A method for intelligent diagnosis and safety control of multiple faults of a ship shore power system joint debugging box

Abstract

The present application relates to the technical field of ship electrical system, specifically to a kind of ship shore power system joint debugging box multi-fault intelligent diagnosis and safety control method;First, install multiple sensors in joint debugging box Real-time acquisition key electrical parameters, constitute sample vector, and the data is mean and standard deviation standardization processing, eliminate dimension difference;Subsequently, the covariance matrix is calculated using principal component analysis method and eigenvalue decomposition, and the first k principal components with cumulative contribution rate of more than 85% are selected to realize dimension reduction;For specific fault, by randomly dividing training set and test set, the direction cosine value of the principal component matrix is calculated and the upper and lower limits of error control are determined, and then the fault feature direction library is repeatedly established for each fault mode;Finally, real-time acquisition new data is compared with feature library after dimension reduction processing, if the cosine value falls into the preset interval, the fault is determined, power-off, alarm, data recording and reset detection are automatically triggered, intelligent fault diagnosis and safety control are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ship electrical system, and particularly relates to a kind of ship shore power system joint debugging box multi-fault intelligent diagnosis and safety control method. BACKGROUND

[0002] In recent years, with the continuous improvement of ship electrification level and the increasing safety requirements of marine transportation, the traditional ship electrical system is faced with single-phase-to-ground short circuit, phase-to-phase short circuit, open phase, overvoltage, undervoltage and three-phase imbalance and other faults in the process of debugging and running. These faults not only may cause equipment damage and electrical fire, but also may seriously shorten the service life of equipment and reduce the reliability of the system. The new installation or modification of power supply facilities on the ship often exposes the problems of frequent electrical faults and various types of faults in practical application, so that the traditional diagnosis method relying on experience and simple power protection has been difficult to meet the requirements of real-time monitoring and accurate early warning. Therefore, an intelligent fault diagnosis and safety control method is urgently needed to ensure that the ship shore power system can be quickly powered off, alarm and record fault data when an abnormality occurs, so as to provide scientific and effective technical support for the stable operation of the ship electrical system. SUMMARY

[0003] The present application aims at the problems in the background art and provides a kind of ship shore power system joint debugging box multi-fault intelligent diagnosis and safety control method.

[0004] The technical scheme of the present application is as follows: A kind of ship shore power system joint debugging box multi-fault intelligent diagnosis and safety control method, specifically comprising the following steps:

[0005] S1, real-time acquisition of key electrical parameters;

[0006] S2, standardization processing of the collected key electrical parameters;

[0007] S3, all standardized samples are integrated into a data matrix, and the characteristic vector matrix is obtained by calculating the covariance matrix and its eigenvalue decomposition. After arranging in descending order of eigenvalue, the first k characteristic vectors are selected, and then the data is projected into a low-dimensional space using the characteristic vectors;

[0008] S4, randomly divide the training set and the test set under the fault state, and perform standardization preprocessing and principal component analysis on the two groups of data. Calculate the inter-principal component matrix cosine similarity, and determine the upper and lower limits of fault error by multiple grouping statistics;

[0009] S5, determine the fault occurred in the ship electrical system, analyze the characteristic vector and the corresponding cosine value statistical result of each fault mode, determine the error upper and lower limits of each fault mode, and organize the fault mode information into a fault characteristic direction library;

[0010] S6, real-time collection of new samples, through standardization and dimensionality reduction to obtain feature vectors, fault analysis, and each mode vector in the fault feature library to calculate the cosine similarity, if the similarity is in the preset error interval, it is determined as a fault, otherwise it is considered normal;

[0011] S7, when the cosine similarity is out of limit, the system is powered off, alarms, records data and automatically resets.

[0012] Preferably, the standardization processing process is as follows:

[0013] For each component of each sample, the following formula is used:

[0014]

[0015] Wherein, Z i is the standardized i-th sample; m is the sample mean vector; n represents the total number of samples; v is the sample standard deviation vector, and the component calculation formula is:

[0016]

[0017] Wherein, x ij represents the j-th variable in the i-th sample; m j is the mean of the j-th variable.

[0018] Preferably, the projection process of projecting data into a low-dimensional space using feature vectors is as follows:

[0019] S31, all standardized samples are integrated into a data matrix: Z = [Z1, Z2, …, Z i ,…,Z n ];

[0020] Wherein, Z represents the data matrix of all integrated standardized samples;

[0021] S32, calculate the covariance matrix S:

[0022]

[0023] Wherein, T represents the transpose operation of the matrix;

[0024] S33, eigenvalue decomposition is performed on the covariance matrix S to solve the eigenvalues and the corresponding eigenvectors:

[0025] SW = WΛ;

[0026] Wherein, W is the eigenvector matrix, W = [w1,..,w i ,…,w p ]; w i represents any direction; Λ is a diagonal matrix, and the elements λ1, λ2, …, λp The variance contribution of each direction is represented in sequence;

[0027] S34, arrange in descending order according to the eigenvalue size, select the first k eigenvectors W k = [w1, w2, …, w k ] so that the cumulative contribution rate meets:

