Mining cable insulation on-line monitoring method and system based on decision tree

Abstract

The invention provides a mining cable insulation online monitoring method and system based on a decision tree, and belongs to the technical field of cable monitoring. The method comprises the following steps: performing decision sub-tree synthesis based on insulation characteristic parameters of the mining cable to obtain a plurality of decision sub-trees; wherein each decision sub-tree is synthesized by different insulation characteristic parameters; establishing a decision tree model based on each decision sub-tree; carrying out real-time synchronous sampling on the zero-sequence current and the zero-sequence voltage of the mining cable; and inputting the zero-sequence current and the zero-sequence voltage of the mining cable in a preset sampling time period into the decision tree model to obtain a mining cable insulation state monitoring judgment result. And step-by-step classification judgment from top to bottom is realized through a decision tree model method, so that a mining cable insulation state monitoring judgment result is quickly and effectively obtained, the purpose of classification judgment of mining cable insulation is realized, and the possibility of grounding or short-circuit faults of the cable is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of cable monitoring, and in particular to a decision tree-based online monitoring method for mining cable insulation, a decision tree-based online monitoring system for mining cable insulation, a machine-readable storage medium and an electronic device. Background Art

[0002] Mining cables are important energy transmission components of coal mine power supply systems. If the insulation status of mining cables cannot be monitored in real time, it is easy to cause unbalanced operation of coal mine power supply systems, affecting the reliability and safety level of coal mine power supply. In underground mines where gas and coal dust gather, the electric sparks generated at the moment when the cable insulation is broken down can easily cause explosion accidents and cause casualties in the mine. Therefore, from the perspective of coal mine power supply reliability and safety production, it is required to monitor the insulation status of mining cables in coal mine power supply systems in real time. However, for three-core mining cables with a voltage level of 6 / 10kV, the leakage current is small when the insulation deteriorates, and the signal characteristics are not obvious, which makes it difficult to accurately diagnose the insulation status. The actual application of existing cable insulation status diagnosis methods is not ideal, especially the lack of application experience in mining cables.

[0003] Coal mine cables have a variety of insulation states (for example: normal insulation, single-phase insulation deterioration, and two-phase insulation deterioration). Each insulation state is different, and the classification of insulation states is relatively complex. In view of the three-phase close grounding of the metal shielding layer of the mining cable and the inability of the existing insulation state diagnosis method to distinguish the insulation deterioration phase of the mining cable, how to quickly and effectively solve the complex classification of mining cable insulation is an urgent problem to be solved. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for online monitoring of mining cable insulation based on a decision tree, so as to at least solve the above-mentioned problem of how to quickly and effectively solve the complex classification of mining cable insulation.

[0005] In order to achieve the above object, the first aspect of the present invention provides a method for online monitoring of insulation of mining cables based on a decision tree, comprising: Based on the insulation characteristic parameters of the mining cable, decision subtrees are synthesized to obtain multiple decision subtrees; wherein each decision subtree is synthesized by different insulation characteristic parameters; Based on each decision subtree, a decision tree model is established; Real-time synchronous sampling of zero-sequence current and zero-sequence voltage of mining cables; The zero-sequence current and zero-sequence voltage of the mining cable within a preset sampling time period are input into the decision tree model to obtain the mining cable insulation status monitoring judgment result.

[0006] Optionally, the multiple decision subtrees include a cable insulation symmetry decision subtree, a single-phase insulation degradation diagnosis decision subtree, and a two-phase insulation degradation diagnosis decision subtree.

[0007] Optionally, the insulation characteristic parameters of the mining cable include the conductivity value and distributed capacitance value of the mining cable line; The establishment rules of the above cable insulation symmetry decision subtree include: Under the assumption that the insulation of all lines of the mining cable is symmetrical, it is determined that the insulation state of the mining cable satisfies the first differential equation; Synchronously sample the zero-sequence current and zero-sequence voltage of mining cables to obtain continuous data of multiple sampling points; Based on the midpoint method and the data of each sampling point, the first differential equation is arranged into a derivative form to obtain an overdetermined system of equations; Based on the overdetermined equations, the conductivity and distributed capacitance of the mining cable line are obtained; When the conductance value and the distributed capacitance value of the mining cable line are both positive values, it is determined that the assumption that the insulation of all lines of the mining cable is symmetrical is established, and the cable insulation state is judged based on the numerical value of the conductance value; wherein the cable insulation state includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level and the insulation state corresponding to the third insulation state level, the first insulation state level is higher than the second insulation state level, and the second insulation state level is higher than the third insulation state level; When the conductance and distributed capacitance of the mining cable line are negative, the assumption that the insulation of all mining cable lines is symmetrical is not valid, and the conclusion that the insulation of the mining cable line is asymmetrical is obtained; Based on the conclusion of the cable insulation state corresponding to the assumption being true and the insulation asymmetry of the mining cable line corresponding to the assumption being false, a cable insulation symmetry decision subtree is established.

