CN107093036A - The emergency first-aid repair car system of the light source containing XED and the intelligent dispatching method based on BP dijkstra's algorithms - Google Patents

Abstract

The invention discloses an emergency repair vehicle system containing an XED light source and an intelligent scheduling method based on the BP-Dijkstra algorithm. The system includes an intelligent scheduling unit, a vehicle navigation terminal unit, a monitoring information management unit, and a data entry and report analysis unit; The intelligent dispatching unit includes an information server module, an intelligent fault location module and a repair dispatching module; the vehicle navigation terminal unit includes an XED energy-saving lighting module, a GPRS wireless network module, and a GPS receiving module; the monitoring information management unit includes a GIS geographic information module, a positioning monitoring system module, a status monitoring system module, and a remote image capture module; the data entry and report analysis unit includes a data entry module, a report analysis module, and the data bus module. The beneficial effect is that scientific and reasonable emergency repair scheduling can be carried out according to the location information of the fault, the scheduling time can be reduced to the greatest extent, intelligent scheduling can be realized, manpower and material resources can be saved, and the timely emergency repair of power failure can be facilitated.

Description

Emergency repair vehicle system with XED light source and intelligent system based on BP-Dijkstra algorithm scheduling method

technical field

The invention relates to the field of power emergency repair systems, in particular to an emergency repair vehicle system containing an XED light source and an intelligent scheduling method based on the BP-Dijkstra algorithm.

Background technique

With the continuous development of the national economy and the continuous expansion of the scale of the power grid, ensuring the normal use of electricity by power users is the basis for the service of the power grid company. It often causes power failures and large-scale power outages, which is not conducive to the safety and stability of the power system and the long-term development of power companies. Therefore, whether the emergency repair is timely after the power failure occurs is the key to solving the power failure problem. The main questions are as follows:

1. Emergency repair dispatching: At present, power grid companies mainly rely on the 95598 manual dispatching platform to dispatch electric emergency repair vehicles. According to decision makers' information on the cause and location of faults, human judgments and dispatches are made. This scheduling method lacks scientific basis, cannot minimize the scheduling time, lacks scheduling tools to realize intelligent scheduling, and the scheduling method is obviously backward, consuming manpower and material resources, and is not conducive to the emergency repair of power failures.

2. The problem of emergency repair monitoring: At present, the supervision of the emergency repair process is insufficient, and the emergency repair experts cannot give on-site guidance in real time, resulting in the control center not being able to know the emergency repair progress and process in real time, and the emergency repair personnel cannot be assessed. In remote areas, grass-roots emergency repair personnel have poor communication with the control center, which reduces the efficiency of emergency repairs and cannot efficiently mobilize emergency repair vehicles. As a result, the work orders in the application system cannot achieve the expected results, which is not conducive to the rapid and effective restoration of power supply.

3. On-site lighting problems: At present, electric emergency repair vehicles are large in size, but their functions are relatively simple. They are engaged in relatively simple emergency repair work. Most of the lighting sources equipped with emergency repair vehicles still use traditional light sources such as sodium lamps, metal halide lamps, and LED lamps, and the illumination is low. , high energy consumption, poor heat dissipation, fast light decay, short service life, and serious harm to human body caused by blue light. In the case of insufficient light and complex environment at night for emergency repairs, the lack of good lighting sources will lead to the efficiency of emergency repair personnel. Low, prone to mistakes.

Contents of the invention

The technical problem to be solved by the present invention is to provide an emergency repair vehicle system with XED light source and a BP-Dijkstra algorithm-based system that can solve the problem of low repair efficiency caused by inflexible dispatching methods, backward monitoring methods, and insufficient on-site light source irradiation. Smart scheduling method.

