Intelligent control method and system for construction electricity

Abstract

The present invention provides a method and system for intelligent control of construction electricity consumption, which relates to the field of electricity control technology. The monitoring device receives the identifier of each partition of the actual energy consumption data sequence of at least one partition in the current preset time period sent by the electric energy management device. For each partition, when the power consumption of the partition is abnormal, the monitoring device determines the alarm level based on the preset early warning rules and the actual energy consumption data sequence of the partition in the current preset time period, and determines and pushes the target electricity consumption control strategy based on the alarm level of the partition. The above method realizes real-time monitoring, accurate alarm, automatic push of control strategy and other means, realizes comprehensive management and control of electricity consumption, and helps to improve the level of energy efficiency management, reduce energy waste, and achieve energy conservation and emission reduction goals. At the same time, the characteristics of automation and intelligence also improve work efficiency and data security.

Description

Technical Field

[0001] The present application relates to the field of electricity control technology, and in particular to a method and system for intelligent control of construction electricity consumption. Background Art

[0002] In modern construction sites, electricity is the key energy source to maintain the normal operation of various equipment. Construction sites usually include a large number of electrical equipment, such as cranes, welders, concrete mixers, power tools and lighting equipment. The power requirements and energy consumption of these equipment vary greatly, which makes power management during the construction process complex and challenging.

[0003] In the prior art, a fixed power supply time and power supply amount are usually set to control the operation of each electrical equipment, or a load management system is used to monitor and adjust the power usage at the construction site, or the construction process is divided into several stages, with only part of the electrical equipment turned on in each stage to avoid excessive power load caused by running a large number of equipment at the same time.

[0004] However, the above method lacks flexibility and cannot respond to changes in actual electricity demand on site in real time. It may also prolong the construction period and increase the overall construction cost. Summary of the invention

[0005] The present application provides a method and system for intelligent construction electricity management and control to address the problems of existing methods lacking flexibility, being unable to respond in real time to changes in actual on-site electricity demand, and possibly prolonging the construction period and increasing overall construction costs.

[0006] In a first aspect, the present application provides a construction power intelligent management and control method, which is applied to an intelligent management and control system, wherein the intelligent management and control system includes a monitoring device and an electric energy management device, wherein the electric energy management device manages multiple partitions, each partition includes multiple electric devices, and the monitoring device, the electric energy management device and each electric device are in communication connection; the method includes:

[0007] The monitoring device receives a sequence of actual energy consumption data of at least one partition in a current preset time period and an identifier of each partition sent by the power management device;

[0008] For each partition, when the power consumption of the partition is abnormal, the monitoring device determines the alarm level based on the preset early warning rules and the actual energy consumption data sequence of the partition in the current preset time period, and the alarm level includes low-level alarm, medium-level alarm or high-level alarm;

[0009] The monitoring device determines and pushes a target power consumption control strategy based on the alarm level of the partition.

[0010] In combination with the first aspect, in some embodiments, the method further includes:

[0011] For each partition, the monitoring device receives a sequence of actual energy consumption data of the partition in the last preset time period sent by the power management device;

[0012] The monitoring device performs prediction calculation on the actual energy consumption data sequence of the partition in the previous preset period based on the preset energy consumption prediction model, and generates a predicted energy consumption data sequence of the partition in the current preset period;

[0013] The monitoring device calculates the abnormal power consumption warning value corresponding to the partition based on the predicted energy consumption data sequence of the partition in the current preset time period to obtain the abnormal power consumption warning value corresponding to the partition.

[0014] In combination with the first aspect, in some embodiments, the monitoring device performs a prediction calculation on the actual energy consumption data sequence of the partition in the previous preset time period based on a preset energy consumption prediction model to generate a predicted energy consumption data sequence of the partition in the current preset time period, including:

[0015] For each partition, the monitoring device inputs the actual energy consumption data sequence of the partition in the previous preset period into the energy consumption prediction model, performs preprocessing and feature extraction, and obtains feature data;

[0016] The monitoring device calculates the feature data based on a preset fusion formula to obtain fused feature data;

[0017] The monitoring device calculates the fused feature data using a feature representation formula and performs pooling processing to generate a predicted energy consumption data sequence for the partition within a current preset time period.

[0018] In combination with the first aspect, in some embodiments, the monitoring device calculates the abnormal power consumption warning value corresponding to the partition based on the predicted energy consumption data sequence of the partition in the current preset time period to obtain the abnormal power consumption warning value corresponding to the partition, including:

[0019] For each partition, the monitoring device calculates the energy consumption conversion rate of two adjacent moments in the predicted energy consumption data sequence of the partition within the current preset time period;

[0020] The monitoring device calculates the abnormal power consumption warning value corresponding to the partition based on each energy consumption conversion rate and the predicted energy consumption data sequence of the partition in the current preset time period.

[0021] In combination with the first aspect, in some embodiments, the method further includes:

[0022] Step 1: The monitoring device performs multi-scale convolution fusion calculation on the pre-acquired training set based on a pre-set initial fusion formula to obtain a fusion result;

[0023] Step 2: The monitoring device performs feature representation processing on the fusion result based on a preset initial feature representation formula to obtain prediction data corresponding to the training set;

[0024] Step 3: The monitoring device calculates the loss value based on the prediction data corresponding to the training set and a preset loss function formula;

[0025] Step 4: The monitoring device updates the parameters in the initial fusion formula and the initial feature representation formula based on the loss value to obtain a new fusion formula and a new feature representation formula, and repeats steps 1 to 4 until a preset accuracy rate is reached to obtain the energy consumption prediction model.

