System and method for analyzing energy consumption of power utilization loop of distribution box

Abstract

The invention discloses an analysis system and analysis method for the energy consumption of an electric loop of a distribution box, and the system comprises an acquisition unit which is used for collecting the current values of an input current port and an output current port in the electric loop, and a receiving unit which is used for receiving the power values of the input current port and the output current port collected by the acquisition unit. The processing unit is used for calculating the energy consumption of each power utilization loop according to the power value through a calculation model, the prediction unit calculates and predicts an energy consumption difference value by adopting a machine learning model based on the historical energy consumption data and the current energy consumption data of each power utilization loop, and finally the output unit outputs the predicted energy consumption difference value data of the power utilization loop. The method and the device are used for solving the technical problem that when a traditional electric energy management mode encounters the problems of abnormal energy consumption increase, low equipment efficiency or energy waste and the like, management lacking detailed data support is often difficult to quickly position the root of the problem, so that the optimal opportunity for taking effective energy-saving measures is delayed.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit energy consumption analysis, and in particular to an energy consumption analysis system and analysis method for an electric circuit of a distribution box. Background Art

[0002] The main function of the distribution box is to receive the electric energy from the power supply and reasonably distribute the electric energy to each power circuit, so as to control, measure and protect the power circuit. The power circuit in the distribution box refers to a series of circuits that are separated from the main power supply of the distribution box and are individually controlled by circuit breakers or switches. These circuits each supply power to a functional area or a group of electrical equipment.

[0003] The design and implementation of most current power distribution systems do not fully utilize advanced metering technology, especially for multi-circuit distribution boxes, which generally lack detailed monitoring methods for the power consumption of each circuit. Traditional power management methods mostly rely on metering at the main incoming line. Although this method can roughly reflect the overall energy consumption, it cannot measure the energy consumption analysis of each power unit or circuit. Therefore, when encountering problems such as abnormal increase in energy consumption, inefficient equipment or energy waste, management without detailed data support often makes it difficult to quickly locate the root cause of the problem, thus delaying the best time to take effective energy-saving measures. This situation not only affects the transparency of energy use, but also hinders the exploration of energy-saving potential and the continuous improvement of energy efficiency. Summary of the invention

[0004] The purpose of the present invention is to provide a distribution box power circuit energy consumption analysis system and analysis method to solve the problems described in the background technology.

[0005] A first aspect of the present invention provides a distribution box power circuit energy consumption analysis system, comprising: a control unit, and a collection unit, a receiving unit, a processing unit, a prediction unit and an output unit connected to the control unit;

[0006] The acquisition unit is used to collect current values ​​of the input current port and the output current port in the power circuit, the receiving unit is used to receive the power values ​​of the input current port and the output current port collected by the acquisition unit, the processing unit is used to calculate the energy consumption of each power circuit using the power value through a calculation model, the prediction unit uses a machine learning model to calculate and predict the energy consumption difference based on the historical energy consumption data and current energy consumption data of each power circuit, and finally outputs the predicted energy consumption difference data of the power circuit through the output unit.

[0007] Optionally, the acquisition unit includes a current transformer and a voltage transformer, both of which are arranged around the conductor, and are used to detect the current value and voltage value of a single power circuit respectively, and the product of the current value and the voltage value is used to obtain the power value.

[0008] Optionally, the receiving unit includes a sampling circuit, and the sampling circuit is used to receive the power values ​​of the input current port and the output current port collected by the collection unit, and convert the signal of obtaining the power value into a digital signal used by the processing unit.

[0009] Optionally, the calculation model is used to receive the power value digital signal, and calculate the energy consumption weight of each power circuit for the power values ​​of the multiple power circuits, the energy consumption weight includes the weight of the historical energy consumption data and the current energy consumption data, wherein the calculation model uses a calculation formula to obtain the energy consumption weight of each power circuit, and the calculation formula is:

[0010] E=P×T

[0011] Wherein, E is energy consumption, P is average power, and T is usage time. By knowing the power P and time T, the energy consumption E of each power circuit can be directly calculated.

