Cable well cable abnormal heating identification method and system based on temperature rise

Abstract

The invention discloses a temperature rise-based cable well cable abnormal heating identification method and system, and belongs to the technical field of power cables. The method comprises the following steps: acquiring temperature data of a cable line in an elevator shaft to obtain a temperature data set; the temperature data set is preprocessed, temperature differences in the temperature data set are unified, abnormal values are removed, the lengths of all temperature measurement nodes are unified, and a unified temperature array set is obtained; solving a temperature rise trend in the unified temperature array set to obtain a temperature rise trend data set; solving a heating fault weight of the temperature measurement node according to the temperature rise trend data set; and when the heating fault weight of the temperature measurement node exceeds a set threshold value, determining that the cable is abnormally heated, thereby realizing cable abnormal heating identification of the temperature rise cable well. According to the invention, a large amount of temperature measurement data transmitted by the cable well can be effectively utilized and analyzed, and abnormal heating identification is carried out after effective data is extracted, so that the fault identification efficiency and accuracy of the cable well are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power cables, and in particular relates to a method and system for identifying abnormal heating of cables in cable wells based on temperature rise. Background Art

[0002] The cables in the cable well are monitored during operation through daily patrols by the on-duty personnel, which is a single method and cannot be observed directly. It is difficult to detect fires or unsafe hidden dangers in the operation of the cables in a timely manner. Cable trench fires are highly concealed, have a large impact range, and take a long time to repair and restore. Once they occur, they may cause serious consequences. In addition to damaging the cables, cable fires may also cause equipment tripping, load reduction, and even harm to firefighters. Not only will it cause serious losses to the economy, but it will also disrupt the normal life and production order of the majority of residents and enterprises. It is urgent to study reliable methods for determining hidden faults such as heating of cables in cable wells.

[0003] Currently, the methods for diagnosing power cable degradation and abnormality are mainly divided into offline detection and online monitoring.

[0004] Commonly used methods for off-line detection include impedance method, traveling wave method and regular preventive insulation tests. These methods are usually carried out under power-off conditions, which should be avoided as much as possible in the power system. Preventive tests are usually carried out on all cables. Some cables that were originally in good condition may age their insulation more quickly due to repeated tests at voltages higher than the rated voltage.

[0005] The main online monitoring technologies include DC component method, DC superposition method and partial discharge method. These methods have limitations, such as the DC component is difficult to detect, easily interfered by other signals, and has large errors.

[0006] At present, there are also related research and applications on high-voltage power cable status detection in China. However, with the continuous improvement of the manufacturing level and operation requirements of high-voltage power cables, the existing detection technology has great limitations and uncertainties, which makes the status detection of power cables not make much progress. Summary of the invention

[0007] In order to solve the deficiencies in the prior art, the present invention provides a method and system for identifying abnormal heating of cables in cable wells based on temperature rise, which can effectively utilize a large amount of temperature measurement data transmitted by the cable well, analyze and process the data, extract valid data and then perform abnormal heating identification, thereby improving the efficiency and accuracy of cable well fault identification, and effectively reducing the workload of personnel inspecting a large amount of temperature data to ensure the safe and stable operation of the cable well.

[0008] The present invention adopts the following technical solution.

[0009] The first aspect of the present invention provides a method for identifying abnormal heating of cables in cable wells based on temperature rise, comprising:

[0010] Collect temperature data of the cable lines in the elevator shaft to obtain a temperature data set;

[0011] Preprocess the temperature data set, including unifying the temperature differences in the temperature data set, removing outliers, and unifying the lengths of all temperature measurement nodes to obtain a unified temperature array set;

[0012] Solve the temperature rise trend in the unified temperature array set to obtain a temperature rise trend data set;

[0013] Based on the temperature rise trend data set, the heating fault weight of the temperature measurement node is solved;

[0014] When the heating fault weight of the temperature measurement node exceeds the set threshold, the cable is judged to be abnormally heated, and abnormal heating of the cable in the temperature-rising cable well can be identified.

[0015] Preferably, the temperature data of N temperature measuring nodes on the cable line in the elevator shaft are collected and sent to the cable operation and maintenance monitoring system. The storage array and timer of each temperature measuring node are initialized in the cable operation and maintenance monitoring system. After receiving the first temperature data, the timing starts and the received temperature data is stored. When the time reaches T2, the storage stops. The stored temperature array is M. i [n i ] represents the temperature array of the i-th temperature measurement node, n i represents the temperature number of the i-th temperature measurement node, i∈[1,N], the number of temperature measurement nodes is N, and T2 is the total time.