[0026] In combination with the first aspect, in some embodiments, for each partition, when the power consumption of the partition is abnormal, before the monitoring device determines the alarm level based on a preset early warning rule and an actual energy consumption data sequence of the partition within a current preset time period, the method further includes:

[0027] For each partition, if the actual total energy consumption of the partition in the current preset time period exceeds the abnormal power consumption warning value corresponding to the partition, the monitoring device determines that the power consumption of the partition is abnormal.

[0028] In combination with the first aspect, in some embodiments, the monitoring device determines a target power consumption control strategy based on the alarm level of the partition, including:

[0029] If the alarm level is a low-level alarm, the monitoring device will prompt the electricity user as the target electricity consumption control strategy.

[0030] In combination with the first aspect, in some embodiments, the method further includes:

[0031] If the alarm level is a medium alarm, the monitoring device will adjust the power consumption time of the power-consuming device as the target power consumption control strategy.

[0032] In combination with the first aspect, in some embodiments, the method further includes:

[0033] If the alarm level is a high alarm, the monitoring device uses power failure detection as the target power consumption control strategy.

[0034] In the second aspect, the present application provides a smart management and control system, including: a monitoring device and an electric energy management device, wherein the electric energy management device manages multiple partitions, each partition contains multiple power-consuming devices, and the monitoring device, the electric energy management device and each power-consuming device are communicatively connected to execute the smart management and control method for construction electricity use described in any one of the above-mentioned first aspects.

[0035] In a third aspect, the present application provides a monitoring device, comprising: a processor, and a memory communicatively connected to the processor, a plurality of sensors, and a communication interface;

[0036] The memory stores computer-executable instructions;

[0037] The processor executes the computer execution instructions stored in the memory to implement the intelligent management and control method for construction electricity use described in any one of the first aspects.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the intelligent construction electricity management method described in any one of the first aspects above.

[0039] In a fifth aspect, the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the intelligent construction electricity management method described in any one of the first aspects above.

[0040] The intelligent control method and system for construction electricity provided by the present application, the monitoring device receives the identifier of each partition of the actual energy consumption data sequence of at least one partition in the current preset time period sent by the power management device. For each partition, when the power consumption of the partition is abnormal, the monitoring device determines the alarm level based on the preset early warning rules and the actual energy consumption data sequence of the partition in the current preset time period, and determines and pushes the target electricity control strategy based on the alarm level of the partition. The above method realizes real-time monitoring, accurate alarm, automatic push of control strategy and other means, realizes comprehensive management and control of electricity consumption, helps to improve the level of energy efficiency management, reduce energy waste, and achieve energy conservation and emission reduction goals. At the same time, the characteristics of automation and intelligence also improve work efficiency and data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] Figure 1 A flowchart of the first embodiment of the construction power intelligent control method provided in the embodiment of the present application;

[0043] Figure 2 A flow chart of the second embodiment of the construction power intelligent control method provided in the embodiment of the present application;

[0044] Figure 3 A flowchart of a third embodiment of the construction power intelligent control method provided in the embodiment of the present application;

[0045] Figure 4 A flowchart of a fourth embodiment of the construction power intelligent control method provided in the embodiment of the present application;

[0046] Figure 5 A flowchart of a fifth embodiment of the construction power intelligent control method provided in the embodiment of the present application;

[0047] Figure 6 A flowchart of a sixth embodiment of the construction power intelligent control method provided in the embodiment of the present application;

[0048] Figure 7 A schematic diagram of the structure of the intelligent management and control system provided in the embodiment of the present application;

[0049] Figure 8 A schematic diagram of the structure of the monitoring device provided in an embodiment of the present application.

[0050] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0051] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0052] In modern construction sites, electricity is the key energy source to maintain the normal operation of various equipment. Construction sites usually include a large number of electrical equipment, such as cranes, electric welders, concrete mixers, power tools and lighting equipment. The power requirements and energy consumption of these equipment vary greatly, which makes power management during the construction process complex and challenging. In the prior art, a fixed power supply time and power supply amount are usually set to control the operation of each electrical equipment, or a load management system is used to monitor and adjust the power use of the construction site, or the construction process is divided into several stages, and only part of the electrical equipment is turned on in each stage to avoid excessive power load caused by running a large number of equipment at the same time. However, the above method lacks flexibility and cannot respond to changes in actual power demand on site in real time. It may also extend the construction period and increase the overall construction cost.

