A monitoring and protection method for diesel generator access

Abstract

The present invention provides a monitoring and protection method for diesel generator access, comprising the following steps: collecting basic data of the diesel generator in operation, establishing a first evaluation index, conducting a subjective and objective evaluation on the first evaluation index, and obtaining a comprehensive weight of the first evaluation index; collecting basic data of multiple loads in operation, establishing a second evaluation index, conducting a subjective and objective evaluation on the second evaluation index, and obtaining a comprehensive weight of the second evaluation index; constructing a first neural evaluation network, evaluating the overall power quality of a power supply branch network connected to the diesel generator based on the second evaluation index, and outputting a first adjustment parameter; establishing a second neural evaluation network, evaluating the power quality of the diesel generator based on the first evaluation index, and outputting a second adjustment parameter based on the evaluation result.

Description

Technical Field

[0001] The invention relates to the technical field of generator protection, and in particular to a monitoring and protection method for accessing a diesel generator. Background Art

[0002] Diesel generators have the advantages of large torque and good economic performance. They are currently often used in emergency response of power systems. Their diesel generators usually need to drive multiple loads. Therefore, the diesel generators need to be precisely controlled based on feedback to meet the load requirements. However, the current control of diesel generators is relatively simple, and the relationship between the optimal power quality output by the diesel generator and the power quality required by the load is not considered. Summary of the invention

[0003] The object of the present invention is to provide a monitoring and protection method for diesel generator access to solve the problems raised in the above background technology.

[0004] The present invention is implemented by the following technical solutions: In a first aspect, the present invention provides a monitoring and protection method for diesel generator access, comprising the following steps:

[0005] Collecting basic data of the diesel generator in operation, establishing a first evaluation index, conducting a subjective and objective evaluation on the first evaluation index, and obtaining a comprehensive weight of the first evaluation index;

[0006] Collecting basic data of multiple loads during operation, establishing a second evaluation index, conducting a subjective and objective evaluation on the second evaluation index, and obtaining a comprehensive weight of the second evaluation index;

[0007] Constructing a first neural evaluation network, evaluating the overall power quality of the power supply branch network connected to the diesel generator based on the second evaluation index, and outputting a first adjustment parameter;

[0008] Establishing a second neural evaluation network, evaluating the power quality of the diesel generator based on the first evaluation index, and outputting a second adjustment parameter based on the evaluation result;

[0009] A third neural evaluation network is established to obtain the optimal adjustment parameters of the diesel generator based on the first adjustment parameters and the second adjustment parameters.

[0010] Optionally, basic data of the diesel generator during operation is collected, specifically including: collecting the current signal output by the diesel generator, and obtaining two-dimensional orthogonal components, frequency shift information, stroboscopic information, total harmonic distortion information and phase imbalance information based on the current signal.

[0011] Optionally, the first evaluation index includes two-dimensional orthogonal components, frequency shift, stroboscopic condition, total harmonic distortion, and phase balance condition.

[0012] Optionally, the second evaluation index includes the continuous working time of a single load, the rated power of the load, the actual power of the load, the voltage deviation of the load, the frequency deviation of the load, the voltage fluctuation, and the voltage flicker.

[0013] Optionally, the first evaluation index and the second evaluation index are evaluated subjectively and objectively respectively, specifically including: using the hierarchical analysis method to determine the subjective weight of the first evaluation index or the second evaluation index respectively, using the grey correlation analysis method to determine the objective weight of the first evaluation index or the second evaluation index respectively, and calculating the comprehensive weight value of the first evaluation index or the second evaluation index respectively by the following formula: G=α*W1+β*W2, where α is the relative importance of the hierarchical analysis method, β is the relative importance of the grey correlation analysis method, W1 is the weight determined by the grey correlation analysis method, and W2 is the weight determined by the hierarchical analysis method.

[0014] Optionally, the first neural evaluation network includes a main evaluation network and a sub-evaluation network, the main evaluation network and the sub-evaluation network are both composed of an input layer, a hidden layer and an output layer, the input layer of the sub-evaluation network is the second evaluation index of a single load, the result of its output layer is the status of a single load, and the comprehensive weight of the second evaluation index is used as the initial weight of the sub-evaluation network;

[0015] The input layer of the main evaluation network is the status of multiple loads, and the output layer is the first adjustment parameter of the generator.

