency is called rated current, usually in amperes. The rated current reflects the current consumption of the generator under rated load. Rated speed: The rotation speed of the generator under rated load and rated voltage, usually in revolutions per minute (rpm). The rated speed is an important parameter for the normal operation of the generator and is related to the grid frequency and the number of poles. Rated torque: The torque generated by the generator under rated load and rated voltage is an important parameter to describe the output capacity of the generator. Power factor: A measure of the proportion of active power actually consumed in the apparent power input of the asynchronous motor. The higher the power factor, the more fully the generator is utilized in the energy conversion process.
[0070] Step 2: Monitor and obtain the working status data of the asynchronous generator, construct the generator operating status data set, and construct the operating abnormality degree of the asynchronous generator from the data in the motor operating status data set. If the operation is abnormal Exceeded expectations and issued external testing instructions;
[0071] The step 2 includes the following contents:
[0072] Step 201: After receiving the abnormal monitoring instruction, an abnormal monitoring cycle including several monitoring nodes is also set to monitor the working status data of the asynchronous generator at each monitoring node, including: the power factor of the asynchronous generator and operating noise ,After aggregating the acquired monitoring data, a generator operation status data set is constructed;
[0073] Step 202: construct the abnormality degree of the asynchronous generator under the current environmental conditions based on the data in the motor operation status data set. , as follows: for power factor and operating noise Perform linear normalization and map the corresponding data values to the interval Then follow the steps below:
[0074]
[0075] in, is the value of the power factor at the i-th monitoring node, is the value of the operating noise at the i-th monitoring node;
[0076] in, , n is the number of monitoring nodes; weight coefficient: , , where the weight coefficient can be obtained by referring to the hierarchical analysis method;
[0077] Based on historical data and expectations for generator operation management, an abnormality threshold is set for the generator in advance; if the generator operation abnormality If it exceeds the expectation, that is, exceeds the abnormality threshold, it means that the generator may have some abnormality in the current operating environment and needs to be processed in time, for example, adjusting the load and rated voltage of the asynchronous generator, etc. At this time, a test instruction is issued to the outside;
[0078] When using, combine the contents in steps 201 and 202:
[0079] When it is determined that the asynchronous generator is in a relatively abnormal use environment, the operating status of the asynchronous generator is first monitored, and the abnormality degree of the asynchronous generator is constructed by obtaining several representative parameters. , according to the degree of abnormal operation The value of is used to judge whether the asynchronous generator currently has an operating abnormality. If there is an operating abnormality, refer to linear regression analysis or correlation analysis. If there is a correlation between the operating abnormality and the current environment, the use environment of the asynchronous generator can be adjusted first. If the correlation is not high, the working status and corresponding parameters of the asynchronous generator itself need to be adjusted. Based on abnormal monitoring and corresponding judgment results, it can be timely judged whether the asynchronous generator can still be used normally, thereby ensuring the availability of the asynchronous generator.
[0080] Step 3: Pre-build the test conditions of the voltage filter, build a test data set from the test data after the test, and build the abnormal density of the waveform abnormality of the asynchronous generator from the acquired test data. , if the abnormal density If the density threshold is exceeded, a load test instruction is issued to the outside.