[0053] In response to the above problems, the present application provides a method and system for intelligent control of construction electricity consumption, which realizes accurate, efficient and flexible intelligent electricity consumption control. Specifically, in the prior art, a fixed power supply time and power supply amount are usually set to control the operation of each power-consuming equipment, or a load management system is used to monitor and adjust the power use of the construction site, or the construction process is divided into several stages, and only part of the power-consuming equipment is turned on in each stage to avoid excessive power load caused by running a large number of equipment at the same time. However, the above method lacks flexibility and cannot respond to changes in actual power demand on site in real time, and may also extend the construction period and increase the overall construction cost. Taking these problems into consideration, the inventor has studied whether it is possible to use monitoring equipment to intelligently predict the energy consumption of different partitions of the construction site, and calculate the abnormal power consumption warning value based on the predicted energy consumption data, and perform real-time control of the actual energy consumption based on the abnormal power consumption warning value. When a high-level alarm is reached, intelligent automatic fault detection and positioning can also be achieved. Based on this, the technical solution of the present application is proposed.

[0054] The intelligent control method for construction electricity provided in the present application is mainly applied to the scenario of large-scale construction sites, which includes an intelligent control system. The intelligent control system includes a monitoring device, an electric energy management device and N electric energy devices at the construction site. The N electric energy devices at the construction site are divided into M partitions according to the operation requirements. Each partition includes P electric energy devices, and the external power supply is connected to the main distribution box. The main distribution box includes at least one distribution box, and each distribution box includes at least one branch distribution box. Each branch distribution box is connected to at least one electric energy device. The partition corresponds to the distribution box or the branch distribution box. Each partition is equipped with electric energy metering equipment and sensors such as current, voltage, and temperature. Among them, the electric energy management device is used to obtain data from the electric energy metering device and sensor data. The device can be located at the construction site or not at the construction site. The monitoring device can be a cloud or a remote system, which is used to communicate with the electric energy management system and monitor and warn energy consumption data.

[0055] Optionally, the location of the power management device does not need to be considered. The power management device can communicate with the power metering device and the monitoring system based on the mobile communication network. If the construction site is located in a remote area and there is no mobile communication network or the signal is poor, a LoRa communication device is installed in the power metering device, and the power metering device and the power management device communicate through the LoRa network. In this case, the power management system equipment is set at a location with a mobile communication network, and the power management device and the monitoring device are connected through the mobile communication network.

[0056] The monitoring equipment can realize intelligent management and control of the electricity consumption of each partition based on the electricity consumption data of different partitions stored in the power management equipment.

[0057] For the physical devices in the above scenarios, this application does not specifically limit the specific form and type.

[0058] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0059] Figure 1 The flowchart of the first embodiment of the construction power intelligent control method provided in the embodiment of the present application is as follows: Figure 1 As shown, the method is applied to a smart management and control system, wherein the smart management and control system includes a monitoring device and an electric energy management device, the electric energy management device manages multiple partitions, each partition includes multiple electric devices, and the monitoring device, the electric energy management device and each electric device are communicatively connected. The method specifically includes:

[0060] S101: A monitoring device receives a sequence of actual energy consumption data of at least one partition within a current preset time period and an identifier of each partition sent by an electric energy management device.

[0061] In this step, in order to realize intelligent control of electricity consumption at the construction site, each section of the construction site can be monitored at different time periods, which can not only monitor the electricity consumption in real time but also save manpower.

[0062] Specifically, when the monitoring device performs power consumption control on each partition, the actual energy consumption data sequence of at least one partition in the current preset time period sent by the power management device is received, and the identifier of each partition, wherein the power management device performs data management on all partitions, and the data of different partitions are divided according to the identifier of each partition, and the actual energy consumption data sequence in the current preset time period includes the actual energy consumption at every moment in the preset time period. The preset time period can be one hour, two hours, three hours, etc., and this application does not make specific limitations, and can be freely set according to the specific management situation of the construction site.

[0063] S102: For each partition, when the power consumption of the partition is abnormal, the monitoring device determines the alarm level based on the preset warning rules and the actual energy consumption data sequence of the partition in the current preset time period.

[0064] In this step, for each partition, when the electricity consumption of the partition is abnormal, in order to promote the standardization of electricity consumption management and control and improve the efficiency of management and control response, the actual energy consumption data sequence of the partition in the current preset time period is obtained, and then the actual total energy consumption in the preset time period is obtained, and compared with the thresholds of different alarm levels in the preset early warning rules, and then the alarm level of the partition is determined, where the alarm levels are divided into low-level alarms, medium-level alarms and high-level alarms.

[0065] Specifically, the abnormal power consumption warning value of each partition within the preset time period is calculated in advance, and based on the abnormal power consumption warning value, high-level interval division is performed.

[0066] Exemplarily, assuming that the abnormal power consumption warning value is E, [E, 1.2E] is determined as a low-level warning interval, [1.2E, 1.4E] is determined as a medium-level warning interval, and above 1.4E is determined as a high-level warning.

[0067] S103: The monitoring device determines and pushes a target power consumption control strategy based on the alarm level of the partition.

[0068] In this step, after the above steps, the monitoring device determines the alarm level of the partition, then for intelligent management and control, it determines the target power consumption control strategy based on the alarm level, and pushes the target power consumption control strategy to the user.

[0069] Specifically, if the alarm level is a low-level alarm, the monitoring device will prompt the electricity user as the target electricity consumption control strategy. If the alarm level is a medium-level alarm, the monitoring device will adjust the power consumption time of the electricity-consuming equipment as the target electricity consumption control strategy. If the alarm level is a high-level alarm, the monitoring device will use power fault detection as the target electricity consumption control strategy.

