CN112859741A - Method and system for evaluating operation reliability of sequential action units of machine tool - Google Patents
Method and system for evaluating operation reliability of sequential action units of machine tool Download PDFInfo
- Publication number
- CN112859741A CN112859741A CN202011643607.3A CN202011643607A CN112859741A CN 112859741 A CN112859741 A CN 112859741A CN 202011643607 A CN202011643607 A CN 202011643607A CN 112859741 A CN112859741 A CN 112859741A
- Authority
- CN
- China
- Prior art keywords
- action
- machine tool
- discrete
- sequential
- time
- 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
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
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
- G05B19/4065—Monitoring tool breakage, life or condition
-
- 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
- G05B2219/37—Measurements
- G05B2219/37616—Use same monitoring tools to monitor tool and workpiece
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a method and a system for evaluating the running reliability of a machine tool sequential action unit based on beats, wherein the method comprises the following steps: collecting discrete action time of the numerical control machine tool during normal processing; obtaining a discrete action time fluctuation interval during normal processing of the numerical control machine tool by adopting a machine learning algorithm, wherein the upper limit and the lower limit of the discrete action time fluctuation interval are used as judgment thresholds; collecting discrete action time in real time during the machining of the numerical control machine tool, comparing the current discrete action time with the fluctuation interval threshold value, and judging whether the current discrete action time exceeds the fluctuation interval; and analyzing whether the discrete action time trend is abnormal or not according to the judgment result, and evaluating and predicting the operation reliability of the action unit. Correspondingly, the invention also provides a system corresponding to the method. The invention evaluates the operation reliability of the action units by monitoring and analyzing the discrete action beats of the sequential action units, and has low cost and strong real-time property.
Description
Technical Field
The invention relates to the field of machine tool fault monitoring, in particular to a method and a system for realizing real-time monitoring and evaluation of the operation reliability of a sequential action unit of a machine tool by monitoring the discrete action beat of the machine tool.
Background
In modern industrial production lines, a numerical control machine tool is one of core processing equipment in the production line, and plays a significant role in the fields of aerospace, ships, automobiles, power generation equipment and the like. In a large-batch and high-precision production line, a numerical control machine tool is not provided with replaceable machining equipment. However, the numerical control machine tool has a high requirement for reliability as a high-precision and complex mechanical-electrical-hydraulic integrated device, once the numerical control machine tool has a reduced processing performance or even a fault, a processed workpiece can be scrapped, a processing beat can be delayed when the numerical control machine tool is serious, the processing efficiency is reduced, the processing cost is increased, and huge economic loss is caused. Therefore, a system for monitoring the performance of a machine tool in real time is needed, which can monitor the performance degradation of the numerical control machine before the numerical control machine fails.
Most of the existing monitoring systems for numerical control machines perform fault monitoring, prediction and diagnosis functions on machine tools according to the performance conditions of characteristic values after the characteristic values are extracted by processing analog quantity signals such as vibration signals, current signals, pressure signals and the like. For example, chinese patent application No. 201810642786.5 discloses a system and method for evaluating reliability of a machine tool cutter, which uses historical data as a fitting sample based on the functions of artificial neural network self-learning and self-adaptation, and monitors performance parameter indexes, such as vibration signals, current signals, sound wave signals, wear loss and machining roughness, affecting the cutter reliability in real time during machining. Through the real-time monitoring to the cutter running state, the real-time reliability information of the cutter is fed back, the remaining service life of the cutter is estimated, and a processing enterprise can make preventive measures in advance, so that the loss is reduced, and the overall processing efficiency is improved.
However, in the methods similar to the above patents, in order to obtain the corresponding analog quantity, a corresponding sensor needs to be added at a corresponding position of the numerical control machine tool, which is time-consuming and costly, and in addition, a lot of time is consumed when data processing is performed on the measured noise-containing signal, which affects the real-time performance and the accuracy of judgment.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method and a system for evaluating the running reliability of a machine tool sequential action unit, which solve the problems of high monitoring cost, poor real-time performance and low accuracy of the existing machine tool sequential action unit.
