A method for identifying the attribute of an impact load on a distribution outgoing line side

Abstract

The application discloses a kind of method and system for identifying the attribute of impact load on distribution transformer outlet side, comprising: obtaining the instantaneous power signal and average power signal of the equipment under each time node in the preset time period when impact load occurs;Multiple load attributes that can constitute the instantaneous power signal of the corresponding time node under each time node are generated;According to the average power under each time node, the occurrence probability of each of the multiple load attributes is evaluated;According to the occurrence probability, the optimal solution of the load attribute is determined, which is output as the load attribute of the equipment.The application is a non-intrusive, high-precision method that can be installed on the distribution transformer outlet side, and is suitable for impact load behavior.

Description

Technical Field

[0001] This invention relates to the field of load attribute identification technology, and specifically to a method for identifying the impact load attributes on the outgoing line side of a distribution transformer. Background Technology

[0002] Traditional equipment load status identification requires equipping each target device with an intrusive load identification device, which then characterizes and identifies load attributes by collecting power signals. This traditional monitoring method suffers from high equipment deployment costs, the need for relocation when the size of the target equipment changes, and poor data integrity and accuracy. Therefore, a non-intrusive, highly accurate identification algorithm suitable for impact load behavior, which can be installed on the outgoing line side of the distribution transformer, is needed. Summary of the Invention

[0003] The purpose of this invention is to propose a method for identifying the impact load attributes on the outgoing line side of a distribution transformer. This method is a non-invasive, highly accurate method that can be installed on the outgoing line side of the distribution transformer and is applicable to impact load behavior.

[0004] To achieve the above objectives, this invention proposes a method for identifying the impact load attributes on the outgoing line side of a distribution transformer, comprising:

[0005] Acquire the instantaneous power signal and average power signal of the equipment subjected to impact load at various time points within a preset time period;

[0006] Generate multiple load attributes that may constitute the instantaneous power signal at each time node;

[0007] The probability of occurrence of each of the multiple load attributes is assessed based on the average power at each time point.

[0008] The optimal solution for the load attribute is determined based on the occurrence probability, and its output is used as the load attribute of the equipment.

[0009] Preferably, the multiple load attributes that may constitute the instantaneous power signal at each time node include:

[0010] By performing a traversal solution, multiple load attributes that may constitute the instantaneous power signal at each time node are obtained.

[0011] Preferably, determining the occurrence probability of each of the plurality of load attributes based on the average power includes:

[0012] The multiple load attributes are processed by a pre-trained neural network model with the average power input to determine the probability of occurrence of each of the multiple load attributes.

[0013] Preferably, determining the optimal solution for the load attribute based on the occurrence probability and outputting it as the load attribute of the equipment includes:

[0014] The load attribute with the highest probability of occurrence is selected as the optimal solution.

[0015] This invention also proposes a system for identifying the impact load attributes of the outgoing line side of a distribution transformer, comprising:

[0016] The power acquisition module is used to acquire the instantaneous power signal and average power signal of the equipment subjected to impact load at various time points within a preset time period;

[0017] The load attribute generation module is used to generate multiple load attributes that may constitute the instantaneous power signal at each time node.

[0018] The probability prediction module is used to assess the probability of occurrence of each of the multiple load attributes based on the average power at each time point.

[0019] The output module is used to determine the optimal solution of the load attribute based on the occurrence probability and output it as the load attribute of the equipment.

[0020] Preferably, the load attribute generation module is specifically used for:

[0021] By performing a traversal solution, multiple load attributes that may constitute the instantaneous power signal at each time node are obtained.

[0022] Preferably, the probability prediction module is specifically used for:

[0023] The multiple load attributes are processed by a pre-trained neural network model with the average power input to determine the probability of occurrence of each of the multiple load attributes.

[0024] Preferably, the output module is specifically used for:

[0025] The load attribute with the highest probability of occurrence is selected as the optimal solution.

