Summary of the invention
Embodiment of the present invention technical matters to be solved is, there is provided a kind of to detect in transformer each gas content in oil and to warn the method and system of value, by considering the factors such as each transformer load and weather, extract the oil chromatography data of each transformer on oil chromatography on-line monitoring, and to calculate in each transformer each gas content in oil and to warn accordingly value, effectively can improve accuracy and reliability that transformer oil chromatographic on-line monitoring warns, avoid the wasting of resources, reduce equipment Risk.
In order to solve the problems of the technologies described above, embodiments provide and a kind ofly to detect in transformer each gas content in oil and to warn the method for value, it realizes on the N number of transformer including M oil dissolved gas, and described method comprises:
A, extract in described N number of transformer value of all warning with a described M oil dissolved gas and calculate the data be associated; Wherein, described data comprise the first data be associated with a described M oil dissolved gas in each transformer, and the second data be associated with oil temperature in each transformer; M, N are positive integer;
B, according to described in the data extracted, train each oil dissolved gas content in N number of transformer and to warn the current computation model of value correspondence respectively; Wherein, described computation model comprises the statistical distribution pattern trained according to described first data and the relation analysis model jointly trained according to described first data and described second data;
C, warn after the current computation model of value all trained until described M oil dissolved gas content in described N number of transformer, and the current computation model of value of warning according to each oil dissolved gas content in the described N number of transformer trained, obtain the value of warning that in N number of transformer described in current time, described M oil dissolved gas content is corresponding respectively.
Wherein, the concrete steps of described step b comprise:
1 to M in described N number of transformer oil dissolved gas is all trained corresponding statistical distribution pattern according to described first data, obtain M*N statistical distribution pattern, and all jointly train corresponding relation analysis model according to described first data and described second data, obtain M*N relation analysis model;
Calculate the degree of fitting of a described M*N statistical distribution pattern and the degree of fitting of a described M*N relation analysis model;
According to the described degree of fitting of the M*N a calculated statistical distribution pattern and the degree of fitting of M*N relation analysis model, the size cases of the degree of fitting of the relation analysis model that the degree of fitting detecting the statistical distribution pattern that same oil dissolved gas obtains in same transformer successively in 1 to N number of transformer obtains with it;
When detecting that the degree of fitting of the statistical distribution pattern that one or more oil dissolved gas obtains in described N number of transformer is all less than the degree of fitting of the relation analysis model that it obtains, then in the N number of transformer detected described in determining, the warn current computation model of value of one or more oil dissolved gas content is relation analysis model;
When detecting that the degree of fitting of the statistical distribution pattern that one or more oil dissolved gas obtains in described N number of transformer is all greater than the degree of fitting of the relation analysis model that it obtains, then in the N number of transformer detected described in determining, the warn current computation model of value of one or more oil dissolved gas content is statistical distribution pattern.
Wherein, the concrete steps of " current computation model of value of warning according to each oil dissolved gas content in the described N number of transformer trained obtains the value of warning that in N number of transformer described in current time, described M oil dissolved gas content is corresponding respectively " in described step c comprising:
When one or more oil dissolved gas content in the described N number of transformer trained warn the current computation model of value be statistical distribution pattern time, obtain by three-sigma principle the value of warning that in N number of transformer described in current time, one or more oil dissolved gas content is corresponding respectively;
When one or more oil dissolved gas content in the described N number of transformer trained warn the current computation model of value be relation analysis model time, the oil temperature threshold value preset by each transformer substitutes in relation analysis model corresponding to described one or more oil dissolved gas respectively, obtains the value of warning that in N number of transformer described in current time, one or more oil dissolved gas content is corresponding respectively.
Wherein, before described step a, described method also comprises:
By chromatography online monitoring system for transformer oil, obtain the first data that described N number of transformer is corresponding respectively, and by transformer temperature monitoring system, obtain the second data that described N number of transformer is corresponding respectively.