In a first aspect of the present invention, a method for evaluating operational reliability of a sequential operation unit of a machine tool includes:
s1, collecting discrete action time of the numerical control machine tool during normal processing;
s2, based on the discrete action time during normal processing, obtaining a discrete action time fluctuation interval during normal processing of the numerical control machine tool by adopting a machine learning algorithm, wherein the upper limit and the lower limit of the discrete action time fluctuation interval are used as judgment thresholds;
s3, collecting discrete action time in real time during machining of the numerical control machine tool, comparing the current discrete action time with the fluctuation interval threshold value, and judging whether the current discrete action time exceeds the fluctuation interval;
and S4, analyzing whether the discrete action time trend is abnormal or not according to the judgment result of S3, and evaluating and predicting the operation reliability of the action unit.
Optionally, in S4, the discrete action time trend may be analyzed by a corresponding diagnostic algorithm to determine whether the discrete action time trend is abnormal, and to evaluate and predict the operation reliability of the action unit. Further, the analyzing whether the discrete action time trend is abnormal or not includes any one of the following criteria:
(1) discrete action time points are outside the set control limit;
(2) the continuous n discrete action time points are on the same side of the mean value line;
(3) there is a tendency for not less than n discrete action time points to rise or fall continuously;
(4) the continuous n adjacent discrete action time points alternate up and down;
(5) the continuous n discrete action time points on either side are outside the standard deviation of +/-1 time of the discrete action time;
when any of the above (1) to (5) is satisfied, it is determined to be abnormal.
The method of the invention takes the discrete action time as an important index for monitoring the working state of the sequential action unit by counting and processing the time beats of each discrete action, thereby solving the problems of high monitoring cost, poor real-time performance and low accuracy of the sequential action unit of the existing numerical control machine.
In a second aspect of the present invention, there is provided a system for evaluating operational reliability of a sequential operation unit of a machine tool, comprising:
the action generating and marking module is used for marking the action generating and ending time of the sequential action unit of the numerical control machine tool, finishing the calculation of discrete action time and obtaining the beat of the sequential action;
the data acquisition and recording module is used for acquiring the sequential action beats of the action generation and marking module through data communication, analyzing and sorting the sequential action beats, and storing the result in a database;
the learning module is used for counting and classifying the normal beats and the abnormal beats of the sequential actions according to the results of the data acquisition and recording module to complete the setting of the control limit;
and the diagnosis module analyzes whether the discrete action time trend is abnormal or not through a diagnosis algorithm according to the result of the data acquisition and recording module and the control limit of the learning module, and evaluates and predicts the operation reliability of the action unit.
Optionally, the learning module is divided into an offline learning part and an online learning part. Off-line learning is carried out to complete off-line statistics and classification learning of normal beats and abnormal beats of sequential actions, and setting of control boundaries is completed; and the online learning completes the online statistics and classification learning of the normal beats and the abnormal beats of the sequential actions, and sets a control limit. Specifically, the learning module obtains data provided by the data acquisition and recording module and completes a learning task through a learning algorithm.
In a third aspect of the present invention, there is provided a computer comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the method for evaluating the operational reliability of the sequential action units of the machine tool.
Compared with the prior art, the embodiment of the invention has at least one of the following beneficial effects:
the method and the system of the invention monitor and evaluate the reliability of the operation of the sequential action unit of the machine tool in real time by monitoring the discrete action beat of the machine tool, solve the problems of high monitoring cost, poor real-time performance and low accuracy of the prior sequential action unit of the machine tool, and have important practical significance in the fields of machine tool fault monitoring and the like.