[0026] Compared with the prior art, the present invention has at least the following advantages:

[0027] Its equipment deployment cost is low. When the scale of the target equipment changes, there is no need to rearrange it. It only needs to continue to acquire the instantaneous power signal and average power signal of the equipment at each time node within the preset time period to identify and generate load attributes. It has universal applicability and does not have problems such as poor data integrity and accuracy. It can be installed on the outgoing line side of the distribution transformer. It has the characteristics of non-intrusion and high accuracy and is suitable for the identification of impact load behavior.

[0028] Other features and advantages of the present invention will be set forth in the following description. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of a method for identifying the impact load attributes of a distribution transformer outgoing line in an embodiment of the present invention.

[0031] Figure 2 This is a schematic diagram of a distribution transformer outgoing line side impact load attribute identification system in an embodiment of the present invention. Detailed Implementation

[0032] The various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. Furthermore, numerous specific details are set forth in the following detailed embodiments to better illustrate the invention. Those skilled in the art will understand that the invention can be practiced without certain specific details. In some instances, means well known to those skilled in the art have not been described in detail in order to highlight the spirit of the invention.

[0033] See Figure 1 This invention proposes a method for identifying the impact load attributes on the outgoing line side of a distribution transformer. The method includes:

[0034] Step S1: Obtain the instantaneous power signal and average power signal of the equipment subjected to impact load at each time node within a preset time period;

[0035] Step S2: Generate multiple load attributes that may constitute the instantaneous power signal at each time node;

[0036] Specifically, the load attribute in the steps refers to the power curve of the equipment;

[0037] Step S3: Evaluate the occurrence probability of each of the multiple load attributes based on the average power at each time point;

[0038] Step S4: Determine the optimal solution for the load attribute based on the occurrence probability, and output it as the load attribute of the equipment.

[0039] Specifically, impact loads are either periodic or non-periodic, characterized by sudden and significant changes, such as electric arc furnaces and rolling mills. While the duration of maximum load is generally short, its peak value can be several or even tens of times higher than the average load. These loads have a significant impact on the power system; when their amplitude of change is large relative to the system capacity, they can potentially cause continuous oscillations in the system frequency and voltage fluctuations. Typically, impact loads require specialized research and the development of corresponding countermeasures to meet the requirements of power system safety, stability, and power quality. The method in this embodiment primarily aims to study the load attributes of equipment experiencing impact loads in order to propose appropriate countermeasures for this type of equipment, thereby meeting the requirements of power system safety, stability, and power quality.

[0040] In implementation, this invention periodically receives the instantaneous and average power of the equipment at various time points and performs corresponding identification. Only one identification device is needed to receive the instantaneous and average power of multiple target devices and perform calculations and identifications. The device deployment cost is low. When the scale of the target devices changes, there is no need to redeploy. It is only necessary to continue to acquire the instantaneous and average power signals of the devices at various time points within a preset time period for identification and load attribute generation. It has universal applicability and does not have problems such as poor data integrity and accuracy. It can be installed on the outgoing line side of the distribution transformer and has the characteristics of non-intrusiveness and high accuracy, making it suitable for the identification of impact load behavior.

[0041] Preferably, step S2 includes:

[0042] By performing a traversal solution, multiple load attributes that may constitute the instantaneous power signal at each time node are obtained.

[0043] Specifically, in this embodiment, the load attribute refers to the power curve of the equipment. In the layout, the power of each time node in the power curve is determined based on the instantaneous power signal at each time node, and then the possible power curves are solved by traversing based on the power of each time node.

[0044] Preferably, step S3 includes:

[0045] The multiple load attributes are processed by a pre-trained neural network model with the average power input to determine the probability of occurrence of each of the multiple load attributes.

[0046] Specifically, average power differs from instantaneous power. Average power is related to the final power curve, meaning they should match. The main step is to solve for the degree of matching between the two. The higher the degree of matching, the higher the probability.

[0047] Preferably, step S4 includes:

[0048] The load attribute with the highest probability of occurrence is selected as the optimal solution.

