Accurate Cable Fault Location Method And Implementation Technology Based On Artificial Intelligence

With the rapid development of economy and society,the demand for electricity in all walks of life is increasing day by day,and the requirements for power quality are also increasing,which promotes the leapfrog development of strong smart grid construction.As the key carrier of power transmission in distribution lines and the supporting artery of functional operation in urban constructions,power cables are widely applied in engineering construction.They are frequently used and their distributions become more complicated.However,once the fault takes place on the cables which are buried deeply underground,if it is not eliminated in time,it may threaten the safety of power grid seriously and affect the production of enterprises and the lives of residents.Therefore,in the face of sudden cable faults,it is urgent to locate,repair faults and restore power supply as soon as possible.While in the process of traditional cable fault location,both the prepositioning and the precise positioning need to identify the fault information and label the pulse delay manually,which is subjective and inefficient.In order to get rid of the limitations of manual operation in traditional cable fault location methods,this paper uses the field test data to carry out research on the cable fault location method based on artificial intelligence,aiming at improving the automation and intelligence level of cable fault location.And the main work and achievements of this thesis are as follows:(1)This paper proposes a prepositioning method based on intelligent recognition of breakdown discharged waveform.Firstly,the system structure and operating principle of the pulse current method and the secondary pulse method are analyzed.Since recognizing the breakdown discharged waveform is the premise of locating faults,a recognition algorithm of breakdown discharged waveform based on PSO-SVM is designed.After distinguishing the breakdown and non-breakdown discharged waveforms by using the time-frequency domain characteristic parameters,the PSO-SVM recognition model is constructed.And it can identify(the breakdown discharged waveform intelligently after training and testing.After the recognition is completed,the wavelet modulus maxima and Pearson correlation coefficient are used to label the time difference automatically to calculate the fault distance.In this way,intelligent recognition and automatic prepositioning of cable faults can be realized.(2)This paper proposes a precise positioning method based on intelligent recognition of acoustic and magnetic waveforms.Firstly,the distribution characteristics of sound field and magnetic field and the operating principle of acoustic and magnetic synchronization method are analyzed.Aiming at the restriction of artificial recognition of acoustic and magnetic signals,a recognition algorithm of acoustic and magnetic waveforms based on CNN is designed.After.depicting the key differences between acoustic and magnetic signals and interference signals by using the time-frequency diagrams,the GoogleNet-CNN recognition model is constructed.And it can identify the acoustic and magnetic waveforms intelligently after training and testing.After the recognition is completed,the EMD is used to filter out noise interference and the TEO is used to label the time difference between acoustic and magnetic signals automatically.And the specific location of the fault point can be searched according to the time difference.In this way,intelligent recognition and automatic precise positioning of cable faults can be realized.(3)The proposed prepositioning method and precise positioning method are verified by practical testing and measured data.The intelligent recognition effect of the recognition model for fault information is evaluated,and the automatic calibration effect of the calibration algorithm for time difference is tested.Thus,the fault distance is calculated and the fault point is searched.The experimental results verify the effectiveness and feasibility of the proposed positioning system,which can realize fast and accurate positioning of cable faults.