The method and the system can analyze the running beat of the sequential action unit by collecting the signal of the numerical control system, and solve the problems of low sampling precision and the like caused by other methods of arranging an external sensor and the like. Meanwhile, by monitoring the running rhythm of the sequential action unit, the problems of long data processing time, high cost and the like caused by the fact that various external sensors are arranged to monitor the running state are solved, and the monitoring method is simplified.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a flow chart of a method for evaluating the operational reliability of sequential operation units of a machine tool according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for evaluating the operational reliability of sequential operation units of a machine tool according to a preferred embodiment of the present invention;
fig. 3 is a block diagram of a system for evaluating the operational reliability of a sequential operation unit of a machine tool according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
Fig. 1 is a flowchart of a method for evaluating the operational reliability of a sequential operation unit of a machine tool according to an embodiment of the present invention. Specifically, referring to fig. 1, the method for evaluating the operational reliability of the sequential action unit of the machine tool in the present embodiment may be implemented by referring to the following steps:
s1, collecting discrete action time of the numerical control machine tool during normal processing;
s2, based on the discrete action time during normal processing, obtaining a discrete action time fluctuation interval during normal processing of the numerical control machine tool by adopting a machine learning algorithm, wherein the upper limit and the lower limit of the discrete action time fluctuation interval are used as judgment thresholds;
s3, collecting discrete action time in real time during machining of the numerical control machine tool, comparing the current discrete action time with the fluctuation interval threshold value, and judging whether the current discrete action time exceeds the fluctuation interval;
and S4, analyzing whether the discrete action time trend is abnormal or not according to the judgment result of S3, and evaluating and predicting the operation reliability of the action unit.
The embodiment solves the problem of high reliability evaluation difficulty of the sequential action units of the existing numerical control machine tool by statistically processing the time of each sequential action (also called discrete action) and taking the time of the sequential action as an important index for evaluating the reliability of the action units.
In S4, the discrete action time trend may be analyzed by a corresponding diagnostic algorithm to determine whether the discrete action time trend is abnormal, and the operation reliability of the action unit may be evaluated and predicted. Specifically, the judgment criterion for analyzing whether the trend of the dispersion action time is abnormal in the present embodiment includes any one of the following criteria:
(1) discrete action time points are outside the set control limit;
(2) the continuous n discrete action time points are on the same side of the mean value line;
(3) there is a tendency for not less than n discrete action time points to rise or fall continuously;
(4) the continuous n adjacent discrete action time points alternate up and down;
(5) the continuous n discrete action time points on either side are outside the standard deviation of +/-1 time of the discrete action time;
when any of the above (1) to (5) is satisfied, it is determined to be abnormal. The above n can be set and can be corrected according to learning. After judging whether the abnormal conditions exist, determining the abnormal types, wherein the abnormal types comprise early warning and alarming, and the judgment criteria are as follows: when some is outside the control limit, starting an alarm; and when any one of the judgment criteria (2) to (5) is met, starting early warning.
In the above S3, the real-time acquisition of the discrete action time during the machining of the numerical control machine tool may be further transmitted to the data processing device through a network, so as to perform other subsequent processing on the data processing device. Optionally, the data processing device transmits the diagnosis result to the numerical control system, the edge monitoring device, and the like, and performs actions such as continuous operation, early warning, alarming, and the like.
FIG. 2 is a flow chart of a method for evaluating the operational reliability of sequential operation units of a machine tool according to a preferred embodiment of the present invention. Specifically, referring to fig. 1, the method for evaluating the operational reliability of the sequential action unit of the machine tool in the present embodiment may be implemented by referring to the following steps:
and S100, acquiring discrete action time during normal machining of the numerical control machine tool through a numerical control system, and using the discrete action time as a training set for machine learning.
S200, obtaining a discrete action time fluctuation interval during normal machining of the numerical control machine tool through a machine learning algorithm, and taking the upper limit and the lower limit as judgment thresholds. The algorithm in this embodiment may be implemented using existing technology.
