A Smart Management Method and System for Energy Consumption Data in Tunnel Construction

Abstract

The present invention relates to the technical field of data processing, and particularly relates to a smart management method and system for tunnel construction energy consumption data. During the process of tunnel construction, the method obtains the energy consumption data of at least three energy-consuming devices in real time to obtain corresponding energy consumption data sequences; maps all the energy consumption data sequences onto the same two-dimensional coordinate system to obtain curves corresponding to each energy consumption data sequence, analyzes each curve to obtain an energy consumption difference index; maps all the energy consumption data sequences onto the same N-dimensional coordinate system to obtain an N-dimensional curve, where N is greater than 2, and performs surface fitting on all the energy consumption data sequences to obtain an energy consumption fitting surface, analyzes the energy consumption fitting surface and the N-dimensional curve to obtain the degree of abnormal energy consumption change; combines the energy consumption difference index and the degree of abnormal energy consumption change to perform abnormal identification on the energy consumption data, improving the accuracy of abnormal management of the energy consumption data.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a smart management method and system for tunnel construction energy consumption data. Background Art

[0002] A tunnel is an engineering structure buried in the ground, which is a form of human utilization of underground space. Tunnel construction is divided into stages such as tunneling, lining, and restoration. Among them, the tunneling stage is the stage with the most equipment investment and the highest energy consumption. Therefore, this stage is the core stage of tunnel construction. The tunneling stage mainly includes excavating tunnels underground through mechanical or manual means. The main energy-consuming equipment includes shield machines, ventilators, drainage pumps, etc. These equipment operate at high loads during this stage, and their energy consumption accounts for the vast majority of the total energy consumption of tunnel construction. Therefore, it is particularly important to monitor the construction energy consumption data of the tunneling stage in real time.

[0003] In the traditional method, a fixed threshold is set for each energy-consuming equipment. When a certain energy-consuming equipment exceeds its corresponding fixed threshold, it is determined that the energy consumption data is abnormal during tunnel construction. However, there is a synergistic effect between various energy-consuming equipment. For example, for shield machines, ventilators, and drainage pumps, in soft soil strata, the shield machine has a faster propulsion speed, and the demand for ventilation and drainage is also higher. While in hard rock strata, the propulsion speed is slower, and the demand for ventilation and drainage also decreases accordingly. The abnormal determination of energy consumption data in the traditional method ignores the synergistic effect between construction conditions and energy-consuming equipment, lacks systematicness and integrity, and leads to inaccurate abnormal determination of energy consumption data.

[0004] Therefore, how to improve the accuracy of abnormal management of energy consumption data according to the synergy between various energy-consuming equipment has become an urgent problem to be solved. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a smart management method and system for tunnel construction energy consumption data to solve the problem of how to improve the accuracy of abnormal management of energy consumption data according to the synergy between various energy-consuming equipment.

[0006] In a first aspect, embodiments of the present invention provide a smart management method for tunnel construction energy consumption data, and the method includes the following steps:

[0007] During the process of tunnel construction, the energy consumption data of at least three energy-consuming equipment is obtained in real time to obtain corresponding time series, and the data in each of the time series is linearly normalized respectively to obtain corresponding energy consumption data series;

[0008] Map all energy consumption data sequences onto the same two-dimensional coordinate system to obtain the curve corresponding to each energy consumption data sequence, and fit all energy consumption data sequences to obtain an energy consumption fitting curve. The abscissa of the two-dimensional coordinate system represents time, and the ordinate represents energy consumption data. According to the similarity between the curve corresponding to each energy consumption data sequence and the energy consumption fitting curve, and the collaborative difference between each energy consumption data sequence, obtain the energy consumption difference index between all energy consumption data sequences;

[0009] Map all energy consumption data sequences onto the same N-dimensional coordinate system, and fit the data in all energy consumption data sequences to obtain an N-dimensional curve, where N is greater than 2, and perform surface fitting on all energy consumption data sequences to obtain an energy consumption fitting surface. The N coordinate axes of the N-dimensional coordinate system respectively represent the energy consumption data of each energy-consuming device. According to the projected area of the energy consumption fitting surface on each coordinate plane of the N-dimensional coordinate system, and the curvature of each data point on the N-dimensional curve, obtain the degree of abnormal energy consumption change between all energy consumption data sequences;

[0010] Combine the energy consumption difference index and the degree of abnormal energy consumption change to perform abnormal management on the energy consumption data during the construction of the tunnel.

[0011] Preferably, the obtaining of the energy consumption difference index between all energy consumption data sequences according to the similarity between the curve corresponding to each energy consumption data sequence and the energy consumption fitting curve, and the collaborative difference between each energy consumption data sequence includes:

[0012] According to the similarity between the curve corresponding to each energy consumption data sequence and the energy consumption fitting curve, and the abnormal data in all energy consumption data sequences, obtain the data difference degree between all energy consumption data sequences;

[0013] Obtain the intersection points between the curves corresponding to each energy consumption data sequence, cluster all intersection points to obtain at least two clusters, and according to the distance between each two clusters, obtain the collaborative difference index between all energy consumption data sequences;

[0014] Calculate the average value between the data difference degree and the collaborative difference index to obtain the energy consumption difference index between all energy consumption data sequences.

