Cable working condition monitoring system and monitoring method
By injecting alternating square wave test signals into the cable metal shielding layer in the cable operating condition monitoring system, combining signal acquisition and machine learning methods, the problem that the existing technology cannot monitor the cable operating conditions for a long time is solved, and the accuracy of cable failure is achieved Identify and monitor in real time.
Patent Information
- Application Number
- CN202411444335.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-16
- Publication Date
- 2025-02-18
AI Technical Summary
The prior art cannot meet the needs of long-term monitoring of cable working status, especially when the tiny cable defects are not obvious at the initial stage and the offline detection method has frequent shutdowns and frequent inspections.
A cable operating condition monitoring system is designed, by injecting alternating square wave test signals into the metal shielding layer of the cable, the signal acquisition mechanism is used to obtain the current signal of the cable ground point and conductor, and the operating condition of the cable is evaluated through the control mechanism. The system includes a signal generation mechanism, a signal acquisition mechanism and a control mechanism, and uses machine learning methods to identify faults.
Real-time monitoring of cable operating conditions is realized, common cable faults can be identified, and the characteristics of cable fault waveforms are highlighted through non-industrial frequency alternating square wave signals, improving the accuracy and efficiency of fault identification.
Smart Images
Figure CN119471222A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of cable monitoring, and in particular relates to a cable working condition monitoring system and a monitoring method. Background Art
[0002] Power cables are important primary equipment for electric energy transmission, and cable condition detection is a necessary step in maintaining the safe operation of cables. Minor defects such as local insulation defects may occur in cables during production, installation, and operation. Minor defects continue to expand and may extend to both ends of the insulation layer, forming a discharge channel under the action of electrical stress. Since the insulation has not been completely destroyed at this time, the discharge channel is intermittently turned on, forming an intermittent arc fault, also known as an initial cable fault. This initial cable fault can be eliminated autonomously as the arc inside the insulation is extinguished, and the cable can continue to operate. The continuous development of minor defects in the cable will eventually lead to permanent cable failure, but the minor defects are not obvious in the initial stage. Currently, offline detection methods such as local discharge method and time-frequency domain reflection method are commonly used.
[0003] Cable offline status detection technology cannot meet the needs of long-term monitoring of cable working status because it requires the cable to be shut down for maintenance and cannot be detected frequently. Summary of the invention
[0004] The technical problem to be solved by the present invention is to provide a cable working condition monitoring system and a monitoring method in view of the deficiencies of the prior art.
[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A cable working condition monitoring system comprises a signal generating mechanism, a signal collecting mechanism and a control mechanism; The signal generating mechanism is connected to the metal shielding layer at one end of the cable to be monitored, and is used to inject an alternating square wave test signal into the metal shielding layer; The signal acquisition mechanism includes a first acquisition device and a second acquisition device; the first acquisition device is connected to the grounding point of the cable to be monitored, and is used to obtain the current signal of the cable grounding point; the second acquisition device is connected to the conductor at the other end of the cable to be monitored, and is used to obtain the current signal of the cable conductor; The signal generating mechanism and the signal collecting mechanism are both electrically connected or communicatively connected to the control mechanism; the control mechanism is used to control the signal generating mechanism to inject a test signal into the cable, and is used to evaluate the operating condition of the cable based on the current signal collected by the signal collecting mechanism.
[0006] Furthermore, the signal generating mechanism includes a voltage regulating unit, a rectifying unit and an inverting unit; The voltage regulating unit is used to convert the 220V 50Hz input power into a specified voltage; The rectifying unit is used to convert the voltage converted by the voltage regulating unit into a DC signal; The inverter unit is used to convert the DC signal output by the rectifier unit into an alternating square wave signal.
[0007] Furthermore, the first acquisition device and the second acquisition device both include a current transformer, a noise reduction filter unit and an operational amplifier unit; The current transformer is used to induce a current signal; The noise reduction and filtering unit is used to filter the interference frequency in the current signal by means of noise reduction, filtering, etc.; The operational amplifier unit is used to amplify the current signal.
[0008] Furthermore, the control mechanism is also used to control the size and frequency of the test signal output by the signal generating mechanism.
[0009] A cable condition monitoring method, comprising: Get the cable condition data set; Construct a cable condition identification model; The cable condition recognition model is trained using the cable condition dataset; Inject an alternating square wave test signal into the metal shielding layer of the cable, and collect the current signals of the cable conductor before and after the injection and the current signals of the cable grounding point; The collected current signal is input into the cable working condition identification model to obtain the working status of the cable.