[0012] Optionally, the prediction unit uses a machine learning model to calculate and predict the energy consumption difference, including using a statistical analysis method and a data visualization tool to select the current energy consumption data weight as the reference calculation data weight, and to make a difference between the historical energy consumption data weight and the current energy consumption data weight to obtain the difference between the current energy consumption data weight and the historical energy consumption data weight;

[0013] Wherein, the statistical analysis method comprises the following specific steps:

[0014] The power consumption in different time periods and different regions is collected and generated into multiple node energy consumption;

[0015] Storing the energy consumption of the plurality of nodes in a database;

[0016] Utilizing the adjacent node energy consumption analysis among the plurality of node energy consumptions to obtain the power consumption value for each time period;

[0017] Additional power distribution monitoring equipment is provided according to the energy consumption value.

[0018] Optionally, the statistical analysis method comprises:

[0019] The historical energy consumption data weights are stored in the energy consumption database;

[0020] The data weight is calculated based on the current energy consumption data weight, and each weight of the historical energy consumption data is subtracted from the weight of the currently collected energy consumption data to obtain the difference between the energy consumption data weight and the historical energy consumption data weight.

[0021] Optionally, the method for using the data visualization tool includes:

[0022] Storing historical energy consumption data in an energy consumption database;

[0023] Any one of line graphs, bar graphs and scatter graphs is used, based on the historical energy consumption data weights stored in the energy consumption database, the data weights are calculated based on the current energy consumption data weights, and the difference between each weight of the historical energy consumption data and the current energy consumption data weight is used to make any one of the line graphs, bar graphs and scatter graphs.

[0024] Optionally, the historical energy consumption data is the energy consumption data before the current energy consumption data is collected, wherein the historical energy consumption data includes energy consumption data collected and received within a natural month, and the energy consumption data weights for each day of the month are recorded through a machine learning model.

[0025] Optionally, the output unit includes a machine display screen, and the machine display screen is used to display the digital signal of the power circuit predicted energy consumption data transmitted by the control unit.

[0026] A second aspect of the present invention provides a method for analyzing energy consumption of a power circuit of a distribution box, comprising:

[0027] In response to the power-on process of the power circuit, the acquisition unit determines the current values ​​of the input current port and the output current port in the power circuit;

[0028] Receiving, by a receiving unit, current values ​​of an input current port and an output current port in a power circuit determined by the acquisition unit, and generating power values ​​of the current values ​​of the input current port and the output current port;

[0029] Inputting the power value into a processing unit, and calculating the energy consumption of each power circuit through a calculation model of the processing unit;

[0030] The prediction unit is used to calculate the results based on the weights of historical energy consumption data and current energy consumption data, and the machine learning model is adapted to predict the energy consumption difference based on the calculated data;

[0031] The predicted energy consumption data of the power circuit is outputted through the output unit.

[0032] The beneficial effects of the present invention are:

[0033] The control unit controls the collection unit, receiving unit, processing unit, prediction unit and output unit throughout the process. The collection unit is used to collect current values ​​of input current ports and output current ports in the power circuit. The receiving unit is used to receive power values ​​collected by the collection unit at the input current port and output current port. The processing unit is used to calculate the energy consumption of each power circuit through a calculation model using the power value. The prediction unit uses a machine learning model to calculate and predict the energy consumption difference based on the historical energy consumption data and the current energy consumption data of each power circuit. Finally, the output unit outputs the predicted energy consumption difference data of the power circuit to solve the technical problem that when traditional power management methods encounter problems such as abnormal increase in energy consumption, low equipment efficiency or energy waste, management without detailed data support often finds it difficult to quickly locate the root cause of the problem, thereby delaying the best time to take effective energy-saving measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a system block diagram of the present invention;

[0035] Figure 2 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0036] In order to better understand the technical content of the present invention, specific embodiments are provided below, and the present invention is further described in conjunction with the accompanying drawings.