[0015] Preferably, the obtaining of the data difference degree between all energy consumption data sequences according to the similarity between the curve corresponding to each energy consumption data sequence and the energy consumption fitting curve, and the abnormal data in all energy consumption data sequences includes:

[0016] Calculate the DTW distance between the curve corresponding to each of the energy consumption data sequences and the energy consumption fitting curve respectively. After performing weighted summation on all the DTW distances and then linear normalization, obtain the first variable;

[0017] Obtain the abnormal data in all the energy consumption data sequences through a box plot, calculate the ratio between the number of all the abnormal data and the number of all the data in all the energy consumption data sequences, and perform linear normalization on the ratio to obtain the second variable;

[0018] Perform weighted summation on the first variable and the second variable to obtain the degree of data difference between all the energy consumption data sequences.

[0019] Preferably, obtaining the collaborative difference index between all the energy consumption data sequences according to the distance between each two of the clusters includes:

[0020] For any two clusters, respectively obtain the cluster centers of the any two clusters, calculate the Euclidean distance between the cluster centers of the any two clusters to obtain the inter-cluster distance between the any two clusters;

[0021] Obtain the inter-cluster distance between each two of the clusters, calculate the coefficient of variation of all the inter-cluster distances, and perform linear normalization on the coefficient of variation to obtain the collaborative difference index between all the energy consumption data sequences.

[0022] Preferably, obtaining the degree of abnormal energy consumption change between all the energy consumption data sequences according to the projected area of the energy consumption fitting surface on each coordinate plane of the N-dimensional coordinate system and the curvature of each data point on the N-dimensional curve includes:

[0023] Obtain the non-differentiable points on the N-dimensional curve, calculate the proportion of the number of all the non-differentiable points in the number of all the data points on the N-dimensional curve to obtain the instantaneous abnormal feature value;

[0024] Obtain the curvature of each data point in the N-dimensional curve, calculate the absolute value of the difference between the curvatures of every two adjacent data points in the N-dimensional curve, and use the average value of all the absolute values of the differences as the curvature change rate;

[0025] Obtain the projected area of the energy consumption fitting surface on each coordinate plane in the N-dimensional coordinate system, calculate the absolute value of the difference between every two of the projected areas to obtain the area difference, perform weighted summation on all the area differences and then perform linear normalization to obtain the data discreteness index;

[0026] Perform weighted summation on the instantaneous abnormal feature value, the curvature change rate and the data discreteness index to obtain the degree of abnormal energy consumption change between all the energy consumption data sequences.

[0027] Preferably, combining the energy consumption difference index and the abnormal degree of energy consumption change to perform abnormal management on the energy consumption data during the construction of the tunnel, including:

[0028] Performing weighted summation on the energy consumption difference index and the abnormal degree of energy consumption change to obtain the comprehensive energy consumption abnormality degree of all energy consumption data sequences;

[0029] Performing abnormal management on the energy consumption data during the construction of the tunnel according to the comprehensive energy consumption abnormality degree.

[0030] Preferably, the performing abnormal management on the energy consumption data during the construction of the tunnel according to the comprehensive energy consumption abnormality degree includes:

[0031] If the comprehensive energy consumption abnormality degree is greater than the preset comprehensive energy consumption abnormality degree threshold, it is determined that the energy consumption data during the construction of the tunnel is abnormal, and an abnormal energy consumption warning is given to the at least three energy-consuming devices.

[0032] In a second aspect, an embodiment of the present invention further provides a smart management system for tunnel construction energy consumption data, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements a smart management method for tunnel construction energy consumption data as described in the first aspect.

[0033] The beneficial effects of the embodiment of the present invention compared with the prior art are:

[0034] During the tunnel construction process, the present invention obtains the energy consumption data of at least three energy-consuming devices in real time, obtains the corresponding time series, linearly normalizes the data in each of the time series respectively to obtain the corresponding energy consumption data series; maps all the energy consumption data series into the same two-dimensional coordinate system, obtains the curve corresponding to each energy consumption data series, and fits all the energy consumption data series to obtain an energy consumption fitting curve. The abscissa of the two-dimensional coordinate system represents time, and the ordinate represents energy consumption data. According to the similarity between the curve corresponding to each energy consumption data series and the energy consumption fitting curve, and the collaborative difference between each energy consumption data series, an energy consumption difference index between all the energy consumption data series is obtained; maps all the energy consumption data series into the same N-dimensional coordinate system (N>2), fits the data in all the energy consumption data series to obtain an N-dimensional curve, and performs surface fitting on all the energy consumption data series to obtain an energy consumption fitting surface. The N coordinate axes of the N-dimensional coordinate system respectively represent the energy consumption data of each energy-consuming device. According to the projected area of the energy consumption fitting surface on each coordinate plane of the N-dimensional coordinate system and the curvature of each data point on the N-dimensional curve, the degree of abnormal energy consumption change between all the energy consumption data series is obtained; combining the energy consumption difference index and the degree of abnormal energy consumption change, abnormal management is carried out on the energy consumption data during the tunnel construction process. Among them, considering the synergistic effect between the energy consumption data of multiple energy-consuming devices during the tunnel construction process, the abnormal management of the energy consumption data during the tunnel construction process is carried out by combining the characteristics (energy consumption difference index) of the energy consumption data series corresponding to multiple energy-consuming devices in the two-dimensional space and the characteristics (degree of abnormal energy consumption change) in the N-dimensional space. Compared with the early warning method based on whether the energy consumption data of each energy-consuming device exceeds the threshold, the probability of missed reports is reduced, and at the same time, the probability of false reports due to the increase in the energy consumption data of a certain energy-consuming device caused by environmental factors and other factors while the actual energy consumption data is not abnormal is reduced, and the accuracy of abnormal identification of energy consumption data is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 It is a flowchart of a method for intelligent management of tunnel construction energy consumption data provided in Embodiment 1 of the present invention;

[0037] Figure 2Schematic diagram of curves of energy consumption data sequences corresponding to a shield machine, a ventilator, and a drainage pump provided in an embodiment of the present invention in a two-dimensional coordinate system;

[0038] Figure 3 Schematic diagram of curves of energy consumption data sequences corresponding to a shield machine, a ventilator, and a drainage pump provided in an embodiment of the present invention in a three-dimensional coordinate system. Detailed implementation manners

[0039] The embodiments of the present disclosure will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, in which the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0040] It should be noted that the terms "first", "second", etc. in the specification of the present disclosure and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0041] In order to illustrate the technical solution of the present invention, specific embodiments will be used for illustration below.