[0016] Preferably, the temperature difference of each temperature measurement node in the unified temperature data set is expressed by the following formula:

[0017]

[0018] In the formula,

[0019] M i [] min is the temperature array M of the i-th temperature measurement node i [n i ],

[0020] i∈[1,N], N is the number of temperature measurement nodes,

[0021] M i [] max is the temperature array M of the i-th temperature measurement node i [n i ],

[0022] M i [n] is the temperature array M of the i-th temperature measurement node i [n i ] the nth temperature data,

[0023] n∈[0,n i -1],n i represents the temperature number of the i-th temperature measurement node,

[0024] M′ i [n] is the temperature array M of the i-th temperature measurement node after unifying the temperature differences of each temperature measurement node in the temperature data set i [n i ] in the temperature data.

[0025] Preferably, the temperature array M of the i-th temperature measuring node after the temperature difference of each temperature measuring node in the unified temperature data set is i [n i ] in the temperature data M′ i [n] is decomposed in the scale metric space j and expressed as follows:

[0026]

[0027] In the formula,

[0028] K is the position index,

[0029] ∑ K D1(K)ω j-1，K (n) is an outlier,

[0030] A0(K) is the original signal,

[0031] Φ j，K (n) is the basis function,

[0032] Φ j-1，K (n) is the scaling function after the first layer decomposition, which is expressed as follows:

[0033]

[0034] A1(K) is the coefficient of scale metric space j-1, A j (K) is calculated using the following formula:

[0035]

[0036] In the formula,

[0037] h0[k] is the low-pass filter coefficient.

[0038] Preferably, for M′ i[n] Perform five-level decomposition and iterate to solve A5(K) and Φ j-5，K (n), remove the corresponding outliers, and get the temperature array after removing the outliers, which is expressed by the following formula:

[0039]

[0040] In the formula,

[0041] M″ i [n i ] is the temperature array of the i-th temperature measurement node after removing abnormal values,

[0042] Φ j-5，K (n) is the scale function after the fifth layer decomposition,

[0043] A5(K) coefficients in the scaled metric space j-5.

[0044] Preferably, the temperature array M″ of the i-th temperature measurement node after removing the abnormal value is i [n i ] interpolation is unified to T2 / T1, where T2 is the total time and T1 is the maximum sampling time, and the temperature array M″ of the i-th temperature measurement node after unification is obtained i [m], m=1, 2...T2 / T1.

[0045] Preferably, the temperature array M″ of the ath temperature measurement node after unification a [m], m = 1, 2...T2 / T1, divided into Q segments, use M" aq [P] represents the temperature array of the a-th temperature measurement node in the q-th segment, where q∈[1,Q], P is the number of temperatures in each segment, P=T2 / (T1·Q), T2 is the total time, T1 is the maximum sampling time, and the array M″ of the a-th temperature measurement node a The qth segment array sequence M″ in [P] aq [P] and the array M″ of the b-th temperature measurement node b The qth segment array sequence M″ in [P] bq The temperature rise trend of [P] q (M″ aq [P],M″ bq [P]), expressed as follows:

[0046]

[0047] In the formula,

[0048] M″ aq [p] is the array M″ of the a-th temperature measurement node a The pth temperature data of the qth array sequence in [P],

[0049] M″ bq [p] is the array M″ of the bth temperature measurement node b The pth temperature data of the qth array sequence in [P],

[0050] a, b∈[1,N], a≠b,

[0051] M″ aq The average value of the qth segment of the array sequence in [p],

[0052] M″ bq The average value of the qth segment of the array sequence in [p].

[0053] Preferably, the array M″ of the ath temperature measurement node a [P] and the temperature rise trend set r of all other temperature measurement node arrays q (M″ aq [P],M″ b′q [P]), where b′=1, 2, ...N, b′≠a; q∈[1, Q], the temperature rise trend set is formed into an array r ab′ [Q],r ab′ [Q] represents the temperature rise trend set of the ath temperature measurement node and all other temperature measurement nodes, with a length of Q segments;

[0054] Initialize r ab′ All r in [Q] ab″ [q] corresponds to the weight z ab″ The value of r is 0, ab″ [q] represents the temperature rise trend of the a-th temperature measurement node and the b″-th temperature measurement node in the qth segment, a∈[1,N], b″∈[1,N], b″≠a, and the value of the temperature rise trend is ab″ When [q] is less than 0.4, r ab″ [q] corresponds to the weight z ab″ Add 1, and the heating fault weight of the a-th temperature measurement node is ΔZ a , expressed as follows:

[0055]

[0056] In the formula,

[0057] N represents the number of temperature measurement nodes.

