CN112540580A - Method for monitoring equipment state of wire making and feeding system based on historical production data - Google Patents
Method for monitoring equipment state of wire making and feeding system based on historical production data Download PDFInfo
- Publication number
- CN112540580A CN112540580A CN202011186045.4A CN202011186045A CN112540580A CN 112540580 A CN112540580 A CN 112540580A CN 202011186045 A CN202011186045 A CN 202011186045A CN 112540580 A CN112540580 A CN 112540580A
- Authority
- CN
- China
- Prior art keywords
- data
- system based
- feeding
- historical production
- feeding system
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000010801 machine learning Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 238000004140 cleaning Methods 0.000 claims abstract description 4
- 238000013500 data storage Methods 0.000 claims abstract description 4
- 238000007619 statistical method Methods 0.000 claims abstract description 4
- 238000003860 storage Methods 0.000 claims abstract description 4
- 238000003066 decision tree Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 241000208125 Nicotiana Species 0.000 abstract description 7
- 235000002637 Nicotiana tabacum Nutrition 0.000 abstract description 7
- 238000007689 inspection Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 235000019504 cigarettes Nutrition 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 235000013599 spices Nutrition 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 235000011194 food seasoning agent Nutrition 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a method for monitoring equipment state of a tobacco making and feeding system based on historical production data, belonging to the field of tobacco, and the method for monitoring the equipment state of the tobacco making and feeding system based on the historical production data is realized by adopting the following steps: step 1, cleaning, analyzing, classifying and completing real-time data and historical fault data of equipment, and manually marking if a new fault type occurs; step 2, after the data are forwarded to a data storage area, the data are respectively stored in a distributed storage database, a time sequence database or a real-time cache and relational database according to the use requirements of the data; step 3, selecting a large amount of data of a proper artificial intelligence algorithm to perform statistical analysis, feature processing and machine learning modeling; and 4, verifying the model, deploying the model in a server, and providing an interface to receive real-time data and send a calculation result. The equipment state and the fault occurrence point are accurately and timely judged, and the processing time when the fault occurs is saved.
Description
Technical Field
The invention belongs to the field of tobacco, and particularly relates to a method for monitoring equipment state of a tobacco making and feeding system based on historical production data.
Background
In the production process of the cigarette, the feeding process is taken as an essential key process, and the effects of seasoning, aroma enhancement, moisture retention, mildew prevention and the like can be achieved. At present, the main working mode of the mainstream charging system is that the instantaneous flow of the tobacco material measured by the electronic scale is multiplied by the set application proportion, the instantaneous flow is used as the target amount of applying essence and spice, the actual addition is measured by the mass flow meter by controlling the executing structures such as the gear pump accurately by the PLC, the essence and the spice are uniformly applied to the tobacco material, and the result is fed back to the PLC, so that a closed-loop control system is formed. The whole charging system is also provided with a plurality of valves which are driven by a signal control valve component output by the PLC. Because the requirement on control accuracy is high, the interaction relation of all elements is tight, the influence on the feeding accuracy due to equipment failure is great, the conditions of large feeding accuracy deviation, instable instantaneous feeding accuracy and the like can be caused, and the fluctuation of the internal quality of the cigarette product is caused. Traditionally, the equipment faults are prevented by methods such as periodically replacing spare parts, routing inspection by operators, experience of maintenance personnel and the like, and the influence of the equipment faults on the quality of a charging process is reduced.
The equipment state of the traditional charging system needs to depend on manual point inspection and routing inspection, which is a work highly dependent on manual responsibility and professional skills, and has higher responsibility and better technology in time, and the running state of the equipment cannot be continuously monitored; when a fault occurs, a large amount of time is used for judging a fault occurrence point according to the current state of equipment, the experience and the technical level of a repair worker are very tested, even the most experienced repair worker needs a certain time to judge the type of the fault, and the quality defect caused by overlong downtime and the loss caused by shutdown of a production line are caused; the knowledge of equipment operators and maintenance personnel only belongs to the conditions of personal shift, movement or retirement and the like, and a large amount of time is needed for accumulating experience of newly-entered personnel, so that the knowledge is not explicit. Uncertain information cannot be determined, implicit knowledge cannot be made explicit, and the efficiency is low.