Wherein, described first data comprise the gas content of each oil dissolved gas in described N number of transformer and gas production rate corresponding to each oil dissolved gas described; Described second data comprise the accumulated value that oil temperature in described N number of transformer and each oil temperature associated with the duration.
Wherein, described statistical distribution pattern is by carrying out normal distribution matching acquisition to the gas content of current gas; Described relation analysis model is by carrying out linear regression fit acquisition to the gas content of described current gas and the oil temperature of described current gas place transformer.
The embodiment of the present invention additionally provides and a kind ofly to detect in transformer each gas content in oil and to warn the system of value, and it realizes on the N number of transformer including M oil dissolved gas, and described system comprises:
Data extracting unit, calculates for extracting in described N number of transformer value of all warning with a described M oil dissolved gas data be associated; Wherein, described data comprise the first data be associated with a described M oil dissolved gas in each transformer, and the second data be associated with oil temperature in each transformer; M, N are positive integer;
Model training and determining unit, for the data extracted described in basis, train each oil dissolved gas content in N number of transformer and to warn the current computation model of value correspondence respectively; Wherein, described computation model comprises the statistical distribution pattern trained according to described first data and the relation analysis model jointly trained according to described first data and described second data;
Value of warning acquiring unit, after all having trained for the current computation model of value of warning until described M oil dissolved gas content in described N number of transformer, the current computation model of value of warning according to each oil dissolved gas content in the described N number of transformer trained, obtains the value of warning that in N number of transformer described in current time, described M oil dissolved gas content is corresponding respectively.
Wherein, described model training and determining unit comprise:
Model training module, for 1 to M in described N number of transformer oil dissolved gas is all trained corresponding statistical distribution pattern according to described first data, obtain M*N statistical distribution pattern, and all jointly train corresponding relation analysis model according to described first data and described second data, obtain M*N relation analysis model;
Degree of fitting computing module, for the degree of fitting of the degree of fitting and a described M*N relation analysis model that calculate a described M*N statistical distribution pattern;
Comparison module, for the degree of fitting of M*N statistical distribution pattern that calculates described in basis and the degree of fitting of M*N relation analysis model, the size cases of the degree of fitting of the relation analysis model that the degree of fitting detecting the statistical distribution pattern that same oil dissolved gas obtains in same transformer successively in 1 to N number of transformer obtains with it;
First model determination module, for when detecting that the degree of fitting of the statistical distribution pattern that one or more oil dissolved gas obtains in described N number of transformer is all less than the degree of fitting of the relation analysis model that it obtains, then in the N number of transformer detected described in determining, the warn current computation model of value of one or more oil dissolved gas content is relation analysis model;
Second model determination module, for when detecting that the degree of fitting of the statistical distribution pattern that one or more oil dissolved gas obtains in described N number of transformer is all greater than the degree of fitting of the relation analysis model that it obtains, then in the N number of transformer detected described in determining, the warn current computation model of value of one or more oil dissolved gas content is statistical distribution pattern.
Wherein, described system also comprises:
Preset unit, for by chromatography online monitoring system for transformer oil, obtain the first data that described N number of transformer is corresponding respectively, and by transformer temperature monitoring system, obtain the second data that described N number of transformer is corresponding respectively.
Wherein, described first data comprise the gas content of each oil dissolved gas in described N number of transformer and gas production rate corresponding to each oil dissolved gas described; Described second data comprise the accumulated value that oil temperature in described N number of transformer and each oil temperature associated with the duration.
Implement the embodiment of the present invention, there is following beneficial effect:
In embodiments of the present invention, due to the oil chromatography data (gas production rate that gas content and each oil dissolved gas as extracted each each oil dissolved gas of transformer are corresponding) by extracting each transformer on oil chromatography on-line monitoring, and consider the factors such as each transformer load and weather (as the accumulated value that the oil temperature in each transformer that extraction transformer temperature monitoring system gathers and each oil temperature associated with the duration), train the computation model of degree of fitting the best, and according to this optimal computed model, obtain the value of warning that in each transformer of current time, each oil dissolved gas content is corresponding respectively, effectively can improve accuracy and reliability that transformer oil chromatographic on-line monitoring warns, avoid the wasting of resources, reduce equipment Risk.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, the present invention is described in further detail.
