CN204044340U - A kind of light fault detection system - Google Patents
A kind of light fault detection system Download PDFInfo
- Publication number
- CN204044340U CN204044340U CN201420484153.3U CN201420484153U CN204044340U CN 204044340 U CN204044340 U CN 204044340U CN 201420484153 U CN201420484153 U CN 201420484153U CN 204044340 U CN204044340 U CN 204044340U
- Authority
- CN
- China
- Prior art keywords
- controller
- signal
- detection system
- data
- car light
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Lighting Device Outwards From Vehicle And Optical Signal (AREA)
Abstract
The utility model relates to a kind of light fault detection system, belongs to automotive field, and this system comprises the voltage and current signal that signal gathering unit gathers car light circuit; Controller, utilize genetic optimization BP network algorithm to the data analysis process of collecting unit, voltage, the current signal of observation circuit are no more than system thresholds; Display screen, connection control device, the detection Output rusults of display controller; Alarm unit, connection control device, sends warning and reminds after receiving the alarm signal of controller.The utility model can the whether normally bright problem of Real-Time Monitoring car light remind the brightness of driver's car light to reduce problem in time, decreases the potential safety hazard of running car.The car light signal data of BP network algorithm to collecting unit collection after simultaneously applying genetic optimization in automobile detection system of the present utility model processes, real-time optimal data can be optimized to controller, avoid abnormal data that accidentalia causes and transfer to the false alarm situation that controller causes.
Description
Technical field
The utility model relates to automotive field, particularly a kind of car light fault detect.
Background technology
Automobile there is various lamp as headlight, taillight, steering indicating light and Brake lamp, but in driving process, car light whether normal luminous, without any prompting in car, driver only has could find fault by quantitative check, and can not get rid of car light fault in time can bring very large hidden danger to vehicle security drive.
Except car light does not work except this fault, the brightness of car light also can due to the circuit problem of automotive interior or tenure of use problem and dimmed, affect the normal usage function of car light.And the bulb of large lampet in use, filament often blows, and causes bulb to burn, and its reason has voltage regulator to have fault, overtension; The many reasons such as short circuit are had between generator armature and field coil.
Summary of the invention
In order to solve the deficiency that in prior art, automobile is not pointed out the car light situation that do not work, the utility model provides a kind of light fault detection system.
The technical solution of the utility model is: a kind of light fault detection system, and this system comprises
Signal gathering unit, connection control device, gathers the voltage and current signal of car light circuit;
Controller, the information of Received signal strength collecting unit, utilize genetic optimization BP network algorithm to the data analysis process of collecting unit, voltage, the current signal of observation circuit are no more than system thresholds;
Display screen, connection control device, the detection Output rusults of display controller;
Alarm unit, connection control device, sends warning and reminds after receiving the alarm signal of controller.
Described signal gathering unit comprises voltage sensor, current sensor and luminance sensor.Sensor in described signal gathering unit is uniformly distributed.Described controller does not receive voltage signal data or current signal data all can send warning prompting to alarm unit.Described controller is provided with database, and database is for preserving the information of signal gathering unit.Described alarm unit comprises hummer and warning lamp, is positioned on display screen.
The utility model has following good effect: light detecting system in the utility model, can the whether normally bright problem of Real-Time Monitoring car light remind the brightness of driver's car light to reduce problem in time, decreases the potential safety hazard of running car.The car light signal data of BP network algorithm to collecting unit collection after simultaneously applying genetic optimization in automobile detection system of the present utility model processes, real-time optimal data can be optimized to controller, avoid abnormal data that accidentalia causes and transfer to the false alarm situation that controller causes.
Accompanying drawing explanation
Fig. 1 is the theory diagram of the light detecting system in the utility model;
Fig. 2 is the workflow diagram of the light detecting system method in the utility model;
Fig. 3 is the process flow diagram of the BP neural network of genetic algorithm optimization in the utility model;
Fig. 4 is the process flow diagram of the neural network algorithm in the utility model.
Embodiment
Contrast accompanying drawing below, by the description to embodiment, embodiment of the present utility model is as the effect of the mutual alignment between the shape of involved each component, structure, each several part and annexation, each several part and principle of work, manufacturing process and operation using method etc., be described in further detail, have more complete, accurate and deep understanding to help those skilled in the art to inventive concept of the present utility model, technical scheme.
A kind of light fault detection system, as shown in Figure 1, this system comprises signal gathering unit, controller, display screen and alarm unit, controller connection signal collecting unit, display screen and alarm unit.
