CN106961100A - New energy is transported to transmission system facility - Google Patents

Abstract

New energy is transported to transmission system facility, it is characterized in that, including biological energy source combustion furnace, wind electricity generating system, the first inverter, the second inverter, small-sized DC power distribution network, cylinder, generator, oily transformer, condenser, condensate pump, feed-water heater, feed pump and transformer fault diagnosis device；The biological energy source combustion furnace is heated the feedwater that feed pump is sent, and obtains entering cylinder acting after superheated steam；The output shaft of cylinder is connected with generator shaft, and the alternating current of generator output delivers to small-sized DC power distribution network after the first inverter turns into direct current；The alternating current that wind electricity generating system is produced is delivered to small-sized DC power distribution network by the second inverter；The high-pressure side of the oily transformer of port of export connection of generator, the lateral feed pump of low pressure and condensate pump power transmission of oily transformer.

Description

New energy distribution and transmission system facility

Technical Field

The invention relates to the field of new energy, in particular to new energy distribution and transmission system facilities.

Background

The new energy power generation refers to a device for generating power by utilizing wind energy, solar energy, biomass energy and the like. The existing new energy power generation and distribution facilities are often used independently and cannot form an organic whole, which brings great inconvenience to the use of technicians in the field. In addition, the oil transformer is used as important in-store equipment for distributing and transmitting electricity, and the correct judgment of the fault state of the oil transformer is also a necessary condition for ensuring the safe operation of the whole system.

Disclosure of Invention

In order to solve the problems, the invention provides a new energy distribution and transmission system facility.

The purpose of the invention is realized by adopting the following technical scheme:

the new energy distribution and transmission system facility comprises a biological energy combustion furnace, a wind energy power generation device, a first inverter, a second inverter, a small direct-current power distribution network, a cylinder, a generator, an oil transformer, a condenser, a condensate pump, a feed water heater, a feed water pump and a transformer fault diagnosis device; the biomass combustion furnace heats the feed water pumped by the feed water pump to obtain superheated steam, and the superheated steam enters the cylinder to do work; the output shaft of the cylinder is connected with the shaft of the generator, and alternating current output by the generator is converted into direct current through the first inverter and then is transmitted to the small direct current distribution network; alternating current generated by the wind power generation device is transmitted to the small direct current distribution network through the second inverter; the outlet end of the generator is connected with the high-voltage side of the oil transformer, and the low-voltage side of the oil transformer supplies power to the water feed pump and the condensate pump; the transformer fault diagnosis device is used for carrying out fault diagnosis on the oil transformer and comprises an initial module, a gradient vector module, a hyper-parameter module, a normal module, a classification module and a fault secondary diagnosis module, wherein the initial module specifically executes: selecting H₂、CH₄、C₂H₆、C₂H₄、C₂H₂The content of the five kinds of characteristic gases is used as an input characteristic variable d of the vector machine classifier, and the input characteristic variable is subjected to standardization processing according to the following formula:

wherein x is a labelNormalized input feature variable, d_minMinimum value of gas content, d_maxFor the maximum value of the gas content, SE is a constant set for the upper limit of the gas content normalization and SP is a constant set for the lower limit of the gas content normalization; the data of the five characteristic gas contents are selected as sample data by a multiple group of 3.

The invention has the beneficial effects that: the new energy distribution and transmission system facility organically combines the wind energy power generation device and the biomass energy power generation device together, the biomass energy power generation device is used as a main power generation means, the wind-reducing power generation device is used as a standby power generation means and a voltage regulation tool of a power distribution network, and meanwhile, an accurate and effective oil transformer fault diagnosis device is also configured, so that the overall safety performance of the system is improved.

Drawings

The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.

FIG. 1 is a schematic view of the overall structure of the present invention;

fig. 2 is a schematic structural diagram of the transformer fault diagnosis apparatus.

Detailed Description

The invention is further described with reference to the following examples.