Disclosure of Invention
According to the invention, fault data are screened out manually by combining maintenance records with expert experiences on the basis of production data of each element of the feeding system acquired by the PLC, the fault data are classified according to fault types, then the screened out data are used as samples, the characteristics of the samples are extracted by using a machine learning method, and when the characteristics reappear due to system aging or other reasons, the fault types of the system are judged in advance and automatically, so that faults are eliminated in time or the positions of the faults are positioned more accurately when the influence of the system is small, and the elimination is convenient.
In order to realize the purpose, the invention adopts the following technical scheme: the method is realized by adopting the following steps: step 1, cleaning, analyzing, classifying and completing real-time data and historical fault data of equipment, and manually marking if a new fault type occurs; step 2, after the acquired data are processed, the data are respectively stored in a distributed storage, a time sequence database or a real-time cache and a relational database according to the use requirements of the data after being forwarded to a data storage area; step 3, selecting a large amount of data of a proper artificial intelligence algorithm to perform statistical analysis, feature processing and machine learning modeling; and 4, verifying the model, deploying the model in a server, and providing an interface to receive real-time data and send a calculation result.
Preferably, in the step 1, in the production process, the system automatically calculates an instantaneous feeding proportion, an instantaneous feeding precision, an accumulated feeding proportion and an accumulated feeding precision index, and stores the calculated index and the acquired instantaneous flow rate of the flowmeter, the rotating speed of the feeding pump, the opening and closing state of the valve and the like into a database to form historical production data, and numbering is performed according to a certain rule to show the difference.
Preferably, the numbering process for the device status adopts one-hot coding, the values of the discrete features are extended to the european space, and a certain value of the discrete features corresponds to a certain point of the european space, specifically, if the tag is made to use 0-9 as the device status differentiation, 0 is a vector [1,0,0,0,0,0, 0] after the one-hot coding, 1 is a vector [0,1,0,0,0,0,0,0,0,0, 0], and the like.
Preferably, in step 2, some abnormal values occur in the collected data processing, the data is null (Nan) or overrun due to communication, interference and the like in normal production, and a lagrange interpolation method or an average of two numbers before and after the data is used as the collected data at the position.
Preferably, in the step 2, data processing is adopted, collected data is subjected to normalization processing, a dimensional expression is converted into a dimensionless expression through transformation, the dimensionless expression becomes a scalar, a machine learning method is used in a later stage, an optimization problem is solved by using methods such as gradient descent and the like, the solving speed of the gradient descent is accelerated, and the convergence speed of the model is improved.
Preferably, in step 3, the model is modeled by using a decision tree in machine learning of the data with the label, and on the basis of the occurrence probability of each known condition, the probability that the expected value of the net present value is greater than or equal to zero is obtained by constructing the decision tree, and the probability of occurrence of each type of label labeling event is evaluated, so that the monitoring of the equipment state and the use of models such as a neural network and a support vector machine are completed.
The invention has the beneficial effects that:
(1) the state of the charging system is automatically monitored through a computer, the work highly dependent on manual responsibility and professional skills, such as manual point inspection, routing inspection and the like, is replaced, and the reliability is high;
(2) through the discovery of historical production data, objective rules hidden in the data are made explicit, so that the knowledge and experience are further summarized and improved, and the method is favorable for guiding workers to work better;
(3) the equipment state and the fault occurrence point are accurately and timely judged, the processing time during fault occurrence is saved, and the fault occurrence point can be quickly and accurately positioned, so that the quality defect caused by overlong downtime and the loss caused by shutdown of a production line are reduced;
(4) the scheme has universality and sharability, and the charging system using similar equipment and similar principles can be quickly modeled and put into use after simply marking historical fault information according to historical production data, and has low requirements on the computing capability and the processing speed of a computer.