Inventor finds, when the paper oil insulation material of inside transformer normally runs, and meeting aging Sum decomposition gradually under heat and electric effect, thus produce a small amount of H
2, low molecular hydrocarbon gas, CO, CO
2deng gas, and equally when heat and electric fault, the paper oil insulation material of inside transformer also can produce above-mentioned gas, the source of above-mentioned gas cannot be distinguished technically, the numerical value of its correspondence does not have strict boundary yet, and the source of above-mentioned gas and the load of transformer and temperature, O in oil
2many variable factors such as content and liquid water content, oily protection system and the circulation system are relevant.
Because the factor such as load and temperature of transformer is always in time in continuous change, therefore the oil dissolved gas content of transformer is warned value also corresponding time to time change, but the relation of the factor such as load, temperature of oil dissolved gas content and transformer in the industry cycle not yet has unified qualitative understanding at present, actual production run cannot be instructed by quantitative model.
Therefore, inventor's knowledge based finds principle, proposes a kind ofly to detect in transformer each gas content in oil and to warn the method for value, in order to determine that the time dependent oil dissolved gas content of each transformer is warned value.As shown in Figure 2, what provide for the present inventor a kind ofly to detect in transformer each gas content in oil and to warn the method for value, and it realizes on the N number of transformer including M oil dissolved gas, and described method comprises:
Step S101, extract in described N number of transformer value of all warning with a described M oil dissolved gas and calculate the data be associated; Wherein, described data comprise the first data be associated with a described M oil dissolved gas in each transformer, and the second data be associated with oil temperature in each transformer; M, N are positive integer;
Detailed process is, before step S101, described method also comprises: by chromatography online monitoring system for transformer oil, obtains the first data that N number of transformer is corresponding respectively, and by transformer temperature monitoring system, obtain the second data that N number of transformer is corresponding respectively.
In the embodiment of the present invention, in order to can in the acquisition transformer of precision in oil each gas content to warn value, in the process of analytical algorithm, namely the data extracted consider the oil chromatography data (the first data as being associated with M oil dissolved gas in each transformer) of each transformer on oil chromatography on-line monitoring, have also contemplated that the factors such as each transformer load and weather and the oil temperature delta data (the second data as being associated with oil temperature in each transformer) that produces.Wherein, first data comprise the data directly got from chromatography online monitoring system for transformer oil, as the gas content data etc. of hydrogen, acetylene, total hydrocarbon, and to the data that oil chromatography online monitoring data is processed, as the gas production rate etc. of hydrogen, acetylene, total hydrocarbon, therefore the first data are defined as the data of the gas content that comprises each oil dissolved gas in N number of transformer and gas production rate corresponding to each oil dissolved gas etc.; Second data comprise the temperature of oil in transformer directly obtained from transformer temperature monitoring system and the data of processing temperature of oil in transformer, as oil temperature and the accumulated value etc. of duration, therefore the second data are defined as the data comprising accumulated value that oil temperature in N number of transformer and each oil temperature associate with the duration etc.
It should be noted that the data such as oil chromatography data and oil temperature of acquisition, all for the data-interface by having set up with all kinds of on-line monitoring system and the online monitoring data got.