Referring to the new energy distribution and transmission system facility shown in fig. 1-2, the facility includes a biological energy combustion furnace 1, a wind energy power generation device 2, a first inverter 3, a second inverter 4, a small dc distribution network 5, a cylinder 6, a generator 7, an oil transformer 8, a condenser 9, a condensate pump 10, a water supply heater 11, a water supply pump 12 and a transformer fault diagnosis device 13.

The biological energy combustion furnace 1 heats the water fed by the water feeding pump 12 to obtain superheated steam which enters the cylinder 6 to do work; the output shaft of the cylinder 6 is connected with a generator 7 shaft, and alternating current output by the generator 7 is converted into direct current through a first inverter 3 and then is sent to a small direct current distribution network 5. The ac power generated by the wind power generator 2 is transmitted to the small dc distribution grid 5 through the second inverter 4. The outlet end of the generator 7 is connected with the high-voltage side of the oil transformer 8, and the low-voltage side of the oil transformer 8 supplies power to the water pump 12 and the condensate pump 10.

The transformer fault diagnosis device 13 is used for performing fault diagnosis on the oil transformer 8 and comprises an initial module A, a gradient vector module B, a super-parameter module C, a normal module D, a classification module F and a fault secondary diagnosis module G.

(1) An initial module A: selecting H₂、CH₄、C₂H₆、C₂H₄、C₂H₂The content of the five kinds of characteristic gases is used as an input characteristic variable d of the vector machine classifier, and the input characteristic variable is subjected to standardization processing according to the following formula:

where x is the normalized input feature variable, d_minMinimum value of gas content, d_maxFor the maximum value of the gas content, SE is a constant set for the upper limit of the gas content normalization and SP is a constant set for the lower limit of the gas content normalization; the data of the five characteristic gas contents are selected as sample data by a multiple group of 3.

As a further preferable mode, the cylinder 6 is a single cylinder, and the wind power generation device 2 is an existing wind power generation device.

(2) Gradient vector module B: setting weight convergence expectation value V_zHyper-parametric convergence expectation M_zAnd a maximum number of iterations N atPhi (x) was obtained from the sample data as follows_n)：

Where n is an iteration variable, x_nFor the input feature variable of the nth iteration, willNamed Q function Q (x)_n,x_i) Iiiiii is the norm symbol, PO is the function coefficient of the Q function;

the gradient vector g is calculated as follows:

wherein,w_nas the current weight, K₀The weighting base quantity is set artificially, and the TE is the noise error coefficient set artificially; when n is 1, let w₁Is a constant weight set by human.

As a further preferred scheme, the low-voltage side of the oil transformer 8 supplies power to the low-voltage bus 14, and power supply wiring of the condensate pump 10 and the water supply pump 12 are connected to the low-voltage bus 14.

(3) A hyper-parameter module C: the matrix H is calculated as follows:

wherein YJ ═ diag [1, y (1) (1-y (1)), y (2) (1-y (2)), …, y (N) (1-y (N)))]，A₀For artificially set constant value symmetrical vector matrix, it is easy to know when n and x_nH is determined to be an N +1 row and N +1 column matrix;

after gradient vector g and matrix H are obtained, the current weight is updated to W 'of'_nIs the updated weight;

solving for hyper-parameters according to the following formulaWherein Is a symmetric matrixThe ith diagonal element, i is less than or equal to n;is a covariance, and when n is 1,and alpha_n-1＝ɑ₀All are artificially set values, and the covariance is quantitative, i.e.All are human set values.

More preferably, the exhaust gas from the cylinder 6 enters a condenser 9 to be condensed, and condensed water after condensation is sent to a feedwater heater 11 by a condensate pump 10 to be heated, wherein the feedwater heater 11 is an indirect heat exchange type heater.

