CN112949194B - Explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion - Google Patents
Explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion Download PDFInfo
- Publication number
- CN112949194B CN112949194B CN202110259613.7A CN202110259613A CN112949194B CN 112949194 B CN112949194 B CN 112949194B CN 202110259613 A CN202110259613 A CN 202110259613A CN 112949194 B CN112949194 B CN 112949194B
- Authority
- CN
- China
- Prior art keywords
- explosion
- proof forklift
- fault
- proof
- parts
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Abstract
The invention discloses an explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion. The method comprises the following steps: 1) simultaneously inputting temperature rise information of different types of explosion-proof forklift parts and corresponding network fault grade parameters A into a one-dimensional convolutional neural network model for training to obtain different types of trained one-dimensional convolutional neural network models; 2) calculating to obtain part cluster information corresponding to different types of explosion-proof forklift parts; 3) in a working site, acquiring temperature rise information of one type of explosion-proof forklift parts in normal working, respectively obtaining network fault grade parameters A and part cluster information of the explosion-proof forklift parts, and calculating a final diagnosis result C to obtain the fault grade of the explosion-proof forklift parts. The temperature information is acquired by using the temperature sensor for safely monitoring each part in the explosion-proof forklift, so that the method is good in economy and wide in applicability, and can be used for fault diagnosis of various explosion-proof forklift parts.
Description
Technical Field
The invention belongs to a fault diagnosis method of an explosion-proof forklift in the field of engineering machinery, and particularly relates to a fault diagnosis method of an explosion-proof forklift based on machine learning and cluster information fusion.
Background
The forklift is a common production and carrying vehicle in industry, is widely applied to ports, stations, airports, goods yards, factory workshops, warehouses, circulation centers, distribution centers and the like, and can finish the operations of loading, unloading, stacking, short-distance transportation and the like of finished pallet goods. The circuit equipment of a common forklift is easy to generate electric sparks during working, and partial parts can generate heat during working to cause local high temperature. These two problems also determine that the conventional forklift can not be used in some occasions with high dust concentration or in the production, transportation and storage of explosive gases. With the development of the petroleum and chemical industries and the continuous increase of chemical raw material varieties, in order to solve the transportation problem in the industrial production process with higher explosion-proof requirements, an intelligent explosion-proof forklift meeting the high-reliability explosion-proof requirements must be designed and researched.
In order to improve the safety of an explosion-proof forklift, a temperature sensor is often needed to monitor the temperature of high-heating parts (such as a car lamp, a running motor, an oil pump motor, a circuit main board and the like) of the forklift in the running process of the forklift.
The existing explosion-proof forklift is mainly manually checked by professional technicians in fault diagnosis, and is often long in diagnosis time period and high in checking difficulty.
Disclosure of Invention
In order to solve the problems and requirements in the background art, the invention provides a method for diagnosing the type and severity of the fault of the important parts of the explosion-proof forklift at the same time, which is efficient and accurate, by utilizing the existing safe temperature monitoring information of the explosion-proof forklift.
The fault diagnosis method provided by the invention integrates a fault diagnosis method based on a one-dimensional convolutional neural network model and a fault diagnosis method based on cluster standard deviation analysis.