The technical scheme involved in the present invention is as follows:

An emergency repair vehicle system containing an XED light source, including an intelligent dispatching unit, a vehicle navigation terminal unit, a monitoring information management unit, and a data entry and report analysis unit;

The intelligent dispatching unit includes an information server module, an intelligent fault location module and a repair scheduling module; the data interface of the information server module is respectively connected with the data bus module data of the intelligent fault location module, the repair dispatching module and the data entry and report analysis unit; The server module is used to realize the two-way data transmission between the intelligent dispatching unit and the data entry and report analysis unit, and the monitoring information management unit; The BP-Dijkstra algorithm enables the electric repair vehicle to quickly arrive at the fault site in the shortest time;

The vehicle navigation terminal unit includes an XED energy-saving lighting module, a GPRS wireless network module, and a GPS receiving module, and the XED energy-saving lighting module includes a communication circuit, a motor control circuit and a lighting drive circuit; the control output of the motor control circuit is connected to the emergency repair vehicle The XED lighting motor module is connected to control the irradiation position and irradiation angle of the XED lighting; the lighting drive circuit is connected to the XED lighting voltage module of the emergency repair vehicle to control the lighting brightness of the XED lighting; GPRS wireless The network module is respectively connected with the network interface of the communication circuit, the data sending end of the GPS receiving module, the data bus module of the data entry and report analysis unit, and the illuminance sensor data of the emergency repair vehicle. The GPRS wireless network module is used to realize the vehicle navigation terminal unit and Two-way transmission of data between the monitoring information management unit, the intelligent dispatching unit, and the data entry and report analysis unit, and the GPS receiving module is used to realize the precise positioning of the electric emergency repair vehicle;

The monitoring information management unit includes a GIS geographic information module, a positioning monitoring system module, a status monitoring system module, and a remote image capture module; the data interface of the GIS geographic information module is respectively connected with the positioning monitoring system module, the status monitoring system module, and the remote image The capture module data connection, the data interface of the positioning monitoring system module, the status monitoring system module and the remote image capture module are respectively connected with the data bus module of the data entry and report analysis unit; the GIS geographic information module is used to realize the display of dynamic map data And directly reflect the overall operation status; the positioning monitoring system module is used to realize the electronic display of the power network and traffic network, the status monitoring system module is used to realize the real-time display of the status of power equipment and the status of electric repair vehicles, and the remote image capture module is used to realize Supervise on-site emergency repair progress;

The data entry and report analysis unit includes a data entry module, a report analysis module and the data bus module; the data output terminals of the data entry module and the report analysis module are respectively connected with the data bus module, and the data bus module is used for Realize data collection, summary and exchange, the data entry module is used to manage the use of emergency repair vehicles and record customer feedback information, and the report analysis module is used to realize repair log records and query functions.

Preferably, the intelligent fault location module includes a remote sensor circuit and a wireless data receiving circuit, and the data sending end of the remote sensor circuit is wirelessly connected to the data receiving end of the wireless data receiving circuit.

Preferably, the positioning monitoring system module includes a digital-to-analog signal conversion circuit and a video format conversion circuit, and the data output end of the digital-to-analog signal conversion circuit is connected to the data input end of the video format conversion circuit.

An intelligent scheduling method based on the BP-Dijkstra algorithm, comprising the following steps:

1. Define the period vector I, determine several sets of sample data and divide them into training sample data and test sample data, each set of sample data is a sample pair composed of sample input data and expected output data, and normalize the sample data ;

2. Establish the BP neural network model of the input layer, hidden layer and output layer, and select the excitation function, training function and learning function;

The input layer includes road traffic volume, traffic density, road length, number of lanes, road surface type, slope, lane function division, and lateral clearance, a total of 8 neuron nodes; the output layer is the average speed of vehicles passing through the road section during the corresponding period Value v, a total of 1 neuron node; the hidden layer is determined by the empirical formula Confirm, in the formula, G is the number of neurons in the hidden layer, n is the number of input neurons in the input layer, m is the number of output neurons in the output layer, the value of a is a constant between 1 and 10, and according to the training sample data , test the sample data to train the BP neural network model, and finally determine the value of a;

3. Initialize the weights and thresholds of the neural network, set the number of training steps and training error precision, predict the speed value v, and determine the distance matrix D;

4. Initialize the navigation initial time t ₀ , set t ₀ ∈ [T _k-1 ,T _k ], k=1,2,3...48, T _k represents the divided time period; initialize the initial position S ₀ , that is, S={ S ₀ }, S'=NS; S means the node set of the path traveled, S' means the node set of the remaining path, and N means the node set of the traffic road network;

5. Let i∈S, j∈S', i represents the initial node, j represents the midway node, and the formula for calculating the travel time t _ij of road section i→j is: d _ij and v _ij respectively represent the driving path and average speed of the i→j section;

6. According to L _ij = min(t _ij ), determine the next midway node j of the path, and modify and determine new S and S' according to L _ij , that is, S _new = S∪{j}, S' _new = S'- {j}; L _ij represents the shortest travel time under different routes;

7. L=ΣL _ij , Z={d _ij }, L represents the sum of the shortest travel time, Z represents the path node corresponding to the shortest time;

8. If j=n, n is the destination node, calculate the shortest travel time L and the path Z corresponding to the shortest time according to step 7; otherwise, set i=j for the node j newly added to S, and return to step 5.