[0028]

[0029] S35, use the selected eigenvectors W k Project the data to a low-dimensional space to obtain the reduced dimension data Y:

[0030]

[0031] Preferably, the generation process of the upper and lower limits of the fault error is as follows:

[0032] S41, extract the samples in the fault state from the collected data, and then randomly divide them into a training set X train And a test set X test ;

[0033] S42, generate principal component matrices W train And W test ;

[0034] S43, calculate the direction cosine value:

[0035]

[0036] Where, cos<W train ,W test > represents the direction cosine value of the principal component matrices W train And W test ; W train ·W test is the dot product between the corresponding eigenvectors; ||W train || and ||W test || are the Euclidean norms of the vectors in the matrices, respectively;

[0037] S44, calculate the cosine value by randomly grouping the samples multiple times, and statistically determine the upper and lower limits of the error control of the fault state.

[0038] Preferably, the construction process of the fault feature direction library is as follows: define the fault type j that occurs in the ship electrical system, analyze to obtain the respective eigenvectors W j and the corresponding cosine value statistical results, determine the error lower limit LCL j and the upper limit UCL j of each fault mode, and finally organize the information of each fault mode into a fault feature direction library {typej ,W j ,LCL j ,UCL j}。

[0039] Preferably, the fault analysis process is as follows:

[0040] S61, acquire a new sample X new , and normalize and reduce its dimension to obtain the feature vector W new of the new data;

[0041] S62, compare W new with the feature vector W j of each fault mode in the feature library, and calculate the cosine similarity:

[0042] S63, if a certain cosine value falls within the error control interval [LCL j , UCL j ] corresponding to the fault mode, it is determined that the new data matches the fault; otherwise, it is considered normal or not to reach the fault standard.

[0043] Compared with the prior art, the above technical solutions of the present application have the following beneficial technical effects:

[0044] The present application designs a kind of ship shore power system joint debugging box multi-fault intelligent diagnosis and safety control method, from data acquisition, dimension reduction feature extraction, fault feature library construction to real-time intelligent diagnosis and safety control Whole process automation provides a kind of efficient, accurate, safe fault prevention and processing technology for ship shore power system:

[0045] (1) real-time efficient fault diagnosis: through multi-sensor data acquisition and data standardization processing, combined with principal component analysis (PCA) to extract key features, realize the real-time monitoring and intelligent diagnosis of various faults (such as single-phase-to-ground short circuit, phase-to-phase short circuit, open phase, overvoltage, undervoltage and three-phase unbalanced fault) of ship shore power system, significantly improve the accuracy of fault identification;

[0046] (2) dimensionality reduction and noise reduction, extract core information: use PCA method to reduce the dimension of data, which not only reduces the redundant information, but also suppresses the interference of noise, making the subsequent fault feature comparison more reliable, and providing a unified standard for building multi-fault feature direction library;

[0047] (3) standard feature direction library construction: through multiple random grouping calculations of each fault mode, a standard feature direction and error control range are established, which provides a strong basis for accurate comparison under different fault states, and enhances the system's ability to identify fault types;

[0048] (4) Intelligent safety control measures: After detecting a fault, automatically trigger safety measures such as power-off, alarm, data recording, and reset detection, isolate the fault in time, prevent the spread of accidents, and improve the safety and reliability of the overall system;

[0049] (5) Reduce maintenance cost and risk: Through the realization of automatic monitoring and fault early warning, not only reduces the demand for manual intervention, but also reduces the risk of equipment damage or fire accidents caused by faults, helps to prolong the service life of the equipment and reduce the maintenance cost. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 The existing shore power reconstruction system topology reference diagram;

[0051] Figure 2 The device assembly diagram in the embodiment of the present application;

[0052] Figure 3 The electrical schematic diagram of the device in the embodiment of the present application;

[0053] Figure 4 The device plane layout diagram in the embodiment of the present application;

[0054] Figure 5 The equivalent circuit diagram of the pressure loss control in the embodiment of the present application;

[0055] Figure 6 The off voltage coefficient K MX Characteristic analysis diagram;

[0056] Figure 7 The pressure loss control circuit diagram in the embodiment of the present application;

[0057] Figure 8 The pressure loss coil voltage characteristic simulation diagram in the embodiment of the present application;

[0058] Figure 9 The construction flowchart of the fault feature direction library proposed by the present application;

[0059] Figure 10 The diagnosis flowchart after the start of the commissioning box debugging of the present application.