[0081] The step three includes the following contents:
[0082] Step 301: After receiving the test instruction, prepare for the voltage filter to test. The test preparation includes:
[0083] Install the voltage filter at the output end of the generator, after setting the test area, reduce the electromagnetic interference intensity in the test area to within the expected threshold, connect the input end of the voltage filter to the output of the asynchronous generator, and connect the output end of the voltage filter to the test instrument and the load box;
[0084] Step 302, after completing the test preparation, testing the generator, including: starting the generator, gradually increasing the load of the generator, measuring the output voltage using a digital multimeter, observing the output voltage waveform using an oscilloscope, setting a test cycle including a number of test nodes, and obtaining voltage waveform data at each test node, combining a preset standard reference image, and constructing a test data set after continuously obtaining a number of groups;
[0085] Step 303: After presetting the tolerable interval, the difference ratio between the current waveform and the standard waveform is obtained by difference analysis based on the waveform images in the test data set and the pre-prepared standard images. Based on the relationship between the difference ratio and the tolerable interval, it is determined whether the current waveform is abnormal. If there is an abnormality, the difference ratio is used as the current waveform abnormality degree. , and obtain the time information of the corresponding abnormal waveform;
[0086] Step 304: construct the abnormal density of the abnormal waveform based on the acquired waveform abnormality and the corresponding time information , where the time center of each abnormal waveform is calculated by the time difference between any two abnormal waveforms , the specific method is as follows:
[0087]
[0088] Where k is the number of abnormal waveforms, is the time difference between abnormal waveform i and abnormal waveform j;
[0089] Step 305: After obtaining the time center of each abnormal waveform and waveform abnormality Finally, the abnormal density constructed for the waveform abnormalities during the test , for time centrality and waveform abnormality After normalization, follow the following method:
[0090]
[0091] Where i is the abnormal waveform number, ; for The mean of the time centrality, for The mean value of the abnormality of the waveforms; For the The temporal center of the abnormal waveform, For the The waveform abnormality of each abnormal waveform;
[0092] Weight coefficient: , , which can be obtained by analytic hierarchy process;
[0093] Based on the abnormal management and historical data of asynchronous generators, the density threshold is pre-set; if the abnormal density If the density threshold is exceeded, it means that the current waveform has a high frequency of abnormalities, which means that the voltage filter has an abnormality during operation. At this time, a load test instruction is issued to the outside.
[0094] When using, combine the contents in steps 301 to 305:
[0095] When the availability of asynchronous generators needs to be verified, different test conditions are set in advance, and the tests are carried out respectively to obtain the corresponding test data. Since there is a certain degree of tolerance for abnormalities of asynchronous generators, the tolerable range is set in advance to screen out the abnormal situations, and the abnormal density is constructed according to the abnormal degree and distribution of the abnormal situations. , according to the abnormal density Further judgment can be made on whether the asynchronous generator is still in normal use, which can supplement the preliminary judgment to a certain extent, realize comprehensive evaluation of the abnormality of the asynchronous generator, and also realize the test of the voltage filter.
[0096] Step 4: Under different load conditions, obtain the waveform similarity between loaded and unloaded, and construct the improvement of the voltage filter on the waveform based on the similarity data. , based on the improvement Evaluate the improvement of the filter on waveform distortion. If the voltage filter is lower than expected, an optimization instruction for the voltage filter is issued to the outside.
[0097] The step 4 includes the following contents:
[0098] Step 401: After receiving the load test instruction, set different load conditions for the generator, perform load tests on the generator under various load conditions, and record the output voltage and corresponding waveforms under different load conditions. After obtaining the waveform image when the filter is not installed, perform similarity analysis to analyze the waveform similarity between the loaded and unloaded waveforms. ; Aggregate the obtained waveform similarities to obtain a waveform similarity data set;
[0099] Step 402: Compare the difference between the voltage waveforms before and after filtering based on the data in the waveform similarity data set, and construct the improvement degree of the voltage filter on the waveform based on the similarity data. , as follows:
[0100]
[0101] in, , is the number of load conditions, weight coefficient: , and ;The value of the weight coefficient remains consistent with the previous value; is the waveform similarity between the load and non-load conditions under the i-th load condition, is the mean value of waveform similarity, is its qualified standard value;
[0102] Based on historical data and performance management expectations for voltage filters, the improvement threshold is pre-set. The relationship between the improvement threshold and the filter is used to evaluate the improvement of the waveform distortion; if the improvement Less than expected, that is, the improvement obtained When it is lower than the improvement threshold, it means that, based on the test data, it can be judged that the performance of the voltage filter is lower than the expected level. At this time, the voltage filter can be optimized and an optimization instruction of the voltage filter can be issued to the outside.