As a further preference, the sample input data in step 1 includes road traffic volume, traffic density, road length, number of lanes, road surface type, slope, lane function division and lateral clearance, and the expected output data is the driving speed of the corresponding time period.

The beneficial effects of the present invention are:

1. Scientific and reasonable emergency repair scheduling can be carried out according to the location information of the fault, which can minimize the scheduling time, realize intelligent scheduling, save manpower and material resources, and facilitate timely repair of power failures.

2. The monitoring information management unit can supervise the emergency repair process, and can realize the real-time on-site guidance of the emergency repair experts, realize the real-time information of the emergency repair progress and the emergency repair process in the control center, and assess the emergency repair personnel; especially in remote areas, it can ensure The smooth communication between grass-roots emergency repair personnel and the control center improves the efficiency of emergency repairs, and enables efficient mobilization of emergency repair vehicles, which is conducive to the rapid and effective restoration of power supply.

3. Through the vehicle navigation terminal unit, the XED light source can be adjusted in time according to the actual situation of the fault site. In the case of insufficient light and complex environment at the fault site at night, it can provide a good lighting source to improve the repair efficiency of the rescue personnel.

Description of drawings

Fig. 1 is the structural block diagram of the emergency repair vehicle system containing XED light source involved in the present invention;

Fig. 2 is the algorithm flow chart of the intelligent scheduling method of the present invention based on BP-Dijkstra algorithm to realize that the electric emergency repair vehicle arrives at the fault scene quickly in the shortest time;

Fig. 3 is 7:00 to 7:30 period traffic road network speed prediction results in the specific embodiment of the present invention;

Fig. 4 is a schematic diagram of a traffic road network in a specific embodiment of the present invention.

detailed description

The specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

As shown in Figure 1, the present invention relates to an emergency repair vehicle system containing XED light sources, including an intelligent dispatching unit, a vehicle navigation terminal unit, a monitoring information management unit, and a data entry and report analysis unit.

The intelligent dispatching unit includes an information server module, an intelligent fault location module and a repair scheduling module; the data interface of the information server module is respectively connected with the data bus module data of the intelligent fault location module, the repair dispatching module and the data entry and report analysis unit; The server module is used to realize the two-way transmission of data between the intelligent scheduling unit and the data entry and report analysis unit, and the monitoring information management unit. The intelligent fault location module includes remote sensor circuits and wireless data receiving circuits, and the data transmission of remote sensor circuits The end is wirelessly connected with the data receiving end of the wireless data receiving circuit, and is used to locate fault points in the power network. The emergency repair scheduling module is used to realize the intelligent scheduling method based on the BP-Dijkstra algorithm to realize the electric emergency vehicle to arrive at the fault site in the shortest time.

The vehicle navigation terminal unit includes an XED energy-saving lighting module, a GPRS wireless network module, and a GPS receiving module. The XED energy-saving lighting module includes a communication circuit, a motor control circuit and a lighting drive circuit, and the signal output terminals of the communication circuit are respectively connected to the motor control circuit. Connect to the input terminal of the lighting driving circuit. The control output end of the motor control circuit is connected to the XED lighting motor module of the emergency repair vehicle, and is used to control the irradiation position and the irradiation angle of the XED lighting; the lighting drive circuit is connected to the XED lighting voltage module of the emergency repair vehicle , used to control the lighting brightness of the XED lighting; the GPRS wireless network module is respectively connected to the network interface of the communication circuit, the data sending end of the GPS receiving module, the data bus module of the data entry and report analysis unit, and the light sensor data of the emergency repair vehicle The GPRS wireless network module is used to realize the two-way transmission of data between the vehicle navigation terminal unit and the monitoring information management unit, the intelligent dispatching unit, and the data entry and report analysis unit, and transmit the received data to the motor control circuit and the report analysis unit respectively through the communication circuit. The lighting drive circuit, the GPS receiving module is used to realize the precise positioning of the electric emergency repair vehicle.