[0016] Optionally, the input layer of the second neural evaluation network is the parameter value of the first evaluation index, and the result of its output layer is the second adjustment parameter of the generator, and the comprehensive weight of the first evaluation index is used as the initial weight of the second neural evaluation network.

[0017] A monitoring and protection device for diesel generator access, the device comprising:

[0018] A first acquisition module is used to collect basic data of the diesel generator in operation, and classify and normalize the basic data according to a first evaluation index;

[0019] A second collection module is used to collect basic data of multiple loads during operation, and classify and normalize the basic data according to a second evaluation index;

[0020] A first deep learning module, comprising a first neural evaluation network, evaluates the overall power quality of the power supply branch network connected to the diesel generator based on a second evaluation index, and outputs a first adjustment parameter;

[0021] A second deep learning module includes a second neural evaluation network, which evaluates the power quality of the diesel generator based on the first evaluation index and outputs a second adjustment parameter based on the evaluation result;

[0022] The third deep learning module includes a third neural evaluation network, which obtains the optimal adjustment parameters of the diesel generator based on the first adjustment parameters and the second adjustment parameters.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The present invention provides a monitoring and protection method for diesel generator access. By executing the first adjustment parameter on the generator, the optimal overall power quality of the power supply network can be obtained. The second adjustment parameter can make the generator output the optimal power quality. When both the power quality of the generator and the overall power quality of the power supply network are suitable, a third neural evaluation network is established, and the first adjustment parameter and the second adjustment parameter are used as input to obtain the optimal adjustment parameter. Under the optimal adjustment parameter, the power quality of the generator and the overall power quality of the power supply network are in a better state. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only preferred embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A flow chart of a monitoring and protection method for diesel generator access provided by the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical scheme and advantages of the present invention more obvious, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present invention.

[0028] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0029] It should be understood that the present invention can be implemented in different forms and should not be interpreted as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make the disclosure thorough and complete and to fully convey the scope of the present invention to those skilled in the art.

[0030] The purpose of the terms used herein is only to describe specific embodiments and is not intended to be limiting of the present invention. When used herein, the singular forms "one", "an" and "said / the" are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "consisting of" and / or "comprising", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0031] In order to fully understand the present invention, a detailed structure will be proposed in the following description to illustrate the technical solution proposed by the present invention. The optional embodiments of the present invention are described in detail as follows, but in addition to these detailed descriptions, the present invention may also have other implementations.

[0032] See also Figure 1 , a monitoring and protection method for diesel generator access, comprising the following steps:

[0033] S1. Collect basic data of the diesel generator in operation, establish a first evaluation index, conduct subjective and objective evaluation on the first evaluation index, and obtain a comprehensive weight of the first evaluation index;

[0034] Collecting basic data of the diesel generator in operation specifically includes: collecting the current signal output by the diesel generator, and obtaining two-dimensional orthogonal components, frequency shift information, stroboscopic information, total harmonic distortion information and phase imbalance information based on the current signal, and establishing a first evaluation index according to the above-mentioned decomposed data, that is, the first evaluation index includes two-dimensional orthogonal components, frequency shift, stroboscopic information, total harmonic distortion, phase balance, and normalizing the above data.

[0035] S2. Collect basic data of multiple loads during operation and establish a second evaluation index, where the second evaluation index includes the continuous working time of a single load, the rated power of the load, the actual power of the load, the voltage deviation of the load, the frequency deviation of the load, the voltage fluctuation, and the voltage flicker. Perform a subjective and objective evaluation on the second evaluation index and obtain a comprehensive weight of the second evaluation index.