[0010] Furthermore, the method for obtaining the cable condition data set includes: Construct an electrical simulation model of the cable in the simulation software; Simulating the injection of an alternating square wave test signal into the metal shielding layer of the simulation model; In the simulation model, current signals of the cable conductor and the cable grounding point are collected before and after the test signal is injected; Superimpose different cable faults in the simulation model and collect current signals of the cable conductor and the cable grounding point before and after the test signal is injected under the fault state; The cable operating condition data set is constructed based on the voltage value of the test signal, the frequency of the test signal, the cable specification, the cable conductor current signal, the cable grounding point current signal and the fault type.
[0011] Furthermore, the method for collecting the current signal of the cable conductor before and after injection and the current signal of the cable grounding point includes: collecting ~ At the time, the current signal of the cable conductor and the current signal of the cable grounding point; is the moment when the test signal reaches the i-th acquisition point, is the preset collection time. ; is the injection duration of the test signal, ; f is the frequency of the test signal, and f is the non-industrial frequency.
[0012] Further, the method of injecting a test signal into the metal shielding layer of the cable comprises: The test signal is injected into the metallic shield of the cable at regular time intervals.
[0013] Furthermore, It is the moment of the first zero crossing of the square wave signal collected at the i-th collection point after the test signal is injected.
[0014] Furthermore, is the injection time of the test signal and the accumulated value of the time it takes for the test signal to be transmitted to the i-th acquisition point.
[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention monitors the working condition of the cable by injecting a test signal into the metal shielding layer of the cable, according to the characteristics of the current disturbance caused by the initial fault of the cable, by acquiring the current signal of the cable grounding point and the current signal of the cable conductor, and can identify common faults of the cable. The test signal injected by the present invention is a non-industrial frequency alternating square wave signal, so the characteristics of the cable fault waveform can be highlighted according to the special waveform of the square wave signal, and the fault identification performed by machine learning means will be more accurate and efficient. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The present invention is further described in detail below in conjunction with the accompanying drawings.
[0017] Figure 1 : A schematic diagram of the structure of Embodiment 1 of the present invention; Figure 2 : Flow chart of Embodiment 2 of the present invention; Figure 3 : A schematic diagram of a cable operating condition identification model in Embodiment 2 of the present invention; Among them: 11-signal generating mechanism, 111-voltage regulating unit, 112-rectifying unit, 113-inverting unit, 12-signal collecting mechanism, 121-current transformer, 122-noise reduction filtering unit, 123-operational amplifier unit, 124-first collecting device, 125-second collecting device, 13-control mechanism, 131-processor, 132-memory. DETAILED DESCRIPTION
[0018] In order to better understand the present invention, the content of the present invention is further clearly described below in conjunction with the embodiments and the accompanying drawings, but the protection content of the present invention is not limited to the following embodiments. In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is obvious to those skilled in the art that the present invention can be implemented without one or more of these details.
[0019] Embodiment 1: The purpose of this embodiment is to provide a cable condition monitoring system. Figure 1 As shown, the monitoring system includes a signal generating mechanism 11 , a signal collecting mechanism 12 and a control mechanism 13 .
[0020] The signal generating mechanism 11 is connected to the metal shielding layer at one end of the cable to be monitored, and is used to inject an alternating square wave test signal into the metal shielding layer. Specifically, the signal generating mechanism 11 includes a voltage regulating unit 111, a rectifier unit 112 and an inverter unit 113. The voltage regulating unit 111 is used to convert the 220V 50Hz input power supply into a specified voltage, the rectifier unit 112 is used to convert the voltage converted by the voltage regulating unit 111 into a DC signal, and the inverter unit 113 is used to convert the DC signal into an alternating square wave signal. At the same time, the signal generating mechanism 11 is also connected to the control mechanism 13 in communication or electrical connection, so that the control mechanism 13 can control the size and frequency of the square wave signal output by the inverter unit 113.
[0021] The signal acquisition mechanism 12 includes a first acquisition device 124 and a second acquisition device 125 of the same structure. The first acquisition device 124 is connected to the grounding point of the cable to be monitored, and is used to obtain the current signal of the cable grounding point; the second acquisition device 125 is connected to the conductor at the other end of the cable to be monitored, and is used to obtain the current signal of the cable conductor. Specifically, the signal acquisition mechanism 12 (i.e., the first acquisition device 124 and the second acquisition device 125) both include a current transformer 121, a noise reduction unit 122 and an operational amplifier unit 123. The current transformer 121 is used to induce a current signal from the cable, the noise reduction filter unit 122 is used to filter the interference frequency in the current signal by means of noise reduction, filtering, etc., and the operational amplifier unit 123 is used to amplify the current signal. At the same time, the signal acquisition mechanism 12 is also electrically connected or communicatively connected to the control mechanism 13, and is used to transmit the current signal to the control mechanism 13.
[0022] The control mechanism 13 is used to control the signal generating mechanism 11 to inject a test signal into the cable, and is used to evaluate the operating condition of the cable according to the current signal collected by the signal collecting mechanism 12. Specifically, the control mechanism 13 monitors the cable condition by executing the monitoring method provided in Example 2.