[0060] Reference signs: 1, circuit breaker; 2, primary input terminal; 3, power indicator light; 4, output live indicator light; 5, emergency stop button; 6, electric operating mechanism; 7, sampling control unit; 8, dissipation resistance; 9, first standard socket; 10, second standard socket; 11, portable handle; 101, opening; 12, three-phase power supply wire hole; 13, wire binding support; 14, grounding column. DETAILED DESCRIPTION

[0061] Embodiment one, the common transport ship shore power system isFigure 1 As shown, in the entire shore power system, the input is the shore power supply pile (within the red box), and the ship's shore power system receiving facilities (within the blue box), including: 1. a ship's cable winch (100m as specified in the propulsion plan), 2. a shore power box, 3. a measuring box, and 4. an isolation transformer; the output is connected to the ship's main switchboard. The basic functions of the ship's shore power system receiving facilities are: three-phase power supply, emergency stop capability in case of fault, etc. After the shore power system receiving facilities are installed or modified on the ship, it is necessary to verify whether the installation and commissioning of the ship's shore power system receiving facilities are qualified. Ideally, the standard shore power supply pile facilities should be used directly for commissioning and testing. However, this ideal situation is limited by external conditions: 1. Untested and unverified receiving facilities are not allowed to be connected to standard power supply piles; 2. Whether the ship is in berth; 3. Whether standard power supply piles are available on shore; 4. Whether the ship's testing and commissioning time period occupies the normal power supply operation time of the dock, etc. These inconveniences hinder the commissioning and acceptance of the ship's shore power system receiving facilities.

[0062] In general, the larger the gross tonnage of a ship, the larger its rated load capacity. This is mainly determined by the size of the ship's load. Most ships on inland waterways and the Yangtze River use shore power systems with interfaces of 63A and 125A. A 63A shipboard power receiving system requires a commissioning system with a 63A standard interface for testing and debugging; similarly, a 125A shipboard power receiving system requires a commissioning system with a 125A standard interface. According to regulations, regardless of whether it's a 63A or 125A shore power system, the shore power cable, including the emergency stop control line and the power line, is installed on a cable winch to supply power to the ship. When the ship docks, the winch releases the cable and connects to the shore power pile; when the ship departs, the winch retracts the cable. The power supply cable is relatively long (to ensure connection to the shore system; the cable length on the winch is generally at least 100 meters), and the impact of distributed capacitance needs special consideration. While distributed capacitance can be ignored over short distances, it must be taken into account in the design and application phases.

[0063] like Figure 1 The diagram shown is a topology reference diagram of a shore power retrofit system, which details the structural components of the shore power system, including shore power supply piles with 63A and 125A standard sockets; a shipboard cable winch connecting the shore power supply piles and the shore power box on the ship; and a shore power commissioning box provided in this embodiment, which serves as a substitute for the shore power supply piles within the red box during shore power system commissioning.

[0064] The overall assembly drawing of the shore power commissioning box is as follows: Figure 2 As shown, it includes a housing; a first standard socket 9 and a second standard socket 10 are respectively provided on both sides of the housing for connecting with different types of vessels, which serve as a commissioning tool to connect to the ship's shore power system; wherein, the first standard socket 9 is a 125A marine socket; the second standard socket 10 is a 63A marine socket;

[0065] A portable handle 11 is provided on the top of the box, which can be used to move the box to a designated position.

[0066] The enclosure contains a circuit breaker 1, a primary input terminal block 2, an electric operating mechanism 6, a sampling control unit 7, and a dissipation resistor 8. By connecting and combining the circuit breaker 1, the primary input terminal block 2, the electric operating mechanism 6, the sampling control unit 7, and the dissipation resistor 8, a control circuit that can control and switch sockets is formed.

[0067] The front of the enclosure is hinged with a sealed door; the power indicator light 3, the output live indicator light 4 and the emergency stop button 5 are all integrated on the sealed door of the enclosure; the circuit breaker 1, the primary input terminal 2, the power indicator light 3, the output live indicator light 4, the emergency stop button 5, the electric operating mechanism 6, the sampling control unit 7 and the dissipation resistor 8 are electrically connected.

[0068] The operating handle of circuit breaker 1 passes through the opening 101 on the front door of the enclosure, facilitating the opening and closing of circuit breaker 1 from outside the enclosure. A three-phase power inlet hole 12 is located at the bottom of the enclosure for connecting to an external three-phase power supply. A separate grounding post 14 is installed at the bottom of the enclosure. Specifically, to ensure the operational safety of this commissioning box, an external protective earth (PE) is connected to the primary input terminal 2 during commissioning. This PE is connected to both the enclosure casing and the front door. Furthermore, protective earths (PE) are also connected to the 125A marine standard socket 9 and the 63A marine standard socket 10.

[0069] In this embodiment, a cable tie 13 is provided along one side of the three-phase power inlet hole 12 to fix the power cord and prevent it from shifting during use.

[0070] like Figure 3 The external three-phase power supplies ABC and PE are connected to the primary input terminal DZ1 via a primary cable; the output of the primary input terminal DZ1 is connected to the upper ports L1, L2, and L3 of circuit breaker 1QF via cables; PE is connected to the PE connection points of the 125A and 63A standard marine sockets and a separate grounding post at the bottom of the enclosure via cables; the lower ports L11, L12, and L13 of circuit breaker 1QF are simultaneously connected to the three-phase interfaces of the 125A and 63A standard marine sockets via wires; A610 and C610 lines are led out from the lower ports L11 and L13 of circuit breaker 1QF, and the output indicator light Hr is connected across the A610 and C610 lines; fuses FU1 and FU2 are connected in series at the upper ports L1 and L3 of circuit breaker 1QF, and A600 and C600 lines are led out; the power indicator light Hw is connected in parallel across the A600 and C600 lines.