[0042] Refer to Figure 1 , which is a flowchart of a method for intelligent management of tunnel construction energy consumption data provided in Embodiment 1 of the present invention. As Figure 1 shown, the method may include:

[0043] Step S101, during the process of tunnel construction, obtain the energy consumption data of at least three energy-consuming devices in real time, obtain the corresponding time series, and linearly normalize the data in each of the time series respectively to obtain the corresponding energy consumption data sequences.

[0044] Tunnel construction is divided into stages such as the tunneling stage, the lining stage, and the restoration stage. Among them, the tunneling stage is the stage with the most equipment investment and the highest energy consumption. The energy-consuming devices in this stage include shield machines, ventilators, drainage pumps, air compressors, shotcrete machines, mobile substations, etc. These devices all operate at high load during the tunneling stage, and their energy consumption accounts for the vast majority of the total energy consumption of tunnel construction. Therefore, it is particularly important to effectively manage the construction energy consumption data in this stage.

[0045] In the traditional method, a fixed threshold is set for each energy-consuming device. When an energy-consuming device exceeds its corresponding fixed threshold, it is determined that the energy consumption data is abnormal during tunnel construction. However, there is a synergy effect among energy-consuming devices. For example, for a shield machine, a ventilation fan, and a drainage pump, in soft soil strata, the shield machine has a faster propulsion speed, and the demand for ventilation and drainage is also higher. While in hard rock strata, the propulsion speed is slower, and the demand for ventilation and drainage also decreases accordingly. Another example is an air compressor, a shotcreting machine, a rock bolt drilling rig, and a mobile substation. When the surrounding rock stability is poor, the workload of the shotcreting machine and the rock bolt drilling rig is large, and the air compressor needs to provide compressed air services for the shotcreting machine and the rock bolt drilling rig, so the energy consumption of the air compressor increases accordingly. At the same time, the mobile substation powers various devices, and its energy consumption also increases accordingly. The abnormal determination of energy consumption data in the traditional method ignores the synergy effect among energy-consuming devices, lacks systematicness and integrity, resulting in inaccurate abnormal determination of energy consumption data. Therefore, in the embodiments of the present invention, according to the synergy among various energy-consuming devices, the abnormal conditions of each energy-consuming device are determined to improve the accuracy of abnormal management of energy consumption data.

[0046] First, during tunnel construction, the energy consumption data of at least three energy-consuming devices are obtained in real time to obtain corresponding time series. In the embodiments of the present invention, taking a shield machine, a ventilation fan, and a drainage pump as an example, there is no limitation here, and the implementer can set according to the specific scenario. Then, the data in each time series are linearly normalized to obtain corresponding energy consumption data series to unify the dimension for subsequent analysis and processing. Among them, linear normalization is a prior art and will not be elaborated here.

[0047] Step S102, map all the energy consumption data series to the same two-dimensional coordinate system to obtain the curve corresponding to each energy consumption data series, and fit all the energy consumption data series to obtain an energy consumption fitting curve. The abscissa of the two-dimensional coordinate system represents time, and the ordinate represents energy consumption data. According to the similarity between the curve corresponding to each energy consumption data series and the energy consumption fitting curve, and the synergy difference between each energy consumption data series, an energy consumption difference index among all the energy consumption data series is obtained.

[0048] Considering that there is a certain correlation among the energy consumption data of the three energy-consuming devices, namely a shield machine, a ventilation fan, and a drainage pump, that is, the dust and heat generated by the shield machine will directly increase the ventilation load, and the energy consumption of the drainage pump will also increase significantly accordingly. And the two-dimensional curve is the curve of the energy consumption data of each energy-consuming device changing with time. Therefore, the energy consumption data series corresponding to the three energy-consuming devices, namely a shield machine, a ventilation fan, and a drainage pump, can be mapped to the same two-dimensional coordinate system to obtain the curves corresponding to the shield machine, the ventilation fan, and the drainage pump respectively, that is, the curve corresponding to each energy consumption data series. Among them, the abscissa of the two-dimensional coordinate system represents time, and the ordinate represents energy consumption data. Refer toFigure 2 It is a schematic diagram of an energy consumption curve in a two-dimensional coordinate system for the energy consumption data sequences corresponding to a shield machine, a ventilation fan, and a drainage pump. Figure 2 In it, the curve indicated by the shield machine is the curve of the energy consumption data sequence corresponding to the shield machine, the curve indicated by the ventilation fan is the curve of the energy consumption data sequence corresponding to the ventilation fan, and the curve indicated by the drainage pump is the curve of the energy consumption data sequence corresponding to the drainage pump. At the same time, the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, are subjected to polynomial curve fitting to obtain an energy consumption fitting curve, which is used to characterize the average energy consumption among the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump. Among them, polynomial curve fitting is a prior art and will not be elaborated here. Further, based on the similarity between the curve corresponding to each energy consumption data sequence and the energy consumption fitting curve, the abnormal degree of the energy consumption data is preliminarily determined to reduce the probability of false alarms caused by the growth of the energy consumption data of a certain energy-consuming device due to environmental and other factors while the actual energy consumption data is normal: the lower the similarity between the curves corresponding to the three energy-consuming devices and the energy consumption fitting curve, the more likely it is that the energy consumption data of at least one of the three energy-consuming devices is abnormal, indirectly reflecting a greater abnormal degree of the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump.