(4) A normal module D: increment iteration variable n until w 'is obtained'_nAnd alpha_nRespectively converge to respective desired values V_z、M_zThen vector machine probabilistic model Z (w 'is output as follows'_n|ɑ_n)：

Where N (.) is a normal distribution function.

As a further preferable scheme, the heating steam source of the feed water heater 11 is steam extracted from the middle stage of the cylinder 6, and the low-voltage bus 14 is a 380V voltage bus.

(5) A classification module F: the attention value x of the gas content given in the analysis and judgment guide of the dissolved gas in the transformer oil of the national standard DL/T722-2000 is introduced_sRecording the quasi-early warning item TR according to the following formula:

wherein TI is d ≧ x_sCumulative time of (d), in seconds;

inputting the content of five characteristic gases to be detected into the vector machine probability model to obtain an initial probability value P, and when TR is smaller than a set value TR of a quasi-early warning item_SAt the time, the P value is updated toTaking the obtained initial probability value P as a final probability value, or else, directly taking the obtained initial probability value P as the final probability value; if the obtained final probability value is greater than 0.5, judging the state to be a normal state, otherwise, judging the state to be a fault state; if the obtained final probability value is between 0 and 0.25, judging the fault as an electrical fault, and if the obtained final probability value is between 0.25 and 0.5, judging the fault as a non-electrical fault; if the obtained final probability value is between 0 and 0.125, the high-energy discharge fault is judged, and if the obtained final probability value is between 0.125 and 0.25, the low-energy discharge fault is judged; if the obtained final probability value is between 0.25 and 0.375, the high-temperature overheating fault is judged, and if the obtained final probability value isWhen the temperature is between 0.375 and 0.5, it is determined as a low temperature overheating fault.

As a further preferred embodiment, the small-sized dc distribution network 5 is further provided with a voltage controller (not shown), and the voltage controller detects the online voltage of the small-sized dc distribution network 5, adjusts the reactive power of the wind power generation apparatus 2 according to the online voltage value, and further adjusts the voltage of the small-sized dc distribution network 5.

(6) And a fault secondary diagnosis module G: converting the initial probability value P according to the following formula to obtain a secondary probability value P_k:

If the obtained quadratic probability value is more than 0.6, judging the state to be a normal state, otherwise, judging the state to be a fault state; if the obtained quadratic probability value is between 0 and 0.2, judging the fault as an electrical fault, and if the obtained quadratic probability value is between 0.2 and 0.6, judging the fault as a non-electrical fault; if the obtained quadratic probability value is between 0 and 0.13, judging the high-energy discharge fault, and if the obtained quadratic probability value is between 0.13 and 0.2, judging the low-energy discharge fault; if the obtained quadratic probability value is between 0.2 and 0.4, judging the fault as a high-temperature overheating fault, and if the obtained quadratic probability value is between 0.4 and 0.6, judging the fault as a low-temperature overheating fault; fault judgment and P of final probability value in fault judgment module_kThe fault judgment of (2) is in a relation of (a) and (b), and if both are satisfied, a corresponding fault alarm is sent out.

The diagnosis device can output the diagnosis result in a probability form, is convenient for analyzing the uncertainty of the problem, can effectively solve the diagnosis problem under the condition of less sample data, and has excellent diagnosis accuracy and higher diagnosis speed; the gas content attention value and the overrun accumulated time given by the analysis and judgment guide of the dissolved gas in the national standard transformer oil are introduced as the correction basis of the probability P, so that the error caused by gas content acquisition can be overcome to a great extent, and a more reliable basis is improved for the final fault judgment; meanwhile, by increasing the conversion and judgment of the sine probability, the problem that false alarm is easy to occur due to the fact that the probability output is not smooth enough in the prior art is solved, and the reliability of fault judgment is improved. .

Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (6)

1. The new energy distribution and transmission system facility is characterized by comprising a biological energy combustion furnace, a wind energy power generation device, a first inverter, a second inverter, a small direct-current power distribution network, a cylinder, a generator, an oil transformer, a condenser, a condensate pump, a feed water heater, a feed water pump and a transformer fault diagnosis device; the biomass combustion furnace heats the feed water pumped by the feed water pump to obtain superheated steam, and the superheated steam enters the cylinder to do work; the output shaft of the cylinder is connected with the shaft of the generator, and alternating current output by the generator is converted into direct current through the first inverter and then is transmitted to the small direct current distribution network; wind energyAlternating current generated by the power generation device is transmitted to the small direct current distribution network through the second inverter; the outlet end of the generator is connected with the high-voltage side of the oil transformer, and the low-voltage side of the oil transformer supplies power to the water feed pump and the condensate pump; the transformer fault diagnosis device is used for carrying out fault diagnosis on the oil transformer and comprises an initial module, a gradient vector module, a hyper-parameter module, a normal module, a classification module and a fault secondary diagnosis module, wherein the initial module specifically executes: selecting H₂、CH₄、C₂H₆、C₂H₄、C₂H₂The content of the five kinds of characteristic gases is used as an input characteristic variable d of the vector machine classifier, and the input characteristic variable is subjected to standardization processing according to the following formula:

$x=d\×\frac{d-d_{min}}{d_{max}-d_{min}}\×\frac{\sqrt{(SE-SP)}}{{(SP+SE)}^2},$

where x is the normalized input feature variable, d_minMinimum value of gas content, d_maxFor the maximum value of the gas content, SE is a constant set for the upper limit of the gas content normalization and SP is a constant set for the lower limit of the gas content normalization; the data of the five characteristic gas contents are selected as sample data by a multiple group of 3.

2. The new energy distribution and transmission system facility according to claim 1, wherein the cylinder is a single cylinder, and the wind power generation device is an existing wind power generation device; the gradient vector module specifically performs:

setting weight convergence expectation value V_zHyper-parametric convergence expectation M_zAnd a maximum number of iterations N, obtaining φ (x) in the sample data as follows_n)：

$\mathrm{\φ}\left(x_n\right)={\[1,\exp (-\frac{\left|\right|x_n-x_1\left|\right|}{2{\mathrm{PO}}^2}),\exp (-\frac{\left|\right|x_n-x_2\left|\right|}{2{\mathrm{PO}}^2}),...,\exp (-\frac{\left|\right|x_n-x_N\left|\right|}{2{\mathrm{PO}}^2})\]}^T$

Where n is an iteration variable, x_nFor the input feature variable of the nth iteration, willNamed Q function Q (x)_n,x_i) Iiiiii is the norm symbol, PO is the function coefficient of the Q function;

the gradient vector g is calculated as follows:

$g=\frac{\sqrt{|t\left(n\right)-y\left(n\right)|}}{\sqrt[3]{{\mathrm{TE}}^2+{K_0}^2}}\×{\[\mathrm{\φ}\left(x_n\right)\]}^T$

wherein y (n) ═ w_n×Q(x_n,x_N)+K₀，w_nAs the current weight, K₀The weighting base quantity is set artificially, and the TE is the noise error coefficient set artificially; when n is 1, let w₁Is a constant weight set by human.

3. The new energy distribution and transmission system facility according to claim 2, wherein the low-voltage side of the oil transformer supplies power to a low-voltage bus, and power supply connections of a condensate pump and a feed pump are connected to the low-voltage bus; the hyper-parameter module specifically executes:

the matrix H is calculated as follows:

$H=-\sqrt{\frac{{\left(TE+1\right)}^2}{1-TE}}\×\mathrm{\φ}\left(x_n\right)\×{\[\mathrm{\φ}\left(x_n\right)\]}^T\×YJ-\sqrt{\frac{{\left(TE+1\right)}^2}{1-TE}}\×A_0$

wherein YJ ═ diag [1, y (1) (1-y (1)), y (2) (1-y (2)), …, y (N) (1-y (N)))]，A₀For artificially set constant value symmetrical vector matrix, it is easy to know when n and x_nH is determined to be an N +1 row and N +1 column matrix;

after gradient vector g and matrix H are obtained, the current weight is updated to W 'of'_nIs the updated weight;

solving the over-parameter alpha according to the following formula_n:Wherein ∑_i,iIs a matrixThe ith diagonal element, i is less than or equal to n;is a covariance, and when n is 1,and alpha_n-1＝ɑ₀All are artificially set values, and the covariance is quantitative, i.e.All are human set values.