S300, collecting discrete action time from the numerical control system in real time during the machining of the numerical control machine.
And S400, transmitting the discrete action time acquired in real time to data processing equipment through a network.
S500, comparing the current discrete action time with a fluctuation interval threshold value, judging whether the discrete action time exceeds a fluctuation interval, and selecting the standard deviation of +/-3 times of the acquired discrete action time as a control limit.
S600, analyzing whether the discrete action time trend is abnormal or not through a diagnosis algorithm, diagnosing the abnormal type, and evaluating and predicting the operation reliability of the action unit.
And S700, the data processing equipment transmits the diagnosis result to a numerical control system, edge monitoring equipment and the like, and the actions of continuous operation, early warning, alarming and the like are carried out.
According to the embodiment of the invention, the running beat of the sequential action unit can be analyzed by collecting the signal of the numerical control system, so that the problems of low sampling precision and the like caused by other methods such as arranging an external sensor and the like are solved. Meanwhile, by monitoring the running rhythm of the sequential action unit, the problems of long data processing time, high cost and the like caused by the fact that various external sensors are arranged to monitor the running state are solved, and the monitoring method is simplified.
As in the embodiment shown in fig. 1, in the present embodiment, whether the discrete action time trend is abnormal or not, the type of abnormality diagnosis, and the operational reliability of the action unit evaluation and prediction can be performed by corresponding diagnostic algorithms. Analyzing whether the discrete action time trend is abnormal or not, wherein the judgment criterion comprises the following steps:
(1) discrete action time points are outside the control limit;
(2) the continuous n discrete action time points are on the same side of the mean value line;
(3) there is a tendency for not less than n discrete action time points to rise or fall continuously;
(4) the continuous n adjacent discrete action time points alternate up and down;
(5) the consecutive n discrete action time points on either side are outside ± 1 times the standard deviation of the discrete action time. The above n can be set and can be corrected according to learning.
According to the judgment criterion of the abnormal type, when the abnormal type is a little outside the control limit, starting an alarm; and when any one of the judgment criteria (2) to (5) is met, starting early warning. Setting the distance between the current point and the time fluctuation central axis of the discrete action as d, setting the critical distance between the time point and the central axis as delta d, establishing a health index h (h is more than or equal to 0 and less than or equal to 1) for the operation of the sequential action unit, and setting the fluctuation interval threshold as +/-t, then defining the health index h as a formula (1):
wherein h-1 represents 100% of healthy state. The smaller h represents the worse reliability. So that the reliability can be quantitatively evaluated.
Fig. 3 is a block diagram of a system for evaluating the operational reliability of a sequential operation unit of a machine tool according to an embodiment of the present invention. Referring to fig. 3, in the present embodiment, a system for monitoring operation reliability of a sequential action unit based on discrete action time includes an action generation and marking module, a data acquisition and recording module, a learning module, and a diagnosis module. The action generating and marking module is used for marking action generating and ending time of a sequential action unit of the numerical control machine tool, finishing calculation of discrete action time and obtaining a sequential action beat; the data acquisition and recording module is used for acquiring the sequential action beats of the action generation and marking module through data communication, analyzing and sorting the sequential action beats, and storing the result in a database; the learning module performs statistics and classification learning of normal beats and abnormal beats of sequential actions according to the results of the data acquisition and recording module to complete setting of a control limit, for example, selecting a standard deviation of the control limit to be +/-3 times of the acquired discrete action time; the diagnosis module analyzes whether the discrete action time trend is abnormal or not through a diagnosis algorithm according to the results of the data acquisition and recording module and the control limit of the learning module, diagnoses the abnormal type according to the judgment criterion of the abnormal type, calculates the health degree, and evaluates and predicts the operation reliability of the action unit.