[0049] Since box plots can reveal outliers in the data, in the embodiments of the present invention, a box plot is constructed based on the data in all energy consumption data sequences (the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump), and the abnormal data in the energy consumption data sequences corresponding to the three energy-consuming devices is screened out through the box plot to improve the accuracy of the preliminary determination of the abnormal degree of the energy consumption data: the more the number of abnormal data, the greater the possibility that the energy consumption data is abnormal, indirectly reflecting a greater abnormal degree of the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump. Among them, the box plot is a prior art and will not be elaborated here.

[0050] Combining the similarity between the curves corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, and the energy consumption fitting curve, and the abnormal data in the energy consumption data sequences corresponding to the three energy-consuming devices, the data difference degree among the energy consumption data sequences corresponding to the three energy-consuming devices is obtained to preliminarily determine the abnormal degree of the energy consumption data. Specifically:

[0051] Calculate the DTW distance between the curve corresponding to each energy consumption data sequence and the energy consumption fitting curve respectively, perform weighted summation on all DTW distances and then perform linear normalization to obtain a first variable. Among them, the DTW distance is a prior art and will not be elaborated here;

[0052] Obtain the abnormal data in all energy consumption data sequences through a box plot, calculate the ratio between the number of all abnormal data and the number of all data in all energy consumption data sequences, and linearly normalize the ratio to obtain a second variable;

[0053] Perform weighted summation on the first variable and the second variable to obtain the degree of data difference between all energy consumption data sequences.

[0054] In an embodiment, the calculation formula for the degree of data difference between the energy consumption data sequences corresponding to the shield machine, the ventilator, and the drainage pump is:

[0055]

[0056] Among them, represents the degree of data difference between the energy consumption data sequences corresponding to the shield machine, the ventilator, and the drainage pump; represents the weight of the curve of the energy consumption data sequence corresponding to the i-th energy-consuming device. In the embodiment of the present invention, the shield machine is denoted as the 1st energy-consuming device, the ventilator is denoted as the 2nd energy-consuming device, and the drainage pump is denoted as the 3rd energy-consuming device. There is no limitation here, and the implementer can set it according to the specific scenario; represents the curve of the energy consumption data sequence corresponding to the i-th energy-consuming device; represents the energy consumption fitting curve; represents the DTW distance between the curve of the energy consumption data sequence corresponding to the i-th energy-consuming device and the energy consumption fitting curve; m represents the number of abnormal data; M represents the number of all data in all energy consumption data sequences; represents the weight; represents the linear normalization function.

[0057] It should be noted that is used to characterize the similarity between the curve corresponding to the i-th energy-consuming device and the energy consumption fitting curve. The larger it is, the lower the similarity between the curve corresponding to the i-th energy-consuming device and the energy consumption fitting curve, that is, the greater the difference between the energy consumption of the i-th energy-consuming device and the average energy consumption, and the greater the possibility that the energy consumption data of the i-th energy-consuming device is abnormal. Furthermore The larger it is, the greater the degree of abnormality of the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump; the larger m is, the more the number of abnormal data in the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump. Furthermore The larger it is, the greater the degree of abnormality of the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump. Since the shield machine is the main device among the three energy-consuming devices, and the ventilation fan has a stronger synergy with the shield machine than the drainage pump does with the shield machine, the weight corresponding to the shield machine is set to and the weight corresponding to the ventilation fan is set to and the weight corresponding to the drainage pump is set to That is, set , , . There is no limitation here, and the implementer can set it according to the specific scenario.

[0058] Also, considering that in a two-dimensional coordinate system, the intersection points between the curves corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, represent the intersection positions of the energy consumption data corresponding to these three energy-consuming devices during the change process. The more regular the distance between every two adjacent intersection points is, the more regular the change of the energy consumption data corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, is, and the stronger the synergy among these three energy-consuming devices during the data change process is, that is, the stronger the correlation among the energy consumption data corresponding to these three energy-consuming devices is, and thus indirectly reflects that the degree of abnormality of the energy consumption data corresponding to these three energy-consuming devices is smaller; on the contrary, if the difference in the distance between every two adjacent intersection points is larger, it indirectly reflects that the degree of abnormality of the energy consumption data corresponding to these three energy-consuming devices is larger. Therefore, in the embodiment of the present invention, the intersection points between the curves corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, are clustered to obtain at least two clusters, and the synergy difference index between all energy consumption data sequences is obtained according to the distance between every two clusters, so as to indirectly reflect the degree of abnormality of the energy consumption data corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump. Considering that the DBSCAN clustering can automatically divide the data points to be clustered into multiple clusters without the need to pre-specify the number of clusters, so in the embodiment of the present invention, the DBSCAN clustering algorithm is selected to cluster the intersection points between the curves corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump. The DBSCAN clustering algorithm is a prior art and will not be elaborated here. Then the specific process of obtaining the synergy difference index between the energy consumption data sequences corresponding to the shield machine, the ventilation fan, and the drainage pump is as follows:

[0059] For any two clusters, the clustering centers of the any two clusters are respectively obtained, and the Euclidean distance between the clustering centers of the any two clusters is calculated to obtain the inter-cluster distance between the any two clusters;

[0060] The inter-cluster distance between every two of the clusters is obtained, the coefficient of variation of all the inter-cluster distances is calculated, and the coefficient of variation is linearly normalized to obtain the synergy difference index between all energy consumption data sequences, denoted as The larger the coefficient of variation, the more uneven the distribution of all inter-cluster distances, that is, among all the intersections between the curves corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, the distances between every two adjacent intersections are more irregular. The smaller the synergy among these three energy-consuming devices during the data change process, and thus the larger the synergy difference index, the greater the degree of abnormality of the energy consumption data corresponding to these three energy-consuming devices. Here, the coefficient of variation is the prior art and will not be elaborated further.