(5) The device can continuously learn by self, can learn again about equipment problems which are not encountered, can accurately identify and judge fault points when next problems recur, and has self-learning property.
Drawings
FIG. 1 is a flow chart of the process of the present method;
fig. 2 is a data processing diagram.
Having the embodiments
In order to facilitate the understanding and implementation of the present invention for those skilled in the art, the technical solutions of the present invention will be further described with reference to the accompanying drawings and specific embodiments.
Before production begins, in order to accurately and uniformly spray the feed liquid on the material, a pipeline system needs to be pre-filled, a feeding pump runs at a fixed frequency, the feed liquid returns to a feeding tank after running for a circle through a filter, a stop valve, a feeding pump, a flow meter and a material return valve, redundant air in the pipeline is discharged, and the pipeline is filled with the feed liquid to be applied. During normal production, when the instantaneous flow of the electronic scale in front of the feeder reaches the set minimum flow (generally 200 kg/h), the nozzle valve and the injection steam valve are opened, the material return valve is closed, and the PID module in the PLC calculates the frequency of the feeding pump according to the set feeding proportion to perform fixed-proportion feeding. In the production process, the system automatically calculates indexes such as instantaneous feeding proportion, instantaneous feeding precision, accumulated feeding proportion, accumulated feeding precision and the like, and stores the calculated indexes and the acquired instantaneous flow rate of the flowmeter, the rotating speed of the feeding pump, the opening and closing states of the valve and the like into a database to form historical production data. By checking maintenance records, a series of equipment parameter conditions such as the charging proportion, the instantaneous charging precision, the accumulated charging proportion, the accumulated charging precision, the time charging proportion, the instantaneous flow of the electronic scale, the states of the nozzle valve, the injection steam valve, the state of the feed back valve and the like when faults are about to occur and have occurred in historical data can be accurately judged, and equipment technical experts with abundant experience number the equipment parameter conditions according to certain rules to show and distinguish the equipment parameter conditions, wherein if a normal state is represented by 0, moderate wear of the charging pump is represented by 1, severe wear of the charging pump is represented by 2, moderate blockage of the charging nozzle is represented by 3 and the like. The number of the mark is irrelevant to the judgment method, is only used as the distinction of one category, and can be defined by self.
The collected data items should cover all valves, pressure gauges, flow meters, frequency converters and the like involved in normal production of the charging system as much as possible. A person skilled in the art may vary in forms and details depending on the particular apparatus involved, without thereby departing from the scope of the present method as defined by the appended claims.
In the tag processing, a one-hot encoding is used, the value of the discrete feature is extended to the european space, and a certain value of the discrete feature corresponds to a certain point of the european space, specifically, if the tag is distinguished by using 0 to 9 as the device status, 0 is a vector [1,0,0,0,0,0,0, 0] after the one-hot encoding, 1 is a vector [0,1,0,0,0,0,0,0,0,0, 0], after the one-hot encoding, and the like.
Data acquisition systems have application in almost all cigarette factories, however, large amounts of data have not been mined to what value they should be. The method comprises the steps of cleaning, analyzing, classifying and completing real-time data and historical fault data of the equipment, manually marking if a new fault type occurs, and respectively storing the data into a distributed storage database, a time sequence database or a real-time cache and a relational database according to the use requirements of the data after the data are forwarded to a data storage area. A large amount of data of a proper artificial intelligence algorithm is selected for statistical analysis, feature processing and machine learning modeling, the model is verified, then the model is deployed in a server, an interface is provided for receiving real-time data and sending a calculation result, and when a user uses the model, the user does not need to pay attention to details and algorithms of model implementation, only needs to pay attention to self work, and receives prompts and then carries out timely processing.