The technical scheme adopted by the invention is as follows:
the invention comprises the following steps:
1) selecting a plurality of explosion-proof forklift parts of the same type and different fault grades;
2) measuring temperature rise data of one type of explosion-proof forklift parts from the beginning to the end of work, wherein the temperature rise data are used as temperature rise information of the explosion-proof forklift parts, and network fault grade parameters A of the explosion-proof forklift parts with different fault grades are different;
3) simultaneously inputting temperature rise information of the explosion-proof forklift part and a network fault grade parameter A corresponding to the fault grade into a one-dimensional convolutional neural network model for training to obtain a trained one-dimensional convolutional neural network model corresponding to the explosion-proof forklift part;
4) repeating the steps 1) and 2) for the rest types of explosion-proof forklift parts, and respectively obtaining trained one-dimensional convolution neural network models corresponding to the different types of explosion-proof forklift parts;
5) collecting temperature rise information of one type of explosion-proof forklift parts in normal work at a working site, inputting the temperature rise information into a trained one-dimensional convolutional neural network model corresponding to the explosion-proof forklift parts, and outputting a network fault grade parameter A of the explosion-proof forklift parts by the trained one-dimensional convolutional neural network model;
6) calculating the average temperature and the standard deviation of the temperature rise information of all the explosion-proof forklift parts of the same type in the step 1), wherein the average temperature and the standard deviation of the explosion-proof forklift parts of the type are used as part cluster information of the explosion-proof forklift parts of the type;
7) repeating the step 5) for all the explosion-proof forklift parts of the rest types, and respectively obtaining part cluster information corresponding to the explosion-proof forklift parts of different types;
8) judging the temperature rise information of the explosion-proof forklift parts collected in the working site in the step 5) according to the part cluster information of the type, and outputting a cluster fault grade parameter B;
9) and finally diagnosing the faults by using the network fault grade parameter A and the cluster fault grade parameter B of the explosion-proof forklift part to obtain a final diagnosis result C, and diagnosing the faults of the explosion-proof forklift part according to the final diagnosis result C.
The step 2) is specifically as follows:
2.1) selecting a plurality of explosion-proof forklift parts with the same type of normal faults, light faults and heavy faults, wherein the network fault grade parameter A of the normal explosion-proof forklift part meets the condition that A is 0, the network fault grade parameter A of the explosion-proof forklift part with the light faults meets the condition that A is 0.5, and the network fault grade parameter A of the explosion-proof forklift part with the heavy faults meets the condition that A is 1;
2.2) the selected explosion-proof forklift parts are installed on the explosion-proof forklift, then the explosion-proof forklift parts are started at rated power and kept in a running state, temperature rising data of the explosion-proof forklift parts within working time T are measured under different room temperature conditions, the temperature rising data are sampled in real time, temperature rise information of the explosion-proof forklift parts is obtained, and the explosion-proof forklift stops running after the temperature rise information is collected.
The network fault level parameter A specifically has three numerical values, namely a network fault level parameter A which is equal to 0, a network fault level parameter A which is equal to 0.5 and a network fault level parameter A which is equal to 1, and three fault levels of normal fault, light fault and severe fault are sequentially corresponded.
The step 8) is specifically as follows:
judging the temperature rise information of the explosion-proof forklift parts collected on the working site in the step 5) according to the part cluster information of the type:
if the temperature data of at least one moment in the temperature rise information of the explosion-proof forklift part is out of the range of standard deviation of three times of the average temperature of the corresponding moment of the explosion-proof forklift part, the fault grade of the explosion-proof forklift part is a severe fault, and a cluster fault grade parameter B is 1;
otherwise, if the temperature data of at least one moment in the temperature rise information of the explosion-proof forklift part is within the range from the average temperature of the corresponding moment of the explosion-proof forklift part multiplied by one standard deviation to the average temperature multiplied by three standard deviations, the fault grade of the explosion-proof forklift part is a medium fault, and the cluster fault grade parameter B is 0.5;
otherwise, the fault grade of the explosion-proof forklift part is normal, and the cluster fault grade parameter B is 0.
The step 9) is specifically as follows:
carrying out final fault diagnosis after weighting and summing the network fault grade parameter A and the cluster fault grade parameter B of the explosion-proof forklift part to obtain a final diagnosis result C, wherein the final diagnosis result C meets the following requirements: c ═ a × a + B × B.
The invention has the following beneficial effects:
(1) the invention can directly utilize the temperature sensor for safety monitoring of the explosion-proof forklift to carry out fault diagnosis on forklift parts without adding new hardware equipment.
(2) According to the method, the fault diagnosis of the explosion-proof forklift part is carried out through the one-dimensional convolutional neural network, the one-dimensional convolutional neural network is suitable for processing one-dimensional signals, the optimal characteristics can be directly extracted from original data, the complexity of manually extracting the characteristics is avoided, and the method has a wide part diagnosis range.