[0070] The intelligent control method for construction electricity provided in this embodiment is that the monitoring device receives the identifier of each partition of the actual energy consumption data sequence of at least one partition in the current preset time period sent by the power management device. For each partition, when the power consumption of the partition is abnormal, the monitoring device determines the alarm level based on the preset early warning rules and the actual energy consumption data sequence of the partition in the current preset time period, and determines and pushes the target electricity control strategy based on the alarm level of the partition. The above method realizes real-time monitoring, accurate alarms, automatic push of control strategies and other means, realizes comprehensive management and control of electricity consumption, and helps to improve the level of energy efficiency management, reduce energy waste, and achieve energy conservation and emission reduction goals. At the same time, the characteristics of automation and intelligence also improve work efficiency and data security.

[0071] Figure 2 The flowchart of the second embodiment of the construction power intelligent control method provided in the embodiment of the present application is as follows: Figure 2 As shown, based on the above embodiment, the method further includes:

[0072] S201: For each partition, the monitoring device receives a sequence of actual energy consumption data of the partition in the last preset time period sent by the power management device.

[0073] S202: The monitoring device performs a prediction calculation on the actual energy consumption data sequence of the partition in the previous preset time period based on a preset energy consumption prediction model, and generates a predicted energy consumption data sequence of the partition in the current preset time period.

[0074] In order to realize intelligent management and control of electricity consumption at the construction site, thereby ensuring electricity safety and improving construction efficiency, for each partition, the monitoring device receives the actual energy consumption data sequence of the partition in the previous preset time period sent by the power management device, and predicts the energy consumption in the current preset time period based on the energy consumption prediction model, thereby generating a predicted energy consumption data sequence for the partition in the current preset time period.

[0075] Specifically, for each partition, the monitoring device inputs the actual energy consumption data sequence of the partition in the previous preset time period into the energy consumption prediction model, performs preprocessing and feature extraction, obtains feature data, calculates the feature data based on the preset fusion formula, obtains fused feature data, calculates the fused feature data using the feature representation formula, and performs pooling processing to generate a predicted energy consumption data sequence for the partition in the current preset time period.

[0076] S203: The monitoring device calculates the abnormal power consumption warning value corresponding to the partition based on the predicted energy consumption data sequence of the partition in the current preset time period, and obtains the abnormal power consumption warning value corresponding to the partition.

[0077] In this step, after the monitoring device predicts the energy consumption of the partition in the current preset time period through the above steps, in order to more accurately monitor the power consumption of the partition, the abnormal power consumption warning value of the partition in the current preset time period is calculated based on the predicted energy consumption data sequence of the partition in the current preset time period to obtain the abnormal power consumption warning value corresponding to the partition.

[0078] Specifically, for each partition, the monitoring device calculates the energy consumption conversion rate at two adjacent moments in the predicted energy consumption data sequence of the partition within the current preset time period, and calculates the abnormal power consumption warning value corresponding to the partition based on each energy consumption conversion rate and the predicted energy consumption data sequence of the partition within the current preset time period.

[0079] The intelligent control method for construction electricity provided in this embodiment is that for each partition, the monitoring device receives the actual energy consumption data sequence of the partition in the previous preset time period sent by the power management device, and based on the preset energy consumption prediction model, predicts and calculates the actual energy consumption data sequence of the partition in the previous preset time period, generates the predicted energy consumption data sequence of the partition in the current preset time period, and finally calculates the abnormal electricity consumption warning value corresponding to the partition based on the predicted energy consumption data sequence of the partition in the current preset time period, and obtains the abnormal electricity consumption warning value corresponding to the partition. The abnormal electricity consumption warning value corresponding to the partition is accurately obtained through the above method, thereby providing a data basis for the intelligent control of construction electricity, and also improving the control efficiency.

[0080] Figure 3 The flowchart of the third embodiment of the construction power intelligent control method provided in the embodiment of the present application is as follows: Figure 3 As shown, based on the above embodiment, step S202 specifically includes:

[0081] S301: For each partition, the monitoring device inputs the actual energy consumption data sequence of the partition in the previous preset time period into the energy consumption prediction model, performs preprocessing and feature extraction, and obtains feature data.

[0082] In this step, in order to accurately predict the energy consumption of the partition in the current preset period, the prediction can be based on the actual energy consumption data series in the previous preset period. First, the actual energy consumption data series in the previous preset period needs to be preprocessed and feature extracted.

[0083] Specifically, for preprocessing, data cleaning can be performed to handle missing values: depending on the characteristics of the data, methods such as filling (such as mean, median, nearest neighbor value, etc.), interpolation, or deleting records containing missing values ​​can be used. Handling outliers: Identifying and handling outliers, which can be achieved by setting thresholds, using statistical methods (such as IQR rules), or machine learning anomaly detection algorithms. Removing noise: If there is noise in the data, filters (such as sliding average filters, median filters, etc.) can be used for denoising. Feature extraction can extract time features and statistical features in the actual energy consumption data series, such as mean, standard deviation, maximum value, minimum value, median, etc., which reflect the basic characteristics of energy consumption data, as well as trend features, such as calculating differences, moving averages, cumulative sums, etc., to capture the changing trends of energy consumption data.

[0084] S302: The monitoring device calculates the feature data based on a preset fusion formula to obtain fused feature data.