[0037] refer to Figure 1 In a first aspect, the present invention provides an energy consumption analysis system for a power circuit of a distribution box, comprising: a control unit, and a collection unit, a receiving unit, a processing unit, a prediction unit and an output unit connected to the control unit; the collection unit is used to collect current values ​​of an input current port and an output current port in the power circuit, the receiving unit is used to receive power values ​​collected by the collection unit at the input current port and the output current port, the processing unit is used to calculate the energy consumption of each power circuit through a calculation model based on the power value, the prediction unit uses a machine learning model to calculate and predict the energy consumption difference based on the historical energy consumption data and the current energy consumption data of each power circuit, and finally outputs the predicted energy consumption difference data of the power circuit through the output unit.

[0038] It should be noted that the control unit single chip controller controls the connection of the acquisition unit, the receiving unit, the processing unit, the prediction unit and the output unit.

[0039] Specifically, the control unit controls the entire process of the collection unit, the receiving unit, the processing unit, the prediction unit and the output unit. The collection unit is used to collect current values ​​of the input current port and the output current port in the power circuit. The receiving unit is used to receive the power values ​​of the input current port and the output current port collected by the collection unit. The processing unit is used to calculate the energy consumption of each power circuit through a calculation model using the power value. The prediction unit uses a machine learning model to calculate and predict the energy consumption difference based on the historical energy consumption data and the current energy consumption data of each power circuit. Finally, the output unit outputs the predicted energy consumption difference data of the power circuit to solve the technical problem that when traditional power management methods encounter problems such as abnormal increase in energy consumption, low equipment efficiency or energy waste, management without detailed data support often finds it difficult to quickly locate the root cause of the problem, thereby delaying the best time to take effective energy-saving measures.

[0040] Preferably, the acquisition unit includes a current transformer and a voltage transformer, both of which are arranged around the conductor, and are used to detect the current value and voltage value of a single power circuit respectively, and the product of the current value and the voltage value is used to obtain the power value.

[0041] For example, when the current transformer is arranged around the conductor, it allows the primary side conductor to pass through the center of the transformer, and electromagnetically couples with the secondary winding. According to the principle of electromagnetic induction, the secondary side generates a current proportional to the primary side. Therefore, by measuring the current on the secondary side and combining the transformer's transformation ratio, that is, the ratio of the primary current to the secondary current, the actual current value on the primary side is calculated; similarly, when the voltage transformer is arranged around the conductor, its primary winding is directly connected in parallel to the high-voltage circuit, and the secondary winding is connected to the measurement or protection device. Also based on the principle of electromagnetic induction, when the primary side voltage changes, a low voltage proportional to the primary voltage will be induced on the secondary side. By measuring the secondary side voltage and combining the transformer's transformation ratio, the voltage value on the primary side is obtained. The power value of the power circuit of this section can be obtained by multiplying the actual current value of the primary side and the voltage value of the primary side. Similarly, each power circuit in the distribution box uses this method to detect the power value.

[0042] Preferably, the receiving unit comprises a sampling circuit, and the sampling circuit is used to receive the power values ​​of the input current port and the output current port collected by the collecting unit, and convert the signal of the acquired power value into a digital signal used by the processing unit.

[0043] The power value signals obtained from the current transformer and the voltage transformer are converted into digital signals that can be used by the processing unit to facilitate subsequent modeling calculations.

[0044] Preferably, the calculation model is used to receive the power value digital signal, and calculate the energy consumption weight of each power circuit for the power values ​​of multiple power circuits, the energy consumption weight includes the weight of historical energy consumption data and current energy consumption data, wherein the calculation model uses a calculation formula to obtain the energy consumption weight of each power circuit, and the calculation formula is:

[0045] E=P×T

[0046] In the formula, E is energy consumption, P is average power, and T is usage time. By knowing the power P and time T, the energy consumption E of each power circuit can be directly calculated.