Drawings
FIG. 1 is a schematic diagram of an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a one-dimensional convolutional neural network model.
Detailed Description
The specific embodiment of the invention is as follows:
as shown in fig. 1, the present invention comprises the steps of:
1) selecting a plurality of explosion-proof forklift parts of the same type and different fault grades;
2) measuring temperature rise data of one type of explosion-proof forklift parts from the beginning to the end of work, wherein the temperature rise data are used as temperature rise information of the explosion-proof forklift parts, and network fault grade parameters A of the explosion-proof forklift parts with different fault grades are different;
the step 2) is specifically as follows:
2.1) selecting a plurality of explosion-proof forklift parts with the same type and normal, light faults and heavy faults, wherein the network fault grade parameter A of the normal explosion-proof forklift part meets A (0), the network fault grade parameter A of the explosion-proof forklift part with the light faults meets A (0.5), the network fault grade parameter A of the explosion-proof forklift part with the heavy faults meets A (1), in specific implementation, the number of the normal explosion-proof forklift parts is 50, the number of the explosion-proof forklift parts with the light faults and the heavy faults is not less than 50, and at least 10 explosion-proof forklift parts with the light faults or the heavy faults are provided;
2.2) the selected explosion-proof forklift parts are installed on the explosion-proof forklift, then the explosion-proof forklift parts are started at rated power and kept in a running state, temperature rising data of the explosion-proof forklift parts within working time T are measured under different room temperature conditions, the temperature rising data are sampled in real time, temperature rise information of the explosion-proof forklift parts is obtained, the explosion-proof forklift stops running after the temperature rise information is collected, in the specific implementation, the room temperature range is-10-35 ℃, and the sampling frequency is 10 Hz. The method needs to ensure that the quantity of temperature rise information sampled by explosion-proof forklift parts of each fault level is not less than 100 in the room temperature range of every 5 ℃; for example, the quantity of temperature rise information of normal explosion-proof forklift parts obtained under the room temperature condition of (0,5 ℃) is not less than 100; the rated power is the power of the explosion-proof forklift part under normal work, and the temperature rise information is a plurality of discrete temperature data sampled within the working time T.
The network fault level parameter a specifically has three values, namely a network fault level parameter a being 0, a network fault level parameter a being 0.5 and a network fault level parameter a being 1, which correspond to three fault levels of normal, mild and severe faults in sequence.
3) Simultaneously inputting temperature rise information of the explosion-proof forklift part and the network fault grade parameter A corresponding to the fault grade into a one-dimensional convolutional neural network model for training to obtain a trained one-dimensional convolutional neural network model corresponding to the explosion-proof forklift part, as shown in FIG. 2;
4) repeating the steps 1) and 2) for the rest types of explosion-proof forklift parts, and respectively obtaining trained one-dimensional convolution neural network models corresponding to the different types of explosion-proof forklift parts;
5) collecting temperature rise information of one type of explosion-proof forklift parts in normal work at a working site, inputting the temperature rise information into a trained one-dimensional convolutional neural network model corresponding to the explosion-proof forklift parts, and outputting a network fault grade parameter A of the explosion-proof forklift parts by the trained one-dimensional convolutional neural network model;
6) calculating the average temperature and the standard deviation of the temperature rise information of all the explosion-proof forklift parts of the same type in the step 1), wherein the average temperature and the standard deviation of the explosion-proof forklift parts of the type are used as part cluster information of the explosion-proof forklift parts of the type;
7) repeating the step 5) for all the explosion-proof forklift parts of the rest types, and respectively obtaining part cluster information corresponding to the explosion-proof forklift parts of different types;
8) judging the temperature rise information of the explosion-proof forklift parts collected in the working site in the step 5) according to the part cluster information of the type, and outputting a cluster fault grade parameter B;
the step 8) is specifically as follows:
judging the temperature rise information of the explosion-proof forklift parts collected on the working site in the step 5) according to the part cluster information of the type:
if the temperature data of at least one moment in the temperature rise information of the explosion-proof forklift part is out of the range of standard deviation of three times of the average temperature of the corresponding moment of the explosion-proof forklift part, the fault grade of the explosion-proof forklift part is a severe fault, and a cluster fault grade parameter B is 1;
otherwise, if the temperature data of at least one moment in the temperature rise information of the explosion-proof forklift part is within the range from the average temperature of the corresponding moment of the explosion-proof forklift part multiplied by one standard deviation to the average temperature multiplied by three standard deviations, the fault grade of the explosion-proof forklift part is a medium fault, and the cluster fault grade parameter B is 0.5;
otherwise, the fault grade of the explosion-proof forklift part is normal, and the cluster fault grade parameter B is 0.