In the data processing of the acquisition, if some abnormal values occur, for example, the data is empty (Nan) or overrun and the like due to communication, interference and the like in normal production, a lagrange interpolation method or an average of two numbers before and after the normal production can be used as the acquisition data of the position, and as a continuous production process, the numerical value change of the data in a plurality of acquisition intervals can be considered to be continuous, so that the final result is not influenced.
The collected data are normalized, a dimensional expression is transformed into a dimensionless expression to form a scalar, and when a machine learning method is used in the later period, optimization problems can be solved conveniently by using methods such as gradient descent and the like, the solving speed of the gradient descent is accelerated, and the convergence speed of the model is improved.
Modeling is carried out on data with labels by using a decision tree in machine learning, on the basis of the known occurrence probability of various conditions, the probability that the expected value of the net present value is greater than or equal to zero is obtained by forming the decision tree, and the probability of occurrence of labeling events of various types of labels is evaluated, so that the monitoring of the equipment state is completed. The models such as the neural network and the support vector machine are used, the models belong to supervised machine learning, certain difference exists in classification accuracy, and the effectiveness of the method is not influenced under the condition of meeting specific requirements.
Example 1.
As shown in fig. 1 and 2, the specific implementation steps are as follows:
1. in the data acquisition system, equipment information of a plurality of batches in a normal production state is collected, and the equipment state is marked as 0.
2. The equipment technical expert searches the equipment information when various types of faults occur in the data acquisition system according to the maintenance records, and distinguishes the faults according to different types of the faults which occur by 1,2,3 and 4 … ….
3. And summarizing the equipment information in the normal state and the equipment information in the fault state.
4. The tag is subjected to the one-hot encoding of the preferred scheme.
5. And searching whether an abnormal value exists in the summary information, if so, performing data processing of the preferred scheme, if not, performing data normalization processing, and then randomly scrambling the data.
6. Modeling the data after random disorder, preferably selecting a model with the highest classification accuracy from models such as a neural network, a decision tree, a support vector machine and the like, and evaluating the model by adopting the following method:
true Positive (TP): the true category is a positive example and the predicted category is a positive example.
False Positive (FP): the true category is a negative example and the predicted category is a positive example.
False Negative (FN): the true category is a positive example and the predicted category is a negative example.
True Negative (TN): the true category is a negative example and the predicted category is a negative example.
A Confusion Matrix (fusion Matrix) was then constructed as shown in the following table.
The model of the embodiment comprises a normal state, 8 equipment states in total, 16298 samples in total, wherein 11405 samples are used as learning samples, modeling is carried out by using a decision tree after disturbance, 4888 samples are used as verification samples, and the accuracy of model judgment is verified. Wherein the judgment is wrong by 7, and the judgment is correct by 4881, and the accuracy of the total judgment is 99.85 percent.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (6)
1. A method for monitoring the equipment state of a wire making and feeding system based on historical production data is characterized in that: the method is realized by adopting the following steps: step 1, cleaning, analyzing, classifying and completing real-time data and historical fault data of equipment, and manually marking if a new fault type occurs; step 2, after the acquired data are processed, the data are respectively stored in a distributed storage, a time sequence database or a real-time cache and a relational database according to the use requirements of the data after being forwarded to a data storage area; step 3, selecting a large amount of data of a proper artificial intelligence algorithm to perform statistical analysis, feature processing and machine learning modeling; and 4, verifying the model, deploying the model in a server, and providing an interface to receive real-time data and send a calculation result.
2. The method for monitoring equipment states of the wire making and feeding system based on historical production data as claimed in claim 1, wherein the method comprises the following steps: step 1, in the production process, the system automatically calculates the indexes of instantaneous feeding proportion, instantaneous feeding precision, accumulated feeding proportion and accumulated feeding precision, and stores the calculated indexes and the acquired instantaneous flow rate of the flowmeter, the rotating speed of the feeding pump, the opening and closing states of the valve and the like into a database to form historical production data, and numbering is carried out according to certain rules to show the difference.