The monitoring information management unit includes a GIS geographic information module, a positioning monitoring system module, a status monitoring system module, and a remote image capture module; the data interface of the GIS geographic information module is respectively connected with the positioning monitoring system module, the status monitoring system module, and the remote image The data connection of the capturing module, the data interfaces of the positioning monitoring system module, the state monitoring system module and the remote image capturing module are respectively connected with the data bus module of the data entry and report analysis unit. The GIS geographic information module is used to realize the display of dynamic map data and directly reflect the overall operation status; the positioning monitoring system module includes a digital-to-analog signal conversion circuit and a video format conversion circuit, and the data output terminal of the digital-to-analog signal conversion circuit and the video format conversion circuit The data input terminal connection is used to realize the electronic display of the power network and the traffic network; the status monitoring system module is used to realize the real-time display of the status of the power equipment and the status of the power repair vehicle, and the remote image capture module is used to realize the supervision of the on-site repair progress.

The data entry and report analysis unit includes a data entry module, a report analysis module and the data bus module; the data output terminals of the data entry module and the report analysis module are respectively connected with the data bus module, and the data bus module is used for Realize data collection, summarization and exchange, the data entry module is used to manage the use of emergency repair vehicles, record customer feedback information and other functions, and the report analysis module is used to realize repair log records, queries and other functions.

As shown in Figure 2, the intelligent scheduling method based on the BP-Dijkstra algorithm to realize the rapid arrival of the electric repair vehicle at the fault site in the shortest time includes the following steps:

1. Define the period vector I, I=[T ₀ , T ₁ ,...,T _k ]; determine several groups of sample data and divide them into training sample data and test sample data, each group of sample data is composed of sample input data and A sample pair composed of expected output data, and normalize the sample data; the sample input data includes road traffic volume, traffic density, road length, number of lanes, road surface type, slope, lane function division and lateral clearance, The expected output data is the driving speed of the corresponding time period.

2. Establish the neural network model of the input layer, hidden layer, and output layer, and select the excitation function, training function, and learning function. The input layer includes road traffic volume, traffic density, road length, number of lanes, road surface type, slope, lane function division, and lateral clearance, a total of 8 neuron nodes; the output layer is the average speed of vehicles passing through the road section during the corresponding period Value v, a total of 1 neuron node; the hidden layer is determined by the empirical formula Confirm, in the formula, G is the number of neurons in the hidden layer, n is the number of input neurons in the input layer, m is the number of output neurons in the output layer, the value of a is a constant between 1 and 10, and according to the training sample data 1. Test the sample data to train the BP neural network model, and finally determine the value of a.

3. Initialize the weights and thresholds of the neural network, set the number of training steps and training error precision, predict the speed value v, and determine the distance matrix D.

4. Initialize the navigation initial time t ₀ , set t ₀ ∈ [T _k-1 ,T _k ], k=1,2,3...48, T _k represents the divided time period; initialize the initial position S ₀ , that is, S={ S ₀ }, S'=NS; S represents the node set of the traversed path, S' represents the node set of the remaining path, and N represents the node set of the traffic road network.

5. Let i∈S, j∈S', i represents the initial node, j represents the midway node, and the formula for calculating the travel time t _ij of road section i→j is: d _ij and v _ij represent the driving path and average speed of the i→j road segment, respectively.

6. According to L _ij = min(t _ij ), determine the next midway node j of the path, and modify and determine new S and S' according to L _ij , that is, S _new = S∪{j}, S' _new = S'- {j}; L _ij represents the shortest travel time under different routes.

7. L=∑L _ij , Z={d _ij }, L represents the sum of the shortest travel time, and Z represents the path node corresponding to the shortest time.

8. If j=n, n is the destination node, then calculate the shortest travel time L and the path Z corresponding to the shortest time according to step 7; otherwise, set i=j for the node j newly added to S, and return to step 5.