[0085] In this step, after obtaining the characteristic data, in order to simultaneously capture the characteristics and patterns of energy consumption data in time and space dimensions, construction electricity consumption may show different rules in different regions and time periods. Therefore, in order to effectively integrate this information and provide a more comprehensive and accurate prediction, the characteristic data is calculated according to the pre-set fusion formula to obtain fused characteristic data.

[0086] Specifically, the fusion formula is expressed as:

[0087]

[0088] in, represents the fusion weight coefficient, represents scale 1 features, Represents scale 2 features.

[0089] The scale 1 feature can be expressed as:

[0090]

[0091] The scale 2 feature can be expressed as:

[0092]

[0093] in, is the number of input channels, indicating the number of feature dimensions of the input data, i.e., feature data, and W represents other dimensions related to energy consumption. , , Represent the size of the convolution kernel in time, partition and other dimensions respectively, , , They represent the step size of convolution in time, partition and other dimensions respectively, and control the movement interval of convolution operation in the corresponding dimensions. Represents the number of output channels, that is, the number of feature maps generated by the convolution operation, , , The distribution represents the index of the output feature in the time dimension, which is used to represent a specific time point; the index of the output feature in the partition dimension, which is used to represent a specific partition; the index of the output feature in other possible dimensions (such as the spatial dimension), Represents the value of input data at a specific channel, time, partition, and other dimensions.

[0094] S303: The monitoring device calculates the fused feature data using a feature representation formula and performs a pooling process to generate a predicted energy consumption data sequence for the partition within the current preset time period.

[0095] In this step, after the fused feature data is calculated through the above steps, the predicted energy consumption book sequence is continued to be calculated, which can be calculated based on the feature representation formula and pooling processing.

[0096] The specific feature representation formula and pooling calculation formula can be expressed by the following formula:

[0097]

[0098] in, represents the input data, i.e., the fused feature data, Indicates the hidden state at the previous moment, , , , , , is the weight matrix, , is the bias term, is a nonlinear function, represents the bilateral tangent function, Represents element-wise multiplication.

[0099] Optional, and It can be updated to dynamically adjust the weights according to the characteristics of the power consumption data of the construction site. For example, the sensitivity of the gate can be adaptively changed according to the fluctuation amplitude or periodicity of the energy consumption data to better capture the time characteristics of different situations. This improves the accuracy of the prediction.

[0100] Then the updated formula can be expressed as:

[0101]

[0102] in, represents the time characteristic function based on energy consumption data, , represents the learning parameters.

[0103] Optionally, after step S302, in order to reduce the size of the feature data and thus reduce the computational complexity, a maximum pooling process may be performed. Specifically, the process may be performed using the following formula:

[0104]

[0105] in, represents the fused feature data after pooling, s represents the step size, represents the input fusion feature data, Represents each position in the pooling window .

[0106] The intelligent control method for construction electricity provided in this embodiment is that for each partition, the monitoring device inputs the actual energy consumption data sequence of the partition in the previous preset time period into the energy consumption prediction model, performs preprocessing and feature extraction, obtains feature data, calculates the feature data based on the preset fusion formula, obtains fused feature data, calculates the fused feature data through the feature representation formula, and undergoes pooling processing to generate the predicted energy consumption data sequence of the partition in the current preset time period. Through the above method, it can effectively improve energy utilization efficiency, strengthen energy management, promote energy conservation and emission reduction, improve management level and decision-making efficiency, and has real-time abnormality detection and alarm functions.

[0107] Figure 4 The flowchart of the fourth embodiment of the construction power intelligent control method provided in the embodiment of the present application is as follows: Figure 4 As shown, based on the above embodiments, step 203 specifically includes:

[0108] S401: For each partition, the monitoring device calculates the energy consumption change rate at two adjacent moments in the predicted energy consumption data sequence of the partition within the current preset time period.

[0109] In this step, in order to accurately calculate the abnormal power consumption warning value of the partition, it is also necessary to consider the energy consumption change rate at adjacent moments in the preset period. The monitoring device calculates the energy consumption change rate at two adjacent moments in the predicted energy consumption data sequence of the partition in the current preset period. The specific calculation formula can be expressed as:

[0110]

[0111] S402: The monitoring device calculates the abnormal power consumption warning value corresponding to the partition based on each energy consumption conversion rate and the predicted energy consumption data sequence of the partition in the current preset time period.

[0112] After the energy consumption conversion rate at adjacent moments is obtained, the abnormal power consumption warning value is calculated according to a preset calculation formula for the abnormal power consumption warning value.

[0113] Specifically, the formula is expressed as:

[0114]

[0115] in, represents the predicted energy consumption at time i, It represents the change rate of the energy consumption forecast value at time i, n represents n consecutive moments, and k represents the change rate adjustment factor, which is used to adjust the impact of the change rate on the energy consumption warning value.