3. The method for monitoring equipment states of the wire making and feeding system based on historical production data as claimed in claim 2, wherein the method comprises the following steps: the numbering process for the device states adopts one-hot coding, the values of the discrete features are expanded to the Euclidean space, and a certain value of the discrete features corresponds to a certain point of the Euclidean space, specifically, if a label is made to use 0-9 as the distinction of the device states, 0 uses one-hot coding and then becomes a vector [1,0,0,0,0, 0], 1 uses one-hot coding and then becomes a vector [0,1,0,0,0,0,0,0,0,0], and the like.
4. A method of monitoring equipment status of a wire-making charging system based on historical production data as claimed in claim 2 or 3, wherein: in the step 2, some abnormal values appear in the acquired data processing, the data is null (Nan) or overrun due to communication, interference and the like in normal production, and a lagrange interpolation method or an average of two numbers before and after the simple method is used as the acquired data at the position.
5. The method for monitoring equipment states of the wire making and feeding system based on historical production data as claimed in claim 4, wherein the method comprises the following steps: and 2, the data processing adopts the steps of carrying out normalization processing on the acquired data, converting a dimensional expression into a dimensionless expression through transformation, forming the dimensionless expression into a scalar, using a machine learning method in the later stage, solving the optimization problem by using methods such as gradient descent and the like, accelerating the solving speed of the gradient descent and improving the convergence speed of the model.
6. The method for monitoring equipment state of the wire making and feeding system based on historical production data as claimed in any one of claims 2,3 and 5, wherein the method comprises the following steps: and 3, modeling the data with the labels by using a decision tree in machine learning, obtaining the probability that the expected value of the net present value is greater than or equal to zero by forming the decision tree on the basis of the known occurrence probability of various conditions, and evaluating the occurrence probability of various label labeling events, thereby completing the monitoring of the equipment state and the use of models such as a neural network, a support vector machine and the like.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011186045.4A CN112540580A (en) | 2020-10-30 | 2020-10-30 | Method for monitoring equipment state of wire making and feeding system based on historical production data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011186045.4A CN112540580A (en) | 2020-10-30 | 2020-10-30 | Method for monitoring equipment state of wire making and feeding system based on historical production data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112540580A true CN112540580A (en) | 2021-03-23 |
Family
ID=75013605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011186045.4A Pending CN112540580A (en) | 2020-10-30 | 2020-10-30 | Method for monitoring equipment state of wire making and feeding system based on historical production data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112540580A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113721518A (en) * | 2021-08-31 | 2021-11-30 | 中冶华天南京工程技术有限公司 | Data acquisition and storage method for steel production |
| CN115857416A (en) * | 2023-01-25 | 2023-03-28 | 江苏新恒基特种装备股份有限公司 | Remote control method and system for pipe bending equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
| CN110084412A (en) * | 2019-04-12 | 2019-08-02 | 重庆邮电大学 | A kind of photovoltaic power generation big data prediction technique based on the study of Feature Conversion multi-tag |
| CN110138843A (en) * | 2019-04-23 | 2019-08-16 | 迈赫机器人自动化股份有限公司 | A kind of agricultural machinery manufacture Internet of Things monitoring method and system |
| CN110320892A (en) * | 2019-07-15 | 2019-10-11 | 重庆邮电大学 | The sewage disposal device fault diagnosis system and method returned based on Lasso |
| CN110430260A (en) * | 2019-08-02 | 2019-11-08 | 哈工大机器人（合肥）国际创新研究院 | Robot cloud platform based on big data cloud computing support and working method |