[0008] Optionally, the process of establishing the above-mentioned overdetermined equations includes: Based on the matrix least squares method, the overdetermined equations are organized into a linear function.

[0009] Optionally, the establishment rules of the above single-phase insulation degradation diagnosis decision subtree include: Monitor zero-sequence current and calculate the change of zero-sequence current; According to the phase relationship between the zero-sequence current variation and the voltage to ground of each phase, the insulation deterioration phase of the mining cable line is determined; Synchronously sample the zero-sequence current and zero-sequence voltage of mining cables to obtain continuous data of multiple sampling points; Based on the second differential equation satisfied by the relationship between the data of each sampling point and the zero-sequence component of the single-phase insulation deteriorated line, the conductance value of each line of the mining cable is obtained; Based on the conductance values ​​of each line of the mining cable, a first total insulation conductance of the mining cable line is obtained; According to the insulation degradation phase of the mining cable line and the numerical value of the first total insulation conductance of the mining cable line, the single-phase insulation degradation state of the cable is judged; Comprehensively consider the cable single-phase insulation degradation status and establish a single-phase insulation degradation diagnosis decision subtree; The single-phase insulation degradation state of the cable includes the single-phase insulation degradation state of cable a phase, the single-phase insulation degradation state of cable b phase, the single-phase insulation degradation state of cable c phase and the two-phase insulation degradation state; The insulation degradation state of the single-phase a phase of the cable includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level that is decreased in the a phase insulation, and the insulation state corresponding to the third insulation state level that is decreased in the a phase insulation. The first insulation state level is higher than the second insulation state level, and the second insulation state level is higher than the third insulation state level. The insulation degradation state of the single-phase b phase of the cable includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level due to the insulation degradation of the b phase, and the insulation state corresponding to the third insulation state level due to the insulation degradation of the b phase; The single-phase insulation degradation state of phase c of the cable includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level when the insulation of phase c is degraded, and the insulation state corresponding to the third insulation state level when the insulation of phase c is degraded.

[0010] Optionally, the calculation process of the zero-sequence current variation includes: Get the interval time for Two zero-sequence current values; Based on the interval time The two zero-sequence current values ​​are subtracted to obtain the zero-sequence current change; among them, △t represents a sampling period, and N is a non-zero natural number.

[0011] Optionally, the establishment rules of the above two-phase insulation degradation diagnosis decision subtree include: According to the phase relationship between the zero-sequence current variation and the voltage to ground of each phase, the two-phase insulation deterioration phase of the mining cable line is determined; Based on the third differential equation satisfied by the relationship between the data of each sampling point and the zero-sequence component of the two-phase insulation deterioration line, the conductance value corresponding to the two-phase insulation degradation is obtained; Based on the conductance values ​​corresponding to the insulation degradation of the two phases, the second total insulation conductance of the mining cable line is obtained; Based on the two-phase insulation degradation phase of the mining cable line and the second total insulation conductance of the mining cable line, the two-phase insulation degradation state of the cable is judged; Comprehensively consider the insulation degradation status of two phases of the cable and establish a two-phase insulation degradation diagnosis decision subtree; The two-phase insulation degradation state of the cable includes the two-phase insulation degradation state of the cable ab, the two-phase insulation degradation state of the cable bc and the two-phase insulation degradation state of the cable ac; The insulation degradation state of the two-phase cable ab includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level when both phase a and phase b are degraded, and the insulation state corresponding to the third insulation state level when both phase a and phase b are degraded; The insulation degradation state of the cable bc double phase includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level when both the b phase and the c phase are degraded, and the insulation state corresponding to the third insulation state level when both the b phase and the c phase are degraded; The insulation degradation states of the two-phase AC cable include the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level when both phases A and C are degraded, and the insulation state corresponding to the third insulation state level when both phases A and C are degraded.

[0012] Optionally, the above-mentioned determining the two-phase insulation deterioration phase of the mining cable line according to the phase relationship between the zero-sequence current change and the voltage to ground of each phase includes: When the zero-sequence current variation is not in the same phase as any of the three-phase-to-ground voltages and is between two of the phases, the two phases between which the zero-sequence current variation is located are determined to be the two-phase insulation deteriorated phases of the mining cable line.

[0013] Optionally, the decision tree model is established based on each decision subtree, including: The associated attributes between the decision subtrees are connected to obtain a decision tree model; wherein the associated attributes represent the same and / or similar attributes between the decision subtrees.

[0014] A second aspect of the present invention provides a mining cable insulation online monitoring system based on a decision tree, comprising: A decision subtree synthesis module is used to synthesize decision subtrees based on the insulation characteristic parameters of the mining cable to obtain multiple decision subtrees; wherein each decision subtree is synthesized by different insulation characteristic parameters; A decision tree model building module is used to build a decision tree model based on each decision subtree; Synchronous sampling module, used for real-time synchronous sampling of zero-sequence current and zero-sequence voltage of mining cables; The insulation status monitoring module is used to input the zero-sequence current and zero-sequence voltage of the mining cable within a preset sampling time period into the decision tree model to obtain the insulation status monitoring judgment result of the mining cable.