[0116] The intelligent control method for construction electricity provided in this embodiment is that for each partition, the monitoring device calculates the energy consumption conversion rate of two adjacent moments in the predicted energy consumption data sequence of the partition in the current preset time period, and calculates the abnormal electricity consumption warning value corresponding to the partition based on each energy consumption conversion rate and the predicted energy consumption data sequence of the partition in the current preset time period. Through the above method, not only the energy consumption value is considered, but also the rate of change of the predicted energy consumption value. This allows the abnormal electricity consumption warning value to more comprehensively reflect the overall situation and fluctuation of energy use, and helps to take energy-saving measures in advance to avoid energy waste and potential risks. By adjusting the change rate adjustment factor k, the contribution of energy consumption value and change rate to the abnormal electricity consumption warning value can be balanced according to different application scenarios and needs. This makes the early warning system more flexible and able to adapt to different energy usage scenarios.

[0117] Figure 5 The flowchart of the fifth embodiment of the construction power intelligent control method provided in the embodiment of the present application is as follows: Figure 5 As shown, based on the above embodiments, the method further includes:

[0118] Step 1: The monitoring device performs multi-scale convolution fusion calculation on the pre-acquired training set based on a pre-set initial fusion formula to obtain a fusion result.

[0119] Step 2: The monitoring device performs feature representation processing on the fusion result based on a preset initial feature representation formula to obtain the prediction data corresponding to the training set.

[0120] Step 3: The monitoring device calculates the loss value based on the predicted data corresponding to the training set and the pre-set loss function formula.

[0121] The aforementioned steps 1 and 2 are calculated in the same manner as the steps 302 and 303 in the aforementioned embodiment, and the calculation formula is also the same. The difference is that in the calculation process of steps 1 and 2, the parameters of the formula are randomly initialized parameters, and then based on the calculation of the randomly initialized formula, the prediction data corresponding to the training set is obtained. In order to accurately calculate and realize accurate energy consumption prediction, it is necessary to design a loss function, and the loss function formula is expressed as:

[0122]

[0123] Among them, N=M×T, represents the total number of data points, M represents the number of partitions, and T represents the number of time. Represents the weight factor, which can be freely set according to the importance of different partitions and different times. Represents the adjustment parameter, which is used to indicate the sensitivity of the error. Represents the balance coefficient, which is used to control the relative importance of absolute error and square error.

[0124] Step 4: The monitoring device updates the parameters in the initial fusion formula and the initial feature representation formula based on the loss value to obtain a new fusion formula and a new feature representation formula, and repeats steps 1 to 4 until the preset accuracy is reached to obtain the energy consumption prediction model.

[0125] After the loss value is calculated, the aforementioned initial fusion formula and initial feature representation formula are adjusted with the goal of minimizing the loss value, thereby repeating the prediction calculation on the training set until the loss value reaches the threshold, thereby obtaining the energy consumption prediction model, that is, the fusion formula and feature representation formula ultimately used to perform the calculations in steps 302 and 303 of the aforementioned embodiment.

[0126] The intelligent control method for construction electricity provided in this embodiment is that the monitoring device performs multi-scale convolution fusion calculation on the pre-acquired training set based on a pre-set initial fusion formula to obtain a fusion result, performs feature representation processing on the fusion result based on a pre-set initial feature representation formula to obtain the feature representation corresponding to the training set, calculates the loss value based on the feature representation corresponding to the training set and the pre-set loss function formula, updates the parameters in the initial fusion formula and the initial feature representation formula based on the loss value, obtains a new fusion formula and a new feature representation formula, repeats the above operation until the preset accuracy is reached, and obtains an energy consumption prediction model. Through the iterative update calculation of the above method, an energy consumption prediction model that can predict the energy consumption data of construction electricity is obtained. Through intelligent prediction, the energy utilization rate is improved, which can not only perform intelligent monitoring of construction electricity in real time, but also indirectly improve construction efficiency.

[0127] Figure 6The flowchart of the sixth embodiment of the construction power intelligent control method provided in the embodiment of the present application is as follows: Figure 6 As shown, based on the above embodiments, step S103 specifically includes:

[0128] S601: If the alarm level is a low-level alarm, the monitoring device will prompt the electricity user as a target electricity consumption control strategy.

[0129] S602: If the alarm level is a medium alarm, the monitoring device will adjust the power consumption time of the power-consuming device as a target power consumption control strategy.

[0130] S603: If the alarm level is a high alarm, the monitoring device uses power failure detection as a target power consumption control strategy.

[0131] If a low-level alarm is determined by judging the actual total energy consumption in the current preset time period, it means that the energy consumption deviates from the normal level to a lesser extent, and there may be minor energy consumption anomalies that need to be paid attention to. If a medium-level warning means that the energy consumption problem has worsened and more forceful measures need to be taken, and if a high-level warning is used, it means that the energy consumption situation is seriously out of control and emergency action must be taken.

[0132] Specifically, when a low-level alarm occurs, the monitoring device will prompt the electricity user as the target electricity consumption control strategy. If it is a medium-level alarm, the power consumption time of the electricity-consuming equipment will be adjusted as the target electricity consumption control strategy. If it is a high-level alarm, power fault detection will be used as the target electricity consumption control strategy.

[0133] For example, if there are only low-level alarms at the beginning, it may be that some electrical equipment is running at high energy consumption for a short period of time; and when it comes to high-level alarms, it may be that the power system of the entire construction area has a serious fault or unreasonable power consumption habits are widespread. Different levels of alarms correspond to management and control strategies of different intensities and types. In the case of low-level alarms, the measures are relatively mild, mainly investigation and publicity; in the case of medium-level alarms, equipment inspections and operating time adjustments are required; high-level alarms require more stringent measures such as suspending construction tasks. For example, in the case of low-level alarms, it may be necessary to check only a few frequently used large equipment; medium-level alarms may require comprehensive inspections of all similar equipment; high-level alarms may require the entire construction process to be replanned.