In system, signal gathering unit connection control device, gather the voltage and current signal of car light circuit, signal gathering unit comprises voltage sensor, current sensor and luminance sensor, and sensor has multiple signals collecting of carrying out also evenly to arrange.Luminance sensor is positioned at the other Real-Time Monitoring vehicle lamp brightness of car light and luminance signal is sent to controller and carries out data analysis and process, voltage and current sensor is arranged in the circuit system of car light, voltage in Real-Time Monitoring car light, current conditions, and whether the data monitored being sent to controller, to carry out analysis circuit normal.
Controller, the information of Received signal strength collecting unit also sends a signal to display screen and alarm unit, judges whether the signal of collecting unit is less than system normality threshold, once be greater than system thresholds, send alarm signal to alarm unit and display screen in controller.If controller does not receive the signal of collecting unit, be likely that car light inside circuit has wire to blow or other reasons forms off state, controller will send alarm signal equally to alarm unit and display screen.When the electric current and voltage in car light circuit is abnormal, be likely that car light circuit load is excessive, conductor overheating can be caused to cause car light to be burnt or affect engine and normally run.The brightness monitoring no less important of car light simultaneously, particularly evening foggy or dark weather, when visibility is very low, because the car light long vehicle lamp brightness reduction caused service time can affect the normal driving of driver, affect the judgement of surrounding vehicles to this vehicle operating direction simultaneously.So once find voltage, the current coefficient detection exception in car light circuit, driver must on-call maintenance.In the utility model system, utilize genetic optimization BP network algorithm to the data analysis process of collecting unit in controller, the training of algorithm model utilizes the database data arranged in controller to carry out preserving in database data and the historical data of signal gathering unit, conveniently carry out machine training, in controller, the voltage of observation circuit, current signal are no more than system thresholds; After utilizing the data of this algorithm optimization collecting unit, real-time optimal data can be optimized to controller, avoid abnormal data that accidentalia causes and transfer to the false alarm situation that controller causes.
Display screen, connection control device, the detection Output rusults of display controller, like this can be clearer and more definite demonstrate which car light do not work or brightness inadequate, facilitate searching and keeping in repair of driver.
Alarm unit, connection control device, alarm unit comprises hummer and warning lamp, can be positioned on display screen, sends warning and remind after receiving the alarm signal of controller.Controller does not receive voltage signal data or current signal data all can send warning prompting to alarm unit.
A kind of light fault detection system method, as shown in Figure 2, the method step comprises:
The signal of S01 step one, collection car light and car light circuit.Step one completes collection signal task by signal gathering unit and mainly comprises voltage sensor, current sensor and luminance sensor, gather the luminance signal of car light and the voltage and current signal of car light circuit, voltage in Real-Time Monitoring car light, current conditions, and whether the data monitored being sent to controller, to carry out analysis circuit normal.
S02 step 2, utilize the BP neural network model of genetic optimization to carry out pre-service to the data that step one collects, the BP neural network model of genetic optimization is positioned at system controller inside, to the Data Management Analysis that controller receives.
First the BP neural network model of genetic optimization carries out pre-service to the data collected, pre-service is normalized the data that sensor records, normalization can accelerate the convergence of training network, and normalized concrete effect is the statistical distribution concluding unified samples.No matter be in order to modeling or in order to calculate, first basic measuring unit is same, the use of convenient Genetic BP Neutral Network algorithm below.
Data after S03 step 3, network model analyzing and processing.The BP neural network model of genetic optimization mainly carries out the BP neural network algorithm Treatment Analysis of genetic optimization to data, select optimum, most accurate data.
Genetic BP Neutral Network algorithm is mainly divided into three parts: determine BP neural network structure; Genetic algorithm optimization weights and threshold; BP neural metwork training and prediction.Its flow process as shown in Figure 3, Figure 4, first the topological structure of neural network is determined, then coding is carried out to the weights and threshold of neural network and obtain initial population, genetic algorithm processing section is entered after the process of neural network algorithm part, the new colony produced in genetic algorithm continues when can not meet end condition to run from neural network algorithm part, if meet end condition, carries out decoding process and obtains best neural network weight and threshold value.
BP part of neural network process flow diagram in BP neural network algorithm after genetic optimization as shown in Figure 4, after initial population is obtained to neural network weight and threshold coding, decoding obtains weights and threshold, weights and threshold is assigned to newly-built BP network, use training sample training network, then use test sample book test network, finally carry out test error, continue to enter in genetic algorithm flow process.Network training is a process constantly revising weights and door screen value, by training, makes the output error of network more and more less.