[0023] The control mechanism 13 is an electronic device, including a processor 131 and a memory 132. The processor 131 stores executable instructions, and the processor 131 is used to execute the instructions to implement the monitoring method described in Example 2.
[0024] Embodiment 2: The purpose of this embodiment is to provide a cable working condition monitoring method.
[0025] When an alternating square wave test signal is injected into the metal shielding layer of the cable, the waveform of the current signal of the cable conductor and the cable grounding point is a square wave, a sine wave, or a composite waveform of a square wave and a sine wave. After the test signal is injected, if the cable is in normal working condition, the waveform of the grounding point current signal should be a square wave, and the waveform of the conductor current signal should be a sine wave; if there is an insulation defect in the cable and a breakdown occurs, the waveform of the grounding point current signal has a composite waveform, and the waveform of the conductor current signal still presents a sine wave, or there is a composite waveform.
[0026] Under different fault conditions, the waveform of the current signal has different characteristics. Therefore, machine learning can be used to obtain the intrinsic correlation between the current signal and the fault.
[0027] like Figure 2 As shown, the monitoring method comprises: S1. Obtain cable working condition data set.
[0028] In simulation software such as Simulink and XFdtd, a typical simulation model of the cable is constructed, the injection of the alternating square wave test signal is simulated in the metal shielding layer of the simulation model, and the current signals simulated by the cable conductor and the grounding point before and after the injection are collected. Various common cable faults are superimposed on the simulation model, such as insulation aging, local insulation defects in the inner layer, local insulation defects in the outer layer, single-phase grounding, etc., and the fault state and the current signals simulated by the cable conductor and the grounding point before and after the test signal injection are collected.
[0029] Or build a cable test model in a laboratory environment, inject an alternating square wave into the metal shielding layer of the test model, and collect the current signals of the cable conductor and grounding point before and after the injection. By superimposing various cable faults in the test model, such as insulation aging, local insulation defects, single-phase grounding, etc., and collecting the fault status and the current signals simulated by the cable conductor and grounding point before and after the test signal is injected.
[0030] When collecting the current signals of the cable conductor and the grounding point before and after injection, obtain ~ The current signal of the cable conductor and the current signal of the cable grounding point at the time. is the time when the test signal reaches the i-th acquisition point (the first acquisition device 124 and the second acquisition device 125); is the preset collection time. ; is the injection duration of the test signal, ; f is the frequency of the test signal, and f uses non-industrial frequency.
[0031] The acquired cable operating condition data set should include the voltage value of the test signal, the frequency of the test signal, the cable specification, the cable conductor current signal, the cable grounding point current signal and the fault type.
[0032] S2. Construct a cable working condition identification model.
[0033] In this step, wavelet neural network is used to construct a cable condition identification model, and its structure is as follows: Figure 3 As shown in the figure, the hidden layer uses the Mexihat wavelet basis and its scaling function as wavelet neurons, and the output layer nodes use the Sigmoid function. is the kth input sample, and is the scaling and translation coefficient of the i-th hidden layer, is the output of the jth node in the output layer.
[0034] in is the connection weight between the input layer node k and the hidden layer i, e is the natural base, E is the output error function location, is the expected output value of the jth node in the output layer.
[0035] Combination Figure 3 The number of input layer nodes m of the cable condition identification model corresponds to the data types in the cable condition dataset. The output results cover normal and common cable fault types. The number of output layer nodes N is the number of cable fault types in the dataset + 1; the number of hidden layer nodes n is set as needed.
[0036] S3. Use the cable working condition data set to train the cable working condition identification model.
[0037] The cable condition data set is divided into a training set and a test set in a ratio of 9:1. The training set is input into the cable condition identification model for training, and the maximum number of iterations is set. After the training is completed, the test set is used to verify the ability of the cable condition identification model.
[0038] S4. Inject a test signal into the metal shielding layer of the cable, and collect the current signals of the cable conductor before and after the injection and the current signals of the cable grounding point.
[0039] Inject an alternating square wave test signal into the metal shield of the cable and obtain ~ The current signal of the cable conductor and the current signal of the cable grounding point at the time. is the time when the test signal reaches the i-th acquisition point (the first acquisition device 124 and the second acquisition device 125); is the preset collection time. ; is the injection duration of the test signal, ; f is the frequency of the test signal, and f uses non-industrial frequency.
[0040] The first zero-crossing moment of the square wave signal collected after the test signal is injected is The value of, or the time taken by the test signal to be injected and the signal to be transmitted to the acquisition point is taken as The transmission time of the test signal related to the cable conductor can be determined by injecting the test signal into the cable conductor in advance and then collecting it by the second collection device 125; the transmission time of the test signal related to the cable grounding point can be determined by injecting the test signal into the shielding layer of the phase cable in advance and then collecting it by the first collection device 124.