[0134] Optionally, when an advanced alarm occurs, the fault can also be located. The specific implementation method can be described as follows: first, the power consumption data of each power-consuming device, such as voltage, current, power and temperature, is collected, and then the abnormal data of the collected power consumption data is cleaned and repaired. Then, the historical power consumption data under normal conditions of the construction site is collected, including data of different time periods, different construction tasks and different weather conditions. Then, statistical methods and machine learning algorithms are used to establish a mathematical model of common electricity, determine the reasonable range and change trend of various power consumption parameters, and input the collected power consumption data of each power-consuming device into the model for analysis. After the abnormality is determined, the power consumption data of the abnormal power-consuming device is feature extracted, and the change law of these features is analyzed to preliminarily determine the type of fault, such as short circuit, overload, leakage, etc. Combined with the electrical layout diagram and the installation position of the sensor that collects the data, the algorithm is used to calculate the area where the fault may occur. For complex line networks, a fault location algorithm based on graph theory is used to quickly narrow the scope of the fault. For the initially located fault area, the historical operation data of the relevant equipment and lines are further analyzed to find possible potential fault factors.

[0135] Optionally, once the fault location and type are determined, the system immediately sends detailed alarm information to relevant personnel through SMS, mobile APP push, sound and light alarm, etc., including the specific location, type, severity and possible impact range of the fault. At the same time, the fault information is displayed in a striking way on the visual interface of the monitoring device. And according to the fault type and historical processing experience, the system automatically generates corresponding processing suggestions, such as immediate power off, replacement of equipment, repair of lines, etc. Detailed records are made for each fault that occurs, including the time, location, type, processing process and results of the fault. Regularly analyze the fault data, summarize the fault rules, and optimize the fault diagnosis model and processing flow. For example, if a distribution box has similar fault characteristics many times, it may be that the components inside the distribution box are aging or damaged.

[0136] For example, when the system detects that the power of a welding machine continues to increase abnormally and the temperature exceeds the safety threshold, it is analyzed and determined that the welding machine has an internal short circuit. The system quickly locates the line branch where the welding machine is located and sends an alarm message to the maintenance personnel, and recommends that the branch power supply be cut off immediately to repair the welding machine. After the maintenance is completed, the relevant data of the fault is recorded for subsequent analysis and optimization.

[0137] Through the above-mentioned intelligent automatic fault location, the abnormality can be detected and located in a very short time after the fault occurs, greatly shortening the time interval from the occurrence of the fault to the discovery and processing. For example, a short circuit fault that may take hours or even longer to be discovered in the past can now be accurately located within a few minutes. It is also possible to promptly discover and deal with safety hazards such as leakage and overload, reducing the risk of electrical accidents. For example, the system can quickly detect line leakage and cut off the power in time to avoid electric shock accidents. Then quickly locate and repair the fault, reducing construction progress delays and equipment damage caused by power outages. Assuming that a key equipment is out of power for one hour due to a fault, it will cause the entire construction process to stagnate, causing huge economic losses, while intelligent positioning can shorten the power outage time to more than ten minutes, significantly reducing losses. It is also possible to handle faults in a timely manner to avoid the expansion and chain reaction of faults, improve the stability and reliability of the entire construction site power system, and save labor costs.

[0138] The intelligent construction power control method provided in this embodiment, if the alarm level is a low-level alarm, the monitoring device will prompt the electricity user as a target power control strategy; if the alarm level is a medium-level alarm, the monitoring device will adjust the power consumption time of the power-consuming equipment as a target power control strategy; if the alarm level is a high-level alarm, the monitoring device will use power fault detection as a target power control strategy. By performing graded power control on alarms as described above, not only the power management efficiency is improved, but also a large amount of manpower and material resources are avoided for detection due to minor abnormalities, thereby shortening the construction period.

[0139] Figure 7 A schematic diagram of the structure of the intelligent management and control system provided in the embodiment of the present application is shown in FIG. Figure 7 As shown, the smart management and control system 700 includes: a monitoring device 701 and an electric energy management device 702. The electric energy management device 702 manages multiple partitions, each partition includes multiple power-consuming devices, and the monitoring device 701, the electric energy management device 702 are communicatively connected with each power-consuming device to execute the smart management and control method for construction electricity in any of the aforementioned embodiments.

[0140] Figure 8 A schematic diagram of the structure of the monitoring device provided in the embodiment of the present application, such as Figure 7 As shown, the monitoring device 800 includes: a processor 802, a memory 801 and a communication interface 803 which are communicatively connected to the processor 802;

[0141] The memory 801 stores computer executable instructions;

[0142] The processor 802 executes the computer execution instructions stored in the memory 801 to implement the intelligent management and control method of construction electricity use in any method embodiment.

[0143] The communication interface 803 is used for data communication.

[0144] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to execute the methods provided in the various embodiments described above.