[0047] For example, the distribution box is divided into A, B, C, D, F, and G sections of power circuits, and the current transformer and voltage transformer are used to detect the current value and voltage value of the power circuit of section A to obtain P A， At the detection time T A , we get E A , the energy consumption weight of section A is E A , and E is obtained in turn B 、E C 、E D 、E F 、E G .

[0048] Preferably, the historical energy consumption data is the energy consumption data before the current energy consumption data is collected, wherein the historical energy consumption data includes the energy consumption data collected and received within a natural month, and the energy consumption data weights for each day of the month are recorded through a machine learning model.

[0049] For example, the time feature codes are obtained, such as the 1st to 30th in the calendar table. These features can be directly used as model input. During the training process, the model learns the energy consumption weights of each power circuit in different time periods. For the periodically changing energy consumption data, the specific energy consumption weights are recorded as {E A-1 ,E A-2 ……E A-30}.

[0050] Preferably, the prediction unit uses a machine learning model to calculate and predict the energy consumption difference, including using statistical analysis methods and data visualization tools to select the current energy consumption data weight as the benchmark calculation data weight, subtracting the historical energy consumption data weight from the current energy consumption data weight, and obtaining the difference between the current energy consumption data weight and the historical energy consumption data weight.

[0051] For example, using E A For example, E A The historical energy consumption before is the collection of {E A-1 ,E A-2 ……E A-30}, where E A-1 For EA The energy consumption weight of the previous day, and so on, E A-30 is the energy consumption in the first thirty days. A Subtract the historical energy consumption data in the collection in turn to get E A The difference between the current energy consumption E and the historical energy consumption data can be used to determine the current energy consumption E A Is the difference compared with the energy consumption of each day in the historical energy consumption data huge? If the difference is large, corresponding adjustments need to be made to prevent excessive energy loss during subsequent power-on, which does not meet the goal of energy saving.

[0052] Among them, the statistical analysis method includes: storing the weights of historical energy consumption data in the energy consumption database; calculating the data weights based on the current energy consumption data weights, subtracting each weight of the historical energy consumption data from the weight of the currently collected energy consumption data, and obtaining the difference between the energy consumption data weights and the historical energy consumption data weights. The difference between the energy consumption data weights and the historical energy consumption data weights is obtained by using statistical analysis methods to simplify these data to make them easier to understand and explain. By summarizing the statistical standard deviation and visualizing charts, the difference between the current energy consumption data weights and the historical energy consumption data weights can be intuitively displayed, making it easier for staff to understand.

[0053] In addition, the statistical analysis method also includes the following analysis methods: taking the electricity consumption in different time periods and different regions, and aggregating and generating multiple node energy consumptions; storing the multiple node energy consumptions in the database; using the adjacent node energy consumption analysis among the multiple node energy consumptions to obtain the electricity consumption values ​​for each time period; and attaching distribution monitoring equipment based on the energy consumption values.

[0054] For example, within a district, there are areas with low and high electricity consumption, and areas with low electricity consumption (suburbs or rural areas) will also experience increased electricity consumption during specific times (Chinese New Year and other holidays), and areas with high electricity consumption (cities or factories) will also experience reduced electricity consumption during specific times (Chinese New Year and other holidays). Therefore, the energy consumption data of areas with low and high electricity consumption are taken, and the node energy consumption is stored in the database. The node energy consumption is used to analyze the electricity consumption of areas with low and high electricity consumption, so as to set up power monitoring equipment (such as meter controllers, which are used to upload to the database) and power distribution shunting equipment (electric switch control circuit current increases or decreases power distribution) to prevent sudden excessive power consumption and avoid sudden electrical fires.