Specifically, the action generating and marking module is used for marking the action generating and ending time of the sequential action unit of the numerical control machine tool to finish the beat calculation of the action. The action generation and the marking and calculation of the marking module can be completed in a numerical control system and a programmable controller of the numerical control machine tool. Taking the action unit for clamping and loosening the cutter as an example, the generation and ending time of the clamping and loosening action of the cutter can be marked in a programmable controller of a numerical control system.
Specifically, the data acquisition and recording module acquires sequential action beats through data communication, analyzes and arranges the beats, and stores results in the database. The data acquisition and recording module can adopt an edge computer, and the obtained data is stored in the edge computer through communication with the numerical control system. Taking the action unit for clamping and releasing the cutter as an example, the action time of clamping and releasing the cutter is transmitted to a computer analysis device such as an edge computer in a real-time manner through a network and the like, and the obtained original data is stored in the computer.
Specifically, the learning module is divided into an offline learning part and an online learning part. Taking an action unit for clamping and releasing the cutter as an example, offline learning is carried out to complete offline statistics and classified learning of normal beats and abnormal beats of the clamping and releasing actions of the cutter, and the setting of a control limit is completed; and finishing the online statistics and classification learning of the normal and abnormal beats of the clamping and loosening actions of the cutter and setting of a trimming control limit. Specifically, the learning module obtains beat data of clamping and loosening of the tool provided by the data acquisition and recording module, and the learning task is completed by a statistical learning method with the mean value and the standard deviation as characteristic quantities.
Optionally, the diagnosis module is responsible for analyzing the sequential action beats on line, performing automatic classification and mode judgment on the abnormal beats, and meanwhile, quantitatively evaluating the operation reliability by calculating the health degree. Furthermore, after the operation reliability is quantitatively evaluated, the diagnosis module synthesizes the diagnosis result, evaluates the operation reliability of the action unit and timely provides early warning and alarming. Specifically, taking an action unit for clamping and loosening a cutter as an example, according to a judgment criterion of a discrete action abnormal mode, when the action unit is a point outside a control limit, an alarm is started; when the following judgment criteria (a) to (d) are met, that is:
(a) the continuous 8 discrete action time points are on the same side;
(b) there is a tendency to rise or fall for not less than 6 discrete action time points in succession;
(c) the continuous 15 adjacent discrete action time points alternate up and down;
(d) the 8 consecutive action time points on either side were outside of ± 1 times the standard deviation of the discrete action time.
Then the early warning is started to inform maintenance personnel to diagnose and overhaul.
Assuming that the critical distance Δ d between the time point and the motion time fluctuation central axis is σ, and the fluctuation interval threshold t is 3 σ, the health index of the sequential motion can be calculated according to the formula (1).
Of course, the system can further comprise an alarm module, and the alarm module integrates the diagnosis result, evaluates the operation reliability of the action unit and timely provides early warning and alarm.
In another embodiment, the method for evaluating the operational reliability of the sequential action unit of the machine tool is implemented by combining the system, and the specific process may include the following steps:
(a) and in the action generating and marking module, the action generating and marking module is used for marking the action generating and finishing time of the cutter loosening and clamping action unit so as to complete the beat calculation of the action.
(b) In the data acquisition and recording module, the action time of clamping and loosening the cutter is transmitted to a computer and an analysis device such as an edge computer in real time in a network mode and the like, and the obtained original data is stored in the computer.
(c) The tool loosening and clamping action time during normal machining of the numerical control machine tool is collected through a numerical control system and used as a training set for machine learning.
(d) In the learning module, a time fluctuation interval of tool loosening and clamping actions during normal machining of the numerical control machine tool is obtained through a machine learning algorithm, and the upper limit and the lower limit of the time fluctuation interval are used as judgment thresholds.
(e) When the numerical control machine tool is processed, the time of tool loosening and clamping actions is collected in real time from the numerical control system and transmitted to the data processing equipment through a network.