[0058] Preferably, the heating fault weight of each temperature measurement node is repeatedly solved every T2 period, and the heating number threshold and heating weight threshold are set. The heating fault weight ΔZ of the ath temperature measurement node is a When the number of times greater than the heating threshold exceeds the heating number threshold, it indicates that the a-th temperature measurement node has a heating fault.

[0059] The second aspect of the present invention provides a system for identifying abnormal heating of cables in cable wells based on temperature rise, which is used to run the method for identifying abnormal heating of cables in cable wells based on temperature rise, comprising:

[0060] Data acquisition module: used to collect temperature data of cable lines in the elevator shaft to obtain a temperature data set;

[0061] Preprocessing module: used to preprocess the temperature data set, including unifying the temperature differences in the temperature data set, removing abnormal values ​​and unifying the lengths of all temperature measurement nodes to obtain a unified temperature array set;

[0062] Solving module: used to solve the temperature rise trend in the unified temperature array set, and solve the heating fault weight of the temperature measurement node based on the temperature rise trend data set;

[0063] Fever identification module: It is used to determine that the cable is abnormally heated when the fever fault weight of the temperature measurement node exceeds the set threshold, and to realize the abnormal heating identification of the cable in the temperature rise cable well.

[0064] The beneficial effect of the present invention is that, compared with the prior art, a method for identifying abnormal heating based on multiple temperature nodes is proposed, which can effectively utilize the temperature measurement data of different nodes transmitted by the cable well, analyze and process them, and extract valid data to identify abnormal heating, thereby improving the efficiency and accuracy of heating fault identification, and effectively reducing the workload of personnel inspecting a large amount of temperature data to ensure the safe and stable operation of the cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a working principle diagram of the present invention;

[0066] Figure 2 This is a diagram showing the effect of eliminating abnormal data after five-layer decomposition in the present invention;

[0067] Figure 3 It is a flow chart of abnormal fever identification and weight calculation in the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0069] Embodiment 1 of the present invention proposes a method for identifying abnormal heating of cables in cable wells based on temperature rise, comprising:

[0070] Step 1: Collect temperature data of the cable line in the elevator shaft to obtain a temperature data set;

[0071] New domestic high-voltage cable lines are generally equipped with fiber optic temperature measurement systems throughout the line, and various types of temperature sensors are installed in some locations where temperature measurement fibers are not configured to send temperature data to the cable operation and maintenance monitoring system. The sending time and frequency of these temperature data are not uniform. In order to make the data comparable, the storage array and timer of each temperature measurement node are initialized in the cable operation and maintenance monitoring system. After receiving the first data, the timing starts and the received data is stored. When the time reaches T2, the storage stops. In this embodiment, the total time T2 is set to 12 hours, and the stored data temperature arrays M1[n1], M2[n2], M3[n3]...M i [n i ], where M i [n i ] represents the temperature array of the i-th temperature measurement node, n i Represents the temperature number of the i-th temperature measurement node, i∈[1,N], and the number of temperature measurement nodes is N.

[0072] Step 2: Preprocess the temperature data set, including unifying the temperature differences in the temperature data set, removing outliers, and unifying the lengths of all temperature measurement nodes to obtain a unified temperature array set;

[0073] Since the cable well is very long, the initial ambient temperature at different locations may be different, and the maintenance personnel cannot determine where the normal ambient temperature rise is and where the temperature rise is caused by abnormal heating. Therefore, in order to make the temperature monitoring data obtained from each temperature measurement node in the cable well comparable, it is necessary to eliminate the impact caused by the ambient temperature difference and unify the original data to collect the temperature differences of each temperature measurement node in the temperature data set.