[0071] A600, C600 line parallel across another line; A600, 101 access emergency stop button SB; 101, 103 connected 125A relay switch 1DK, and lead to the connection to the 125A standard marine socket control signal connection point P2, P1; 103, 105 connected 63A relay switch 2DK, and lead to the connection to the 63A standard marine socket control signal connection point P2, P1; 105 line through the undervoltage release coil 1QF access C600 line, coil lower end lead to the power resistance access control relay switch group 3DK, which is sampled by the sampling control unit 7 according to the measurement of the cable distribution capacitor, the sampling control unit 7 selects the output control relay group 3DK to access different number of dissipative resistors R1, R2, R3, R4 (same specification 50kΩ, 10W) to the upper end of the undervoltage release coil 1QF, complete the loop, by controlling the number of dissipative resistors accessed circuit in turn control the heat dissipation power and reliable undervoltage release.

[0072] In Figure 2 , the joint box has 125A marine standard socket and 63A marine standard socket, connected to the corresponding standard socket of 125A and 63A shore power box below Figure 3 in 100 meters long standard shore power cable. Taking 125A marine shore power system equipment debugging as an example, after connecting the cable, it can be seen that the original 101, 103 lead to the control signal connection point P2, P1 of the standard marine socket is connected to the P2, P1 of the ship shore power box socket through the 100 meters long cable, which is in series with the emergency stop button SB1 of the shore power box in the ship shore power box; the 63A debugging connection is similar to the above.

[0073] The emergency stop button SB of the device corresponds to the technical solution Figure 2 in the joint debugging box, SB1 corresponds to the 125A shore power box emergency stop button, SB2 corresponds to the 63A shore power box emergency stop button, and the corresponding standard interface is selected for the test scheme of 63A, 125A different specifications of ship shore power system. In debugging, the joint debugging box can provide safe access of test power supply for the power receiving facilities to be tested, and can realize the cutting function of the debugging box and the ship shore power box.

[0074] In the debugging function, the joint debugging box can realize 63A loop debugging and 125A loop debugging functions respectively.

[0075] The sampling control unit 7 detects the limit detection switch equipped in the 125A standard socket 1 and the standard socket 2, and when the 125A socket is detected to be connected, the relay switch 2DK is automatically closed and the relay switch 1DK is automatically opened, at this time, whether the joint debugging box emergency stop button or the shore power box emergency stop button can realize the task of cutting off the test circuit (simulating the accidental emergency power-off in the actual use process); similarly, when the 63A socket is detected to be connected, the relay switch 2DK is automatically opened and the relay switch 1DK is automatically closed, and the specific debugging method is: in the 63A loop debugging, the relay switch 1DK is closed and the relay switch 2DK is opened, and in the circuit state at this time, Figure 3 The joint debugging box emergency stop button SB and the 63A shore power box emergency stop button SB2 are connected in series between A600 and C600 at this time, and whether the joint debugging box emergency stop button SB or the shore power box emergency stop button SB2 can realize the task of cutting off the test circuit (simulating the accidental emergency power-off in the actual use process). In the 125A loop debugging, the relay switch 1DK is opened and the relay switch 2DK is closed, and the joint debugging box emergency stop button SB and the 125A shore power box emergency stop button SB1 are connected in series between A600 and C600. In terms of debugging flexibility, the joint debugging box can flexibly access different capacity dissipative resistors R1, R2, R3 and R4 according to the characteristics of the cable material and length, thereby greatly reducing the influence of the equivalent capacitance of the cable and realizing reliable opening of the line.

[0076] The planar three-view diagram of the joint debugging box is as shown in Figure 4 When testing different specifications of power receiving facilities, the opening and closing of the bypass air switch 1DK and 2DK are adjusted to flexibly select the 63A or 125A shore power system joint debugging test. The joint debugging box is designed with a portable handle to facilitate testing with the ship at any time and anywhere.

[0077] Taking the 125A shore power system joint debugging test as an example, the use operation process is described in detail:

[0078] Preparation stage: measure the open circuit impedance by opening the cable end, and measure the short circuit impedance by shorting the cable end. After completion, the sampling control unit 7 calculates the cable distribution capacitance, and selects the output control relay switch group 3DK to access the dissipative resistor according to the distribution capacitance capacity step;

[0079] Debugging stage: 1. Confirm that the circuit breaker switch is in the open position and the input end is not powered; correct wiring;

[0080] 2. After confirming that the wiring is reliable, power the input end, and if everything is normal, the joint debugging box panel power indicator should be lit, and the circuit breaker 1 should be closed, and if everything is normal, the output indicator should be in the lit state;

[0081] 3、Input from the bottom of the test box hole access to the main power A-B-C three-phase and protective ground PE, for example, the output terminal 125 A shore power system, then the output terminal 125 A standard socket, test box inside the relay switch 2DK;

[0082] 4, press the test box emergency stop SB test test box emergency stop function; emergency stop function is normal after power on, press the test shore power box emergency stop SB1, ensure that the emergency stop function is normal;

[0083] 5, test shore power box emergency stop function is normal after power on, test the ship power supply facilities power on;

[0084] 6, power supply facilities power on test is completed - power - tidy up the harness.