[0049] See Figure 2 This invention also proposes a distribution transformer outgoing line side impact load attribute identification system, including:

[0050] The power acquisition module is used to acquire the instantaneous power signal and average power signal of the equipment subjected to impact load at various time points within a preset time period;

[0051] The load attribute generation module is used to generate multiple load attributes that may constitute the instantaneous power signal at each time node.

[0052] The probability prediction module is used to assess the probability of occurrence of each of the multiple load attributes based on the average power at each time point.

[0053] The output module is used to determine the optimal solution of the load attribute based on the occurrence probability and output it as the load attribute of the equipment.

[0054] Preferably, the load attribute generation module is specifically used for:

[0055] By performing a traversal solution, multiple load attributes that may constitute the instantaneous power signal at each time node are obtained.

[0056] Preferably, the probability prediction module is specifically used for:

[0057] The multiple load attributes are processed by a pre-trained neural network model with the average power input to determine the probability of occurrence of each of the multiple load attributes.

[0058] Preferably, the output module is specifically used for:

[0059] The load attribute with the highest probability of occurrence is selected as the optimal solution.

[0060] It should be noted that, for the system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the specific workflow of the system described in the embodiments can be found in the description of the method flow section of the embodiments, and will not be repeated here.

[0061] As can be seen from the above description of the embodiments, the embodiments of the present invention have at least the following advantages:

[0062] Its equipment deployment cost is low. When the scale of the target equipment changes, there is no need to rearrange it. It only needs to continue to acquire the instantaneous power signal and average power signal of the equipment at each time node within the preset time period to identify and generate load attributes. It has universal applicability and does not have problems such as poor data integrity and accuracy. It can be installed on the outgoing line side of the distribution transformer. It has the characteristics of non-intrusion and high accuracy and is suitable for the identification of impact load behavior.

[0063] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for identifying the impact load attributes of a distribution transformer outgoing line side, characterized in that, include: Acquire the instantaneous power signal and average power signal of the equipment subjected to impact load at various time points within a preset time period; Multiple load attributes are generated that may constitute the instantaneous power signal at each time point; load attributes refer to the power curve of the equipment. The probability of occurrence of each of the multiple load attributes is evaluated based on the average power at each time point. This includes processing the multiple load attributes and the average power into a pre-trained neural network model to determine the probability of occurrence of each load attribute. The higher the matching degree between the load attribute and the average power, the higher the probability of occurrence of the load attribute. The optimal solution for the load attribute is determined based on the occurrence probability, and its output is used as the load attribute of the equipment.

2. The method as described in claim 1, characterized in that, The multiple load attributes that may constitute the instantaneous power signal at each time node include: By performing a traversal solution, multiple load attributes that may constitute the instantaneous power signal at each time node are obtained.

3. The method as described in claim 2, characterized in that, The step of determining the optimal solution for the load attribute based on the occurrence probability and outputting it as the load attribute of the equipment includes: The load attribute with the highest probability of occurrence is selected as the optimal solution.

4. A system for identifying the impact load attributes of a distribution transformer outgoing line side, characterized in that, include: The power acquisition module is used to acquire the instantaneous power signal and average power signal of the equipment subjected to impact load at various time points within a preset time period; The load attribute generation unit is used to generate multiple load attributes that may constitute the instantaneous power signal at each time node; the load attribute refers to the power curve of the equipment. The probability prediction unit is used to evaluate the occurrence probability of the multiple load attributes based on the average power at each time point. This includes processing the multiple load attributes and the average power into a pre-trained neural network model to determine the occurrence probability of the multiple load attributes. The higher the matching degree between the load attribute and the average power, the higher the occurrence probability of the load attribute. The optimal solution for the load attribute is determined based on the occurrence probability, and its output is used as the load attribute of the equipment.

5. The system as described in claim 4, characterized in that, The multiple load attributes that may constitute the instantaneous power signal at each time node include: By performing a traversal solution, multiple load attributes that may constitute the instantaneous power signal at each time node are obtained.

6. The system as described in claim 5, characterized in that, The step of determining the optimal solution for the load attribute based on the occurrence probability and outputting it as the load attribute of the equipment includes: The load attribute with the highest probability of occurrence is selected as the optimal solution.

Images