[0036] Further: the first evaluation index and the second evaluation index are evaluated subjectively and objectively respectively, specifically including: using the hierarchical analysis method to determine the subjective weight of the first evaluation index or the second evaluation index respectively, using the grey correlation analysis method to determine the objective weight of the first evaluation index or the second evaluation index respectively, and calculating the comprehensive weight value of the first evaluation index or the second evaluation index respectively by the following formula: G=α*W1+β*W2, wherein α is the relative importance of the hierarchical analysis method, β is the relative importance of the grey correlation analysis method, W1 is the weight determined by the grey correlation analysis method, and W2 is the weight determined by the hierarchical analysis method.

[0037] The method of using the hierarchical analysis method to determine the subjective weight of the first evaluation index or the second evaluation index includes: establishing the following evaluation matrix based on the first evaluation index or the second evaluation index:

[0038]

[0039] Where, X ij Indicates the jth value corresponding to the i-th indicator;

[0040] Normalize the evaluation matrix to obtain the following normalized matrix R:

[0041]

[0042] The optimal solution r can be obtained by the normalized decision matrix R *j =maxR ij , the virtual ideal solution R *j =[r *1 ,r *2 ,r *3 ,…,r *n ], where R ij is the corresponding element in the normalized decision matrix R;

[0043] Methods for respectively determining the objective weight of the first evaluation index or the second evaluation index by using the grey correlation analysis method include:

[0044] The grey correlation coefficient ε between the jth value of the ith index and the virtual ideal solution is calculated as:

[0045]

[0046] Based on the grey correlation coefficient ε ij , construct the following grey judgment matrix:

[0047]

[0048] The weight w of the jth value of the ith indicator in the entire indicator is calculated by the following formula:

[0049]

[0050] The objective weight of the evaluation index is calculated by the following formula:

[0051] S3, constructing a first neural evaluation network, evaluating the overall power quality of the power supply branch network connected to the diesel generator based on the second evaluation index, and outputting a first adjustment parameter;

[0052] The first neural evaluation network includes a main evaluation network and a sub-evaluation network, both of which are composed of an input layer, a hidden layer, and an output layer. The input layer of the sub-evaluation network is the second evaluation index of a single load, and the result of its output layer is the status of a single load. The comprehensive weight of the second evaluation index is used as the initial weight of the sub-evaluation network.

[0053] The input layer of the main evaluation network is the status of multiple loads, and the output layer is the first adjustment parameter of the generator.

[0054] S4. Establish a second neural evaluation network, evaluate the power quality of the diesel generator based on the first evaluation index, and output a second adjustment parameter based on the evaluation result. The input layer of the second neural evaluation network is the parameter value of the first evaluation index, and the result of its output layer is the second adjustment parameter of the generator. The comprehensive weight of the first evaluation index is used as the initial weight of the second neural evaluation network.

[0055] S5. Establish a third neural evaluation network, and obtain the optimal adjustment parameters of the diesel generator based on the first adjustment parameters and the second adjustment parameters.

[0056] By executing the first adjustment parameter on the generator, the optimal overall power quality of the power supply network can be obtained. However, the above-mentioned first adjustment parameter may exceed the operating parameters of the generator itself. Therefore, it is necessary to establish a second neural evaluation network to evaluate the power quality output by the diesel generator based on the first evaluation index, and output the second adjustment parameter based on the evaluation result. The second adjustment parameter can make the generator output the optimal power quality. When both the power quality of the generator and the overall power quality of the power supply network are suitable, by establishing a third neural evaluation network, the first adjustment parameter and the second adjustment parameter are used as input to obtain the optimal adjustment parameter. Under the optimal adjustment parameter, the power quality of the generator and the overall power quality of the power supply network are suitable.

[0057] The second embodiment of the present invention discloses a monitoring and protection device for diesel generator access, the device comprising:

[0058] A first acquisition module is used to collect basic data of the diesel generator in operation, and classify and normalize the basic data according to a first evaluation index;

[0059] A second collection module is used to collect basic data of multiple loads during operation, and classify and normalize the basic data according to a second evaluation index;

[0060] A first deep learning module, comprising a first neural evaluation network, evaluates the overall power quality of the power supply branch network connected to the diesel generator based on a second evaluation index, and outputs a first adjustment parameter;

[0061] A second deep learning module includes a second neural evaluation network, which evaluates the power quality of the diesel generator based on the first evaluation index and outputs a second adjustment parameter based on the evaluation result;

[0062] The third deep learning module includes a third neural evaluation network, which obtains the optimal adjustment parameters of the diesel generator based on the first adjustment parameters and the second adjustment parameters.