[0055] In another preferred embodiment, the method for using the data visualization tool includes: storing historical energy consumption data in an energy consumption database; using any one of a line graph, a bar graph, and a scatter graph, based on the weights of the historical energy consumption data stored in the energy consumption database, calculating the data weights based on the current energy consumption data weights, and making a line graph, a bar graph, and a scatter graph using the difference between each weight of the historical energy consumption data and the weight of the current energy consumption data.

[0056] The difference between the current energy consumption data weight and the historical energy consumption data weight is displayed visually in the form of a graphic, allowing staff to quickly grasp the key points and speed up the decision-making process.

[0057] Preferably, the output unit includes a machine display screen, which is used to display the digital signal of the power circuit predicted energy consumption data transmitted by the control unit.

[0058] Specifically, the machine display screen is used to display images of statistical analysis methods and data visualization tools, helping staff to more intuitively understand the changing trend of the difference between the current energy consumption data weight and the historical energy consumption data weight through the machine display screen, and make corresponding adjustments in time to ensure that energy consumption losses are not too large and reduce energy-saving effects.

[0059] refer to Figure 2 The second aspect of the present invention provides a method for analyzing energy consumption of a power circuit of a distribution box, comprising:

[0060] S101: In response to the power-on process of the power circuit, the acquisition unit determines the current values ​​of the input current port and the output current port in the power circuit;

[0061] S102: receiving, by a receiving unit, current values ​​of an input current port and an output current port in a power circuit determined by a collection unit, and generating power values ​​of the current values ​​of the input current port and the output current port;

[0062] S103: inputting the power value into the processing unit, and calculating the energy consumption of each power circuit through the calculation model of the processing unit;

[0063] S104: using a prediction unit to perform result calculation based on the weights of historical energy consumption data and current energy consumption data, and adapting a machine learning model to predict energy consumption difference based on the calculation data;

[0064] S105: Outputting the predicted energy consumption data of the power circuit through the output unit.

[0065] It should be noted that the method uses a control unit, and a collection unit, a receiving unit, a processing unit, a prediction unit and an output unit connected to the control unit. Therefore, its working principle is the same as the working principle of the system, and will not be repeated here.

[0066] The method controls the collection unit, the receiving unit, the processing unit, the prediction unit and the output unit throughout the process through the control unit. The collection unit is used to collect the current values ​​of the input current port and the output current port in the power circuit. The receiving unit is used to receive the power values ​​of the input current port and the output current port collected by the collection unit. The processing unit is used to calculate the energy consumption of each power circuit through the calculation model. The prediction unit uses a machine learning model to calculate and predict the energy consumption difference based on the historical energy consumption data and the current energy consumption data of each power circuit. Finally, the output unit outputs the predicted energy consumption difference data of the power circuit. This is used to solve the technical problem that when the traditional power management method encounters problems such as abnormal increase in energy consumption, low equipment efficiency or energy waste, the management lacking detailed data support often finds it difficult to quickly locate the root cause of the problem, thereby delaying the best time to take effective energy-saving measures.

[0067] 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 protection scope of the present invention.

Claims

1. A distribution box power circuit energy consumption analysis system, characterized in that: include: A control unit, and a collection unit, a receiving unit, a processing unit, a prediction unit and an output unit connected to the control unit; The acquisition unit is used to collect current values ​​of the input current port and the output current port in the power circuit, the receiving unit is used to receive the power values ​​of the input current port and the output current port collected by the acquisition unit, the processing unit is used to calculate the energy consumption of each power circuit using the power value through a calculation model, the prediction unit uses a machine learning model to calculate and predict the energy consumption difference based on the historical energy consumption data and current energy consumption data of each power circuit, and finally outputs the predicted energy consumption difference data of the power circuit through the output unit.

2. The energy consumption analysis system for the power circuit of a distribution box according to claim 1 is characterized in that: The acquisition unit includes a current transformer and a voltage transformer, both of which are arranged around the conductor. The current transformer and the voltage transformer are respectively used to detect the current value and voltage value of a single power circuit. The product of the current value and the voltage value is used to obtain the power value.