[0085] Fault handling: 1, the background system detects fault after debugging will immediately issue instructions to the sampling control unit 7 to control the electric mechanism 6 to cut off the circuit breaker 1; among them, the background system selects the existing online monitoring system that can match it; It should be noted that the implementation of the two methods is the monitoring and diagnosis of the test box during debugging and the safety control method.

[0086] 2, when the abnormal power failure occurs, stop testing immediately, extract the debugging fault log, find and eliminate the fault source; after eliminating the fault, start debugging.

[0087] It is worth noting that the test box will generate a certain amount of heat during use, and the device does not have an active cooling device, so it should be avoided for long-term uninterrupted use. After the debugging work is completed without error, the device should be disconnected in time.

[0088] The performance of the above-mentioned shore power test box is verified by the test method of the shore power test box, including the following specific steps:

[0089] S1, impedance analysis of the circuit, construct an equivalent circuit;

[0090] S2, based on the constructed equivalent circuit, analyze the distributed capacitance;

[0091] S3, based on MATLAB tool, analyze the characteristics of the equivalent circuit;

[0092] S4, adjust each parameter in the equivalent circuit based on the analysis result;

[0093] S5, use the adjusted equivalent circuit to simulate and verify the accuracy of the simulation result through experiment.

[0094] Explanation of the influence of distributed capacitance on system emergency stop function:

[0095] During the manufacturing and functional testing of the test box, the initial design does not have Figure 3parallel in the figure to the dissipation resistor across the under-voltage release 1QF R , in the electrical principle Figure 3 , embodied as a dissipation resistor R is infinite. However, in actual debugging operation, there is an abnormal situation that the under-voltage release has a probability of failure to trip off although the emergency stop button is pressed down, resulting in failure of emergency stop in the debugging process. In view of this abnormal working condition, after re-examining the circuit characteristics and working principle, it is determined that the reason for the failure of the under-voltage release 1QF to trip off is that there is a certain distributed capacitance in the long-distance power cable, which causes the voltage on the under-voltage release coil to still not reach the release limit value even if the emergency stop is pressed down.

[0096] In view of the above analysis, a certain dissipation resistor is connected in parallel to the under-voltage release coil, so as to reduce the voltage amplitude on the under-voltage release in the circuit. In order to fully understand the mechanism of the distributed capacitance of the long-distance connecting cable, the control loop is analyzed here.

[0097] When the cable is long, although the emergency stop is disconnected, the long-distance control cable is equivalent to a capacitor connected in series in the loop, and the under-voltage release coil can be equivalent to a resistor and an inductor. The total equivalent circuit structure is as follows Figure 5 as shown.

[0098] The equivalent circuit includes power lines L1, L3, resistors R, R MX , inductors L MX and capacitors C;

[0099] Among them, the resistor R MX , the inductor L MX constitute a series R-L circuit, and then a capacitor C is connected in series and connected to the power line L1; one end of the resistor R MX is connected to the power line L3;

[0100] The resistor R is connected in parallel with the R-L circuit composed of the resistor R MX and the inductor L MX ;

[0101] In this circuit, the power supply is an alternating current with a certain frequency f, and the equivalent impedance of the inductor and the capacitor is affected by the frequency of the power supply. The equivalent impedance of the inductor and the capacitor needs to be brought into analysis.

[0102] The equivalent impedance of the capacitor and the under-voltage release coil: Z MX =(R MX +jωL MX ) / / R, where ω=2πf.

[0103] The voltage on the under-voltage release coil: U MX =K MX (U L1 -U L3), where the coefficient U L1 , U L3 and V are the voltages on L1, L3 and L2 respectively.

[0104] Analysis can be obtained when the power frequency f is constant, the voltage U MX on the loss voltage coil is positively correlated with the coefficient K MX , which can be used to determine the voltage on the loss voltage coil by the coefficient K MX .

[0105] Characteristic analysis: using MATLAB tools, comprehensive quantitative analysis of the coefficient K MX of the loss voltage coil shutdown voltage U MX and the mathematical relationship between the power frequency f, the cable distribution capacitance C and the parallel dissipation resistance R. In mathematical calculation, the loss voltage coil shutdown DC resistance R MX = 100kΩ, L MX = 50H, the cable length is designed to be 100m. The relationship between the coefficient K MX of the voltage U MX on the loss voltage coil and the power frequency f, the cable distribution capacitance C and the parallel dissipation resistance R can be simulated.

[0106] As Figure 6 shown, under the premise of constant cable distribution capacitance, when the power frequency f≥40Hz, with the increase of the resistance value of the longitudinal coordinate parallel dissipation resistance R (corresponding to the decrease of the dissipation power), the coefficient K MX of the shutdown voltage U MX presents an increasing trend, that is, the voltage U MX on the loss voltage coil may appear voltage overlarge leading to disconnection failure, and the appropriate size of the dissipation resistance can reduce the coefficient K MX of the shutdown voltage U MX to a certain extent.