[0015] In a third aspect of the present invention, a machine-readable storage medium is provided, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute the above-mentioned decision tree-based online monitoring method for mining cable insulation.

[0016] In a fourth aspect of the present invention, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the decision tree-based online monitoring method for mining cable insulation is implemented.

[0017] Through the above technical scheme, a method and system for online monitoring of mine cable insulation based on a decision tree is provided, which synthesizes multiple different decision subtrees according to the insulation characteristic parameters of the mine cable. The decision subtrees are connected to obtain a decision tree model. When the insulation state of the mine cable is monitored online, the zero-sequence current and zero-sequence voltage of the mine cable sampled synchronously in real time are input into the decision tree model, and the top-down step-by-step classification judgment is realized through the decision tree model method, so as to quickly and effectively obtain the monitoring judgment result of the mine cable insulation state, realize the purpose of classification judgment of the mine cable insulation, and reduce the possibility of grounding or short circuit failure of the cable. The method and system are real-time in the process of online monitoring of cable insulation, and dynamic monitoring can be realized. It is not affected by the neutral point grounding method of the system, and has a wide range of applications.

[0018] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a method for online monitoring insulation of mining cables based on a decision tree provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a cable insulation symmetry decision subtree provided by an embodiment of the present invention; Figure 3 It is a structural schematic diagram of a single-phase insulation degradation diagnosis decision subtree provided by an embodiment of the present invention; Figure 4 It is a structural schematic diagram of a two-phase insulation degradation diagnosis decision subtree provided by an embodiment of the present invention; Figure 5 It is a structural schematic diagram of a decision tree model provided by one embodiment of the present invention; Figure 6 The invention provides a block diagram of a mining cable insulation online monitoring system based on a decision tree according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0021] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0022] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] Figure 1 FIG. 1 is a flowchart of a method for online monitoring of insulation of mining cables based on a decision tree provided by an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a method for online monitoring of insulation of mining cables based on a decision tree, comprising: S110: synthesizing decision subtrees based on the insulation characteristic parameters of the mining cable to obtain multiple decision subtrees; wherein each decision subtree is synthesized by different insulation characteristic parameters; In some implementations of this embodiment, the above-mentioned multiple decision subtrees include a cable insulation symmetry decision subtree, a single-phase insulation degradation diagnosis decision subtree, and a two-phase insulation degradation diagnosis decision subtree.

[0024] Specifically, the basic condition for subtree synthesis is the existence of the same or similar attributes, and different decision subtrees are synthesized according to different insulation characteristic parameters. For example, according to the attribute of whether the insulation is symmetrical, a cable insulation symmetry decision subtree corresponding to the attribute of cable insulation symmetry can be synthesized, as well as a single-phase insulation degradation diagnosis decision subtree and a two-phase insulation degradation diagnosis decision subtree corresponding to the attribute of cable insulation asymmetry. Both single-phase insulation degradation and two-phase insulation degradation belong to the insulation asymmetry type.

[0025] S120: Building a decision tree model based on each decision subtree; In some implementations of this embodiment, the above-mentioned establishment of a decision tree model based on each decision subtree includes: connecting the associated attributes between each decision subtree to obtain a decision tree model; wherein the associated attributes represent the same and / or similar attributes between the decision subtrees.

[0026] Specifically, by connecting the same and / or similar attributes between decision subtrees, a complete decision tree, namely a decision tree model, can be obtained.

[0027] S130: Real-time synchronous sampling of zero-sequence current and zero-sequence voltage of mining cables; S140: Inputting the zero-sequence current and zero-sequence voltage of the mining cable within a preset sampling time period into a decision tree model to obtain a monitoring and judgment result of the mining cable insulation status.

[0028] Specifically, the method synthesizes a plurality of different decision subtrees according to the insulation characteristic parameters of the mining cable. The decision subtrees are connected to obtain a decision tree model. When the insulation state of the mining cable is monitored online, the zero-sequence current and zero-sequence voltage of the mining cable sampled synchronously in real time are input into the decision tree model, and the decision tree model method is used to realize the top-down classification judgment, so as to quickly and effectively obtain the monitoring judgment result of the insulation state of the mining cable, realize the purpose of classification judgment of the insulation of the mining cable, and reduce the possibility of grounding or short circuit failure of the cable. The method is real-time for the online monitoring process of cable insulation, and dynamic monitoring can be realized. It is not affected by the neutral point grounding method of the system, and has a wide range of applications.