3. The energy consumption analysis system for the power circuit of a distribution box according to claim 1 is characterized in that: The receiving unit includes a sampling circuit, and the sampling circuit is used to receive the power values ​​collected by the collection unit from the input current port and the output current port, and convert the signal of obtaining the power value into a digital signal used by the processing unit.

4. A distribution box power circuit energy consumption analysis system according to claim 1 or 3, characterized in that: The calculation model is used to receive the power value digital signal, and calculate the energy consumption weight of each power circuit for the power values ​​of the multiple power circuits, wherein the energy consumption weight includes the weight of the historical energy consumption data and the current energy consumption data, wherein the calculation model uses a calculation formula to obtain the energy consumption weight of each power circuit, and the calculation formula is: E=P×T Wherein, E is energy consumption, P is average power, and T is usage time. By knowing the power P and time T, the energy consumption E of each power circuit can be directly calculated.

5. The energy consumption analysis system for the power circuit of a distribution box according to claim 1 is characterized in that: The prediction unit uses a machine learning model to calculate and predict the energy consumption difference, including using a statistical analysis method and a data visualization tool to select the current energy consumption data weight as the reference calculation data weight, and compare the historical energy consumption data weight with the current energy consumption data weight to obtain the difference between the current energy consumption data weight and the historical energy consumption data weight; Wherein, the statistical analysis method comprises the following specific steps: The power consumption in different time periods and different regions is collected and generated into multiple node energy consumption; Storing the energy consumption of the plurality of nodes in a database; Utilizing the adjacent node energy consumption analysis among the plurality of node energy consumptions to obtain the power consumption value for each time period; Additional power distribution monitoring equipment is provided according to the energy consumption value.

6. The energy consumption analysis system for the power circuit of a distribution box according to claim 5 is characterized in that: The statistical analysis method comprises: The historical energy consumption data weights are stored in the energy consumption database; The data weight is calculated based on the current energy consumption data weight, and each weight of the historical energy consumption data is subtracted from the weight of the currently collected energy consumption data to obtain the difference between the energy consumption data weight and the historical energy consumption data weight.

7. The energy consumption analysis system for the power circuit of a distribution box according to claim 5 is characterized in that: The method for using the data visualization tool includes: Storing historical energy consumption data in an energy consumption database; Any one of line graphs, bar graphs and scatter graphs is used, based on the historical energy consumption data weights stored in the energy consumption database, the data weights are calculated based on the current energy consumption data weights, and the difference between each weight of the historical energy consumption data and the current energy consumption data weight is used to make any one of the line graphs, bar graphs and scatter graphs.

8. A distribution box power circuit energy consumption analysis system according to claim 6 or 7, characterized in that: The historical energy consumption data is the energy consumption data before the current energy consumption data is collected, wherein the historical energy consumption data includes the energy consumption data collected and received within a natural month, and the energy consumption data weights of each day in the month are recorded through a machine learning model.

9. The energy consumption analysis system for the power circuit of a distribution box according to claim 1 is characterized in that: The output unit includes a machine display screen, and the machine display screen is used to display the digital signal of the power circuit predicted energy consumption data transmitted by the control unit.

10. A method for analyzing energy consumption of a power distribution box circuit, characterized in that: include: In response to the power-on process of the power circuit, the acquisition unit determines the current values ​​of the input current port and the output current port in the power circuit; Receiving, by a receiving unit, current values ​​of an input current port and an output current port in a power circuit determined by the acquisition unit, and generating power values ​​of the current values ​​of the input current port and the output current port; Inputting the power value into a processing unit, and calculating the energy consumption of each power circuit through a calculation model of the processing unit; The prediction unit is used to calculate the results based on the weights of historical energy consumption data and current energy consumption data, and the machine learning model is adapted to predict the energy consumption difference based on the calculated data; The predicted energy consumption data of the power circuit is outputted through the output unit.

Images