CN204027820U - Air conditioning for automobiles fault detection system - Google Patents
Air conditioning for automobiles fault detection system Download PDFInfo
- Publication number
- CN204027820U CN204027820U CN201420484309.8U CN201420484309U CN204027820U CN 204027820 U CN204027820 U CN 204027820U CN 201420484309 U CN201420484309 U CN 201420484309U CN 204027820 U CN204027820 U CN 204027820U
- Authority
- CN
- China
- Prior art keywords
- air conditioning
- automobiles
- model
- data
- fault detection
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 238000004378 air conditioning Methods 0.000 title claims description 51
- 239000002245 particle Substances 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 230000000153 supplemental effect Effects 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 abstract description 15
- 230000008569 process Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 12
- 238000012549 training Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 4
- 230000002068 genetic effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 244000144992 flock Species 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
本实用新型涉及一种汽车空调故障检测系统，属于汽车检测领域，该系统包括：采集汽车空调内部各接头的参数数据的信号采集单元，处理器和车载显示器，处理器采用粒子群优化相关向量机模型对参数数据进行处理分析。本实用新型中应用振动传感器和风量传感器组成的信号采集单元实时对汽车空调内部的接头进行运行状态监测发出警示信号，及时提醒驾驶人员对空调进行检查维修，避免空调的进一步损坏。同时本实用新型中的处理器使用粒子群优化相关向量机模型对待测数据进行分析处理，利用模型处理数据，进行数据对比和分析，增大了检测结果的准确率，减小了误报警情况的发生，解决了现有技术中汽车空调泄漏不能及时发现的问题。
The utility model relates to a fault detection system for an automobile air conditioner, which belongs to the field of automobile detection. The system includes: a signal acquisition unit for collecting parameter data of each joint inside the automobile air conditioner, a processor and an on-board display. The processor adopts a particle swarm optimization correlation vector machine The model processes and analyzes the parameter data. In the utility model, the signal acquisition unit composed of a vibration sensor and an air volume sensor is used to monitor the running status of the joints inside the automobile air conditioner in real time and send out a warning signal to remind the driver to check and maintain the air conditioner in time to avoid further damage to the air conditioner. At the same time, the processor in the utility model uses the particle swarm optimization correlation vector machine model to analyze and process the data to be measured, and uses the model to process the data to perform data comparison and analysis, which increases the accuracy of the detection results and reduces the risk of false alarms. Occurs, solves the problem that automobile air conditioner leakage can not be found in time in the prior art.
Description
Technical field
The utility model relates to automobile detection field, particularly a kind of air conditioning for automobiles fault detection system.
Background technology
Air conditioning for automobiles is arranged on the vehicle of traveling, subject and acutely vibrate frequently and impact, therefore air-conditioning joint easily loosens and leaks, not only affect the refrigeration of air-conditioning, also can increase energy consumption, serious meeting damages the parts such as the compressor of refrigeration system, if keep in repair not in time, the further damage of air-conditioning can be caused, strengthen the maintenance cost in later stage.When leakage failure appears in existing air conditioning for automobiles, user of service is not easy to discover, and needs professional person to check air-conditioning and could find failure problems after overhauling, and gets rid of fault, and this model machine has influence on the use of air-conditioning.
Summary of the invention
Can not the problem of Timeliness coverage in order to solve that air conditioning for automobiles in prior art leaks, the utility model provides a kind of air conditioning for automobiles fault detection system.
The technical solution of the utility model is: a kind of air conditioning for automobiles fault detection system, and this system comprises:
Signal gathering unit, gathers the supplemental characteristic of the inner each joint of air conditioning for automobiles;
Processor, connection signal collecting unit, and the supplemental characteristic that Received signal strength collecting unit sends;
Vehicular display device is the display being positioned at automotive interior, connection handling device, the testing result that video-stream processor sends.
Described signal gathering unit comprise the vibration signal parameter for detecting the inner each interface position of air conditioning for automobiles vibration transducer and for detecting the annular air flow sensor around air conditioning for automobiles internal connection.
Described processor adopts particle group optimizing Method Using Relevance Vector Machine model to carry out Treatment Analysis to supplemental characteristic.Be provided with database in described processor, database preserves real time data and the historical data of signal gathering unit collection.The display data result of Vehicular display device is also preserved in described database.
The utility model has following good effect: the signal gathering unit applying vibration transducer and air flow sensor composition in the utility model carries out monitoring running state to the joint of air conditioning for automobiles inside in real time, once joint will change the air-flow of refrigrant leakage formation simultaneously because loosen vibration frequency, the data that processor detects according to air flow sensor and vibration transducer will send alarm signal, timely prompting human pilot carries out maintenance and inspection to air-conditioning, avoids the further damage of air-conditioning.Processor simultaneously in the utility model uses particle group optimizing Method Using Relevance Vector Machine model to data analysis process to be measured, utilize model treatment data, carry out Data Comparison and analysis, increase the accuracy rate of testing result, reduce the generation of false alarm situation, facilitate checking and keeping in repair of staff.
Accompanying drawing explanation
Fig. 1 is the work block diagram of air conditioning for automobiles fault detection system in the utility model;
Fig. 2 is the workflow diagram of air conditioning for automobiles fault detection method in the utility model;
Fig. 3 is the workflow diagram of particle group optimizing Method Using Relevance Vector Machine model in the utility model;
Fig. 4 is the work structuring figure of air conditioning for automobiles fault detection method 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 air conditioning for automobiles fault detection system, as shown in Figure 1, this system comprises: signal gathering unit, processor and display, processor connection signal collecting unit and display.
Signal gathering unit, for gathering the supplemental characteristic of the inner each joint of air conditioning for automobiles.Involving vibrations sensor and air flow sensor in signal gathering unit, vibration transducer is for detecting the vibration signal parameter at the inner each interface position of air conditioning for automobiles, air flow sensor is for detecting around air conditioning for automobiles internal connection whether have air-flow, and it is more accurate that air flow sensor adopts annular air flow sensor solderless wrapped connection first week to detect.Vibration transducer can detect the Vibration Condition of air conditioning for automobiles, and when joint looseness, joint vibration accelerates, and sensor detects data and undergos mutation, and in addition, when gas leakage delivered to by joint, cold-producing medium can leak formation air-flow, and air flow sensor will detect that air quantity changes.
Processor, the supplemental characteristic that connection signal collecting unit Received signal strength collecting unit send, particle group optimizing Method Using Relevance Vector Machine model is utilized to carry out Treatment Analysis to the supplemental characteristic detected after receiving data, utilize particle group optimizing Method Using Relevance Vector Machine model treatment data, carry out Data Comparison and analysis, increase the accuracy rate of testing result, reduce the generation of false alarm situation, facilitate checking and keeping in repair of staff.
Display is the Vehicular display device of automotive interior, connection handling device, the testing result that video-stream processor sends, and when air conditioning for automobiles breaks down, reminds human pilot to carry out maintenance and inspection to air-conditioning in time, avoids the further damage of air-conditioning.
A kind of air conditioning for automobiles fault detection method, as shown in Figure 2, the method step comprises:
S01 step one, set up air conditioning for automobiles parameter database, line number of going forward side by side Data preprocess.
Air conditioning for automobiles parameter database is that air conditioning for automobiles dispatches from the factory supplemental characteristic, includes the data under the normal condition of the signal gathering unit acquisition testing in system simultaneously, for the machine training of particle group optimizing Method Using Relevance Vector Machine model below provides data.
Data prediction is normalized data, and 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, genetic algorithm be with the statistics of sample in event respectively probability carry out training and predicting, normalization is same statistical probability distribution between 0-1; RVM classifies with linear partition distance after dimensionality reduction and emulates, and therefore the normalization of space-time dimensionality reduction is the statistics coordinate distribution be unified between-1--+1.
S02 step 2, set up RVM model, utilize particle cluster algorithm optimization to train Method Using Relevance Vector Machine (being called for short RVM) model parameter.
Set up RVM(relevance vector machine, i.e. Method Using Relevance Vector Machine) first model select suitable function, and particle group optimizing training is carried out to its hyper parameter, set up suitable RVM model, particle cluster algorithm optimization is utilized to train RVM model parameter, allow model more easily restrain, arithmetic speed is faster.When setting up RVM model, first utilize sample database to carry out particle cluster algorithm optimization and train successful Modling model, the foundation of sample database preserve when air conditioning for automobiles dispatches from the factory and normal condition time detect preserve.
RVM kernel function conventional during the selection of kernel function has 4 kinds:
Linear kernel function:
K( x，z) = x·z (1)
Polynomial kernel function:
K( x，z) = [ s( x·z) + c] q (2)
Gaussian radial basis function (RBF) kernel function:
K( x，z ) = exp( － λ ‖x － z‖2 ) (3)
Sigmoid kernel function:
K (x，z) = tanh［s( x·z) + c］ (4)
Select suitable kernel function to be the key that the method can successfully use, trained by testing authentication, more respective Generalization Capability, select RBF kernel function as the RVM model of fault diagnosis herein.
Particle swarm optimization algorithm (particle swarm optimization, PSO) is a kind of optimizing algorithm based on iteration ［ 8 ］ proposed first in 1995 by Kennedy and Eberhart.This algorithm is the simulation to flock of birds social action, PSO algorithm and genetic algorithm similar, be a kind of optimized algorithm based on colony (population), each particle is by carrying out information interaction with other particles, adjust the Evolutionary direction of oneself, and avoid being absorbed in local optimum; Meanwhile, PSO algorithm adopts the random searching strategy being different from genetic algorithm, operates than genetic algorithm easy too much, therefore demonstrates more remarkable performance when solving some optimization problem.
Utilize the Lagrange multiplier in particle swarm optimization algorithm optimization Method Using Relevance Vector Machine herein, by utilizing particle cluster algorithm (particle swarm optimization, PSO) optimal value that this vector of Lagrange multiplier meets each component of constraint condition in RVM is found, make the spacing distance between two classification maximum, thus construct optimal hyperlane.During initialization population, should constantly judge until the random initial value of each particle meets the constraint condition in optimized Method Using Relevance Vector Machine.Each component of each particle a is by self study and learn to other particles, constantly updates self speed and position, reaches global optimum.
The step of particle cluster algorithm is:
A. initialization population: the scale determining population, initial position and speed, according to the value of constraint condition to each particle initialization Lagrange factor a;
B. the target function value of each particle is calculated, i.e. the value of wanted majorized function;
C. the position local optimum Pbest and global optimum Gbest of each particle a is upgraded;
D. flying speed and the position of each particle a is upgraded;
E. judge whether data reach RVM model criteria, and the standard of reaching jumps out circulation, and calculate related coefficient, otherwise the step B returned, until meet the number of times of iteration;
F. the value of optimum a is returned, and by optimized Parameter transfer to RVM model.
The RVM model obtained after hyperparameter optimization training, namely can be used for classification and the process of data.PSO to the parameter optimisation procedure of RVM algorithm as shown in Figure 3.
In RVM algorithm, the classification accuracy of selection to RVM algorithm of hyper parameter plays conclusive effect, in the past conventional parameter optimization method many employings people is for enumerating the mode such as optimizing, cross validation parameters, but this class methods required time is long, also there is the problem being easily absorbed in local optimum simultaneously.Particle cluster algorithm is a kind of global optimizing algorithm efficiently, and the parameter optimization that can be used for machine learning algorithm is arranged.Adopt the hyper parameter of PSO algorithm optimization RVM algorithm to arrange herein, thus set up the machine mould of fault detect.
S03 step 3, employing Method Using Relevance Vector Machine model carry out diagnostic analysis to testing data.First machine training is carried out to model before model analysis testing data, namely the Method Using Relevance Vector Machine model of database to particle group optimizing set up in step one is utilized to carry out machine training, under the data of normal steady state, the differentiation of fault mode and the normal use of model can be ensured.After machine training, model just can carry out diagnostic analysis to testing data, and testing data refers to the supplemental characteristic that the vibration transducer of monitoring air conditioning for automobiles each connector status and air flow sensor detect.Vibration transducer is for detecting the vibration signal parameter at the inner each interface position of air conditioning for automobiles, and annular air flow sensor, for detecting around air conditioning for automobiles internal connection whether have air-flow, adopts annular air flow sensor solderless wrapped connection first week to detect more accurate.Vibration transducer can detect the Vibration Condition of air conditioning for automobiles, and when joint looseness, joint vibration accelerates, and sensor detects data and undergos mutation, and in addition, when gas leakage delivered to by joint, cold-producing medium can leak formation air-flow, and air flow sensor will detect that air quantity changes.Model is greater than default threshold value once contrast the detection data received, and processor will send alarm signal.
S04 step 4, output diagnostic result.When the data vibration data that vibration transducer detects is abnormal, joint abnormal vibration is described, likely joint looseness, processor receives abnormal vibration data will send alarm signal to Vehicular display device.In addition, when joint looseness or the gas leakage of air-conditioning inside, air-flow will be formed, the data that air flow sensor detects just there will be exception, processor also can send alarm signal according to the exception of air flow sensor and remind human pilot check air conditioning for automobiles in time or ask professional person to check to Vehicular display device, avoids air conditioning for automobiles further to damage.
S05 step 5, diagnostic result and supplemental characteristic are stored in database.Many times air conditioning for automobiles is in normal operating condition, but along with the growth of automobile tenure of use, systemic-function all decreases, and the threshold value of default also should upgrade thereupon.So, when diagnostic result be normal condition there is no a fault time, corresponding sensing data will be preserved in a database, supplemental characteristic under malfunction and result also can stored in databases, conveniently call and Data Comparison, reach the object of known more new database, systems axiol-ogy accuracy is higher, and detection system is more practical.
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 (5)
1. an air conditioning for automobiles fault detection system, is characterized in that, this system comprises:
Signal gathering unit, gathers the supplemental characteristic of the inner each joint of air conditioning for automobiles;
Processor, connection signal collecting unit, and the supplemental characteristic that Received signal strength collecting unit sends;
Vehicular display device is the display being positioned at automotive interior, connection handling device, the testing result that video-stream processor sends.
2. air conditioning for automobiles fault detection system according to claim 1, it is characterized in that, described signal gathering unit comprise the vibration signal parameter for detecting the inner each interface position of air conditioning for automobiles vibration transducer and for detecting the annular air flow sensor around air conditioning for automobiles internal connection.
3. air conditioning for automobiles fault detection system according to claim 1, is characterized in that, described processor adopts particle group optimizing Method Using Relevance Vector Machine model to carry out Treatment Analysis to supplemental characteristic.
4. air conditioning for automobiles fault detection system according to claim 1, is characterized in that, is provided with database in described processor, and database preserves real time data and the historical data of signal gathering unit collection.
5. air conditioning for automobiles fault detection system according to claim 1, is characterized in that, also preserves the display data result of Vehicular display device in described database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420484309.8U CN204027820U (en) | 2014-08-26 | 2014-08-26 | Air conditioning for automobiles fault detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420484309.8U CN204027820U (en) | 2014-08-26 | 2014-08-26 | Air conditioning for automobiles fault detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN204027820U true CN204027820U (en) | 2014-12-17 |
Family
ID=52067663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201420484309.8U Expired - Fee Related CN204027820U (en) | 2014-08-26 | 2014-08-26 | Air conditioning for automobiles fault detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN204027820U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104697765A (en) * | 2014-08-26 | 2015-06-10 | 安徽工程大学 | Method and system for detecting faults of automotive air conditioner |
| CN104808649A (en) * | 2015-03-13 | 2015-07-29 | 芜湖凯博实业股份有限公司 | Cooling tower blower monitoring system and method |
| CN110135121A (en) * | 2019-06-13 | 2019-08-16 | 中国人民解放军海军航空大学 | A Fault Diagnosis Method Based on Lagrangian-Particle Swarm Update Algorithm |
-
2014
- 2014-08-26 CN CN201420484309.8U patent/CN204027820U/en not_active Expired - Fee Related
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104697765A (en) * | 2014-08-26 | 2015-06-10 | 安徽工程大学 | Method and system for detecting faults of automotive air conditioner |
| CN104697765B (en) * | 2014-08-26 | 2017-12-26 | 安徽工程大学 | Air conditioning for automobiles fault detection system and method |
| CN104808649A (en) * | 2015-03-13 | 2015-07-29 | 芜湖凯博实业股份有限公司 | Cooling tower blower monitoring system and method |
| CN110135121A (en) * | 2019-06-13 | 2019-08-16 | 中国人民解放军海军航空大学 | A Fault Diagnosis Method Based on Lagrangian-Particle Swarm Update Algorithm |
| CN110135121B (en) * | 2019-06-13 | 2023-04-18 | 中国人民解放军海军航空大学 | Fault diagnosis method based on Lagrange-particle swarm update algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108303264B (en) | Cloud-based vehicle fault diagnosis method, device and system | |
| CN105372087B (en) | Fault Diagnosis Method Based on Multi-sensor Signal Analysis | |
| US12051315B2 (en) | Methods, internet of things systems, and storage media for smart gas pipeline network inspection | |
| US9122273B2 (en) | Failure cause diagnosis system and method | |
| US10279816B2 (en) | Method and apparatus for monitoring an on-vehicle controller | |
| US20220082409A1 (en) | Method and system for monitoring a gas distribution network operating at low pressure | |
| EP3017972B1 (en) | Wheel diagnostic monitoring | |
| CN110379437A (en) | The method and apparatus of runner wagon internal fault | |
| CN111506048B (en) | Vehicle fault early warning method and related equipment | |
| CN104697765B (en) | Air conditioning for automobiles fault detection system and method | |
| CN204027820U (en) | Air conditioning for automobiles fault detection system | |
| CN112036581A (en) | Performance detection method and device of vehicle air conditioning system, storage medium and terminal | |
| Ma et al. | A novel broad learning system based leakage detection and universal localization method for pipeline networks | |
| CN113065721A (en) | Method, device, equipment and medium for graded early warning of leakage events of community water supply network | |
| CN112595537A (en) | Equipment health state monitoring method and system based on signal analysis and storage medium | |
| CN104568438A (en) | Engine bearing fault detection system and method | |
| CN104808649A (en) | Cooling tower blower monitoring system and method | |
| CN115009296A (en) | Sensor detection method, apparatus, computer equipment and computer program product | |
| CN107255677A (en) | A kind of dam safety damage monitoring system based on piezoelectric intelligent sensor | |
| CN112378480B (en) | Intelligent pit data analysis method and system | |
| WO2024168454A1 (en) | Vehicle chassis health management method, apparatus and system | |
| CN108898151A (en) | A kind of mechanical equipment state monitoring method based on local search ant group algorithm | |
| Okolai et al. | Autonomous vehicle fault Detection and Isolation Model Using Stochastic Gradient Descent | |
| CN117605627B (en) | System and method for detecting oil leakage of core body of wind power gear box cooler | |
| RU2798250C2 (en) | Method and system for determining the cause of excessive fuel consumption |
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: 20141217 Termination date: 20150826 |
|
| EXPY | Termination of patent right or utility model |