[0074] The temperature difference of each temperature measurement node in the unified temperature data set is expressed as follows:

[0075]

[0076] In the formula,

[0077] M i [] min is the temperature array M of the i-th temperature measurement node i [n i ],

[0078] i∈[1,N], N is the number of temperature measurement nodes,

[0079] M i [] max is the temperature array M of the i-th temperature measurement nodei [n i ],

[0080] M i [n] is the temperature array M of the i-th temperature measurement node i [n i ] the nth temperature data,

[0081] n∈[0,n i -1],n i represents the temperature number of the i-th temperature measurement node,

[0082] M′ i [n] is the temperature array M of the i-th temperature measurement node after unifying the temperature differences of each temperature measurement node in the temperature data set i [n i ] in the temperature data.

[0083] The operating environment in the cable well is complex. External human factors and electromagnetic interference from temperature sensors may cause bad points in the monitoring data, resulting in misjudgment of heating and causing trouble for the effective operation and maintenance of power cables. Due to the existence of heat conduction and the convection effect of the environment, even if there are local defects, the temperature rise will not change suddenly, but will have a significant upward trend in a relatively short period of time. Therefore, in order to make the monitored data effective and filter out bad points caused by external interference, the discrete wavelet decomposition and reconstruction algorithm is used to decompose and reconstruct the array of monitoring data, so that the stored temperature measurement data is reasonable and effective. The temperature array M of the i-th temperature measurement node after the temperature difference of each temperature measurement node in the unified temperature data set is calculated. i [n i ] in the temperature data M′ i [n] is decomposed in the scale metric space j and expressed as follows:

[0084]

[0085] In the formula,

[0086] K is the position index,

[0087] ∑ K D1(K)ω j-1，K (n) is an outlier,

[0088] A0(K) is the original signal,

[0089] Φ j，K (n) is the basis function,

[0090] Φ j-1，K (n) is the scaling function after the first layer decomposition, which is expressed as follows:

[0091]

[0092] A1(K) is the coefficient of scale metric space j-1, A j (K) is calculated using the following formula:

[0093]

[0094] In the formula,

[0095] h0[k] is the low-pass filter coefficient.

[0096] For M′ i [n] Perform five-level decomposition and iterate to solve A5(K) and Φ j-5，K (n), remove the corresponding outliers, and get the temperature array after removing the outliers, which is expressed by the following formula:

[0097]

[0098] In the formula,

[0099] M″ i [n i ] is the temperature array of the i-th temperature measurement node after removing abnormal values,

[0100] Φ j-5，K (n) is the scale function after the fifth layer decomposition,

[0101] A5(K) coefficients in the scaled metric space j-5.

[0102] The effect of removing abnormal data after five-layer decomposition is as follows: Figure 2 As shown, it can be seen from the figure that after the five-layer decomposition, the curve is smooth and the bad points are removed.

[0103] Step 3: Solve the temperature rise trend in the unified temperature array set to obtain a temperature rise trend data set;

[0104] The temperature array after removing outliers is M″1[n1], M″2[n2], M″3[n3]...M″ i [n i ]. Since n1, n2, n3...n i They are not equal, that is, the array lengths are different. In order to unify the data length and thus make it comparable, the data is interpolated by interpolation. Assuming that the maximum sampling time of all temperature measurement nodes is T1 (the optical fiber temperature sensor sampling time is short, with real-time performance of several seconds, while the sampling time of other temperature sensors may reach 10 minutes), the array is unified to T2 / T1 data points.

[0105] The temperature array M″ of the i temperature measurement nodes after removing the outliers i [n i], the number of data is n i , then divide 1 to T2 / T1 into n i point, denoted as x o , o = 1, 2, ... n i , where x1 = 1, Each x o Corresponding to a corresponding value M″ i [o], then M″ i [n i ] to interpolate and solve, and its boundary conditions are:

[0106]

[0107] In the formula,

[0108] S o (x o+1 ) represents the spline function.

[0109] Set o=0, 2, 3...n i Substituting -1 into formula 6 and solving them in sequence, we can get the spline function S o (x o+1 ), corresponding to Total n i -1 independent variable interval, x o+1 =1, 2...T2 / T1 is introduced into the spline function to obtain T2 / T1 values, forming the temperature array M″ of the i-th temperature measurement node after unification i [m], m=1, 2...T2 / T1.