[0061] Furthermore, by combining the degree of data difference and the synergy difference index, an energy consumption difference index between the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, is obtained to preliminarily determine the degree of abnormality of the energy consumption data. Specifically: Calculate the average value between the degree of data difference and the synergy difference index to obtain the energy consumption difference index between all energy consumption data sequences. Then, the calculation formula for the energy consumption difference index is:

[0062]

[0063] Wherein, represents the energy consumption difference index between the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump; represents the degree of data difference between the energy consumption data sequences corresponding to the shield machine, the ventilation fan, and the drainage pump; represents the synergy difference index between the energy consumption data sequences corresponding to the shield machine, the ventilation fan, and the drainage pump.

[0064] It should be noted that, the larger the , the greater the difference between the energy consumption of at least one of the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, and the average energy consumption, and the larger the number of abnormal data points in the energy consumption data sequences corresponding to these three energy-consuming devices. Thus, the larger the , the greater the degree of abnormality of the energy consumption data of these three energy-consuming devices; the larger the , the smaller the synergy among the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, during the data change process. Thus, the larger the , the greater the degree of abnormality of the energy consumption data of these three energy-consuming devices.

[0065] So far, through the analysis of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, in the two-dimensional coordinate system, the energy consumption difference index between the energy consumption data sequences corresponding to these three energy-consuming devices is obtained, and the degree of abnormality of the energy consumption data is preliminarily determined.

[0066] Step S103: Map all the energy consumption data sequences to the same N-dimensional coordinate system, fit the data in all the energy consumption data sequences to obtain an N-dimensional curve (N > 2), and perform surface fitting on all the energy consumption data sequences to obtain an energy consumption fitting surface. The N coordinate axes of the N-dimensional coordinate system respectively represent the energy consumption data of each energy-consuming device. According to the projected area of the energy consumption fitting surface on each coordinate plane of the N-dimensional coordinate system and the curvature of each data point on the N-dimensional curve, obtain the degree of abnormal energy consumption change between all the energy consumption data sequences.

[0067] Considering that if only the energy consumption data sequences corresponding to the three energy-consuming devices of the shield machine, the ventilation machine, and the drainage pump are analyzed in a two-dimensional space, that is, analyzing the energy consumption data sequences corresponding to the three energy-consuming devices of the shield machine, the ventilation machine, and the drainage pump in a two-dimensional coordinate system, it is impossible to comprehensively determine whether the energy consumption data is abnormal based on the cooperation of the three energy-consuming devices of the shield machine, the ventilation machine, and the drainage pump. Therefore, in the embodiments of the present invention, N-dimensional analysis (N > 2) is performed on the energy consumption data sequences corresponding to each energy-consuming device, that is, the energy consumption data sequences corresponding to each energy-consuming device are mapped to the same N-dimensional coordinate system to present the potential abnormal data in the energy consumption data sequences corresponding to the three energy-consuming devices of the shield machine, the ventilation machine, and the drainage pump from multiple angles, making the abnormal determination of the energy consumption data more accurate. Curve fitting is performed on the energy consumption data sequences corresponding to each energy-consuming device.

[0068] Since the embodiments of the present invention take the three energy-consuming devices of the shield machine, the ventilation machine, and the drainage pump as examples, in the embodiments of the present invention, three-dimensional analysis is performed on the energy consumption data sequences corresponding to these three energy-consuming devices, that is, the energy consumption data sequences corresponding to these three energy-consuming devices are mapped to the same three-dimensional coordinate system, and polynomial curve fitting is performed on the energy consumption data sequences corresponding to these three energy-consuming devices to obtain a three-dimensional curve. Among them, the three coordinate axes of the three-dimensional coordinate system respectively represent the energy consumption data of the three energy-consuming devices of the shield machine, the ventilation machine, and the drainage pump. Refer to Figure 3 , which is a schematic diagram of the curve of the energy consumption data sequences corresponding to a shield machine, a ventilation machine, and a drainage pump in a three-dimensional coordinate system, that is, an energy consumption three-dimensional space curve diagram. Figure 3 In, the curve in the three-dimensional coordinate system is the three-dimensional curve obtained by polynomial curve fitting of the energy consumption data sequences corresponding to the three energy-consuming devices of the shield machine, the ventilation machine, and the drainage pump. If the energy consumption data sequences corresponding to four selected energy-consuming devices are used, four-dimensional analysis needs to be performed on them, that is, the energy consumption data sequences corresponding to the four selected energy-consuming devices are mapped to the same four-dimensional coordinate system to obtain a four-dimensional curve, and so on.