[0103] When using, combine the contents in steps 401 to 402:
[0104] If the asynchronous generator is affected by abnormal environmental conditions, a load test is carried out when the output waveform is abnormal. The waveform of the asynchronous generator output under different load conditions is different from that when the voltage filter is not installed. The improvement degree is established based on the waveform difference. , when the asynchronous generator itself has an abnormality, confirm whether the installed voltage filter has the desired effect and implement the performance test of the voltage filter;
[0105] Furthermore, on the basis of monitoring the operating status of the asynchronous generator, by pre-setting different test conditions and obtaining corresponding test data under the corresponding test conditions, the interference caused by the asynchronous generator when testing the voltage filter can be reduced, thereby ensuring the reliability of the test data when performing multiple tests on the voltage filter.
[0106] Step 5: Obtain the corresponding optimization features from the test data analysis under different test conditions. If the voltage filter is optimized, the filter optimization knowledge graph gives the corresponding optimization solution. After the optimization is completed, a digital twin model is constructed based on the voltage filter to verify the optimized voltage filter.
[0107] The step five includes the following contents:
[0108] Step 501: after receiving the optimization instruction, different test conditions are obtained through adjustment, for example, various electrical shocks, vibrations and loads that may be encountered in the operation of the ship are simulated, and various test data in the test are recorded under various test conditions, including load size, voltage reading, waveform diagram, etc., and the obtained test data are aggregated to construct a test data set;
[0109] Step 502: according to the performance expectation of the voltage filter, set the qualification standard for each parameter in the test data set, identify and compare the data, and analyze and obtain the corresponding optimization features according to the deficiencies of some parameters; take filter optimization as the target word, after deep retrieval and build entity relationships, construct the filter optimization knowledge graph; use the trained matching model, according to the correspondence between the optimization features and the optimization scheme, give the corresponding optimization scheme from the filter optimization knowledge graph; execute the optimization scheme to optimize the current voltage filter;
[0110] During use, considering that the voltage filter and the asynchronous generator are usually in the same working environment, therefore, according to the actual use scenario of the asynchronous generator, the test data of the voltage filter under the corresponding use scenario is obtained respectively, so that the test data is more comprehensive and complete; further, after completing the comprehensive test, according to the pre-set judgment criteria, the corresponding optimization features are identified and analyzed to determine the corresponding optimization target when optimizing the voltage filter;
[0111] At the same time, by pre-constructing the filter optimization knowledge graph, when the voltage filter needs to be optimized, the corresponding optimization plan can be quickly obtained and used as a reference plan. After testing the voltage filter, the voltage filter can be optimized to improve the reliability of the voltage filter and the matching between the voltage filter and the asynchronous generator.
[0112] Step 503: After obtaining the optimization solution, the specification data, performance data and operating environment condition data of the voltage filter are collected and summarized as sample data; an initial model is constructed by a neural convolutional network, and the initial model is trained and tested using the sample data to construct a digital twin model of the voltage filter. Based on the digital twin model of the voltage filter, the optimized voltage filter is simulated and analyzed, and corresponding test data is obtained;
[0113] The improvement degree is obtained again based on the test data, and the feasibility of the filter is verified based on the improvement degree. If the optimized voltage filter is feasible, the optimization of the voltage filter is terminated; if it is not feasible, the test and optimization process are repeated after the optimization until it is confirmed after the test that the voltage filter meets the actual use requirements;
[0114] When using, combine the contents in steps 501 to 503:
[0115] After optimizing the power filter, in order to improve the efficiency of subsequent testing and optimization, a digital twin model of the voltage filter is constructed to perform simulation tests on the optimized voltage filter. Based on the data obtained from the simulation test, it is determined whether the current optimized voltage filter is usable, thereby improving the efficiency of subsequent optimization and testing.
[0116] See also Figure 2 This embodiment provides a test system for a voltage filter of an asynchronous generator for a ship, comprising:
[0117] The environmental condition evaluation unit periodically monitors the environmental conditions of the asynchronous generator environment, and constructs a working condition data set based on the acquired monitoring data, and constructs an environmental condition coefficient based on the working condition data. , if the environmental condition coefficient If it exceeds expectations, an abnormal monitoring instruction will be issued to the outside;
[0118] The abnormal state monitoring unit monitors and obtains the working state data of the asynchronous generator, constructs the generator operation state data set, and constructs the operation abnormality degree of the asynchronous generator from the data in the motor operation state data set. If the operation is abnormal Exceeded expectations and issued external testing instructions;
[0119] The load test unit constructs the test conditions of the voltage filter in advance, constructs the test data set from the test data after the test, and constructs the abnormal density of the waveform abnormality of the asynchronous generator from the acquired test data , if the abnormal density If the density threshold is exceeded, a load test instruction is issued to the outside.