Step S102, according to described in the data extracted, train each oil dissolved gas content in N number of transformer and to warn the current computation model of value correspondence respectively; Wherein, described computation model comprises the statistical distribution pattern trained according to described first data and the relation analysis model jointly trained according to described first data and described second data;
Detailed process is, 1 to M in N number of transformer oil dissolved gas is all trained corresponding statistical distribution pattern according to the first data, obtain M*N statistical distribution pattern, and all jointly train corresponding relation analysis model according to the first data and the second data, obtain M*N relation analysis model;
Calculate the degree of fitting of M*N statistical distribution pattern and the degree of fitting of M*N relation analysis model;
According to the degree of fitting of M*N the statistical distribution pattern calculated and the degree of fitting of M*N relation analysis model, the size cases of the degree of fitting of the relation analysis model that the degree of fitting detecting the statistical distribution pattern that same oil dissolved gas obtains in same transformer successively in 1 to N number of transformer obtains with it;
When detecting that the degree of fitting of the statistical distribution pattern that one or more oil dissolved gas obtains in N number of transformer is all less than the degree of fitting of the relation analysis model that it obtains, then determine that the warn current computation model of value of one or more oil dissolved gas content in N number of transformer of detecting is relation analysis model; Wherein, relation analysis model is by carrying out linear regression fit acquisition to the gas content of described current gas and the oil temperature of described current gas place transformer;
When detecting that the degree of fitting of the statistical distribution pattern that one or more oil dissolved gas obtains in N number of transformer is all greater than the degree of fitting of the relation analysis model that it obtains, then determine that the warn current computation model of value of one or more oil dissolved gas content in N number of transformer of detecting is statistical distribution pattern; Wherein, statistical distribution pattern is by carrying out normal distribution matching acquisition to the gas content of current gas.
As an example, the application scenarios of step S102 is further illustrated:
(1) start to train the warn computation model of value of a jth oil dissolved gas (as total hydrocarbon) of i-th transformer;
(2) corresponding statistical distribution pattern is trained, as carried out normal distribution matching to the gas content data of total hydrocarbon according to the first data; Corresponding relation analysis model is jointly trained, as carried out linear regression fit to total hydrocarbon content and oil temperature data according to the first data and the second data;
(3) calculate the degree of fitting of statistical distribution pattern corresponding to a jth oil dissolved gas and the relation analysis model degree of fitting of correspondence thereof respectively, select the good model of degree of fitting as optimization model;
(4) when the degree of fitting of statistical distribution pattern corresponding to a jth oil dissolved gas is greater than and the relation analysis model degree of fitting of correspondence time, the warn computation model of value of the jth oil dissolved gas of this i-th transformer is the statistical distribution pattern that a jth oil dissolved gas is corresponding;
(5) when the degree of fitting of statistical distribution pattern corresponding to a jth oil dissolved gas is less than and the relation analysis model degree of fitting of correspondence time, the warn computation model of value of the jth oil dissolved gas of this i-th transformer is the relation analysis model model that a jth oil dissolved gas is corresponding.
Step S103, warn after the current computation model of value all trained until described M oil dissolved gas content in described N number of transformer, and the current computation model of value of warning according to each oil dissolved gas content in the described N number of transformer trained, obtain the value of warning that in N number of transformer described in current time, described M oil dissolved gas content is corresponding respectively.
Detailed process is, after all computation models have been trained, when oil dissolved gas content one or more in the N number of transformer trained warn the current computation model of value be statistical distribution pattern time, obtain by three-sigma principle the value of warning that in the N number of transformer of current time, one or more oil dissolved gas content is corresponding respectively;
When oil dissolved gas content one or more in the N number of transformer trained warn the current computation model of value be relation analysis model time, the oil temperature threshold value preset by each transformer substitutes in relation analysis model corresponding to one or more oil dissolved gas respectively, obtains the value of warning that in the N number of transformer of current time, one or more oil dissolved gas content is corresponding respectively.
It should be noted that the oil temperature threshold value that the relation analysis model of current one or more oil dissolved gas substitutes into is corresponding with default oil temperature threshold value in its place transformer.
As shown in Figure 3, the embodiment of the present invention additionally provides and a kind ofly to detect in transformer each gas content in oil and to warn the system of value, and it realizes on the N number of transformer including M oil dissolved gas, and described system comprises:
Data extracting unit 110, calculates for extracting in described N number of transformer value of all warning with a described M oil dissolved gas data be associated; Wherein, described data comprise the first data be associated with a described M oil dissolved gas in each transformer, and the second data be associated with oil temperature in each transformer; M, N are positive integer;
Model training and determining unit 120, for the data extracted described in basis, train each oil dissolved gas content in N number of transformer and to warn the current computation model of value correspondence respectively; Wherein, described computation model comprises the statistical distribution pattern trained according to described first data and the relation analysis model jointly trained according to described first data and described second data;
Value of warning acquiring unit 130, after all having trained for the current computation model of value of warning until described M oil dissolved gas content in described N number of transformer, the current computation model of value of warning according to each oil dissolved gas content in the described N number of transformer trained, obtains the value of warning that in N number of transformer described in current time, described M oil dissolved gas content is corresponding respectively.