[0069] Since there may be non - differentiable points in the N - dimensional curve, these non - differentiable points are often the cusps, breakpoints or turning points on the N - dimensional curve. These non - differentiable points are very likely to be outliers in the energy consumption data. The more the number of non - differentiable points, the greater the possibility that the energy consumption data is abnormal. At the same time, the difference between the curvatures of every two adjacent data points on the N - dimensional curve can reflect the regularity of the change of the energy consumption data. The greater the difference between the curvatures of every two adjacent data points on the N - dimensional curve, the more irregular the change of the energy consumption data, and thus the greater the possibility that the energy consumption data is abnormal, that is, the greater the degree of abnormality of the energy consumption data.

[0070] In order to judge the degree of abnormality of the energy consumption data according to the cooperation between each energy - consuming device in the N - dimensional coordinate system, in the embodiments of the present invention, the energy - consumption data sequences corresponding to each energy - consuming device are subjected to polynomial surface fitting to obtain an energy - consumption fitting surface. According to the projected areas of the energy - consumption fitting surface on each coordinate plane in the N - dimensional coordinate system, the cooperation between each energy - consuming device is reflected, and thus the degree of abnormality of the energy - consumption data is indirectly reflected: if the difference between the projected areas on every two coordinate planes is large, it indicates that the change difference of the energy - consumption data between the energy - consuming devices is greater, the cooperation between the energy - consuming devices is worse, and indirectly indicates that the energy - consumption data is likely to be abnormal, that is, the greater the degree of abnormality of the energy - consumption data. Among them, the polynomial fitting surface is the prior art and will not be elaborated here.

[0071] Therefore, in the embodiments of the present invention, according to the number of non - differentiable points and the curvature of each data point on the three - dimensional curve corresponding to the shield machine, the ventilator and the drainage pump, as well as the projected areas of the energy - consumption fitting surface on each coordinate plane in the three - dimensional coordinate system, the degree of abnormality of the energy - consumption change between the energy - consumption data sequences corresponding to the shield machine, the ventilator and the drainage pump is obtained to reflect the degree of abnormality of the energy - consumption data in the N - dimensional space. Specifically:

[0072] Use SymPy to implement the symbolic differentiation method, obtain the non - differentiable points on the N - dimensional curve through the symbolic differentiation method, calculate the proportion of the number of all non - differentiable points in the number of all data points on the N - dimensional curve to obtain the instantaneous anomaly eigenvalue. Among them, using SymPy to implement the symbolic differentiation method and obtaining non - differentiable points through the symbolic differentiation method are the prior art and will not be elaborated here;

[0073] Obtain the curvature of each data point in the N - dimensional curve, calculate the absolute value of the difference between the curvatures of every two adjacent data points in the N - dimensional curve, and take the average value of all absolute values of the differences as the curvature change rate;

[0074] Obtain the projected areas of the energy consumption fitting surface on each coordinate plane in the N-dimensional coordinate system, calculate the absolute value of the difference between every two of the projected areas to obtain the area difference, perform weighted summation on all the area differences and then perform linear normalization to obtain the data discreteness index;

[0075] Perform weighted summation on the instantaneous anomaly eigenvalue, the curvature change rate, and the data discreteness index to obtain the degree of anomaly in energy consumption change among all energy consumption data sequences.

[0076] In one embodiment, the formula for calculating the degree of anomaly in energy consumption change among the energy consumption data sequences corresponding to the shield machine, the ventilator, and the drainage pump is:

[0077]

[0078] wherein, represents the degree of anomaly in energy consumption change among the energy consumption data sequences corresponding to the shield machine, the ventilator, and the drainage pump; q represents the number of all non-differentiable points on the N-dimensional curve (a three-dimensional curve in the embodiment of the present invention); Q represents the number of all data points on the N-dimensional curve (a three-dimensional curve in the embodiment of the present invention); j represents the curvature of the j-th data point on the N-dimensional curve (a three-dimensional curve in the embodiment of the present invention); j + 1 represents the curvature of the (j + 1)-th data point on the N-dimensional curve (a three-dimensional curve in the embodiment of the present invention); represents the absolute value of the difference between the curvature of the j-th data point and the curvature of the (j + 1)-th data point on the N-dimensional curve (a three-dimensional curve in the embodiment of the present invention); N represents the number of energy-consuming devices to be analyzed (in the embodiment of the present invention, the three energy-consuming devices of the shield machine, the ventilator, and the drainage pump are selected), that is, the dimension of the N-dimensional coordinate system; S represents the number of absolute values of the differences between the projected areas on every two coordinate planes in the N-dimensional coordinate system, that is, the number of area differences. In the embodiment of the present invention, it is a three-dimensional coordinate system, and the number of area differences is 3; represents the -th area difference; represents the first weight; represents the second weight; represents the third weight; represents the -th weight corresponding to the area difference; represents the linear normalization function.

[0079] It should be noted that, is the instantaneous anomaly eigenvalue. The larger q is, the more non-differentiable points there are in the N-dimensional curve (a three-dimensional curve in the embodiment of the present invention), the more outliers there are in the energy consumption data, and the greater the possibility of anomalies in the energy consumption data. Consequently, the instantaneous anomaly eigenvalue is larger. The larger it is, the greater the degree of abnormality of the energy consumption data; That is the curvature change rate, The larger it is, the greater the change difference between the j-th data point and the (j + 1)-th data point on the N-dimensional curve (a three-dimensional curve in the embodiments of the present invention), the more irregular the change of the energy consumption data, and thus the larger the curvature change rate. The larger it is, the greater the degree of abnormality of the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump; That is the data discreteness index, The larger it is, it indicates that in the N-dimensional coordinate system (a three-dimensional coordinate system in the embodiments of the present invention), the difference between the projected areas on the two coordinate planes corresponding to the th area difference is larger, the change difference between the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, is larger, and the coordination among the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, is poorer. Thus, the data discreteness index is larger. The larger it is, the greater the degree of abnormality of the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump. Considering that the curvature change rate has a greater influence on the degree of abnormality of the energy consumption change, a larger weight is assigned to it, that is The set value is larger, so set , , There is no limitation here, and the implementer can set according to the specific scenario.