[0120] Improve the evaluation unit, obtain the waveform similarity between loaded and unloaded under different load conditions, and construct the improvement degree of the voltage filter on the waveform based on the similarity data , based on the improvement Evaluate the improvement of the filter on waveform distortion. If the voltage filter is lower than expected, an optimization instruction for the voltage filter is issued to the outside.
[0121] The optimization unit obtains the corresponding optimization features by analyzing the test data under different test conditions. If the voltage filter is optimized, the filter optimization knowledge graph gives the corresponding optimization plan. After the optimization is completed, a digital twin model is built based on the voltage filter to verify the optimized voltage filter.
[0122] The Analytic Hierarchy Process (AHP) is a decision analysis method that decomposes decision-related elements into levels such as goals, criteria, and plans, and then conducts qualitative and quantitative analysis on this basis. The AHP regards the complex multi-objective decision-making problem as a system, and decomposes the goal into multiple goals or criteria, and then decomposes it into several levels of multiple indicators (or criteria, constraints). It calculates the hierarchical single ranking (weight) and total ranking through the fuzzy quantification method of qualitative indicators, thus serving as a systematic method for optimizing decision-making of goals (multiple indicators) and multiple plans.
[0123] The basic principle of the hierarchical analysis method is to decompose the decision-making problem into different hierarchical structures in the order of overall goal, sub-goals at each level, evaluation criteria and specific alternative plans, and then use the method of solving the eigenvector of the judgment matrix to obtain the priority weight of each element at each level to an element at the previous level, and finally use the weighted sum method to recursively merge the final weights of each alternative plan to the overall goal. The one with the largest final weight is the optimal plan.
[0124] It should be noted that the construction method of the filter optimization knowledge graph is a complex and systematic process, which involves knowledge and technology in multiple fields. The following is a general construction process, as well as some key steps and considerations:
[0125] Clarify the construction goals and requirements: Before starting to build the filter optimization knowledge graph, you first need to clarify the construction goals and requirements. This includes determining the application scenarios of the knowledge graph, the types of filters and optimization methods that need to be covered, and the expected effects.
[0126] Collecting knowledge related to filter optimization: Collecting knowledge related to filter optimization is the basis for building a knowledge graph. This includes knowledge on the basic principles, design methods, optimization algorithms, performance evaluation indicators, etc. of filters. You can consult relevant literature, books, patents, and other materials, or collect relevant information from the Internet.
[0127] Knowledge extraction and entity recognition: Extracting entities and relationships from the collected knowledge is the core step in building a knowledge graph. Entities can be concepts such as filter types, optimization algorithms, and performance indicators, while relationships are the connections and interactions between these entities. Natural language processing technology can be used to perform operations such as word segmentation, part-of-speech tagging, and named entity recognition on text to extract relevant entities and relationships.
[0128] Knowledge representation and storage: The extracted entities and relationships are represented as knowledge, and a suitable storage method is selected for storage. Knowledge representation can be done using graph structures, relational databases, or graph databases. The choice of storage method should take into account factors such as query efficiency, convenience of data update and maintenance, etc.
[0129] Knowledge graph construction and visualization: Based on the extracted entities and relationships, filter optimization knowledge graphs are constructed. This can be achieved through tools such as graph databases. At the same time, in order to facilitate users to understand and use knowledge graphs, visualization can be performed, such as using a graphical interface to display the relationship between entities, providing query and navigation functions, etc.
[0130] Knowledge graph optimization and update: The construction of knowledge graph is an ongoing process that requires continuous optimization and updating. The knowledge graph can be expanded by introducing new filter types, optimization algorithms, or performance evaluation indicators; at the same time, the existing knowledge needs to be verified and corrected to ensure the accuracy and completeness of the knowledge graph.