[0145] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0146] Optionally, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0147] An embodiment of the present application also provides a computer program product, which includes a computer program. The computer program is stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, the technical solution provided by any of the above method embodiments can be implemented.

[0148] In this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship; in the formula, the character " / " indicates that the previous and next associated objects are in a "division" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0149] It is to be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not intended to limit the scope of the embodiments of the present application. In the embodiments of the present application, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0150] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0151] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for intelligent control of construction electricity consumption, characterized in that: Applied to a smart management and control system, the smart management and control system includes a monitoring device and an electric energy management device, the electric energy management device manages multiple partitions, each partition includes multiple electric devices, the monitoring device, the electric energy management device and each electric device are in communication connection; the method includes: The monitoring device receives a sequence of actual energy consumption data of at least one partition in a current preset time period and an identifier of each partition sent by the power management device; For each partition, when the power consumption of the partition is abnormal, the monitoring device determines the alarm level based on the preset warning rules and the actual energy consumption data sequence of the partition in the current preset time period, and the alarm level includes low-level alarm, medium-level alarm or high-level alarm; pre-calculates the abnormal power consumption warning value of each partition in the preset time period, and divides the alarm level into intervals based on the abnormal power consumption warning value; The monitoring device determines and pushes a target power consumption control strategy based on the alarm level of the partition; The method further comprises: For each partition, the monitoring device receives a sequence of actual energy consumption data of the partition in the last preset time period sent by the power management device; The monitoring device performs prediction calculation on the actual energy consumption data sequence of the partition in the previous preset period based on the preset energy consumption prediction model, and generates a predicted energy consumption data sequence of the partition in the current preset period; The monitoring device calculates the abnormal power consumption warning value corresponding to the partition based on the predicted energy consumption data sequence of the partition in the current preset time period to obtain the abnormal power consumption warning value corresponding to the partition; The monitoring device performs prediction calculation on the actual energy consumption data sequence of the partition in the previous preset period based on the preset energy consumption prediction model to generate a predicted energy consumption data sequence of the partition in the current preset period, including: For each partition, the monitoring device inputs the actual energy consumption data sequence of the partition in the previous preset period into the energy consumption prediction model, performs preprocessing and feature extraction, and obtains feature data; The monitoring device calculates the feature data based on a preset fusion formula to obtain fused feature data; The monitoring device calculates the fused feature data using a feature representation formula and performs pooling processing to generate a predicted energy consumption data sequence for the partition within a current preset time period; The monitoring device calculates the abnormal power consumption warning value corresponding to the partition based on the predicted energy consumption data sequence of the partition in the current preset time period, and obtains the abnormal power consumption warning value corresponding to the partition, including: For each partition, the monitoring device calculates the energy consumption conversion rate of two adjacent moments in the predicted energy consumption data sequence of the partition within the current preset time period; The specific calculation formula is: The monitoring device calculates the abnormal power consumption warning value corresponding to the partition based on each energy consumption conversion rate and the predicted energy consumption data sequence of the partition in the current preset time period; The specific calculation formula is: Among them, E i represents the predicted energy consumption at time i, R i It represents the change rate of the energy consumption forecast value at time i, n represents n consecutive moments, and k represents the change rate adjustment factor, which is used to adjust the impact of the change rate on the energy consumption warning value.

2. The method according to claim 1, characterized in that The method further comprises: Step 1: The monitoring device performs multi-scale convolution fusion calculation on the pre-acquired training set based on a pre-set initial fusion formula to obtain a fusion result; Step 2: The monitoring device performs feature representation processing on the fusion result based on a preset initial feature representation formula to obtain prediction data corresponding to the training set; Step 3: The monitoring device calculates the loss value based on the prediction data corresponding to the training set and a preset loss function formula; Step 4: The monitoring device updates the parameters in the initial fusion formula and the initial feature representation formula based on the loss value to obtain a new fusion formula and a new feature representation formula, and repeats steps 1 to 4 until a preset accuracy rate is reached to obtain the energy consumption prediction model.

3. The method according to claim 1, characterized in that For each partition, when the power consumption of the partition is abnormal, before the monitoring device determines the alarm level based on the preset early warning rules and the actual energy consumption data sequence of the partition in the current preset time period, the method also includes: For each partition, if the actual total energy consumption of the partition in the current preset time period exceeds the abnormal power consumption warning value corresponding to the partition, the monitoring device determines that the power consumption of the partition is abnormal.

4. The method according to claim 1, characterized in that: The monitoring device determines a target power consumption control strategy based on the alarm level of the partition, including: If the alarm level is a low-level alarm, the monitoring device will prompt the electricity user as the target electricity consumption control strategy.

5. The method according to claim 4, characterized in that The method further comprises: If the alarm level is a medium alarm, the monitoring device will adjust the power consumption time of the power-consuming device as the target power consumption control strategy.

6. The method according to claim 4, characterized in that The method further comprises: If the alarm level is a high alarm, the monitoring device uses power failure detection as the target power consumption control strategy.

7. A smart management and control system, characterized in that: include: Monitoring equipment and power management equipment, wherein the power management equipment manages multiple partitions, each partition contains multiple power-consuming devices, and the monitoring equipment, power management equipment and each power-consuming device are communicatively connected to execute the construction power intelligent management and control method described in any one of claims 1 to 6.

Images