[0110] The temperature array M″ of the a-th temperature measurement node after unification a [m], m = 1, 2...T2 / T1, divided into Q segments, use M" aq [P] represents the temperature array of the a-th temperature measurement node in the q-th segment, where q∈[1,Q], P is the number of temperatures in each segment, P=T2 / (T1·Q), T2 is the total time, T1 is the maximum sampling time, and the array M″ of the a-th temperature measurement node a The qth segment array sequence M″ in [P] aq [P] and the array M″ of the b-th temperature measurement node b The qth segment array sequence M″ in [P] bq The temperature rise trend of [P] q (M″ aq [P],M″ bq [P]), expressed as follows:

[0111]

[0112] In the formula,

[0113] M″ aq [p] is the array M″ of the a-th temperature measurement node a The pth temperature data of the qth array sequence in [P],

[0114] M″ bq [p] is the array M″ of the bth temperature measurement node b The pth temperature data of the qth array sequence in [P],

[0115] a, b∈[1,N], a≠b,

[0116] M″ aq The average value of the qth segment of the array sequence in [p],

[0117] M″ bq The average value of the qth segment of the array sequence in [p].

[0118] M″ 1q [P], M″ 2q [P] as an example, its temperature rise trend is:

[0119]

[0120] In the formula,

[0121] M″ 1q The average value of the qth segment of the array sequence in [P],

[0122] M″ 2q The average value of the qth segment of the array sequence in [P].

[0123] According to the above method, by performing pairwise correlation comparison on the data of all temperature monitoring nodes, abnormal temperature rise trends can be identified. If the temperature change trend of a certain node is significantly different and has obvious irrelevance with other nodes, it is judged that the node may have a heating fault.

[0124] Step 4: Based on the temperature rise trend data set, solve the heating fault weight of the temperature measurement node;

[0125] All temperature monitoring node data are compared pairwise for correlation and abnormal temperature rise trend test. If the temperature rise trend of a node is poorly correlated with other nodes, the node is most likely to have a heating fault. In order to quantify the above abnormal temperature rise trend test and measure the significance of the abnormal temperature rise trend of a node, the heating fault weight is ΔZ a .

[0126] The array M″ of the ath temperature measurement node a [P] and the temperature rise trend set r of all other temperature measurement node arrays q (M″ aq [P],M″ b′q [P]), where b′=1, 2, ...N, b′≠a; q∈[1, Q], the temperature rise trend set is formed into an array r ab′ [Q],r ab′ [Q] represents the temperature rise trend set of the ath temperature measurement node and all other temperature measurement nodes, with a length of Q segments;

[0127] Initialize r ab′ All r in [Q] ab″ [q] corresponds to the weight z ab″ The value of r is 0, ab″ [q] represents the temperature rise trend of the a-th temperature measurement node and the b″-th temperature measurement node in the qth segment, a∈[1,N], b″∈[1,N], b″≠a, judge r ab″ When [q] is less than 0.4, r ab″ [q] corresponds to the weight z ab″ Add 1, stop judging the qth segment, and continue judging the q+1th segment. If a group of values ​​is less than 0.4, it is determined that the two segments of data are weakly correlated at this time, and the heating fault weight of the ath temperature measurement node is ΔZ a , expressed as follows:

[0128]

[0129] In the formula,

[0130] N represents the number of temperature measurement nodes.

[0131] In this embodiment 1, the calculation of the heating fault weight ΔZ1 of the temperature monitoring node 1 is taken as an example. Figure 3 As shown, after processing the data in formula 8, the temperature rise trend is obtained by q (M″ 1q [P],M″ 2q [P]), r q (M″ 1q [P],M″ 3q [P])...r q (M″ 1q [P],M″ Nq [P]), q∈[1, Q], N is the total number of temperature measurement nodes. The temperature rise trends obtained above are grouped into an array of length Q, which are respectively denoted as r 12 [Q],r 13 [Q]...r 1N [Q].

[0132] Compare 12 [q],r 13 [q]...r 1N [q], where q∈[1,Q], and the weights correspond to z 12 、z 13 ...z 1N If a group of values ​​is less than 0.4, it is considered that the two segments of data are weakly correlated, and the corresponding weight coefficient is increased by 1. Similarly, the calculation result of ΔZ1 can be obtained.

[0133] Step 5: When the heating fault weight of the temperature measurement node exceeds the set threshold, the cable is determined to be abnormally heated, and abnormal heating of the cable in the temperature rise cable well is identified.

[0134] In step 5, the heating fault weight of each temperature measurement node is repeatedly solved every T2 period, and the heating number threshold and heating weight threshold are set. The heating fault weight ΔZ of the a-th temperature measurement node is a When the number of times greater than the fever threshold exceeds the fever threshold, it indicates that the a-th temperature measurement node has a fever fault, and the operation and maintenance personnel should take corresponding measures to troubleshoot the hidden dangers.