(f) In the diagnosis module, the current tool loosening and clamping action time is compared with a fluctuation interval threshold value, and whether the discrete action time exceeds a fluctuation interval is judged.
(g) And analyzing whether the tool loosening and clamping action time trends are abnormal or not through a diagnosis algorithm, diagnosing abnormal types, calculating health degree, and evaluating and predicting the operation reliability of the action unit.
(h) And the data processing equipment transmits the diagnosis result to a numerical control system, edge monitoring equipment and the like, and performs actions such as continuous operation, early warning, alarming and the like.
Based on the steps, the monitoring of the operation state and the reliability of the clamping and loosening unit of the cutter of the embodiment of the sequential action unit based on the discrete action time can be realized.
In another embodiment of the present invention, there is further provided a computer including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the method for evaluating the operation reliability of the sequential action units of the machine tool in any one of the above embodiments.
The method and the system in the embodiment of the invention monitor and evaluate the running reliability of the sequential action unit of the machine tool in real time by monitoring the discrete action beat of the machine tool, solve the problems of high monitoring cost, poor real-time performance and low accuracy of the prior sequential action unit of the machine tool, and have important practical significance in the fields of machine tool fault monitoring and the like.
The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, and not to limit the invention. Any modifications and variations within the scope of the description, which may occur to those skilled in the art, are intended to be within the scope of the invention.
Claims (10)
1. A method for evaluating the operation reliability of a sequential action unit of a machine tool is characterized by comprising the following steps:
collecting discrete action time of the numerical control machine tool during normal processing;
based on the discrete action time during normal processing, obtaining a discrete action time fluctuation interval during normal processing of the numerical control machine tool by adopting a machine learning algorithm, wherein the upper limit and the lower limit of the discrete action time fluctuation interval are used as judgment thresholds;
collecting discrete action time in real time during the machining of the numerical control machine tool, comparing the current discrete action time with the fluctuation interval threshold value, and judging whether the current discrete action time exceeds the fluctuation interval;
and analyzing whether the discrete action time trend is abnormal or not according to the judgment result, and evaluating and predicting the operation reliability of the action unit.
2. The method for evaluating the operational reliability of the sequential action units of the machine tool according to claim 1, wherein the analyzing whether the trend of the discrete action time is abnormal includes any one of the following criteria:
(1) discrete action time points are outside the set control limit;
(2) the continuous n discrete action time points are on the same side of the mean value line;
(3) there is a tendency for not less than n discrete action time points to rise or fall continuously;
(4) the continuous n adjacent discrete action time points alternate up and down;
(5) the continuous n discrete action time points on either side are outside the standard deviation of +/-1 time of the discrete action time;
when any of the above (1) to (5) is satisfied, it is determined to be abnormal.
3. The method for evaluating the operational reliability of the sequential action units of the machine tool according to claim 1, wherein the operational health index h of the sequential action unit is established, wherein the current point is away from the central axis of the discrete action time fluctuation by a distance d, the time point is away from the central axis by a critical distance Δ d, the operational health index h is greater than or equal to 0 and less than or equal to 1, and the fluctuation interval threshold is ± t, so that the health index h is defined as formula (1):
where h-1 represents the healthy state 100%, and the smaller h, the worse the reliability.
4. The method for evaluating operational reliability of sequential operation units of a machine tool according to claim 1, wherein the discrete operation time of the numerical control machine tool during machining is collected in real time and further transmitted to the data processing apparatus through a network.
5. A system for evaluating the operational reliability of sequential operation units of a machine tool, comprising:
the action generating and marking module is used for marking the action generating and ending time of the sequential action unit of the numerical control machine tool, finishing the calculation of discrete action time and obtaining the beat of the sequential action;
the data acquisition and recording module is used for acquiring the sequential action beats of the action generation and marking module through data communication, analyzing and sorting the sequential action beats, and storing the result in a database;
the learning module is used for counting and classifying the normal beats and the abnormal beats of the sequential actions according to the results of the data acquisition and recording module to complete the setting of the control limit;
and the diagnosis module analyzes whether the discrete action time trend is abnormal or not through a diagnosis algorithm according to the result of the data acquisition and recording module and the control limit of the learning module, and evaluates and predicts the operation reliability of the action unit.