Wherein, described model training and determining unit 120 comprise:
Model training module 1201, for 1 to M in described N number of transformer oil dissolved gas is all trained corresponding statistical distribution pattern according to described first data, obtain M*N statistical distribution pattern, and all jointly train corresponding relation analysis model according to described first data and described second data, obtain M*N relation analysis model;
Degree of fitting computing module 1202, for the degree of fitting of the degree of fitting and a described M*N relation analysis model that calculate a described M*N statistical distribution pattern;
Comparison module 1203, for the degree of fitting of M*N statistical distribution pattern that calculates described in basis and the degree of fitting of M*N relation analysis model, the size cases of the degree of fitting of the relation analysis model that the degree of fitting detecting the statistical distribution pattern that same oil dissolved gas obtains in same transformer successively in 1 to N number of transformer obtains with it;
First model determination module 1204, for when detecting that the degree of fitting of the statistical distribution pattern that one or more oil dissolved gas obtains in described N number of transformer is all less than the degree of fitting of the relation analysis model that it obtains, then in the N number of transformer detected described in determining, the warn current computation model of value of one or more oil dissolved gas content is relation analysis model;
Second model determination module 1205, for when detecting that the degree of fitting of the statistical distribution pattern that one or more oil dissolved gas obtains in described N number of transformer is all greater than the degree of fitting of the relation analysis model that it obtains, then in the N number of transformer detected described in determining, the warn current computation model of value of one or more oil dissolved gas content is statistical distribution pattern.
Wherein, described system also comprises:
Preset unit 140, for by chromatography online monitoring system for transformer oil, obtain the first data that described N number of transformer is corresponding respectively, and by transformer temperature monitoring system, obtain the second data that described N number of transformer is corresponding respectively.
Wherein, described first data comprise the gas content of each oil dissolved gas in described N number of transformer and gas production rate corresponding to each oil dissolved gas described; Described second data comprise the accumulated value that oil temperature in described N number of transformer and each oil temperature associated with the duration.
Implement the embodiment of the present invention, there is following beneficial effect:
In embodiments of the present invention, due to the oil chromatography data (gas production rate that gas content and each oil dissolved gas as extracted each each oil dissolved gas of transformer are corresponding) by extracting each transformer on oil chromatography on-line monitoring, and consider the factors such as each transformer load and weather (as the accumulated value that the oil temperature in each transformer that extraction transformer temperature monitoring system gathers and each oil temperature associated with the duration), train the computation model of degree of fitting the best, and according to this optimal computed model, obtain the value of warning that in each transformer of current time, each oil dissolved gas content is corresponding respectively, effectively can improve accuracy and reliability that transformer oil chromatographic on-line monitoring warns, avoid the wasting of resources, reduce equipment Risk.
It should be noted that in said system embodiment, each included system unit is carry out dividing according to function logic, but is not limited to above-mentioned division, as long as can realize corresponding function; In addition, the concrete title of each functional unit, also just for the ease of mutual differentiation, is not limited to protection scope of the present invention.
One of ordinary skill in the art will appreciate that all or part of step realized in above-described embodiment method is that the hardware that can carry out instruction relevant by program has come, described program can be stored in a computer read/write memory medium, described storage medium, as ROM/RAM, disk, CD etc.
Above disclosedly be only a kind of preferred embodiment of the present invention, certainly can not limit the interest field of the present invention with this, therefore according to the equivalent variations that the claims in the present invention are done, still belong to the scope that the present invention is contained.