Figure 4 is a schematic diagram of the traffic road network of the emergency repair vehicle system with XED light source based on the BP-Dijkstra algorithm, N=[0, 1, 2, 3, 4]. During the time period from 7:00 to 7:30, when the fault occurs at the location node 4, the fault information and the repair vehicle information are uploaded to the monitoring information management unit through the GIS geographic information module, and the monitoring information management unit will pass the location and status of the repair vehicle through the data The bus module transmits to the intelligent dispatching unit, and the emergency repair dispatching module of the intelligent dispatching unit issues dispatching instructions to select emergency repair vehicles near the fault point. Under the condition of insufficient light in the emergency repair environment, the XED energy-saving lighting module adjusts the XED lighting motor module to change the brightness through the lighting drive circuit; at the same time, it changes the irradiation direction and adjusts the irradiation angle through the motor control circuit to provide a good lighting environment. .

The intelligent scheduling method based on the BP-Dijkstra algorithm that the emergency repair scheduling module realizes enables the electric emergency repair vehicle to arrive at the fault scene in the shortest time, and includes the following steps:

1. Obtain road condition data through the traffic website, and use MATLAB-2011b simulation software to predict the speed of the case. Define the period vector I=[T ₀ , T ₁ ,...,T _k ], obtain 365 sets of sample data and divide them into training sample data and test sample data; each set of sample data is composed of sample input data and expected output data sample pairs, and normalize the sample data; the sample input data includes road traffic volume, traffic density, road length, number of lanes, road surface type, slope, lane function division and lateral clearance, and the expected output data is corresponding to The driving speed of the time period.

2. Establish a three-layer BP neural network structure model of input layer-hidden layer-output layer, select Sigmoid as the excitation function, traindm as the training function, and learndm as the learning function;

The input layer includes road traffic volume, traffic density, road length, number of lanes, road surface type, slope, lane function division, and lateral clearance, a total of 8 neuron nodes; the output layer is the corresponding 30-minute period average speed value v, A total of 1 neuron node; the hidden layer is determined by the empirical formula Definitely, G in the formula is the number of neurons in the hidden layer, n is the number of input neurons in the input layer, m is the number of output neurons in the output layer, the value of a is a constant between 1 and 10, and according to the training sample data, test The sample data trains the BP neural network model, and finally determines the value of a.

3. Initialize the weights and thresholds of the neural network, set the number of training steps to 500, and the training error accuracy to 0.0005, and predict the speed value v _(k) , k=1,2,3...10, the simulation results are shown in Figure 3 The predicted data are as follows:

v _(k) = 30.9331 29.9269 34.8314 37.2058 44.9103 40.3679 46.0495 49.976150.1624 44.0109.

Indicates the speed of vehicles traveling on the road from source node 0 to node 4 during the period from 7:00 to 7:30, with a total of 10 sets of data.

The schematic diagram of the traffic road network is shown in Figure 4, and the distance matrix is:

4. Initialize the navigation initial time t ₀ , set the time t ₀ ∈ [7:00-7:30]; select the initial position S ₀ = 0, that is, S = [0], S' = [1,2,3,4 ].

5. Let i∈S, j∈S', the travel time of road section i→j is d _ij and v _ij represent the driving path and average speed of the i→j road segment, respectively.

6. Let i=0, j=1, j=2, j=3, j=4 respectively, calculate the travel time t ₀₁ of the route from source node 0 to node 1 according to step 5 respectively, and from source node 0 to node 1 The path of 1 is d ₀₁ =45, the average speed is v ₀₁ =30.9331; the travel time of the path from source node 0 to node 2 is t ₀₂ =2.3390, the path from source node 0 to node 2 is d ₀₂ =70, and the average speed is v ₀₂ =29.9269; the travel time t ₀₃ of the route from source node 0 to node 3 =0.8612, the route from source node 0 to node 3 is d ₀₃ =30, and the average speed is v ₀₃ =34.8314; the route from source node 0 to node 4 travels Time t ₀₄ =2.6877, the path from source node 0 to node 4 is d ₀₄ =100, the average speed is v ₀₄ =37.2058; from L _ij =min(t _ij ), get L ₀₃ =t ₀₃ ; from S _new =S ∪{j}, _S'new =S'-{j}; calculated: _Snew =[0,3], _S'new =[1,2,4], Z=d ₀₃ ;

7. According to the formula L=∑L _ij , Z={d _ij }, it can be obtained that L=L ₀₃ , Z=d ₀₃ , L represents the shortest travel time, and Z represents the path node corresponding to the shortest time;