[0135] Embodiment 2 of the present invention proposes a system for identifying abnormal heating of cables in cable wells based on temperature rise, which is used to run the method for identifying abnormal heating of cables in cable wells based on temperature rise described in embodiment 1, including:

[0136] Data acquisition module: used to collect temperature data of cable lines in the elevator shaft to obtain a temperature data set;

[0137] Preprocessing module: used to preprocess the temperature data set, including unifying the temperature differences in the temperature data set, removing abnormal values ​​and unifying the lengths of all temperature measurement nodes to obtain a unified temperature array set;

[0138] Solving module: used to solve the temperature rise trend in the unified temperature array set, and solve the heating fault weight of the temperature measurement node based on the temperature rise trend data set;

[0139] Fever identification module: It is used to determine that the cable is abnormally heated when the fever fault weight of the temperature measurement node exceeds the set threshold, and to realize the abnormal heating identification of the cable in the temperature rise cable well.

[0140] The beneficial effect of the present invention is that, compared with the prior art, a method for identifying abnormal heating based on multiple temperature nodes is proposed, which can effectively utilize the temperature measurement data of different nodes transmitted by the cable well, analyze and process them, and extract valid data to identify abnormal heating, thereby improving the efficiency and accuracy of heating fault identification, and effectively reducing the workload of personnel inspecting a large amount of temperature data to ensure the safe and stable operation of the cable.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for identifying abnormal heating of cables in cable wells based on temperature rise, characterized in that: Collect temperature data of the cable lines in the elevator shaft to obtain a temperature data set; Preprocess the temperature data set, including unifying the temperature differences in the temperature data set, removing outliers, and unifying the lengths of all temperature measurement nodes to obtain a unified temperature array set; Solve the temperature rise trend in the unified temperature array set to obtain a temperature rise trend data set; Based on the temperature rise trend data set, the heating fault weight of the temperature measurement node is solved; When the heating fault weight of the temperature measurement node exceeds the set threshold, the cable is judged to be abnormally heated, and abnormal heating of the cable in the temperature-rising cable well can be identified.

2. According to claim 1, a method for identifying abnormal heating of cables in cable wells based on temperature rise is characterized by: The temperature data of N temperature measurement nodes on the cable line in the elevator shaft are collected and sent to the cable operation and maintenance monitoring system. The storage array and timer of each temperature measurement node are initialized in the cable operation and maintenance monitoring system. After receiving the first temperature data, the timing starts and the received temperature data is stored. When the time reaches T2, the storage stops. The stored temperature array is M i [n i ] represents the temperature array of the i-th temperature measurement node, n i represents the temperature number of the i-th temperature measurement node, i∈[1,N], the number of temperature measurement nodes is N, and T2 is the total time.

3. The method for identifying abnormal heating of cables in cable wells based on temperature rise according to claim 1 is characterized in that: The temperature difference of each temperature measurement node in the unified temperature data set is expressed as follows: In the formula, M i [] min is the temperature array M of the i-th temperature measurement node i [n i ], i∈[1,N], N is the number of temperature measurement nodes, M i [] max is the temperature array M of the i-th temperature measurement node i [n i ], M i [n] is the temperature array M of the i-th temperature measurement node i [n i ] the nth temperature data, n∈[0,n i -1],n i represents the temperature number of the i-th temperature measurement node, M′ i [n] is the temperature array M of the i-th temperature measurement node after unifying the temperature differences of each temperature measurement node in the temperature data set i [n i ] in the temperature data.

4. The method for identifying abnormal heating of cables in cable wells based on temperature rise according to claim 1 is characterized in that: The temperature array M of the i-th temperature measurement node after the temperature difference of each temperature measurement node in the unified temperature data set is i [n i ] in the temperature data M′ i [n] is decomposed in the scale metric space j and expressed as follows: In the formula, K is the position index, ∑ K D1(K)ω j-1，K (n) is an outlier, A0(K) is the original signal, Φ j，K (n) is the basis function, Φ j-1，K (n) is the scaling function after the first layer decomposition, which is expressed as follows: A1(K) is the coefficient of scale metric space j-1, A j (K) is calculated using the following formula: In the formula, h0[k] is the low-pass filter coefficient.