[0107] When the distribution capacitance C is 0.001uF, the dissipation resistance R changes in the range of 10kΩ-20kΩ, the coefficient K MX will always be higher than 0.03, which means that the capacitance value of the distribution capacitance C at this time is too small, and the abnormal phenomenon of under-voltage release 1QF disconnection will not appear.

[0108] However, when the distribution capacitance C reaches 0.1uF, the power frequency f=50Hz, from Figure 6 it can be seen that the distribution range of the coefficient K MX expands to close to 1, and the influence of the distribution capacitance on the under-voltage release 1QF is intensified. In Figure 6 , it can be seen that only the dissipation resistance with a resistance value less than 5kΩ can effectively reduce the coefficient K MXLower to 0.5 within.

[0109] Based on the above analysis, the selection of dissipation resistance R needs to fully consider the value of the distributed capacitance C of the cable. For a larger distributed capacitance, the dissipation power needs to be increased and the dissipation resistance value needs to be reduced. For the common cable unit length distributed capacitance range of 10 pF / m to 1000 pF / m, the conclusion is that the power resistance value is controlled in the range of 6 to 10 kΩ, which can eliminate the adverse effects of the distributed capacitance of the cable on the under-voltage release.

[0110] It is worth pointing out that since the dissipation resistance is connected to the line at all times during operation, it inevitably has a certain electrical power consumption. At the same time, the above conclusion that the power resistance value is controlled in the range of 6-10 kΩ, although it can be applied to the common cable distributed capacitance range, the electrical power P=U 2 / R consumed by it can be calculated to be in the power range of 16 W-26.7 W, which is obviously not allowed. On the one hand, high power consumption means that the heat dissipation requirement of the device increases; on the other hand, higher requirements are placed on the reliability of the dissipation resistance.

[0111] Further analysis shows that the unit length distributed capacitance of the cable is mostly concentrated in the range of 100 pF / m to 300 pF / m, and the capacitance value under 100 meters is in the range of 0.01 uF-0.03 uF. The above 6 kΩ-10 kΩ dissipation resistance value range is taken to cope with extreme cases, but the heating power range of the above dissipation resistance is 16 W-26.7 W, which is obviously unreasonable in terms of heating electrical power. Therefore, the equivalent resistance value of the dissipation resistance shown in the following table is set as a reference.

[0112]

[0113] Based on the above analysis, the design is further improved. The distributed capacitance detection function is integrated in the sampling control unit 7. The three-voltage method is used to complete the capacitance value detection of the distributed capacitance of the cable. In the test, the open circuit impedance Z OC and the short circuit impedance Z SC of the cable are measured respectively, and the characteristic impedance of the cable is obtained by applying the formula Further calculation of the propagation constant γ:

[0114] Where l is the cable length, α is the attenuation constant, and β = 2πf / v (v is the propagation speed) is the phase constant. It is worth pointing out that in actual application, the approximate method (α≈0) is usually used to simplify the calculation under low loss conditions, and then the equation set is simplified to approximate the solution;

[0115] The characteristic impedance Z0, the propagation constant gamma, and the inductance L and the capacitance C per unit length have the following relationships: According to the above formula, the capacitance C can be calculated as:

[0116] C≈β / ωZ0=1 / Z0v;

[0117] Before debugging, the sampling control unit can complete the detection of the distributed capacitance of the cable through the three-voltage method before system testing, and according to the measured distributed capacitance value of the cable, the output control relay 3DK step selection access power resistor (R1, R2, R3, R4) is selected according to the above table, so as to eliminate the adverse effects of the distributed capacitance.

[0118] On the basis of the above, the LTspice tool is used for experimental verification, and a voltage simulation circuit as shown in Figure 7 is built, wherein the capacitance is selected as 0.005uF. It includes a path one (R1, L1, C1) without adding a dissipative resistor; a path two (R2, R21, L2, C2) with a 50kΩ dissipative resistor in parallel; and a path three (R3, R31, R32, L3, C3) with two 50kΩ dissipative resistors in parallel. By measuring the voltages of nodes v1, v2, v3, and v4, the voltage across the coil can be calculated as Figure 8 .

[0119] In the path one without parallel resistors, it can be seen that the voltage on the loss voltage coil is obviously higher than that of the path two and the path three with dissipative resistors. By comparison, the 50kΩ dissipative resistor in parallel with the 0.005uF distributed capacitance has a relatively obvious effect on reducing the voltage on the loss voltage coil, and the 50kΩ in parallel has a stronger effect, which can reduce the voltage on the loss voltage coil to an effective range of the protection value, which meets the above analysis.