[0029] It should be noted that the structure of the decision tree contains a root node, a group of internal nodes and a group of leaf nodes. The topmost node is called the root node (the root node has no incoming edges and multiple outgoing edges), the internal nodes (the internal nodes have one incoming edge and multiple outgoing edges) represent the test conditions, the branches represent the test results, and the classification conclusion is obtained at the leaf nodes (the leaf nodes have one incoming edge and no outgoing edges).

[0030] Please refer to Figure 2 , Figure 2It is a structural schematic diagram of a cable insulation symmetry decision subtree provided by an embodiment of the present invention. In some embodiments of the present embodiment, the insulation characteristic parameters of the above-mentioned mining cable include the conductance value and distributed capacitance value of the mining cable line; the establishment rules of the above-mentioned cable insulation symmetry decision subtree include: under the assumption that the insulation of all lines of the mining cable is symmetrical, determine that the insulation state of the mining cable satisfies the first differential equation; synchronously sample the zero-sequence current and zero-sequence voltage of the mining cable to obtain continuous multiple sampling point data; based on the midpoint method and the data of each sampling point, organize the first differential equation into a derivative form to obtain an overdetermined set of equations; based on the overdetermined set of equations, obtain the conductance value and distributed capacitance value of the mining cable line; when the conductance value and distributed capacitance value of the mining cable line are both positive, determine the insulation state of all lines of the mining cable. The assumption of symmetry is established, and the cable insulation state is judged based on the numerical value of the conductance value; wherein, the cable insulation state includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level and the insulation state corresponding to the third insulation state level, the first insulation state level is higher than the second insulation state level, and the second insulation state level is higher than the third insulation state level; when the conductance value and the distributed capacitance value of the mining cable line have negative values, it is determined that the assumption that the insulation of all lines of the mining cable is symmetric is not established, and it is concluded that the insulation of the mining cable line is asymmetric; based on the cable insulation state corresponding to the assumption and the conclusion of the insulation asymmetry of the mining cable line corresponding to the assumption not being established, a cable insulation symmetry decision subtree is established.

[0031] exist Figures 2 to 5 In the figure, w1 represents good insulation, w2 represents insulation degradation requiring moderate attention, and w3 represents insulation degradation requiring high attention. The insulation state corresponding to the first insulation state level represents good insulation, the insulation state corresponding to the second insulation state level represents insulation degradation requiring moderate attention, and the insulation state corresponding to the third insulation state level represents insulation degradation requiring high attention.

[0032] In some implementations of this embodiment, the process of establishing the above-mentioned overdetermined equation system includes: based on the least squares method of the matrix, the overdetermined equation system is sorted into a linear function Specifically, due to the data acquisition error of the transformer, there are rounding errors in the zero-sequence voltage and zero-sequence current values ​​during the computer data processing, and the interference and other problems in the system cause the calculation results to deviate from the theoretical values. In order to reduce the errors in the calculation results caused by the above reasons, the principle of least squares method is used in matrix calculation, and the parameter values ​​that make the overdetermined equations as valid as possible are taken as the calculation results.

[0033] Specifically, the process of establishing the cable insulation symmetry decision subtree is as follows: before the insulation state of the cable is determined, it is assumed that the insulation of all lines of the cable is symmetrical and satisfies the first differential equation: (1); where i i Represents the zero sequence current of the cable line Li, C i represents the zero-sequence capacitance of the cable line Li, u0 represents the zero-sequence voltage of the cable line Li, the subscript i represents the cable line Li, G i Represents the zero-sequence impedance of the cable line Li; synchronous sampling is performed for the zero-sequence current and zero-sequence voltage in formula (1), and multiple points are collected continuously. The midpoint method is used to calculate the derivative of the zero-sequence current, which can reduce the calculation error. The formula is: (2); where k represents the kth acquisition point, is the step length. According to the principle of infinite approximation of derivatives, the smaller the step length, the better. However, when Very small, because and Very close, direct subtraction will cause serious loss of effective figures. Therefore, from the perspective of rounding error, It should not be too small. Therefore, a suitable step size must be selected to minimize the derivative error. Then k groups of data are selected at equal intervals. When the sampling frequency is high, in order to reduce the impact of the rounding error of the sampling data, the interval of the selected data should be larger. The overdetermined equations established by the selected data are: (3); where n represents the serial number of the cable line, k represents the number of data groups selected at equal intervals, and k>2. Theoretically, the solution to the equation group (3) is unique and accurate, but due to the data acquisition error of the transformer, there are rounding errors in the zero-sequence voltage and zero-sequence current values ​​during the computer data processing, and there are interference problems in the system, which makes the calculation results deviate from the theoretical values. In order to reduce the errors in the calculation results caused by the above reasons, the principle of least squares method is used in matrix calculation, and the parameter values ​​that make the equation group as valid as possible are taken as the calculation results. (4); If the cable line insulation is symmetrical, the assumption is valid, and the conductance value and distributed capacitance value of the cable line can be calculated, and the cable insulation can be judged to be in a good or symmetrically degraded state based on the conductance value; on the contrary, if the cable line insulation is asymmetrical, the assumption is not valid, that is, the actual zero-sequence equivalent circuit relationship of the line does not satisfy equation (1). At this time, the calculated conductance value and distributed capacitance value have negative values, and it can be judged that the line insulation is asymmetrical. Its decision subtree is as follows Figure 2 shown.