4. The new energy distribution and transmission system facility according to claim 3, wherein exhaust gas of the cylinders enters a condenser for condensation, condensed water after condensation is pumped into a feed water heater for heating by the condensed water pump, and the feed water heater is an indirect heat exchange type heater; the normal module specifically executes:

increment iteration variable n until w 'is obtained'_nAnd alpha_nRespectively converge to respective desired values V_z、M_zThen vector machine probabilistic model Z (w 'is output as follows'_n|ɑ_n)：

Wherein N (.) is a normal distributionA function.

5. The new energy distribution and transmission system facility according to claim 4, wherein the heating steam source of the feed water heater is extracted from the middle stage of a cylinder, and the low-voltage bus is a 380V voltage bus; the small direct current power distribution network is also provided with a voltage controller, and the voltage controller adjusts the reactive power of the wind power generation device according to the on-line voltage value by detecting the on-line voltage of the small direct current power distribution network so as to adjust the voltage of the small direct current power distribution network; the classification module specifically executes:

the attention value x of the gas content given in the analysis and judgment guide of the dissolved gas in the transformer oil of the national standard DL/T722-2000 is introduced_sRecording the quasi-early warning item TR according to the following formula:

wherein TI is d ≧ x_sCumulative time of (d), in seconds;

inputting the content of five characteristic gases to be detected into the vector machine probability model to obtain an initial probability value P, and when TR is smaller than a set value TR of a quasi-early warning item_SAt the time, the P value is updated toTaking the obtained initial probability value P as a final probability value, or else, directly taking the obtained initial probability value P as the final probability value; if the obtained final probability value is greater than 0.5, judging the state to be a normal state, otherwise, judging the state to be a fault state; if the obtained final probability value is between 0 and 0.25, judging the fault as an electrical fault, and if the obtained final probability value is between 0.25 and 0.5, judging the fault as a non-electrical fault; if the obtained final probability value is between 0 and 0.125, the high-energy discharge fault is judged, and if the obtained final probability value is between 0.125 and 0.25, the low-energy discharge fault is judged; and if the obtained final probability value is between 0.25 and 0.375, judging the fault as a high-temperature overheating fault, and if the obtained final probability value is between 0.375 and 0.5, judging the fault as a low-temperature overheating fault.

6. The new energy distribution and transmission system facility according to claim 5, wherein the fault secondary diagnosis module specifically performs:

converting the initial probability value P according to the following formula to obtain a secondary probability value P_k:

If the obtained quadratic probability value is more than 0.6, judging the state to be a normal state, otherwise, judging the state to be a fault state; if the obtained quadratic probability value is between 0 and 0.2, judging the fault as an electrical fault, and if the obtained quadratic probability value is between 0.2 and 0.6, judging the fault as a non-electrical fault; if the obtained quadratic probability value is between 0 and 0.13, judging the high-energy discharge fault, and if the obtained quadratic probability value is between 0.13 and 0.2, judging the low-energy discharge fault; if the obtained quadratic probability value is between 0.2 and 0.4, judging the fault as a high-temperature overheating fault, and if the obtained quadratic probability value is between 0.4 and 0.6, judging the fault as a low-temperature overheating fault; fault judgment and P of final probability value in fault judgment module_kThe fault judgment of (2) is in a relation of (a) and (b), and if both are satisfied, a corresponding fault alarm is sent out.