[0131] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. A test method for voltage filter of asynchronous generator for ship, characterized in that: include, The environmental conditions of the environment in which the asynchronous generator is located are monitored periodically, and a working condition data set is constructed by summarizing the acquired monitoring data. The environmental condition coefficient To is constructed by the working condition data. If the environmental condition coefficient To exceeds expectations, an abnormal monitoring instruction is issued to the outside. The working condition data set includes the acquired environmental humidity Rs and salt spray concentration Yw. The environmental condition coefficient To is constructed as follows: the environmental humidity Rs and salt spray concentration Yw are linearly normalized, and the corresponding data values are mapped to the interval [0,1], and then according to the following method: in, is the reference standard value of ambient humidity, Rs i is the value of ambient humidity at the i-th monitoring node, Rs avg is the mean value of ambient humidity; is the reference standard value of salt spray concentration, Yw i is the value of salt spray concentration at the i-th monitoring node, Yw avg is the mean value of salt spray concentration; o = 1, 2, ... k, k is the number of monitoring nodes; weight coefficient: 0 ≤ β ≤ 1, 0 ≤ α ≤ 1; Monitor and obtain the working status data of the asynchronous generator, construct the generator operating status data set, and construct the operating abnormality Co of the asynchronous generator from the data in the generator operating status data set. If the operating abnormality Co exceeds expectations, issue a test instruction to the outside; wherein, the operating abnormality Co is constructed as follows: linearly normalize the power factor Gs and the operating noise Zs, map the corresponding data values to the interval [0,1], and then follow the following method: Among them, Gs i is the value of the power factor at the i-th monitoring node, Zs i is the value of the operating noise at the i-th monitoring node; where i = 2, ... 3, n, n is the number of monitoring nodes; weight coefficient: 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1; The test conditions of the voltage filter are constructed in advance, and the test data set is constructed from the test data after the test. The abnormal density Mjo of the waveform abnormality of the asynchronous generator is constructed from the acquired test data. If the abnormal density Mjo exceeds the density threshold, a load test instruction is issued to the outside; wherein, the abnormal density Mjo of the abnormal waveform is constructed from the acquired waveform abnormality and the corresponding time information, wherein the time center Cn of each abnormal waveform in time is calculated by the time difference between any two abnormal waveforms; after the time center Cn and the waveform abnormality Pe of each abnormal waveform are obtained, the abnormal density Mjo constructed for the waveform abnormality in the test process is normalized, and then the following method is used: Where i is the abnormal waveform number, i = 1, 2, ..., k; Cn avg is the mean of k time centralities, Pe avg is the mean value of the abnormality of k waveforms; Cn i is the time center of the ith abnormal waveform, Pe i is the waveform abnormality of the ith abnormal waveform; weight coefficient: 0≤ζ≤1, 0≤χ≤1; Under different load conditions, the waveform similarity between loaded and unloaded is obtained, and the improvement degree So of the voltage filter on the waveform is constructed from the similarity data. The improvement degree of the filter on the waveform distortion is evaluated based on the improvement degree So. If the improvement degree So is less than expected, an optimization instruction of the voltage filter is issued to the outside. Among them, the improvement degree So of the voltage filter on the waveform is constructed from the similarity data in the following way: Where i = 1, 2, ..., p, p is the number of load conditions, weight coefficient: 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1 and F2 + F1 = 1; R i is the waveform similarity between the load and non-load conditions under the i-th load condition, R avg is the mean value of waveform similarity, is its qualified standard value; The corresponding optimization features are obtained by analyzing the test data under different test conditions. If the voltage filter is optimized, the filter optimization knowledge graph gives the corresponding optimization solution. After the optimization is completed, a digital twin model is built based on the voltage filter to verify the optimized voltage filter.