[0034] Please refer to Figure 3 , Figure 3It is a structural schematic diagram of a single-phase insulation degradation diagnosis decision subtree provided by an embodiment of the present invention. In some embodiments of the present embodiment, the establishment rules of the above-mentioned single-phase insulation degradation diagnosis decision subtree include: monitoring zero-sequence current and calculating the zero-sequence current change; determining the insulation degradation phase of the mining cable line according to the phase relationship between the zero-sequence current change and the voltage to ground of each phase; synchronously sampling the zero-sequence current and zero-sequence voltage of the mining cable to obtain continuous multiple sampling point data; based on the second differential equation satisfied by the relationship between each sampling point data and the zero-sequence component of the single-phase insulation degradation line, obtaining the conductance value of each line of the mining cable; based on the conductance value of each line of the mining cable, obtaining the first total insulation conductance of the mining cable line; judging the single-phase insulation degradation state of the cable according to the numerical values ​​of the insulation degradation phase of the mining cable line and the first total insulation conductance of the mining cable line; comprehensively considering the single-phase insulation degradation state of the cable, establishing a single-phase insulation degradation diagnosis decision subtree; wherein, the single-phase insulation degradation state of the cable includes the single-phase insulation degradation state of cable phase a , the single-phase insulation degradation state of cable phase b, the single-phase insulation degradation state of cable phase c and the two-phase insulation degradation state; the single-phase insulation degradation state of cable phase a includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level with insulation degradation of phase a, and the insulation state corresponding to the third insulation state level with insulation degradation of phase a, the first insulation state level is higher than the second insulation state level, and the second insulation state level is higher than the third insulation state level; the single-phase insulation degradation state of cable phase b includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level with insulation degradation of phase b, and the insulation state corresponding to the third insulation state level with insulation degradation of phase b; the single-phase insulation degradation state of cable phase c includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level with insulation degradation of phase c, and the insulation state corresponding to the third insulation state level with insulation degradation of phase c.

[0035] In some implementations of this embodiment, the above-mentioned calculation process of the zero-sequence current variation includes: obtaining the interval time as Two zero-sequence current values; based on the interval time The two zero-sequence current values ​​are subtracted to obtain the zero-sequence current change; wherein, △t represents a sampling period, and N is a non-zero natural number.

[0036] Specifically, during the operation of the cable, the insulation state of the cable always changes from good to suddenly deteriorated in one or two phases. For a cable with single-phase insulation deterioration in phase a, before the insulation deteriorates asymmetrically, its zero-sequence current is ( is the system zero-sequence voltage before insulation degradation of line Lj occurs), after asymmetric insulation degradation occurs, its zero-sequence current is Therefore, the change in zero-sequence current before and after cable insulation degradation is: (5); where Y j represents the admittance of line Lj, ​​U0 represents the system zero-sequence voltage after insulation degradation of line Lj, ​​and U a represents the phase voltage of the degraded phase a, and Gxj represents the equivalent conductance of the degraded phase a. Before and after the asymmetric insulation degradation of the cable occurs, the change of zero-sequence voltage is small, and , so the change of zero-sequence voltage is ignored, that is, (6); where is the voltage of phase a to ground. From formula (6), it can be seen that the change of zero-sequence current is in phase with the voltage of the degraded phase to ground. Therefore, the insulation deterioration phase of the cable line can be selected according to the phase relationship between the change of zero-sequence current and the voltage of each phase to ground. It should be noted that since the waveform of zero-sequence current changes suddenly at the moment of insulation degradation, the current vector value in one cycle from the moment of waveform change is unstable and has no reference. Therefore, when calculating the zero-sequence current phase difference, When Subtract the two phasor values ​​of . The value of If it is not 0 and remains unchanged during the time period, the phase value of the phase difference is compared with the voltage phase of each phase to the ground to determine the degraded phase. The relationship between the zero-sequence components of the single-phase insulation degraded line satisfies the second differential equation: (7); where i j Represents the zero sequence current of the cable line Lj, ​​C j Represents the zero-sequence capacitance of the cable line Lj, ​​G j Represents the zero-sequence admittance of the cable line Lj, ​​and the subscript j represents the cable line Lj. By synchronously collecting k sets of data at equal intervals, the insulation parameters of the line can be obtained: (8); where , , The total insulation conductance of line Lj is the sum of all conductance values: (9). According to the value of the line parameters, the degree of cable single-phase insulation degradation is determined. The decision subtree formed by the cable single-phase insulation diagnosis is as follows: Figure 3 shown.