[0080] So far, through the analysis of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, in the N-dimensional coordinate system, the degree of abnormality of the energy consumption change among the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, is obtained. By combining it with the energy consumption difference index obtained from the analysis of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, in the two-dimensional space, it is more comprehensive to determine whether the energy consumption data is abnormal, and the accuracy of the abnormal management of the energy consumption data is improved.

[0081] Step S104, combining the energy consumption difference index and the degree of abnormality of the energy consumption change, perform abnormal management on the energy consumption data during the construction of the tunnel.

[0082] Combining the analysis of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, in the two-dimensional space and the N-dimensional space, the comprehensive degree of abnormality of the energy consumption of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, is obtained. That is, by combining the degree of abnormality of the energy consumption change and the energy consumption difference index, the comprehensive degree of abnormality of the energy consumption is obtained. Specifically:

[0083] The weighted sum of the energy consumption difference index and the abnormal degree of energy consumption change is calculated to obtain the comprehensive energy consumption abnormal degree of all energy consumption data sequences.

[0084] In an embodiment, the calculation formula for the comprehensive energy consumption abnormal degree of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump, is as follows:

[0085]

[0086] Wherein, represents the comprehensive energy consumption abnormal degree of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump; represents the energy consumption difference index of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump; represents the abnormal degree of energy consumption change of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump; represents the weight corresponding to the energy consumption difference index; represents the weight corresponding to the abnormal degree of energy consumption change.

[0087] It should be noted that, the larger is, the more the number of abnormal data points in the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump, and the worse the correlation of the energy consumption data of these three energy-consuming devices during the data change process. Furthermore, the larger is, the greater the abnormal degree of the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump; the larger is, the more the number of abnormal values in the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump, and the more irregular the change of the energy consumption data of these three energy-consuming devices in the N-dimensional space (in the embodiment of the present invention, it is a three-dimensional space). Furthermore, the larger

[0088] is, the greater the abnormal degree of the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump. It is set that Here, there is no limitation, and the implementer can set according to the specific scenario. Thus, the comprehensive energy consumption abnormal degree of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilator, and the drainage pump, is obtained. Furthermore, according to the comprehensive energy consumption abnormal degree Anomaly management is performed on the energy consumption data during tunnel construction. Compared with the early warning method based on whether the energy consumption data of each energy-consuming device exceeds the threshold, the probability of missed reports is reduced, and the accuracy of anomaly identification for energy consumption data is improved. A preset comprehensive energy consumption anomaly degree threshold is set to 0.6. There is no limitation here, and the implementer can set it according to the specific scenario. If the comprehensive energy consumption anomaly degree of the energy consumption data sequences corresponding to the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, then it is determined that during the tunnel construction process, the energy consumption data of the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, is abnormal. At the same time, an abnormal energy consumption early warning is issued for the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump, to notify the relevant staff to inspect and repair the three energy-consuming devices, namely the shield machine, the ventilation fan, and the drainage pump.

[0089] In summary, during the tunnel construction process, the present invention obtains the energy consumption data of at least three energy-consuming devices in real time, obtains the corresponding time series sequences, linearly normalizes the data in each of the time series sequences respectively to obtain the corresponding energy consumption data sequences; maps all the energy consumption data sequences to the same two-dimensional coordinate system, obtains the curve corresponding to each energy consumption data sequence, and fits all the energy consumption data sequences to obtain an energy consumption fitting curve. The abscissa of the two-dimensional coordinate system represents time, and the ordinate represents energy consumption data. According to the similarity between the curve corresponding to each energy consumption data sequence and the energy consumption fitting curve, and the collaborative difference between each energy consumption data sequence, an energy consumption difference index between all the energy consumption data sequences is obtained; maps all the energy consumption data sequences to the same N-dimensional coordinate system, fits the data in all the energy consumption data sequences to obtain an N-dimensional curve, where N is greater than 2, and performs surface fitting on all the energy consumption data sequences to obtain an energy consumption fitting surface. The N coordinate axes of the N-dimensional coordinate system respectively represent the energy consumption data of each energy-consuming device. According to the projected area of the energy consumption fitting surface on each coordinate plane of the N-dimensional coordinate system, and the curvature of each data point on the N-dimensional curve, the abnormal degree of energy consumption change between all the energy consumption data sequences is obtained; combining the energy consumption difference index and the abnormal degree of energy consumption change, anomaly management is performed on the energy consumption data during the tunnel construction process. Among them, considering the synergistic effect among the energy consumption data of multiple energy-consuming devices during the tunnel construction process, the energy consumption data during the tunnel construction process is managed anomalously by combining the characteristics of the energy consumption data sequences corresponding to multiple energy-consuming devices in the two-dimensional space (energy consumption difference index) and the characteristics in the N-dimensional space (abnormal degree of energy consumption change). Compared with the early warning method based on whether the energy consumption data of each energy-consuming device exceeds the threshold, the probability of missed reports is reduced, and at the same time, the probability of false alarms caused by the increase in the energy consumption data of a certain energy-consuming device due to environmental and other factors while the actual energy consumption data is normal is reduced, and the accuracy of anomaly identification for energy consumption data is improved.