[0063] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A monitoring and protection method for diesel generator access, characterized in that: The following steps are involved: Collecting basic data of the diesel generator in operation, establishing a first evaluation index, conducting a subjective and objective evaluation on the first evaluation index, and obtaining a comprehensive weight of the first evaluation index; Collecting basic data of multiple loads during operation, establishing a second evaluation index, conducting a subjective and objective evaluation on the second evaluation index, and obtaining a comprehensive weight of the second evaluation index; Constructing a first neural evaluation network, evaluating the overall power quality of the power supply branch network connected to the diesel generator based on the second evaluation index, and outputting a first adjustment parameter; Establishing a second neural evaluation network, evaluating the power quality of the diesel generator based on the first evaluation index, and outputting a second adjustment parameter based on the evaluation result; Establishing a third neural evaluation network to obtain the optimal adjustment parameters of the diesel generator based on the first adjustment parameters and the second adjustment parameters; The first evaluation index includes two-dimensional orthogonal components, frequency shift, stroboscopic condition, total harmonic distortion, and phase balance; The second evaluation index includes the continuous working time of a single load, the rated power of the load, the actual power of the load, the voltage deviation of the load, the frequency deviation of the load, the voltage fluctuation, and the voltage flicker; The first neural evaluation network includes a main evaluation network and a sub-evaluation network, both of which are composed of an input layer, a hidden layer, and an output layer. The input layer of the sub-evaluation network is the second evaluation index of a single load, and the result of its output layer is the status of a single load. The comprehensive weight of the second evaluation index is used as the initial weight of the sub-evaluation network. The input layer of the main evaluation network is the status of multiple loads, and the output layer is the first adjustment parameter of the generator; The input layer of the second neural evaluation network is the parameter value of the first evaluation index, and the result of its output layer is the second adjustment parameter of the generator. The comprehensive weight of the first evaluation index is used as the initial weight of the second neural evaluation network.

2. A monitoring and protection method for diesel generator access according to claim 1, characterized in that: Collecting basic data of the diesel generator in operation specifically includes: collecting the current signal output by the diesel generator, and obtaining two-dimensional orthogonal components, frequency shift information, stroboscopic information, total harmonic distortion information and phase imbalance information based on the current signal.

3. A monitoring and protection method for diesel generator access according to claim 2, characterized in that: The first evaluation index and the second evaluation index are evaluated subjectively and objectively respectively, specifically including: using the hierarchical analysis method to determine the subjective weight of the first evaluation index or the second evaluation index respectively, using the grey correlation analysis method to determine the objective weight of the first evaluation index or the second evaluation index respectively, and calculating the comprehensive weight value of the first evaluation index or the second evaluation index respectively by the following formula: G=α*W1+β*W2, wherein α is the relative importance of the hierarchical analysis method, β is the relative importance of the grey correlation analysis method, W1 is the weight determined by the grey correlation analysis method, and W2 is the weight determined by the hierarchical analysis method.

4. A monitoring and protection device for diesel generator access, used to execute the monitoring and protection method according to any one of claims 1 to 3, characterized in that: The device comprises: A first acquisition module is used to collect basic data of the diesel generator in operation, and classify and normalize the basic data according to a first evaluation index; A second collection module is used to collect basic data of multiple loads during operation, and classify and normalize the basic data according to a second evaluation index; A first deep learning module, comprising a first neural evaluation network, evaluates the overall power quality of the power supply branch network connected to the diesel generator based on a second evaluation index, and outputs a first adjustment parameter; A second deep learning module includes a second neural evaluation network, which evaluates the power quality of the diesel generator based on the first evaluation index and outputs a second adjustment parameter based on the evaluation result; The third deep learning module includes a third neural evaluation network, which obtains the optimal adjustment parameters of the diesel generator based on the first adjustment parameters and the second adjustment parameters.

Images