[0037] Please refer to Figure 4 , Figure 4It is a structural schematic diagram of a two-phase insulation degradation diagnosis decision subtree provided by an embodiment of the present invention. In some embodiments of the present embodiment, the establishment rules of the above-mentioned two-phase insulation degradation diagnosis decision subtree include: determining the two-phase insulation degradation phase of the mining cable line based on the phase relationship between the zero-sequence current change and the voltage to ground of each phase; obtaining the conductance value corresponding to the two-phase insulation degradation based on the third differential equation satisfied by the relationship between the data of each sampling point and the zero-sequence component of the two-phase insulation degradation line; obtaining the second total insulation conductance of the mining cable line based on the conductance value corresponding to the two-phase insulation degradation; judging the two-phase insulation degradation state of the mining cable line based on the two-phase insulation degradation phase of the mining cable line and the second total insulation conductance of the mining cable line; comprehensively considering the two-phase insulation degradation state of the cable, establishing a two-phase insulation degradation diagnosis decision subtree; wherein, the two-phase insulation degradation state of the cable includes the insulation degradation state of the two-phase ab of the cable, the insulation degradation state of the two-phase bc of the cable, and the insulation degradation state of the two-phase insulation degradation ... The insulation degradation state and the two-phase insulation degradation state of the cable AC; the two-phase insulation degradation state of the cable AB includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level that both phases a and b have declined, and the insulation state corresponding to the third insulation state level that both phases a and b have declined; the two-phase insulation degradation state of the cable bc includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level that both phases b and c have declined, and the insulation state corresponding to the third insulation state level that both phases b and c have declined; the two-phase insulation degradation state of the cable AC includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level that both phases a and c have declined, and the insulation state corresponding to the third insulation state level that both phases a and c have declined.

[0038] In some implementations of the present embodiment, the above-mentioned determination of the two-phase insulation deterioration phase of the mining cable line based on the phase relationship between the zero-sequence current change and the voltage to ground of each phase includes: when the zero-sequence current change is not in the same phase as any of the three-phase voltage to ground and is between two of the phases, determining that the two phases between which the zero-sequence current change is located are the two-phase insulation deterioration phases of the mining cable line.

[0039] Specifically, the analysis is carried out by taking the insulation degradation of phases a and b as an example. Before and after the insulation of the cable deteriorates in two phases, the change in line zero-sequence current is: (10); where Gxja represents the equivalent conductance of phase a of cable line Lj, ​​Gxjb represents the equivalent conductance of phase b of cable line Lj, ​​and U b represents the phase voltage of the degraded phase b. It can be seen from formula (10) that if the zero-sequence current change of the cable is If the phase is not the same as any of the three-phase voltages to ground, but is between two phases, it is determined that the insulation of two phases of the cable line has deteriorated, and the two phases can be determined to be the corresponding deteriorated phases. At this time, the relationship between the zero-sequence component of the cable line and the line parameters satisfies the third differential equation: (11); where is the voltage of phase b to ground. Through matrix calculation, the insulation parameters of the cable are: (12); where , , At this time, the insulation conductance values ​​of phases a and b and the total conductance value of the line are: (13), G ja Represents the insulation conductivity value of phase a, G jb Represents the insulation conductivity value of phase b, G j∑ represents the total conductance value. In addition, when there is a downstream cable feeder in the line, the zero-sequence current in equations (7) and (11) should be the zero-sequence current of the cable minus the zero-sequence current of all downstream feeders, that is, (in i j0 is the zero-sequence current of line Lj, i jm is the zero-sequence current of the next-level line of line Lj, k is the number of next-level lines). The insulation degree of each phase of the cable is determined based on the calculated cable insulation parameter values. The decision subtree for the diagnosis of two-phase cable insulation degradation is as follows: Figure 4 shown.

[0040] Please refer to Figure 5 , Figure 5 It is a structural schematic diagram of a decision tree model provided by an embodiment of the present invention. The basic condition for subtree synthesis is the existence of the same or similar attributes. In the above three subtrees (i.e., the cable insulation symmetry decision subtree, the single-phase insulation degradation diagnosis decision subtree, and the two-phase insulation degradation diagnosis decision subtree), single-phase insulation degradation and two-phase insulation degradation both belong to the insulation asymmetry type, and the method for judging whether the cable belongs to single-phase or two-phase insulation degradation is the phase relationship between the zero-sequence current transformation amount and each relative voltage to the ground. The three subtrees meet the synthesis conditions, so the three subtrees can be synthesized into a decision tree. The associated attributes of the three subtrees are connected to obtain a complete decision tree.