6. The system for evaluating operational reliability of sequential action units of a machine tool according to claim 4, wherein the learning module is divided into an offline learning part and an online learning part, wherein:
off-line learning is carried out to complete off-line statistics and classification learning of normal beats and abnormal beats of sequential actions, and setting of control boundaries is completed;
online learning is carried out to complete online statistics and classification learning of normal beats and abnormal beats of sequential actions, and setting of control limits is finished;
the learning module obtains the data provided by the data acquisition and recording module and completes the learning task through a learning algorithm.
7. The system of claim 4, wherein the learning module selects a control limit of ± 3 times a standard deviation of the discrete motion time that has been collected.
8. The system for evaluating the operational reliability of sequential action units of a machine tool according to claim 4, wherein the diagnostic module is responsible for analyzing the sequential action tempo online, performing automatic classification and mode judgment on abnormal tempos, and meanwhile, quantitatively evaluating the operational reliability by calculating the degree of health.
9. The system for evaluating the operational reliability of sequential action units of a machine tool according to claim 7, wherein the diagnostic module integrates the diagnostic result after quantitatively evaluating the operational reliability, evaluates the operational reliability of the action units, and timely provides early warning and alarm.
10. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor is adapted to perform the method of any of claims 1 to 4 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643607.3A CN112859741A (en) | 2020-12-31 | 2020-12-31 | Method and system for evaluating operation reliability of sequential action units of machine tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643607.3A CN112859741A (en) | 2020-12-31 | 2020-12-31 | Method and system for evaluating operation reliability of sequential action units of machine tool |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112859741A true CN112859741A (en) | 2021-05-28 |
Family
ID=76000902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011643607.3A Pending CN112859741A (en) | 2020-12-31 | 2020-12-31 | Method and system for evaluating operation reliability of sequential action units of machine tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112859741A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111443326A (en) * | 2020-04-10 | 2020-07-24 | 国网浙江省电力有限公司电力科学研究院 | Running beat diagnostic system for automatic verification assembly line of electric energy meter and working method of running beat diagnostic system |
| CN113189935A (en) * | 2021-04-29 | 2021-07-30 | 浙江陀曼云计算有限公司 | Non-invasive production beat prediction method and system based on time sequence power data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104808587A (en) * | 2015-04-27 | 2015-07-29 | 重庆大学 | Utilization statistical approach based on operation states of machining equipment |
| CN105974886A (en) * | 2016-06-28 | 2016-09-28 | 华中科技大学 | Health monitoring method for numerical control machine tool |
| CN106994625A (en) * | 2015-10-30 | 2017-08-01 | 大隈株式会社 | Lathe monitoring arrangement |
| WO2018122954A1 (en) * | 2016-12-27 | 2018-07-05 | 株式会社Ｆｕｊｉ | Machine tool apparatus |
| US20190278253A1 (en) * | 2016-09-27 | 2019-09-12 | Chongqing University | Method for Judging Key Moments in Whole Process of Machining Step for Computer Numerical Control Machine Tools |
| CN111290335A (en) * | 2018-12-06 | 2020-06-16 | 发那科株式会社 | Processing time monitoring device |
| CN111667198A (en) * | 2020-06-23 | 2020-09-15 | 宝石电气设备有限责任公司 | Remote online monitoring and predictive maintenance system and evaluation method for petroleum drilling machine |
-
2020
- 2020-12-31 CN CN202011643607.3A patent/CN112859741A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104808587A (en) * | 2015-04-27 | 2015-07-29 | 重庆大学 | Utilization statistical approach based on operation states of machining equipment |