[0120] Embodiment two, as shown in Figure 9 and Figure 10 , the present application proposes a kind of ship shore power system joint debugging box multi-fault intelligent diagnosis and safety control method, it is applied to the intelligent diagnosis and safety control in the debugging process of shore power joint debugging box described in embodiment one, specific implementation steps are as follows:

[0121] S1, in the process of ship shore power system joint debugging box debugging, real-time acquisition of its key electrical parameters, key electrical parameters include but are not limited to voltage, current, power factor;

[0122] Each time the data constitutes a sample, denoted as vector X i =[x i1 ,x i2 ,…,x ij ,…,x ip ]T;

[0123] wherein, X i is the ith sample; p represents the number of variables (i.e. sensor measurement items); x ij represents the jth variable in the ith sample;

[0124] It should be noted that the data acquired by the sampling control unit 7 in the onshore joint debugging box can be collected, that is, the system corresponding to the method is in communication connection with the sampling control unit 7 to receive the data of the sampling control unit 7 in real time and issue instructions to the sampling control unit 7.

[0125] S2, to eliminate the influence of different dimensions and orders of magnitude, the original data is standardized, for each component of each sample, the following formula is used:

[0126]

[0127] wherein, Z i is the ith standardized sample; m is the sample mean vector; n represents the total number of samples; v is the sample standard deviation vector, and the component calculation formula is:

[0128]

[0129] wherein, x ij represents the jth variable in the ith sample; m j is the mean of the jth variable.

[0130] S3, principal component analysis (PCA) and feature extraction, that is, the original data is converted into a feature that can more obviously reflect the main change of the sample after dimension reduction, which lays the data structure for subsequent fault mode comparison, specifically:

[0131] S31, all standardized samples are integrated into a data matrix: Z = [Z1, Z2, …, Z i , Z n ];

[0132] wherein, Z represents the data matrix of all integrated standardized samples;

[0133] S32, calculate the covariance matrix S:

[0134]

[0135] It should be noted that each element s ij in the covariance matrix S measures the linear correlation between the ith and jth variables;

[0136] S33, the eigenvalue decomposition of the covariance matrix S is carried out, and the eigenvalue and the corresponding eigenvector are solved:

[0137] SW = WΛ;

[0138] where W is the eigenvector matrix, W = [w1,..,w i ,…,w p ]; w i represents any direction; Λ is a diagonal matrix, whose diagonal elements λ1, λ2, …, λ p represent the variance contribution of each direction in turn;

[0139] S34, arrange in descending order according to the size of the eigenvalue, select the first k eigenvectors W k = [w1, w 2, …, w k ] so that the cumulative contribution rate meets:

[0140]

[0141] Accordingly: the selected W k represents the main feature reduction basis of the original data, and the data is projected into a low-dimensional space using the basis to obtain the reduced dimension data:

[0142]

[0143] It should be noted that this step not only reduces data redundancy, but also extracts features that describe the main information of the sample, providing a unified standard for subsequent fault feature comparison.

[0144] S4, single fault mode feature direction acquisition, a "standard" feature direction and error range of a certain fault are established through grouping and statistics, specifically:

[0145] S41, extract samples in fault state from the collected data, and then randomly divide them into training set X train and test set X test ;

[0146] S42, execute S1-S3 on the two groups of data respectively to obtain their respective principal component matrices W train and W test ;

[0147] S43, to measure the consistency of the features of the two groups of data, calculate the direction cosine value:

[0148]

[0149] where cos<W train ,W test > represents the direction cosine value of the principal component matrices W train and W test ; W train ·W test is the dot product between the corresponding eigenvectors; ||W train || and ||Wtest || represents the Euclidean norm of the vectors in each matrix;

[0150] Therefore: the closer the cosine value is to 1, the more consistent the directions of the two sets of features are; to ensure stability, the cosine value is calculated by randomly grouping the samples multiple times, and the upper and lower limits of error control (LCL and UCL) of the fault state are statistically determined accordingly.

[0151] It should be noted that this step establishes standard characteristic directions for specific fault modes and determines the allowable error range, providing a template for building a multi-fault characteristic library.

[0152] S5, such as Figure 1 As shown, all fault modes are standardized and integrated to form a fault feature direction library for real-time identification, specifically:

[0153] Types of faults that may occur in the ship's electrical system j (Including but not limited to single-phase-to-ground short circuit, phase-to-phase short circuit, phase loss, overvoltage, and three-phase imbalance faults), repeat step S4 to obtain their respective feature vectors W. j Based on the corresponding cosine value statistics, the upper and lower limits of error (LCL) for each fault mode are determined. j and UCL j Finally, the information on each fault mode is organized into a fault feature direction library, in the form of: {type j W j LCL j UCL j};

[0154] S6, such as Figure 2 As shown, real-time fault detection and intelligent diagnosis utilize the aforementioned standards to compare new data in real time, quickly identifying fault types. Specifically:

[0155] S61. Continuously acquire new samples X new The data is then standardized and dimensionality reduced to obtain the feature vector W of the new data. new ;

[0156] S62, W new The feature vector W of each fault mode in the feature library j Compare and calculate cosine similarity:

[0157] S63. If a certain cosine value falls within the error control range [LCL] of the corresponding fault mode. j UCL j If the new data matches the fault, it is considered to be in a normal state or has not met the fault criteria.

[0158] S7, when the detection system finds that a certain fault mode cosine value exceeds the preset normal interval, the following safety measures are triggered immediately:

[0159] Measure one: power-off control: control the mechanical operation structure, quickly disconnect the three-phase power supply, prevent the spread of failure and equipment damage;

[0160] Measure two: alarm prompt: start the buzzer or other alarm device, real-time notify the operator to take necessary measures;

[0161] Measure three: fault data recording: store the sampling data and diagnosis results at the time of failure to the built-in ROM, for subsequent traceability analysis and maintenance optimization;

[0162] Measure four: reset detection: after the fault is removed, the system automatically resets and enters the next detection cycle to ensure continuous monitoring.

[0163] The embodiments of the application are described in detail above in combination with the drawings, but the application is not limited thereto, and various changes can be made within the knowledge range of those skilled in the art without departing from the purpose of the application.

Claims

1. A method for multi-fault intelligent diagnosis and safety control of a ship shore power system integration box, characterized in that, Specifically comprising the following steps: S1, real-time acquisition of key electrical parameters; S2, standardizing the collected key electrical parameters; S3, integrating all standardized samples into a data matrix, obtaining a characteristic vector matrix by calculating a covariance matrix and eigenvalue decomposition thereof, arranging the characteristic values in descending order, selecting the first k characteristic vectors, and projecting the data into a low-dimensional space using the characteristic vectors; The projection process of projecting the data into a low-dimensional space using the characteristic vectors is as follows: S31, integrate all normalized samples into a data matrix: Z = [Z1, Z2, …, Z i ,…,Z n ] ; Wherein, Z represents the data matrix of all integrated standardized samples; S32, calculating the covariance matrix S: ； Wherein, T represents the transpose operation of the matrix; S33, performing eigenvalue decomposition on the covariance matrix S to solve the eigenvalues and the corresponding characteristic vectors: ； where W is the eigenvector matrix, W = [w1,..,w i ,…,w p ]; w i represents any one direction; is a diagonal matrix, whose diagonal elements λ1, λ2, …, λ p represent the variance contribution of each direction in turn; S34, arrange in descending order of eigenvalue size, select the first k eigenvectors W k = [w1, w 2, …, w k ] so that the cumulative contribution rate satisfies: ； S35, utilize the selected feature vector W k Project the data to the low-dimensional space to obtain the reduced dimension data Y: ； S4, randomly dividing the training set and the test set under the fault state, performing standardization preprocessing and principal component analysis on the two groups of data, calculating the inter-principal component matrix cosine similarity, and determining the fault error upper and lower limits through several grouping statistics; S5, determining the fault in the ship electrical system, analyzing the respective characteristic vectors and the corresponding cosine value statistics, determining the error upper and lower limits of each fault mode, and organizing the fault mode information into a fault characteristic direction library; S6, real-time acquisition of new samples, obtaining the characteristic vectors after standardization and dimensionality reduction, performing fault analysis, calculating the cosine similarity with each mode vector in the fault characteristic library, and determining as a fault if the similarity is within the preset error interval, otherwise considering as normal; S7, when the cosine similarity is out of limit, the system is powered off, alarms, records data and automatically resets.

2. The method according to claim 1, characterized in that, The standardization processing process is as follows: For each component of each sample, the following formula is used: ； ； wherein Z i is the standardized ith sample; m is the sample mean vector; n represents the total number of samples; v is the sample standard deviation vector, the components of which are calculated according to: , j = 1, 2,..., p; where x ij represents the jth variable in the ith sample; m j is the mean of the jth variable.

3. The method according to claim 1, characterized in that, The generation process of the fault error upper and lower limits is as follows: S41, extracting samples in a fault state from the collected data, and then randomly dividing into a training set X train and a test set X test ; S42, generating a principal component matrix W train and W test ; S43, calculating the direction cosine value: ； wherein, denotes the principal component matrix W train and W test the direction cosine values; is the dot product between the corresponding eigenvectors; and are the Euclidean norms of the vectors in each matrix, respectively. S44, calculating the cosine value through several random groupings of samples, and statistically determining the error control upper and lower limits of the fault state.

4. The method according to claim 3, characterized in that, The process of constructing the fault characteristic direction library is as follows: Define the fault types that occur in the ship's electrical system. j The eigenvectors W of each element are obtained through analysis. j Based on the corresponding cosine value statistics, the upper and lower limits of error (LCL) for each fault mode are determined. j and UCL j Finally, the information on each fault mode is organized into a fault feature direction library {type}. j W j LCL j UCL j } 5. The method according to claim 4, characterized in that, The fault analysis process is as follows: S61, acquire new sample X new , and perform standardization and dimension reduction processing to obtain the feature vector W of the new data new ; S62, compare the W new with the feature vector W of each failure mode in the feature library j and calculate the cosine similarity: ; S63, if a cosine value falls within the error control interval [LCL j , UCL j ] corresponding to a failure mode, then the new data is determined to match the failure; otherwise it is considered normal or not to meet the failure criteria.

Images