[0041] For the timing of injecting the test signal, a timing method can be adopted, and the injection frequency can be increased when the current in the cable is large, the cable temperature is high, the ambient temperature is high, or the ambient humidity is high, which may easily trigger cable hidden dangers.
[0042] You can also use the method of continuously injecting test signals, with the injection time interval being , thereby achieving uninterrupted monitoring of the cable condition.
[0043] S5. Input the collected current signal into the cable working condition identification model to obtain the working state of the cable.
[0044] The current signal of the cable conductor and the current signal of the cable grounding point collected in step S4, as well as the cable specifications, voltage value and frequency of the test signal are input into the cable working condition identification model, and the cable working condition identification model will output the working status of the cable, such as normal or other specific fault types.
[0045] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Other modifications or equivalent substitutions made to the technical solution of the present invention by ordinary technicians in the field should be included in the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solution of the present invention.
Claims
1. A cable condition monitoring system, characterized in that: It includes a signal generating mechanism, a signal collecting mechanism and a control mechanism; The signal generating mechanism is connected to the metal shielding layer at one end of the cable to be monitored, and is used to inject an alternating square wave test signal into the metal shielding layer; The signal acquisition mechanism includes a first acquisition device and a second acquisition device; the first acquisition device is connected to the grounding point of the cable to be monitored, and is used to obtain the current signal of the cable grounding point; the second acquisition device is connected to the conductor at the other end of the cable to be monitored, and is used to obtain the current signal of the cable conductor; The signal generating mechanism and the signal collecting mechanism are both electrically connected or communicatively connected to the control mechanism; the control mechanism is used to control the signal generating mechanism to inject a test signal into the cable, and is used to evaluate the operating condition of the cable based on the current signal collected by the signal collecting mechanism.
2. The cable condition monitoring system and monitoring method according to claim 1, characterized in that: The signal generating mechanism includes a voltage regulating unit, a rectifying unit and an inverting unit; The voltage regulating unit is used to convert the 220V 50Hz input power into a specified voltage; The rectifying unit is used to convert the voltage converted by the voltage regulating unit into a DC signal; The inverter unit is used to convert the DC signal output by the rectifier unit into an alternating square wave signal.
3. The cable condition monitoring system and monitoring method according to claim 1, characterized in that: The first acquisition device and the second acquisition device both include a current transformer, a noise reduction filter unit and an operational amplifier unit; The current transformer is used to induce a current signal; The noise reduction and filtering unit is used to filter the interference frequency in the current signal by means of noise reduction, filtering, etc.; The operational amplifier unit is used to amplify the current signal.
4. The cable condition monitoring system and monitoring method according to claim 1, characterized in that: The control mechanism is also used to control the size and frequency of the test signal output by the signal generating mechanism.
5. A cable condition monitoring method, characterized in that: include: Get the cable condition data set; Construct a cable condition identification model; The cable condition recognition model is trained using the cable condition dataset; Inject an alternating square wave test signal into the metal shielding layer of the cable, and collect the current signals of the cable conductor before and after the injection and the current signals of the cable grounding point; The collected current signal is input into the cable working condition identification model to obtain the working status of the cable.
6. The cable condition monitoring method according to claim 1, characterized in that: Methods for obtaining cable condition data sets include: Construct an electrical simulation model of the cable in the simulation software; Simulating the injection of an alternating square wave test signal into the metal shielding layer of the simulation model; In the simulation model, current signals of the cable conductor and the cable grounding point are collected before and after the test signal is injected; Superimpose different cable faults in the simulation model and collect current signals of the cable conductor and the cable grounding point before and after the test signal is injected under the fault state; The cable operating condition data set is constructed based on the voltage value of the test signal, the frequency of the test signal, the cable specification, the cable conductor current signal, the cable grounding point current signal and the fault type.
7. The cable condition monitoring method according to claim 1 or 6, characterized in that: The method for collecting the current signal of the cable conductor before and after injection and the current signal of the cable grounding point includes: collecting ~ At the time, the current signal of the cable conductor and the current signal of the cable grounding point; is the moment when the test signal reaches the i-th acquisition point, is the preset collection time. ; is the injection duration of the test signal, ; f is the frequency of the test signal, and f is the non-industrial frequency.
8. The cable condition monitoring method according to claim 7, characterized in that: Methods for injecting a test signal into the metal shield of a cable include: The test signal is injected into the metallic shield of the cable at regular time intervals.
9. The cable condition monitoring method according to claim 7, characterized in that: It is the moment of the first zero crossing of the square wave signal collected at the i-th collection point after the test signal is injected.
10. The cable condition monitoring method according to claim 7, characterized in that: is the injection time of the test signal and the accumulated value of the time it takes for the test signal to be transmitted to the i-th acquisition point.