| CN106994625A (en) * | 2015-10-30 | 2017-08-01 | 大隈株式会社 | Lathe monitoring arrangement |
| CN105974886A (en) * | 2016-06-28 | 2016-09-28 | 华中科技大学 | Health monitoring method for numerical control machine tool |
| US20190278253A1 (en) * | 2016-09-27 | 2019-09-12 | Chongqing University | Method for Judging Key Moments in Whole Process of Machining Step for Computer Numerical Control Machine Tools |
| WO2018122954A1 (en) * | 2016-12-27 | 2018-07-05 | 株式会社Ｆｕｊｉ | Machine tool apparatus |
| CN111290335A (en) * | 2018-12-06 | 2020-06-16 | 发那科株式会社 | Processing time monitoring device |
| CN111667198A (en) * | 2020-06-23 | 2020-09-15 | 宝石电气设备有限责任公司 | Remote online monitoring and predictive maintenance system and evaluation method for petroleum drilling machine |
Non-Patent Citations (2)
| Title |
|---|
| 林源: "统计过程控制在数控加工中的应用研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅰ辑》 * |
| 齐继阳等: "液压系统健康状态的综合评估方法", 《机械设计与制造》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111443326A (en) * | 2020-04-10 | 2020-07-24 | 国网浙江省电力有限公司电力科学研究院 | Running beat diagnostic system for automatic verification assembly line of electric energy meter and working method of running beat diagnostic system |
| CN111443326B (en) * | 2020-04-10 | 2022-08-19 | 国网浙江省电力有限公司营销服务中心 | Running beat diagnostic system for automatic verification assembly line of electric energy meter and working method thereof |
| CN113189935A (en) * | 2021-04-29 | 2021-07-30 | 浙江陀曼云计算有限公司 | Non-invasive production beat prediction method and system based on time sequence power data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
| EP0509817B1 (en) | System and method utilizing a real time expert system for tool life prediction and tool wear diagnosis | |
| AU2002246994B2 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| US20180264613A1 (en) | Abnormality detection apparatus and machine learning apparatus | |
| AU2002246994A1 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| CN109857079B (en) | Intelligent diagnosis method and device for abnormal working state of machining center spindle system | |
| CN108846581A (en) | A kind of machine tool reliability evaluation system and method | |
| CN111046582A (en) | Nuclear power station diesel generating set coil temperature early warning method and system | |
| CN112692646B (en) | Intelligent assessment method and device for tool wear state | |
| CN112859741A (en) | Method and system for evaluating operation reliability of sequential action units of machine tool | |
| CN112393906B (en) | Method for diagnosing, classifying and evaluating health of weak signal fault of bogie bearing of metro vehicle | |
| CN111098463A (en) | Injection molding machine fault diagnosis system and diagnosis method | |
| JP2019098515A (en) | Blade tool state inspection system and method | |
| CN110469496B (en) | Intelligent early warning method and system for water pump | |
| CN113305644A (en) | Cutter state monitoring and early warning method and system based on part measurement data | |
| CN113341879A (en) | Data acquisition and monitoring method and system for numerical control machine tool | |
| CN114326593B (en) | Cutter life prediction system and method | |
| CN116871978A (en) | Drilling tool state monitoring method based on multi-sensor fusion | |
| JP7166839B2 (en) | Health monitoring system | |
| CN109240253B (en) | Online equipment diagnosis and preventive maintenance method and system | |
| KR20220152709A (en) | Prediction method of machine health stability in smart factory system, and recording medium thereof | |
| CN115034094B (en) | Prediction method and system for operation state of metal processing machine tool | |
| CN112621381A (en) | Intelligent health state evaluation method and device for machine tool feeding system | |
| KR102656853B1 (en) | System for artificial intelligence-based cutting tool wear management and method thereof | |
| CN116551467B (en) | Cutter abrasion state identification method based on internet of things monitoring data |
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 |