[0041] Figure 6 FIG. 1 is a block diagram of an online monitoring system for insulation of mining cables based on a decision tree provided by an embodiment of the present invention. Figure 6 As shown, an embodiment of the present invention provides an online monitoring system for insulation of mining cables based on a decision tree, comprising: A decision subtree synthesis module is used to synthesize decision subtrees based on the insulation characteristic parameters of the mining cable to obtain multiple decision subtrees; wherein each decision subtree is synthesized by different insulation characteristic parameters; A decision tree model building module is used to build a decision tree model based on each decision subtree; Synchronous sampling module, used for real-time synchronous sampling of zero-sequence current and zero-sequence voltage of mining cables; The insulation status monitoring module is used to input the zero-sequence current and zero-sequence voltage of the mining cable within a preset sampling time period into the decision tree model to obtain the insulation status monitoring judgment result of the mining cable.

[0042] Specifically, the system synthesizes multiple different decision subtrees according to the insulation characteristic parameters of mining cables. The decision subtrees are connected to obtain a decision tree model. When the insulation status of mining cables is monitored online, the zero-sequence current and zero-sequence voltage of the mining cables sampled synchronously in real time are input into the decision tree model, and the decision tree model method is used to implement top-down classification judgment, so as to quickly and effectively obtain the monitoring and judgment results of the insulation status of mining cables, achieve the purpose of classification and judgment of mining cable insulation, and reduce the possibility of grounding or short circuit failure of the cable. The system's online monitoring process of cable insulation is real-time and dynamic monitoring can be realized. It is not affected by the neutral point grounding method of the system and has a wide range of applications.

[0043] The optional implementation modes of the embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above implementation modes. Within the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical scheme of the embodiments of the present invention, and these simple modifications all belong to the protection scope of the embodiments of the present invention.

[0044] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0045] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0046] In addition, various implementation modes of the embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed by the embodiments of the present invention.

Claims

1. A method for online monitoring of mining cable insulation based on a decision tree, characterized in that: include: Based on the insulation characteristic parameters of the mining cable, decision subtrees are synthesized to obtain multiple decision subtrees; wherein each decision subtree is synthesized by different insulation characteristic parameters; Based on each decision subtree, a decision tree model is established; Real-time synchronous sampling of zero-sequence current and zero-sequence voltage of mining cables; The zero-sequence current and zero-sequence voltage of the mining cable within a preset sampling time period are input into the decision tree model to obtain the mining cable insulation status monitoring judgment result.

2. The online monitoring method for mining cable insulation based on decision tree according to claim 1 is characterized in that: The multiple decision subtrees include a cable insulation symmetry decision subtree, a single-phase insulation degradation diagnosis decision subtree, and a two-phase insulation degradation diagnosis decision subtree.

3. The online monitoring method for mining cable insulation based on decision tree according to claim 2 is characterized in that: The insulation characteristic parameters of the mining cable include the conductivity value and distributed capacitance value of the mining cable line; The establishment rules of the cable insulation symmetry decision subtree include: Under the assumption that the insulation of all lines of the mining cable is symmetrical, it is determined that the insulation state of the mining cable satisfies the first differential equation; Synchronously sample the zero-sequence current and zero-sequence voltage of mining cables to obtain continuous data of multiple sampling points; Based on the midpoint method and the data of each sampling point, the first differential equation is arranged into a derivative form to obtain an overdetermined system of equations; Based on the overdetermined equations, the conductivity and distributed capacitance of the mining cable line are obtained; When the conductance value and the distributed capacitance value of the mining cable line are both positive values, it is determined that the assumption that the insulation of all lines of the mining cable is symmetrical is established, and the cable insulation state is judged based on the numerical value of the conductance value; wherein the cable insulation state includes an insulation state corresponding to a first insulation state level, an insulation state corresponding to a second insulation state level, and an insulation state corresponding to a third insulation state level, the first insulation state level is higher than the second insulation state level, and the second insulation state level is higher than the third insulation state level; When the conductance and distributed capacitance of the mining cable line are negative, the assumption that the insulation of all mining cable lines is symmetrical is not valid, and the conclusion that the insulation of the mining cable line is asymmetrical is obtained; Based on the conclusion of the cable insulation state corresponding to the assumption being true and the insulation asymmetry of the mining cable line corresponding to the assumption being false, a cable insulation symmetry decision subtree is established.

4. The method for online monitoring of mining cable insulation based on decision tree according to claim 3 is characterized in that: The process of establishing the overdetermined equations includes: Based on the matrix least square method, the overdetermined equations are sorted into a linear function.