[0090] Based on the same inventive concept as the above method, an embodiment of the present invention further provides a smart management system for tunnel construction energy consumption data, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above methods for smart management of tunnel construction energy consumption data are implemented.

[0091] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for intelligent management of tunnel construction energy consumption data, characterized in that: The method for intelligent management of tunnel construction energy consumption data comprises: During the tunnel construction process, energy consumption data of at least three energy-consuming devices are acquired in real time to obtain corresponding time series, and the data in each time series is linearly normalized to obtain corresponding energy consumption data series; Mapping all energy consumption data sequences to the same two-dimensional coordinate system, obtaining a curve corresponding to each of the energy consumption data sequences, and fitting all of the energy consumption data sequences to obtain an energy consumption fitting curve, wherein the abscissa of the two-dimensional coordinate system represents time, and the ordinate represents energy consumption data, and obtaining energy consumption difference indicators between all energy consumption data sequences based on the similarity between the curve corresponding to each of the energy consumption data sequences and the energy consumption fitting curve, and the synergy difference between each of the energy consumption data sequences; Map all energy consumption data sequences to the same N-dimensional coordinate system, and fit the data in all energy consumption data sequences to obtain an N-dimensional curve, where N is greater than 2, and perform surface fitting on all energy consumption data sequences to obtain an energy consumption fitting surface, where the N coordinate axes of the N-dimensional coordinate system respectively represent the energy consumption data of each of the energy consuming devices, and obtain the degree of abnormal energy consumption variation between all energy consumption data sequences according to the projected area of ​​the energy consumption fitting surface on each coordinate plane of the N-dimensional coordinate system and the curvature of each data point on the N-dimensional curve; Based on the energy consumption difference index and the abnormal degree of energy consumption change, abnormal management is performed on the energy consumption data of the tunnel during the construction process; The energy consumption difference index between all energy consumption data sequences is obtained based on the similarity between the curve corresponding to each energy consumption data sequence and the energy consumption fitting curve, and the synergy difference between each energy consumption data sequence, including: Calculating the DTW distance between the curve corresponding to each of the energy consumption data sequences and the energy consumption fitting curve respectively, performing linear normalization after weighted summation on all DTW distances, and obtaining a first variable; Obtain abnormal data in all energy consumption data sequences through a box plot, calculate the ratio between the number of all abnormal data and the number of all data in all energy consumption data sequences, and linearly normalize the ratio to obtain a second variable; Performing a weighted summation on the first variable and the second variable to obtain the degree of data difference between all energy consumption data sequences; Obtaining the intersection points between the curves corresponding to each of the energy consumption data sequences, clustering all the intersection points to obtain at least two clusters, and for any two clusters, respectively obtaining the cluster centers of the any two clusters, calculating the Euclidean distance between the cluster centers of the any two clusters, and obtaining the inter-cluster distance between the any two clusters; Obtaining the inter-cluster distance between every two of the clusters, calculating the coefficient of variation of all inter-cluster distances, linearly normalizing the coefficient of variation, and obtaining a synergy difference index between all energy consumption data sequences; The average value between the data difference degree and the synergy difference index is calculated to obtain the energy consumption difference index between all energy consumption data sequences.

2. A method for intelligent management of tunnel construction energy consumption data according to claim 1, characterized in that: The abnormal degree of energy consumption variation among all energy consumption data sequences is obtained according to the projection area of ​​the energy consumption fitting surface on each coordinate plane of the N-dimensional coordinate system and the curvature of each data point on the N-dimensional curve, including: Obtaining non-differentiable points on the N-dimensional curve, calculating the proportion of the number of all non-differentiable points in the number of all data points on the N-dimensional curve, and obtaining an instantaneous abnormal characteristic value; Obtaining the curvature of each data point in the N-dimensional curve, calculating the absolute value of the difference between the curvatures of every two adjacent data points in the N-dimensional curve, and taking the average value of all the absolute values ​​of the differences as the curvature change rate; Obtaining the projection area of ​​the energy consumption fitting surface on each coordinate plane in the N-dimensional coordinate system, calculating the absolute value of the difference between every two projection areas to obtain the area difference, performing weighted summation on all area differences and performing linear normalization to obtain a data discreteness index; The instantaneous abnormal characteristic value, the curvature change rate and the data discreteness index are weightedly summed to obtain the abnormal degree of energy consumption change between all energy consumption data sequences.

3. The method for intelligent management of tunnel construction energy consumption data according to claim 1, characterized in that: The combining the energy consumption difference index and the abnormal degree of energy consumption change to perform abnormal management on the energy consumption data of the tunnel during the construction process includes: Performing a weighted summation on the energy consumption difference index and the energy consumption change abnormality degree to obtain the comprehensive energy consumption abnormality degree of all energy consumption data sequences; The energy consumption data of the tunnel during construction is managed abnormally according to the degree of abnormal comprehensive energy consumption.

4. A method for intelligent management of tunnel construction energy consumption data according to claim 3, characterized in that: The abnormal management of the energy consumption data of the tunnel during the construction process according to the abnormal degree of the comprehensive energy consumption includes: If the comprehensive energy consumption abnormality level is greater than a preset comprehensive energy consumption abnormality level threshold, it is determined that the energy consumption data of the tunnel during construction is abnormal, and abnormal energy consumption warnings are issued for the at least three energy-consuming devices.

5. A tunnel construction energy consumption data intelligent management system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for intelligent management of tunnel construction energy consumption data as described in any one of claims 1-4 are implemented.

Images