9) And finally diagnosing the faults by using the network fault grade parameter A and the cluster fault grade parameter B of the explosion-proof forklift part to obtain a final diagnosis result C, and diagnosing the faults of the explosion-proof forklift part according to the final diagnosis result C.
The step 9) is specifically as follows:
carrying out final fault diagnosis after weighting and summing the network fault grade parameter A and the cluster fault grade parameter B of the explosion-proof forklift part to obtain a final diagnosis result C, wherein the final diagnosis result C meets the following requirements: c ═ a × a + B × B. In specific implementation, a is 0.5, b is 0.5;
if C is more than or equal to 0 and less than or equal to 0.25, the failure grade of the explosion-proof forklift part is normal;
if C is more than 0.25 and less than or equal to 0.75, the fault grade of the explosion-proof forklift part is light fault;
if C is more than 0.75 and less than or equal to 1, the failure grade of the explosion-proof forklift part is a severe failure.
The embodied one-dimensional convolutional neural network model selects TensorFlow1.9 as a deep learning framework, all algorithms are written in python3.6, and all programs are executed on a notebook computer with a GTX1060 video card, an 8 th generation Intel Corei5 processor and a 512GB hard disk.
The one-dimensional convolutional neural network model is based on tensoflow1.14.0 version on a Google Colorator platform, adopts a sequential model (sequential) of a keras framework, and is provided with an input layer, a convolutional layer, a pooling layer, three full-connection layers, a Dropout layer and an output layer. ReLu activation function is used for convolution layer, and softmax function classifier is used for output layer. And (3) taking the temperature rise information of the explosion-proof forklift parts as an input layer of the one-dimensional convolutional neural network, and generating feature mapping by taking the network fault grade parameter A as an output layer.
In specific implementation, the parts of the explosion-proof forklift are divided into an explosion-proof car lamp, a running motor, an oil pump motor, a circuit board, an explosion-proof oil tank and the like. Table 1 shows the operating time T of different explosion-proof forklift parts when acquiring temperature rise information.