5. The method for online monitoring of mining cable insulation based on decision tree according to claim 2, characterized in that: The establishment rules of the single-phase insulation degradation diagnosis decision subtree include: Monitor zero-sequence current and calculate the change of zero-sequence current; According to the phase relationship between the zero-sequence current variation and the voltage to ground of each phase, the insulation deterioration phase of the mining cable line is determined; Synchronously sample the zero-sequence current and zero-sequence voltage of mining cables to obtain continuous data of multiple sampling points; Based on the second differential equation satisfied by the relationship between the data of each sampling point and the zero-sequence component of the single-phase insulation deteriorated line, the conductance value of each line of the mining cable is obtained; Based on the conductance values ​​of each line of the mining cable, a first total insulation conductance of the mining cable line is obtained; According to the insulation degradation phase of the mining cable line and the numerical value of the first total insulation conductance of the mining cable line, the single-phase insulation degradation state of the cable is judged; Comprehensively consider the cable single-phase insulation degradation status and establish a single-phase insulation degradation diagnosis decision subtree; The single-phase insulation degradation state of the cable includes the single-phase insulation degradation state of cable a phase, the single-phase insulation degradation state of cable b phase, the single-phase insulation degradation state of cable c phase and the two-phase insulation degradation state; The single-phase insulation degradation state of phase a of the cable includes an insulation state corresponding to a first insulation state level, an insulation state corresponding to a second insulation state level due to insulation degradation of phase a, and an insulation state corresponding to a third insulation state level due to insulation degradation of phase a, wherein the first insulation state level is higher than the second insulation state level, and the second insulation state level is higher than the third insulation state level; The insulation degradation state of the single-phase b phase of the cable includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level due to the insulation degradation of the b phase, and the insulation state corresponding to the third insulation state level due to the insulation degradation of the b phase; The single-phase insulation degradation state of phase C of the cable includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level due to the insulation degradation of phase C, and the insulation state corresponding to the third insulation state level due to the insulation degradation of phase C.

6. The method for online monitoring of mining cable insulation based on decision tree according to claim 5, characterized in that: The calculation process of the zero-sequence current variation includes: Get the interval time for Two zero-sequence current values; Based on the interval time The two zero-sequence current values ​​are subtracted to obtain the zero-sequence current change; among them, △t represents a sampling period, and N is a non-zero natural number.

7. The method for online monitoring of mining cable insulation based on decision tree according to claim 5, characterized in that: The establishment rules of the two-phase insulation degradation diagnosis decision subtree include: According to the phase relationship between the zero-sequence current variation and the voltage to ground of each phase, the two-phase insulation deterioration phase of the mining cable line is determined; Based on the third differential equation satisfied by the relationship between the data of each sampling point and the zero-sequence component of the two-phase insulation deterioration line, the conductance value corresponding to the two-phase insulation degradation is obtained; Based on the conductance values ​​corresponding to the insulation degradation of the two phases, the second total insulation conductance of the mining cable line is obtained; Based on the two-phase insulation degradation phase of the mining cable line and the second total insulation conductance of the mining cable line, the two-phase insulation degradation state of the cable is judged; Comprehensively consider the insulation degradation status of two phases of the cable and establish a two-phase insulation degradation diagnosis decision subtree; The two-phase insulation degradation state of the cable includes the two-phase insulation degradation state of the cable ab, the two-phase insulation degradation state of the cable bc and the two-phase insulation degradation state of the cable ac; The insulation degradation state of the two-phase cable ab includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level when both phase a and phase b are degraded, and the insulation state corresponding to the third insulation state level when both phase a and phase b are degraded; The cable bc two-phase insulation degradation state includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level when both the b phase and the c phase are degraded, and the insulation state corresponding to the third insulation state level when both the b phase and the c phase are degraded; The cable AC two-phase insulation degradation state includes the insulation state corresponding to the first insulation state level, the insulation state corresponding to the second insulation state level when both phases a and c are degraded, and the insulation state corresponding to the third insulation state level when both phases a and c are degraded.

8. The method for online monitoring of mining cable insulation based on decision tree according to claim 7, characterized in that: Determining the two-phase insulation degradation phase of the mining cable line according to the phase relationship between the zero-sequence current variation and the voltage to ground of each phase includes: When the zero-sequence current variation is not in the same phase as any of the three-phase-to-ground voltages and is between two of the phases, the two phases between which the zero-sequence current variation is located are determined to be the two-phase insulation deteriorated phases of the mining cable line.

9. The method for online monitoring of mining cable insulation based on decision tree according to claim 1, characterized in that: The step of establishing a decision tree model based on each decision subtree includes: The associated attributes between the decision subtrees are connected to obtain a decision tree model; wherein the associated attributes represent the same and / or similar attributes between the decision subtrees.

10. A mining cable insulation online monitoring system based on a decision tree, characterized in that: include: A decision subtree synthesis module is used to synthesize decision subtrees based on the insulation characteristic parameters of the mining cable to obtain multiple decision subtrees; wherein each decision subtree is synthesized by different insulation characteristic parameters; A decision tree model building module is used to build a decision tree model based on each decision subtree; Synchronous sampling module, used for real-time synchronous sampling of zero-sequence current and zero-sequence voltage of mining cables; The insulation status monitoring module is used to input the zero-sequence current and zero-sequence voltage of the mining cable within a preset sampling time period into the decision tree model to obtain the insulation status monitoring judgment result of the mining cable.

11. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the online monitoring method for insulation of mining cables based on a decision tree as described in any one of claims 1 to 9.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the decision tree-based online monitoring method for insulation of mining cables according to any one of claims 1 to 9 is implemented.

Images