8. If j=4, then the algorithm stops, and calculates the shortest travel time L and the path Z corresponding to the shortest time according to step 7; otherwise, for the node 3 newly added to S, let i=j, i.e. i=3, respectively make j=1, j=2, j=4, return to step 5 to calculate the path travel time from node 3 to node 1, node 2 and node 4 respectively;

The path d ₃₁ =25 from node 3 to node 1 has an average speed of v ₃₁ =40.3679, and the calculated t ₃₁ =0.6193;

The path d ₃₂ =20 from node 3 to node 2 has an average speed of v ₃₂ =49.9761, and the calculated t ₃₂ =0.4001;

The path d ₃₄ =60 from node 3 to node 4, the average speed is v ₃₄ =44.0109, calculated t ₃₄ =1.3632;

9. According to the formula in step 6, get S _new = [0,3,2], S' _new = [1,4];

10. According to the formula in step 7: L=∑L _ij , Z={d _ij }; get L=L ₀₃ +L ₃₂ , Z=d ₀₃ -d ₃₂ ;

11. Repeat judgment if j=4, then the algorithm stops; otherwise, for newly added S node 2, set i=j, i.e. i=2, set j=1, j=4 respectively, return to step 5 to calculate from node 2 to The route travel time of node 1 and node 4;

The path d ₂₁ = 50 from node 2 to node 1, the average speed is v ₂₁ = 44.9103, calculated t ₂₁ = 1.1133;

The path from node 2 to node 4 is d ₂₄ =10, the average speed is v ₂₄ =50.1624, and t ₂₄ =0.1993 is calculated;

12. According to the formula in step 6, get S _new =[0,3,2,4], S' _new =[1];

13. According to the formula in step 7: L=∑L _ij , Z={d _ij }, L=L ₀₃ +L ₃₂ +L ₂₄ , Z=d ₀₃ -d ₃₂ -d ₂₄ , L represents the shortest path travel time , Z represents the path node corresponding to the shortest time; at this time, the j=4 algorithm stops, and the optimal path Z=d ₀₃ -d ₃₂ -d ₂₄ and the optimal time L=L ₀₃ +L ₃₂ +L ₂₄ =1.4606 are obtained through calculation .

Although the embodiment of the present invention has been disclosed as above, it is not limited to the use listed in the specification and implementation, it can be applied to various fields suitable for the present invention, and it can be easily understood by those skilled in the art Therefore, the invention is not limited to the specific details and examples shown and described herein without departing from the general concept defined by the claims and their equivalents.

Claims (5)

1. a kind of emergency first-aid repair car system of light source containing XED, it is characterized in that：Including intelligent scheduling unit, vehicle mounted guidance terminal list Member, monitoring information administrative unit, data inputting and statement analysis unit；

The intelligent scheduling unit includes information service module, intelligent trouble locating module and repairing scheduler module；Information takes The data-interface for device module of being engaged in respectively with intelligent trouble locating module, repairing scheduler module and data inputting and statement analysis list The data bus module data cube computation of member；Information service module is used to realize intelligent scheduling unit respectively with data inputting with reporting Data double-way transmission between table analysis unit, monitoring information administrative unit；Intelligent trouble locating module is used to realize power network Localization of fault in network, repairing scheduler module is used to realize makes electric power rush-repair vehicle with most in short-term based on BP-Dijkstra algorithms Between quickly arrive at fault in-situ；

The vehicle mounted guidance terminal unit includes XED energy-saving illuminations module, GPRS wireless network modules, GPS receiver module, XED Energy-saving illumination module includes telecommunication circuit, circuit for controlling motor and illumination driving circuit；The control of the circuit for controlling motor is defeated Go out end to be connected with the XED illuminating lamp motor modules of emergency first-aid repair car, irradiation position and illumination angle for controlling XED illuminating lamps Degree；The illumination driving circuit is connected with the XED lighting modulating voltage modules of emergency first-aid repair car, the photograph for controlling XED illuminating lamps Lightness；Network interface, the data sending terminal and number of GPS receiver module of GPRS wireless network modules respectively with telecommunication circuit According to typing and the data bus module and the illuminance sensor data cube computation of emergency first-aid repair car of statement analysis unit, GPRS is wireless Mixed-media network modules mixed-media is used to realize vehicle mounted guidance terminal unit and monitoring information administrative unit, intelligent scheduling unit and data inputting and report Data double-way transmission between table analysis unit, the GPS receiver module is used to realize being accurately positioned for electric power rush-repair vehicle；