5. The method for identifying abnormal heating of cables in cable wells based on temperature rise according to claim 4 is characterized by: For M′ i [n] Perform five-level decomposition and iterate to solve A5(K) and Φ j-5，K (n), remove the corresponding outliers, and get the temperature array after removing the outliers, which is expressed by the following formula: In the formula, M″ i [n i ] is the temperature array of the i-th temperature measurement node after removing abnormal values, Φ j-5，K (n) is the scale function after the fifth layer decomposition, A5(K) coefficients in the scaled metric space j-5.

6. The method for identifying abnormal heating of cables in cable wells based on temperature rise according to claim 1 is characterized by: The temperature array M″ of the i-th temperature measurement node after removing the abnormal values i [n i ] interpolation is unified to T2 / T1, where T2 is the total time and T1 is the maximum sampling time, and the temperature array M″ of the i-th temperature measurement node after unification is obtained i [m], m=1, 2...T2 / T1.

7. The method for identifying abnormal heating of cables in cable wells based on temperature rise according to claim 1 is characterized by: The temperature array M″ of the a-th temperature measurement node after unification a [m], m = 1, 2...T2 / T1, divided into Q segments, use M" aq [P] represents the temperature array of the a-th temperature measurement node in the q-th segment, where q∈[1,Q], P is the number of temperatures in each segment, P=T2 / (T1·Q), T2 is the total time, T1 is the maximum sampling time, and the array M″ of the a-th temperature measurement node a The qth segment array sequence M″ in [P] aq [P] and the array M″ of the b-th temperature measurement node b The qth segment array sequence M″ in [P] bq The temperature rise trend of [P] q (M″ aq [P],M″ bq [P]), expressed as follows: In the formula, M″ aq [p] is the array M″ of the ath temperature measurement node a The pth temperature data of the qth array sequence in [P], M″ bq [p] is the array M″ of the bth temperature measurement node b The pth temperature data of the qth array sequence in [P], a, b∈[1,N], a≠b, M″ aq The average value of the qth segment of the array sequence in [p], M″ bq The average value of the qth segment of the array sequence in [p].

8. The method for identifying abnormal heating of cables in cable wells based on temperature rise according to claim 1 is characterized by: The array M″ of the ath temperature measurement node a [P] and the temperature rise trend set r of all other temperature measurement node arrays q (M″ aq [P],M″ b′q [P]), where b′=1, 2, ...N, b′≠a; q∈[1, Q], the temperature rise trend set is formed into an array r ab′ [Q],r ab′ [Q] represents the temperature rise trend set of the ath temperature measurement node and all other temperature measurement nodes, with a length of Q segments; Initialize r ab′ All r in [Q] ab″ [q] corresponds to the weight z ab″ The value of r is 0, ab″ [q] represents the temperature rise trend of the a-th temperature measurement node and the b″-th temperature measurement node in the qth segment, a∈[1,N], b″∈[1,N], b″≠a, and the value of the temperature rise trend is ab″ When [q] is less than 0.4, r ab″ [q] corresponds to the weight z ab″ Add 1, and the heating fault weight of the a-th temperature measurement node is ΔZ a , expressed as follows: In the formula, N represents the number of temperature measurement nodes.

9. The method for identifying abnormal heating of cables in cable wells based on temperature rise according to claim 1 is characterized by: Every T2 period, the heating fault weight of each temperature measurement node is repeatedly solved, and the heating number threshold and heating weight threshold are set. The heating fault weight ΔZ of the a-th temperature measurement node is a When the number of times greater than the heating threshold exceeds the heating number threshold, it indicates that the a-th temperature measurement node has a heating fault.

10. A system for identifying abnormal heating of cables in cable wells based on temperature rise, used for running a method for identifying abnormal heating of cables in cable wells based on temperature rise according to any one of claims 1 to 9, characterized in that: Data acquisition module: used to collect temperature data of cable lines in the elevator shaft to obtain a temperature data set; Preprocessing module: used to preprocess the temperature data set, including unifying the temperature differences in the temperature data set, removing abnormal values ​​and unifying the lengths of all temperature measurement nodes to obtain a unified temperature array set; Solving module: used to solve the temperature rise trend in the unified temperature array set, and solve the heating fault weight of the temperature measurement node based on the temperature rise trend data set; Fever identification module: It is used to determine that the cable is abnormally heated when the fever fault weight of the temperature measurement node exceeds the set threshold, and to realize the abnormal heating identification of the cable in the temperature rise cable well.

Images