2. The method for testing a voltage filter of an asynchronous generator for a ship according to claim 1, characterized in that: After receiving the abnormal monitoring instruction, the working status data of the asynchronous generator is monitored at each monitoring node, including: the power factor Gs and operating noise Zs of the asynchronous generator. After the acquired monitoring data are summarized, a generator operating status data set is constructed; the operating abnormality Co of the asynchronous generator under the current environmental conditions is constructed from the data in the generator operating status data set.
3. The method for testing a voltage filter of an asynchronous generator for a ship according to claim 1, characterized in that: After receiving the test instruction, prepare the voltage filter for testing, obtain voltage waveform data at each test node, combine with the preset standard image, and build a test data set after continuously obtaining several groups; After presetting the tolerable interval, the difference ratio between the current waveform and the standard waveform is obtained through difference analysis based on the waveform images in the test data set and the pre-prepared standard images. Based on the relationship between the difference ratio and the tolerable interval, it is judged whether the current waveform is abnormal. If there is an abnormality, the difference ratio is used as the current waveform abnormality Pe, and the time information of the corresponding abnormal waveform is obtained.
4. The method for testing a voltage filter of an asynchronous generator for a ship according to claim 1, characterized in that: After receiving the load test instruction, different load conditions are set for the generator. Under each load condition, the generator is load tested, and the output voltage and corresponding waveform under different load conditions are recorded. After obtaining the waveform image when the filter is not installed, a similarity analysis is performed to analyze the waveform similarity R between with and without load; the obtained waveform similarities are summarized to obtain a waveform similarity data set.
5. The method for testing a voltage filter of an asynchronous generator for a ship according to claim 1, characterized in that: After receiving the optimization instruction, different test conditions are obtained through adjustment, and various test data, including load size, voltage reading and waveform, are recorded under each test condition. The obtained test data are summarized to construct a test data set; after identifying and comparing the data, the corresponding optimization features are analyzed and obtained; Taking filter optimization as the target word, a filter optimization knowledge graph is constructed.
6. The method for testing a voltage filter of an asynchronous generator for a ship according to claim 5, characterized in that: According to the correspondence between the optimization characteristics and the optimization scheme, the corresponding optimization scheme is given by the filter optimization knowledge graph; the optimization scheme is executed to optimize the current voltage filter; a digital twin model of the voltage filter is constructed, and the optimized voltage filter is simulated and analyzed based on the digital twin model of the voltage filter, and corresponding test data is obtained; if the optimized voltage filter is feasible, the optimization of the voltage filter is terminated; if it is not feasible, the test and optimization process is repeated after the optimization.
7. A test system for a voltage filter of an asynchronous generator for a ship, used to implement a test method for a voltage filter of an asynchronous generator for a ship as claimed in any one of claims 1 to 6, characterized in that: include: The environmental condition evaluation unit periodically monitors the environmental conditions in the environment where the asynchronous generator is located, and constructs a working condition data set based on the acquired monitoring data, and constructs an environmental condition coefficient To based on the working condition data. If the environmental condition coefficient To exceeds expectations, an abnormal monitoring instruction is issued to the outside; The abnormal state monitoring unit monitors and obtains the working state data of the asynchronous generator, constructs a generator operating state data set, constructs the operating abnormality Co of the asynchronous generator from the data in the generator operating state data set, and issues a test instruction to the outside if the operating abnormality Co exceeds expectations; A load test unit constructs test conditions of a voltage filter in advance, constructs a test data set from the test data after the test, constructs an abnormality density Mjo of the waveform abnormality of the asynchronous generator from the acquired test data, and issues a load test instruction to the outside if the abnormality density Mjo exceeds a density threshold; The improvement evaluation unit obtains the waveform similarity between loaded and unloaded under different load conditions, constructs the improvement degree So of the voltage filter on the waveform based on the similarity data, and evaluates the improvement degree of the filter on the waveform distortion based on the improvement degree So. If the improvement degree So is less than expected, an optimization instruction of the voltage filter is issued to the outside; The optimization unit obtains the corresponding optimization features by analyzing the test data under different test conditions. If the voltage filter is optimized, the filter optimization knowledge graph gives the corresponding optimization plan. After the optimization is completed, a digital twin model is built based on the voltage filter to verify the optimized voltage filter.