Table 1: working time T of different types of explosion-proof forklift parts
| Details of | T(min) |
| Explosion-proof car lamp | 1.0 |
| Traveling motor/oil pump motor | 10.0 |
| Circuit main board | 5.0 |
| Explosion-proof oil tank | 10.0 |
Claims (5)
1. An explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion is characterized in that: the method comprises the following steps:
1) selecting a plurality of explosion-proof forklift parts of the same type and different fault grades;
2) measuring temperature rise data of one type of explosion-proof forklift parts from the beginning to the end of work, wherein the temperature rise data are used as temperature rise information of the explosion-proof forklift parts, and network fault grade parameters A of the explosion-proof forklift parts with different fault grades are different;
3) simultaneously inputting temperature rise information of the explosion-proof forklift part and a network fault grade parameter A corresponding to the fault grade into a one-dimensional convolutional neural network model for training to obtain a trained one-dimensional convolutional neural network model corresponding to the explosion-proof forklift part;
4) repeating the steps 1) and 2) for the rest types of explosion-proof forklift parts, and respectively obtaining trained one-dimensional convolution neural network models corresponding to the different types of explosion-proof forklift parts;
5) collecting temperature rise information of one type of explosion-proof forklift parts in normal work at a working site, inputting the temperature rise information into a trained one-dimensional convolutional neural network model corresponding to the explosion-proof forklift parts, and outputting a network fault grade parameter A of the explosion-proof forklift parts by the trained one-dimensional convolutional neural network model;
6) calculating the average temperature and the standard deviation of the temperature rise information of all the explosion-proof forklift parts of the same type in the step 1), wherein the average temperature and the standard deviation of the explosion-proof forklift parts of the type are used as part cluster information of the explosion-proof forklift parts of the type;
7) repeating the steps 5) -6) for all the explosion-proof forklift parts of the rest types, and respectively obtaining part cluster information corresponding to the explosion-proof forklift parts of different types;
8) judging the temperature rise information of the explosion-proof forklift parts collected in the working site in the step 5) according to the part cluster information of the type, and outputting a cluster fault grade parameter B;
9) and performing final fault diagnosis by using the network fault grade parameter A and the cluster fault grade parameter B of the explosion-proof forklift part to obtain a final diagnosis result C, and performing fault diagnosis on the explosion-proof forklift part according to the final diagnosis result C.
2. The explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion according to claim 1, characterized in that: the step 2) is specifically as follows:
2.1) selecting a plurality of explosion-proof forklift parts with the same type of normal faults, light faults and heavy faults, wherein the network fault grade parameter A of the normal explosion-proof forklift part meets the condition that A is 0, the network fault grade parameter A of the explosion-proof forklift part with the light faults meets the condition that A is 0.5, and the network fault grade parameter A of the explosion-proof forklift part with the heavy faults meets the condition that A is 1;
2.2) the selected explosion-proof forklift parts are installed on the explosion-proof forklift, then the explosion-proof forklift parts are started at rated power and kept in a running state, temperature rising data of the explosion-proof forklift parts within working time T are measured under different room temperature conditions, the temperature rising data are sampled in real time, temperature rise information of the explosion-proof forklift parts is obtained, and the explosion-proof forklift stops running after the temperature rise information is collected.
3. The explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion according to claim 1, characterized in that: the network fault level parameter A specifically has three numerical values, namely a network fault level parameter A which is equal to 0, a network fault level parameter A which is equal to 0.5 and a network fault level parameter A which is equal to 1, and three fault levels of normal fault, light fault and severe fault are sequentially corresponded.
4. The explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion according to claim 1, characterized in that: the step 8) is specifically as follows:
judging the temperature rise information of the explosion-proof forklift parts collected on the working site in the step 5) according to the part cluster information of the type:
if the temperature data of at least one moment in the temperature rise information of the explosion-proof forklift part is out of the range of standard deviation of three times of the average temperature of the corresponding moment of the explosion-proof forklift part, the fault grade of the explosion-proof forklift part is a severe fault, and a cluster fault grade parameter B is 1;
otherwise, if the temperature data of at least one moment in the temperature rise information of the explosion-proof forklift part is within the range from the average temperature of the corresponding moment of the explosion-proof forklift part multiplied by one standard deviation to the average temperature multiplied by three standard deviations, the fault grade of the explosion-proof forklift part is a medium fault, and the cluster fault grade parameter B is 0.5;
otherwise, the fault grade of the explosion-proof forklift part is normal, and the cluster fault grade parameter B is 0.