| CN111427330A (en) * | 2020-03-19 | 2020-07-17 | 杭州培慕科技有限公司 | Equipment maintenance data-based equipment fault mode and rule analysis method |
-
2020
- 2020-10-30 CN CN202011186045.4A patent/CN112540580A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
| CN110084412A (en) * | 2019-04-12 | 2019-08-02 | 重庆邮电大学 | A kind of photovoltaic power generation big data prediction technique based on the study of Feature Conversion multi-tag |
| CN110138843A (en) * | 2019-04-23 | 2019-08-16 | 迈赫机器人自动化股份有限公司 | A kind of agricultural machinery manufacture Internet of Things monitoring method and system |
| CN110320892A (en) * | 2019-07-15 | 2019-10-11 | 重庆邮电大学 | The sewage disposal device fault diagnosis system and method returned based on Lasso |
| CN110430260A (en) * | 2019-08-02 | 2019-11-08 | 哈工大机器人（合肥）国际创新研究院 | Robot cloud platform based on big data cloud computing support and working method |
| CN111427330A (en) * | 2020-03-19 | 2020-07-17 | 杭州培慕科技有限公司 | Equipment maintenance data-based equipment fault mode and rule analysis method |
Non-Patent Citations (2)
| Title |
|---|
| 权鹏宇;车文刚;余任;周志元;: "云资源池探针的故障检测方法研究", 软件, no. 08 * |
| 杨宏宇，李博超: "基于逆向习得推理的网络异常行为检测模型", 《计算机应用》, vol. 7, no. 39, pages 1967 - 1972 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113721518A (en) * | 2021-08-31 | 2021-11-30 | 中冶华天南京工程技术有限公司 | Data acquisition and storage method for steel production |
| CN115857416A (en) * | 2023-01-25 | 2023-03-28 | 江苏新恒基特种装备股份有限公司 | Remote control method and system for pipe bending equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108460144B (en) | Coal equipment fault early warning system and method based on machine learning | |
| CN106444703B (en) | Dynamic equipment running status fuzzy evaluation and prediction technique based on fault mode probability of happening | |
| CN107358366B (en) | Distribution transformer fault risk monitoring method and system | |
| CN108154291B (en) | Power supply plant performance index evaluation method and system based on strategy library | |
| CN108027594A (en) | For detecting the abnormal method in water distribution system | |
| CN100542779C (en) | Parameterized injection molding system and method | |
| CN110320892A (en) | The sewage disposal device fault diagnosis system and method returned based on Lasso | |
| CN109947088A (en) | Equipment fault early-warning system based on model lifecycle management | |
| CN109840157A (en) | Method, apparatus, electronic equipment and the storage medium of fault diagnosis | |
| DE60205356T2 (en) | SYSTEM, DEVICE AND METHOD FOR DIAGNOSING A FLOW SYSTEM | |
| CN108897954A (en) | Wind turbines temperature pre-warning method and its system based on BootStrap confidence calculations | |
| CN106206346A (en) | Measurement Sampling Method with Sampling Rate Determination Mechanism | |
| CN112540580A (en) | Method for monitoring equipment state of wire making and feeding system based on historical production data | |
| CN108133316B (en) | Detection method for familial defects of power equipment of power supply plant | |
| CN112508053A (en) | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework | |
| CA2938766A1 (en) | Method of identifying anomalies | |
| CN105975797B (en) | A kind of product initial failure root primordium recognition methods based on Fuzzy data processing | |
| CN105573290B (en) | Cigarette factory ultrahigh speed case packing machine multiple operating modes process is monitored on-line and method for diagnosing faults | |
| CN107291830A (en) | A kind of creation method of equipment knowledge base | |
| WO2013041440A1 (en) | System and method for plant wide asset management | |
| CN113091817A (en) | Triethylene glycol dewatering device state monitoring and fault diagnosis system | |
| CN110188984A (en) | A kind of tobacco rolls up the method for building up of anomalous mass data model between hired car | |
| TW202100900A (en) | Intelligent learning mechanism and adaptive regulation system for liquid gas filling | |
| CN114519923A (en) | Intelligent diagnosis and early warning method and system for power plant | |
| CN115099260A (en) | Online monitoring mechanical fault real-time diagnosis method for double-screw oil transfer pump |
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 |