The learning algorithm of BP neural network is based on Gradient Descent, and therefore easy local minimum, exists the slow and network parameter of speed of convergence simultaneously and training parameter is difficult to shortcomings such as determining.Genetic algorithm is a kind of searching algorithm using for reference organic sphere natural selection and natural genetic mechanism, and it can find optimum or quasi-optimal solution in complicated and huge search volume, and has the advantages such as algorithm is simple, applicable, strong robustness, and its application is very ripe at present.Based on the relative merits of BP artificial neural network and genetic algorithms, the two is combined the relative merits making them complementary, have greatly improved.
BP neural network structure is topological structure, is to determine according to the input/output parameters number of sample, so just can determine the number of genetic algorithm optimization parameter, thus determine the code length of population at individual.Because genetic algorithm optimization parameter is initial weight and the door screen value of BP neural network, as long as network structure is known, the number of weights and news value just there is known.The weights and threshold of neural network is generally be [-0.5 by random initializtion, 0.5] interval random number, this initiation parameter is very large on the impact of network training, but cannot accurately obtain again, for identical initial weight value and threshold value, the training result of network is the same, and introducing genetic algorithm is exactly initial weight in order to optimization the best and threshold value, and then selects optimum data.
Genetic algorithm optimization BP neural network is initial weight value and the threshold value of carrying out Optimized BP Neural Network by genetic algorithm, enables the BP neural network after optimization carry out sample predictions better.
Genetic algorithm key element in genetic algorithm optimization BP neural network comprises:
A. fitness is calculated.Calculate and be suitable for angle value: ideal adaptation degree adopts the function error of network, and its fitness of individuality that namely error is large is little, is specifically expressed as the inverse that fitness is network error function.The utility model is in order to make BP network when predicting, the residual error of predicted value and expectation value is little as far as possible, so select the output of norm as objective function of the predicted value of forecast sample and the error matrix of expectation value.
B. selective staining body copies.Selective staining body copies: after the calculating of ideal adaptation degree completes, and selects individual inheritance that fitness is large to the next generation, makes weights more and more close to optimum solution.
C. intersection, mutation process.Intersection, mutation process: adopt the random two-way search technique based on probability, with certain probability, from male parent population, choose two chromosomes randomly carry out interlace operation, when new chromosome makes current solution Quality advance, just receive this solution be modified as new current solution.
D. new colony is produced.
E. judge whether to meet end condition.
F. meet end condition then to terminate, do not meet and then return steps A.In the utility model, utilize genetic algorithm optimization BP neural network, then step F is back to BP part of neural network.
The data that each sensor detects are after the process of genetic optimization BP neural network model, select optimum, optimum data and system thresholds to contrast, judge that sensor detects data and whether is less than threshold value, whether Sensor monitoring position normally works, if normally do not worked, then controller output detections result.
S04 step 4, output detections result.
After the BP neural network model of the genetic optimization in controller analyzed the data of sensor; after controller judges data; meeting output detections result on a display screen; as headlight, taillight, steering indicating light and Brake lamp normal operation or brightness reduction or circuit breaker etc. situation all can show at display screen; simultaneously if car light failure problems; the warning lamp of alarm unit and hummer also can carry out glimmering and send sound and break down problem to remind the car light of driver, thus increase display security.
By reference to the accompanying drawings the utility model is exemplarily described above; obvious the utility model specific implementation is not subject to the restrictions described above; as long as have employed the improvement of the various unsubstantialities that method of the present utility model is conceived and technical scheme is carried out; or design of the present utility model and technical scheme directly applied to other occasion, all within protection domain of the present utility model without to improve.
Claims (6)
1. a light fault detection system, is characterized in that, this system comprises:
Signal gathering unit, connection control device, gathers the voltage and current signal of car light circuit;
Controller, the information of Received signal strength collecting unit, utilize genetic optimization BP network algorithm to the data analysis process of collecting unit, voltage, the current signal of observation circuit are no more than system thresholds;
Display screen, connection control device, the detection Output rusults of display controller;
Alarm unit, connection control device, sends warning and reminds after receiving the alarm signal of controller.
2. light fault detection system according to claim 1, is characterized in that, described signal gathering unit comprises voltage sensor, current sensor and luminance sensor.
3. light fault detection system according to claim 2, is characterized in that, the sensor in described signal gathering unit is uniformly distributed.
4. light fault detection system according to claim 1, is characterized in that, described controller does not receive voltage signal data or current signal data all can send warning prompting to alarm unit.
5. light fault detection system according to claim 1, is characterized in that, described controller is provided with database, and database is for preserving the information of signal gathering unit.
6. light fault detection system according to claim 1, is characterized in that, described alarm unit comprise hummer and or warning lamp, be positioned on display screen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420484153.3U CN204044340U (en) | 2014-08-26 | 2014-08-26 | A kind of light fault detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420484153.3U CN204044340U (en) | 2014-08-26 | 2014-08-26 | A kind of light fault detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN204044340U true CN204044340U (en) | 2014-12-24 |
Family
ID=52244990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201420484153.3U Expired - Fee Related CN204044340U (en) | 2014-08-26 | 2014-08-26 | A kind of light fault detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN204044340U (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104698399A (en) * | 2014-08-26 | 2015-06-10 | 安徽工程大学 | Automotive lamp fault detecting system and method thereof |
| CN104777437A (en) * | 2015-03-31 | 2015-07-15 | 江苏大学 | LED automotive lamp failure positioning detection method based on binomial tree model |
| CN108919144A (en) * | 2018-05-28 | 2018-11-30 | 广州市明美光电技术有限公司 | A kind of LED light output signal real-time monitoring system |
| CN110155122A (en) * | 2019-05-17 | 2019-08-23 | 常州鸣轩自动化设备有限公司 | The platform PIS system that integrated platform failure automatic identification is guided |
| US10946789B2 (en) | 2019-02-06 | 2021-03-16 | Ford Global Technologies, Llc | Vehicle lamp-cleaning system |
-
2014
- 2014-08-26 CN CN201420484153.3U patent/CN204044340U/en not_active Expired - Fee Related
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104698399A (en) * | 2014-08-26 | 2015-06-10 | 安徽工程大学 | Automotive lamp fault detecting system and method thereof |
| CN104777437A (en) * | 2015-03-31 | 2015-07-15 | 江苏大学 | LED automotive lamp failure positioning detection method based on binomial tree model |
| CN104777437B (en) * | 2015-03-31 | 2017-11-17 | 江苏大学 | A kind of LED automobile light fixture failure position finding and detection method based on Two Binomial Tree Model |
| CN108919144A (en) * | 2018-05-28 | 2018-11-30 | 广州市明美光电技术有限公司 | A kind of LED light output signal real-time monitoring system |
| US10946789B2 (en) | 2019-02-06 | 2021-03-16 | Ford Global Technologies, Llc | Vehicle lamp-cleaning system |
| CN110155122A (en) * | 2019-05-17 | 2019-08-23 | 常州鸣轩自动化设备有限公司 | The platform PIS system that integrated platform failure automatic identification is guided |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN204044340U (en) | A kind of light fault detection system | |
| CN104698399A (en) | Automotive lamp fault detecting system and method thereof | |
| CN106371052A (en) | Safety monitoring method, device and system for intelligent electric meter | |
| CN201508484U (en) | Intelligent monitoring system for bridge | |
| CN104568446A (en) | Method for diagnosing engine failure | |
| CN111352971A (en) | Bank system monitoring data anomaly detection method and system | |
| CN101110155A (en) | Built-in intelligent fault diagnosing device based on data inosculating pattern recognition and method thereof | |
| CN109754110A (en) | A kind of method for early warning and system of traction converter failure | |
| CN101720453A (en) | System and method for predictive maintenance of a battery assembly using temporal signal processing | |
| CN106772112A (en) | A kind of healthy and safe state evaluation device for electric automobile | |
| US9815197B1 (en) | Device, system and method for tracking and replacing lights with automated vehicles | |
| CN105139493B (en) | A kind of control system of intelligent space lock | |
| KR102215107B1 (en) | Vehicle state predicting system and method based on driving data | |
| CN110519382A (en) | A kind of automobile intelligent monitoring system | |
| CN114889433A (en) | Thermal runaway alarm system and method for battery of electric vehicle | |
| CN102180170A (en) | Device for collecting, storing, analyzing and displaying vehicle data | |
| CN114330138A (en) | Fault diagnosis method and device and electronic equipment | |
| CN116882981B (en) | Intelligent battery management system based on data analysis | |
| CN103879397B (en) | The brake switch failure judgment method of vehicle and device | |
| CN110472851A (en) | A kind of power distribution network risk hidden danger dynamic evaluation model building method neural network based | |
| CN101551940A (en) | Urban high-speed road traffic state judging and issuing system and method thereof | |
| CN202080217U (en) | Vehicle data collection, storage, analysis and display device | |
| CN113660137A (en) | Vehicle-mounted network fault detection method and device, readable storage medium and electronic equipment | |
| CN116720324A (en) | Traction substation key equipment fault early warning method and system based on prediction model | |
| CN206023812U (en) | The gating device of integrated data collecting transmitter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141224 Termination date: 20150826 |
|
| EXPY | Termination of patent right or utility model |