The monitoring information administrative unit includes GIS geography information module, locating and monitoring system module, condition monitoring system mould Block, distal end image capture module；The data-interface of GIS geography information modules respectively with locating and monitoring system module, condition monitoring System module and distal end image capture module data cube computation, locating and monitoring system module, condition monitoring system module and distal view As the data-interface of capture module is connected with data inputting with the data bus module of statement analysis unit respectively；The GIS Managing information module is used to realize display dynamic map data and directly reflects overall operation situation；Locating and monitoring system module is used for Realize that electric power networks are electronically displayed with transportation network, condition monitoring system module is used to realize that status of electric power and electric power are robbed The real-time display for the state that repairs, distal end image capture module is used to realize supervision scene rush to repair progress；

The data inputting includes data inputting module, statement analysis module and the data/address bus mould with statement analysis unit Block；The data output end of the data inputting module and statement analysis module is connected with data bus module respectively, the data Bus module is for realizing Data Collection, collecting and exchange, and data inputting module is used to realize that management emergency first-aid repair car uses feelings Condition, record client feedback information, statement analysis module are used to realize repairing log recording and query function.

2. the emergency first-aid repair car system of the light source according to claim 1 containing XED, it is characterized in that：The intelligent trouble positioning Module includes distal sensor circuit and wireless data receiving circuit, the data sending terminal and wireless data of distal sensor circuit The data receiver wireless connection of receiving circuit.

3. the emergency first-aid repair car system of the light source according to claim 1 containing XED, it is characterized in that：The locating and monitoring system Module includes digital and analogue signals change-over circuit and video format conversion circuit, the data output end and video of digital and analogue signals change-over circuit The data input pin connection of format conversion circuit.

4. a kind of emergency first-aid repair car system of the light source containing XED as claimed in claim 1 use based on BP-Dijkstra algorithms Intelligent dispatching method, it is characterized in that as follows comprising step：

(1) vector paragraph I when defining, determines some groups of sample datas and is divided into training sample data and test samples data, every group The sample pair that sample data is made up of sample input data and desired output data, and sample data is normalized place Reason；

(2) the BP neural network model of input layer, hidden layer, output layer, selection excitation function, training function and study are set up Function；

The input layer includes road Traffic Volume, traffic density, link length, number of track-lines, road surface types, the gradient, lane function Divide, lateral clearance, totally 8 neuron nodes；Output layer is correspondence vehicle average speed value v of the period by the section, totally 1 Individual neuron node；Hidden layer is by empirical equationIt is determined that, G is hidden layer neuron number in formula, and n is defeated Enter layer input neuron number, m is output layer output neuron number, and a span is the constant between 1~10, and according to instruction Practice sample data, test samples data to be trained BP neural network model, finally determine a values；

(3) initialization neural network weight, threshold value, setting train epochs and training error precision, carry out velocity amplitude v predictions, really Set a distance matrix D；

(4) initialization navigation initial time t₀If, t₀∈[T_k-1,T_k], k=1,2,3 ... 48, T_kRepresent to divide the period；Initialization Initial position S₀, i.e. S={ S₀, S'=N-S；S represents path node set of passing by, S ' expression residual paths node sets, N tables Show traffic network node set；

(5) i ∈ S, j ∈ S', i is made to represent start node, j represents midway node, section i → j running time t_ijCalculation formula For：d_ijAnd v_ijThe driving path and average speed in i → j sections are represented respectively；

(6) according to L_ij=min (t_ij), determine the next midway node in path_j, and according to L_ijModification determines new S and S ', i.e. S_Newly= S ∪ { j }, S '_Newly=S '-{ j }；L_ijRepresent the most short running time under different paths；

(7) L=Σ L_ij, Z={ d_ij, L represents most short running time sum, and Z represents the path node of correspondence shortest time；

(8) if j=n, n are purpose node, the path Z of most short running time L and correspondence shortest time are calculated according to step 7； Otherwise to the new node j for adding S, i=j, return to step 5 are made.

5. the intelligent dispatching method according to claim 4 based on BP-Dijkstra algorithms, it is characterized in that：The step (1) the sample input data in includes road Traffic Volume, traffic density, link length, number of track-lines, road surface types, the gradient, track Function is divided and lateral clearance, and desired output data are the road speed of correspondence period.