5. The explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion according to claim 1, characterized in that: the step 9) is specifically as follows:
carrying out final fault diagnosis after weighting and summing the network fault grade parameter A and the cluster fault grade parameter B of the explosion-proof forklift part to obtain a final diagnosis result C, wherein the final diagnosis result C meets the following requirements: c ═ a × a + B × B.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110259613.7A CN112949194B (en) | 2021-03-10 | 2021-03-10 | Explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110259613.7A CN112949194B (en) | 2021-03-10 | 2021-03-10 | Explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112949194A CN112949194A (en) | 2021-06-11 |
| CN112949194B true CN112949194B (en) | 2022-05-10 |
Family
ID=76229240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110259613.7A Active CN112949194B (en) | 2021-03-10 | 2021-03-10 | Explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949194B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111562113A (en) * | 2020-05-15 | 2020-08-21 | 江苏省特种设备安全监督检验研究院 | Fork truck running state analytic system based on it is embedded |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080161989A1 (en) * | 1995-06-07 | 2008-07-03 | Automotive Technologies International, Inc. | Vehicle Diagnostic or Prognostic Message Transmission Systems and Methods |
| US11327475B2 (en) * | 2016-05-09 | 2022-05-10 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for intelligent collection and analysis of vehicle data |
| US11513480B2 (en) * | 2018-03-27 | 2022-11-29 | Terminus (Beijing) Technology Co., Ltd. | Method and device for automatically diagnosing and controlling apparatus in intelligent building |
| JP2020194273A (en) * | 2019-05-27 | 2020-12-03 | 富士通株式会社 | Optimization device, optimization method and optimization program |
-
2021
- 2021-03-10 CN CN202110259613.7A patent/CN112949194B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111562113A (en) * | 2020-05-15 | 2020-08-21 | 江苏省特种设备安全监督检验研究院 | Fork truck running state analytic system based on it is embedded |
Non-Patent Citations (1)
| Title |
|---|
| 基于加权概率神经网络的齿轮箱抗噪故障诊断;崔逊波等;《机电工程》;20100220(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112949194A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111444169A (en) | Transformer substation electrical equipment state monitoring and diagnosis system and method | |
| CN107291991B (en) | Early defect early warning method for wind turbine generator based on dynamic network sign | |
| CN112085261A (en) | Enterprise production status diagnosis method based on cloud fusion and digital twin technology | |
| CN110097209A (en) | A kind of equipment deterioration analysis method based on parameter residual error | |
| CN111896254A (en) | Fault prediction system and method for variable-speed variable-load large rolling bearing | |
| CN112101439B (en) | High-speed wire quality defect diagnosis and tracing method based on distributed Bayesian network | |
| CN115614292A (en) | Vibration monitoring device and method for vertical water pump unit | |
| CN111931849A (en) | Hydroelectric generating set operation data trend early warning method | |
| CN112949194B (en) | Explosion-proof forklift fault diagnosis method based on machine learning and cluster information fusion | |
| CN105095621A (en) | Transformer online running state evaluation method | |
| Dong et al. | Review of research on intelligent diagnosis of oil transfer pump malfunction | |
| CN117010666B (en) | Intelligent management method and system for production workstation of automobile repair tool | |
| CN111241629B (en) | Intelligent prediction method for performance change trend of hydraulic pump of airplane based on data driving | |
| CN112001511A (en) | Equipment reliability and dynamic risk evaluation method, system and equipment based on data mining | |
| CN108709426B (en) | Sintering machine air leakage fault online diagnosis method based on frequency spectrum characteristic bilateral detection method | |
| CN114066163A (en) | Power equipment state analysis method and device based on three-layer architecture mode | |
| CN115795389A (en) | Method and system for monitoring operation condition of transformer cooling device | |
| CN114971383A (en) | Smoke machine equipment fault diagnosis method and system based on knowledge graph | |
| CN111624985B (en) | Gas turbine control system sensor fault diagnosis method | |
| CN110441081B (en) | Intelligent diagnosis method and intelligent diagnosis system for faults of rotating machinery | |
| CN108804796B (en) | Annular cooler air leakage rate detection method based on frequency spectrum characteristics | |
| CN116135421B (en) | Welding processing path optimization method and system based on artificial intelligence | |
| Jose et al. | Fuzzy logic based fault Diagnosis in Induction motor | |
| CN110928858A (en) | Equipment knowledge base construction method based on digitization and intelligent application | |
| CN115310204B (en) | Production anomaly intelligent tracing method for influencing NVH performance of automobile |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |