CN112858901A - System and method for monitoring operation state and service life prediction of cutter in real time - Google Patents
System and method for monitoring operation state and service life prediction of cutter in real time Download PDFInfo
- Publication number
- CN112858901A CN112858901A CN202110122854.7A CN202110122854A CN112858901A CN 112858901 A CN112858901 A CN 112858901A CN 202110122854 A CN202110122854 A CN 202110122854A CN 112858901 A CN112858901 A CN 112858901A
- Authority
- CN
- China
- Prior art keywords
- data
- cutter
- time
- real
- prediction
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000007405 data analysis Methods 0.000 claims abstract description 16
- 238000012423 maintenance Methods 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000000348 solid-phase epitaxy Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 4
- 125000004432 carbon atom Chemical group C* 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 2
- 238000013480 data collection Methods 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 abstract description 7
- 239000002699 waste material Substances 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a system and a method for monitoring the running state and the service life prediction of a cutter in real time, wherein a CNC is provided with a plurality of sensor signal acquisition modules, and data transmission is carried out with an edge gateway in a local area network in real time, so that the data transmission is faster and more stable than that of a cloud end, two modules of data acquisition and service life prediction are deployed at the gateway, so that data analysis is carried out faster than that of the cloud end, the transmission time of data between the cloud end and equipment is reduced, and the received working data and the data analysis result are displayed on an operation and maintenance webpage billboard in real time at the cloud end, so that the detection and maintenance are more convenient, and the requirement of manual monitoring is reduced. Through training and predicting the service life of the cutter based on the deep neural network, the accuracy and the timeliness of the service life of the cutter are greatly increased, the utilization rate of the cutter is improved, and the waste of insufficient utilization of the cutter and the waste of a large number of processing inferior-quality products caused by untimely cutter replacement are avoided.
Description
Technical Field
The invention relates to the technical field of life prediction of numerical control machine tools, in particular to a system and a method for monitoring the running state and life prediction of a tool based on cooperative work of edge computing and cloud computing.
Background
In the industrial field, the problem that the state of a cutter can be accurately predicted is always solved in the machining field, and if the state of the cutter can not be accurately predicted, the defective rate of machined products of an enterprise is often influenced, a large amount of resources are wasted, and the consideration of purchasing the cutter by the enterprise is influenced. The factors influencing the tool life are very many, and the residual life of the tool cannot be judged from one aspect alone. At present, most enterprises adopt a timing or counting method to predict the service life of the cutter, so that the real state of each cutter cannot be predicted accurately, and the cutter is reported in advance and a large number of inferior-quality products with poor precision are processed.
In the field of cloud computing, a cloud user can obtain high service quality with low cost, but cloud computing often processes a large amount of data in one device, so that the service effect is poor, the large amount of data are sent to the cloud, data delay is caused, the real-time performance is poor, and the industrial field often requires good real-time performance.
Disclosure of Invention
The invention aims to provide a method and a system for monitoring the running state and the service life of a cutter in real time, and solves the problems that the cutter and material are wasted due to low service life prediction accuracy of the cutter in the industrial field, and cloud data is poor in real-time performance and cannot be used in the industrial field.
In order to achieve the purpose, the system for monitoring the operation state and the service life prediction of the cutter in real time comprises a sensor signal acquisition module, an edge gateway, a cloud service platform and an operation and maintenance billboard, wherein the edge gateway is connected with the sensor signal acquisition module; the sensor signal acquisition module is installed on the equipment and acquires operation data of the equipment and various data signals generated by the operation of a cutter on the equipment in real time, the sensor signal acquisition module uploads the acquired data to the edge gateway in real time, the edge gateway is internally provided with the data acquisition processing module and the cutter life prediction module, the data acquisition processing module carries out batch processing on the acquired data to obtain standardized data, the cutter life prediction module carries out real-time prediction on the service life of the cutter through the standardized data, the edge gateway also uploads the operation data and the prediction data acquired in real time to the cloud service platform, and the cloud service platform is compiled into a data analysis API through data screening and aggregation and is used for real-time data analysis and display of the operation and maintenance signboard.
In order to achieve the above object, the method for real-time monitoring the operation state and life prediction of a tool provided by the present invention adopts the edge cloud cooperation-based system for real-time monitoring the operation state and life prediction of a tool to perform real-time monitoring and prediction, and comprises the following steps:
s1: the sensor signal acquisition module acquires various signals and working data of the equipment tool in real time, including operation data of the equipment and various data signals generated by the tool work, and uploads the acquired data to the edge gateway in real time;
s2: the edge gateway sends the data acquired by the sensor signal acquisition module to a data acquisition processing module for batch processing to obtain standardized data;
s3: the edge gateway imports the standardized data into a tool life prediction module, performs real-time prediction on the tool life, and uploads the operation data and prediction data acquired in real time to a cloud database;
s4: the cloud displays the data sent by the edge end in the attribute of the physical model of the equipment and stores the data in a cloud database, and the cloud database is compiled into a data analysis API through data screening and aggregation and is used for real-time data analysis and display of the operation and maintenance signboard;
s5: and monitoring the operation state of each cutter and the result of the service life prediction of the cutter in real time through the real-time monitoring operation and maintenance board, and overhauling and updating the cutters according to the display result.
In the above scheme, the device in step S1 is a CNC device, a sensor signal acquisition module is externally connected to a spindle of the CNC device, and is configured to acquire signals of voltage, current, torque, cutting force, temperature, and power of the spindle in real time, and to upload real-time data acquired by the sensor signal acquisition module to the edge gateway.
In the above scheme, in step S2, a large amount of signal data acquired by the edge gateway is imported into the data acquisition and processing module to control the sampling rate of the signal, and the sampled data is subjected to mean value and variance processing, so as to obtain standardized data for training the deep neural network for tool prediction, and the trained life prediction model is integrated into the tool life prediction module; the data acquisition processing module and the cutter life prediction module are controlled to be started and stopped by the cloud service platform.
In the scheme, the real-time prediction of the service life of the cutter is to analyze data of a period of time, and the service life condition of the cutter obtained in the future period of time is compared with a set threshold value of the service life of the cutter, so that the service life of the cutter is predicted.
In the foregoing solution, step S2 specifically includes the following steps:
s2.1: introducing various preprocessed signal data into EFMSAE to obtain a tool life prediction characteristic and an SPE trend curve;
s2.2: predicting and estimating a characteristic vector and a trend curve of the CNN model, predicting the time series trend of multi-characteristic fusion by using the CNN, and analyzing the abnormal degree of each part.
In the above scheme, the EFMSAE specifically comprises:
a multi-feature sequence representation of unlabeled data is extracted using multiple SAEs, where SAEs are hierarchical deep neural network structures consisting of multiple layers of AEs (auto-encoders), and a sparsity limiting mechanism in SAEs acts on the hidden layer to control the number of "active" neurons. Taking a sigmoid function as an activation function of the network, wherein the range of the sigmoid function is (0, 1), and the sigmoid function is expressed as follows:
in the above formula, the first and second carbon atoms are,
and
representing the ith input layer and the ith output layer, respectively, in an automatic coding network an activation function σ is applied to the input layers and a coding operation is performed thereon to obtain a concealment vector h for the concealment layers. The concealment vector is decoded r in the output layer to obtain an output vector a, expressed as:
the input to the ith hidden layer is X,
e r (m), where N is the total number of datasets and m is the dimension of each dataset, where
A code representing a hidden layer;
representing the decoding weights of the output layer; b1 and b2 represent the encoded and decoded offset values, respectively.
Representing the output of the jth neuron in the hidden layer,
an input representing an ith sample;
further, a plurality of SAEs are fused together by using the deviation value to obtain a Square Prediction Error (SPE) value and an SPE trend curve, and a threshold line is estimated according to the conventional data batch on the basis of the conventional data batch processing (step (c)) (
) And calculating the SPE value according to the test data, wherein the formula is as follows:
where k denotes the sensor number, the residual matrix R can be denoted by X and a and is expressed as: x = A + R and X = A + R,
(ii) a To estimate the threshold over time, SPE α needs to be computed in the SPE, whose distribution can be defined as:
wherein, α represents the confidence of chi-square distribution variable, and is generally 0.05; h represents the average of SPEs in the dataset; v represents the variance value of the SPEs in the dataset;
further, combining the SPE value of the multi-channel sensor to obtain a trend curve of the system;
further, comparing
And
judging the service life of the cutter according to the formula:
furthermore, a CNN model is adopted to predict and estimate the characteristic vector and the trend curve of the input vector subjected to the convolutional layer, the pooling layer and the full-link layer to obtain an output CNN model, the time series trend of multi-feature fusion is predicted, and the abnormal degree of each part is analyzed.
The invention has the beneficial effects that: the sensor signal acquisition module carries out data transmission with the edge gateway in real time in the local area network, make data transmission compare the high in the clouds faster more stable to dispose two modules of data acquisition processing and cutter life prediction in the edge gateway, compare the high in the clouds faster and carry out data analysis, reduce the transmission time of data between high in the clouds and equipment, and show in the fortune dimension web billboard through the working data and the data analysis result of receipt in the high in the clouds in real time, make detection and maintenance more convenient, reduce the demand of manual monitoring. According to the invention, through training and predicting the service life of the cutter based on the deep neural network, compared with the traditional method of predicting the service life of the cutter only by the processing time or times of the cutter, the accuracy and timeliness of the service life of the cutter are greatly increased, the utilization rate of the cutter is greatly improved, and the waste of insufficient utilization of the cutter and the waste of a large number of processing inferior-quality products caused by untimely cutter replacement are avoided.
Description of the drawings:
FIG. 1 is a system framework diagram of the present invention;
fig. 2 is a schematic flow chart of a real-time data acquisition and processing and tool life prediction method based on edge cloud cooperation provided by the invention.
The specific implementation mode is as follows:
the conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Referring to fig. 1, a schematic diagram of a system framework of the present invention is shown, and the present invention relates to a system for monitoring a tool operation state and predicting a tool life in real time based on edge cloud cooperation, the system includes a sensor signal acquisition module 100, an edge gateway 200, a cloud service platform 300, and an operation and maintenance billboard 400; the sensor signal acquisition module 100 is installed on the equipment and acquires operation data of the equipment and various data signals generated by operation of a cutter on the equipment in real time, the sensor signal acquisition module uploads the acquired data to the edge gateway in real time, the edge gateway is provided with a data acquisition processing module 201 and a cutter service life prediction module 202, the data acquisition processing module carries out batch processing on the acquired data to obtain standardized data, the cutter service life prediction module carries out real-time prediction on the service life of the cutter through the standardized data, the edge gateway uploads the operation data and the predicted data acquired in real time to the cloud service platform 300, and the cloud service platform is compiled into a data analysis API through data screening and aggregation and used for real-time data analysis and display of the operation and maintenance board 400.
Referring to fig. 2, the invention further provides a method for monitoring the operation state and the life prediction of the tool in real time based on edge cloud cooperation, which adopts the system to operate and comprises the following steps:
s1: the sensor signal acquisition module acquires various signals and working data of the equipment tool in real time, including operation data of the equipment and various data signals generated by the tool work, and uploads the acquired data to the edge gateway in real time;
s2: the edge gateway sends the data acquired by the sensor signal acquisition module to a data acquisition processing module for batch processing to obtain standardized data;
s3: the edge gateway imports the standardized data into a tool life prediction module, performs real-time prediction on the tool life, and uploads the operation data and prediction data acquired in real time to a cloud database;
s4: the cloud displays the data sent by the edge end in the attribute of the physical model of the equipment and stores the data in a cloud database, and the cloud database is compiled into a data analysis API through data screening and aggregation and is used for real-time data analysis and display of the operation and maintenance signboard;
s5: and monitoring the operation state of each cutter and the result of the service life prediction of the cutter in real time through the real-time monitoring operation and maintenance board, and overhauling and updating the cutters according to the display result.
The device in step S1 is a CNC device, a sensor signal acquisition module is externally connected to a spindle of the CNC device, and the sensor signal acquisition module acquires signals of voltage, current, torque, cutting force, temperature, and power of the spindle in real time, and sends real-time data acquired by the sensor signal acquisition module to the edge gateway. Step S2, a large amount of signal data acquired by the edge gateway are led into a data acquisition and processing module to control the sampling rate of signals, the sampled data are subjected to mean value and variance processing to obtain standardized data used for training a deep neural network for cutter prediction, and a trained life prediction model is integrated into a cutter life prediction module; the data acquisition processing module and the cutter life prediction module are controlled to be started and stopped by the cloud service platform. The real-time prediction of the service life of the cutter is to analyze data of a period of time, and the service life condition of the cutter obtained in the future period of time is compared with a set threshold value of the service life of the cutter, so that the service life of the cutter is predicted.
Step S2 specifically includes the following steps:
s2.1: introducing various preprocessed signal data into EFMSAE to obtain a tool life prediction characteristic and an SPE trend curve;
s2.2: predicting and estimating a characteristic vector and a trend curve of the CNN model, predicting the time series trend of multi-characteristic fusion by using the CNN, and analyzing the abnormal degree of each part.
In the above scheme, the EFMSAE specifically comprises:
a multi-feature sequence representation of unlabeled data is extracted using multiple SAEs, where SAEs are hierarchical deep neural network structures consisting of multiple layers of AEs (auto-encoders), and a sparsity limiting mechanism in SAEs acts on the hidden layer to control the number of "active" neurons. Taking a sigmoid function as an activation function of the network, wherein the range of the sigmoid function is (0, 1), and the sigmoid function is expressed as follows:
in the above formula, the first and second carbon atoms are,
and
representing the ith input layer and the ith output layer, respectively, in an automatic coding network an activation function σ is applied to the input layers and a coding operation is performed thereon to obtain a concealment vector h for the concealment layers. The concealment vector is decoded r in the output layer to obtain an output vector a, expressed as:
the input to the ith hidden layer is X,
e r (m), where N is the total number of datasets and m is the dimension of each dataset, where
A code representing a hidden layer;
representing output layersDecoding the weights; b1 and b2 represent the encoded and decoded offset values, respectively.
Representing the output of the jth neuron in the hidden layer,
an input representing an ith sample;
further, a plurality of SAEs are fused together by using the deviation value to obtain a Square Prediction Error (SPE) value and an SPE trend curve, and a threshold line is estimated according to the conventional data batch on the basis of the conventional data batch processing (step (c)) (
) And calculating the SPE value according to the test data, wherein the formula is as follows:
where k denotes the sensor number, the residual matrix R can be denoted by X and a and is expressed as: x = A + R and X = A + R,
(ii) a To estimate the threshold over time, SPE α needs to be computed in the SPE, whose distribution can be defined as:
wherein, α represents the confidence of chi-square distribution variable, and is generally 0.05; h represents the average of SPEs in the dataset; v represents the variance value of the SPEs in the dataset;
further, combining the SPE value of the multi-channel sensor to obtain a trend curve of the system;
further, comparing
And
judging the service life of the cutter according to the formula:
furthermore, a CNN model is adopted to predict and estimate the characteristic vector and the trend curve of the input vector subjected to the convolutional layer, the pooling layer and the full-link layer to obtain an output CNN model, the time series trend of multi-feature fusion is predicted, and the abnormal degree of each part is analyzed.
The invention is used for carrying out data acquisition on the CNC machine tool cutter to obtain a large amount of relevant operation place working data and sensor signal data; by processing and analyzing the data, the running state of the cutter can be reflected, whether the cutter breaks down within a short period of time is further predicted, and early warning information is sent out in advance; the residual service life of the equipment can be estimated from a long-term angle, and monitoring personnel can timely scrap, replace and the like the CNC machine tool with alarm. Based on edge calculation, the CNC machine tool working data is processed and analyzed by utilizing a deep neural network, and the residual life of the tool is predicted and estimated, so that the predictive maintenance of the CNC machine tool is realized.
The sensor signal acquisition module acquires various signals and working data of the equipment tool in real time, including operation data of the equipment and various data signals generated by the tool work, and uploads the acquired data to the data acquisition processing module in real time. The data acquisition processing module can control the sampling rate of the sensor signals, and batch process a large amount of data, so that the utilization rate of the data is improved. The tool life prediction module can analyze input signal data in real time, predict the tool life in real time and output the residual service life of the tool. The edge gateway can be connected with the equipment end and the cloud service, has good real-time property with the data transmission of the sensor signal acquisition module, completes the analysis and processing of data at the edge gateway, reduces the burden of the cloud, and improves the overall efficiency.
The invention can predict the short-term state of the cutter in the future in advance under the condition of keeping a certain accuracy, maintain and update the cutter in advance, reduce the condition that the cutter is scrapped in advance or inferior-quality products with insufficient precision are processed, and improve the condition that the utilization rate of the cutter in the industrial field is insufficient to a great extent.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.
Claims (7)
1. The system for monitoring the running state and the service life prediction of the cutter in real time is characterized by comprising a sensor signal acquisition module, an edge gateway, a cloud service platform and an operation and maintenance billboard; the sensor signal acquisition module is installed on the equipment and acquires operation data of the equipment and various data signals generated by the operation of a cutter on the equipment in real time, the sensor signal acquisition module uploads the acquired data to the edge gateway in real time, the edge gateway is internally provided with the data acquisition processing module and the cutter life prediction module, the data acquisition processing module carries out batch processing on the acquired data to obtain standardized data, the cutter life prediction module carries out real-time prediction on the service life of the cutter through the standardized data, the edge gateway also uploads the operation data and the prediction data acquired in real time to the cloud service platform, and the cloud service platform is compiled into a data analysis API through data screening and aggregation and is used for real-time data analysis and display of the operation and maintenance signboard.
2. The method for monitoring the running state and the service life prediction of the cutter in real time is characterized in that the method adopts the system for monitoring the running state and the service life prediction of the cutter in real time based on edge cloud cooperation to carry out real-time monitoring and prediction, and comprises the following steps:
s1: the sensor signal acquisition module acquires various signals and working data of the equipment tool in real time, including operation data of the equipment and various data signals generated by the tool work, and uploads the acquired data to the edge gateway in real time;
s2: the edge gateway sends the data acquired by the sensor signal acquisition module to a data acquisition processing module for batch processing to obtain standardized data;
s3: the edge gateway imports the standardized data into a tool life prediction module, performs real-time prediction on the tool life, and uploads the operation data and prediction data acquired in real time to a cloud database;
s4: the cloud displays the data sent by the edge end in the attribute of the physical model of the equipment and stores the data in a cloud database, and the cloud database is compiled into a data analysis API through data screening and aggregation and is used for real-time data analysis and display of the operation and maintenance signboard;
s5: and monitoring the operation state of each cutter and the result of the service life prediction of the cutter in real time through the real-time monitoring operation and maintenance board, and overhauling and updating the cutters according to the display result.
3. The method of claim 2, wherein the device in step S1 is a CNC device, and the CNC device is externally connected with a sensor signal acquisition module on a main shaft, and the voltage, current, torque, cutting force, temperature and power signals of the main shaft are acquired in real time, and the real-time data acquired by the sensor signal acquisition module is uploaded to the edge gateway.
4. The method for real-time monitoring the tool operation state and the tool life prediction as claimed in claim 2, wherein step S2 is to utilize a large amount of signal data collected by the edge gateway to be imported into the data collection and processing module, control the sampling rate of the signal, and process the mean value and the variance of the sampled data, so as to obtain standardized data for training the deep neural network for tool prediction, and integrate the trained life prediction model into the tool life prediction module; the data acquisition processing module and the cutter life prediction module are controlled to be started and stopped by the cloud service platform.
5. The method for real-time monitoring of tool operation and life prediction as claimed in claim 2, wherein the real-time tool life prediction is achieved by analyzing data over a period of time, and comparing the life condition of the tool over a future period of time with a set tool life threshold.
6. The method for real-time monitoring of tool operation status and life prediction as claimed in claim 4, wherein step S2 comprises the following steps:
s2.1: introducing various preprocessed signal data into EFMSAE to obtain a tool life prediction characteristic and an SPE trend curve;
s2.2: predicting and estimating a characteristic vector and a trend curve of the CNN model, predicting the time series trend of multi-characteristic fusion by using the CNN, and analyzing the abnormal degree of each part.
7. The method as claimed in claim 6, wherein the EFMSAE comprises the following steps:
s2.1.1: extracting a multi-feature sequence representation of unlabeled data using a plurality of SAEs, wherein an SAE is a hierarchical deep neural network structure consisting of multiple layers of AEs (automatic encoders), and a sparsity limiting mechanism in an SAE acts on a hidden layer to control the number of "active" neurons; taking a sigmoid function as an activation function of the network, wherein the range of the sigmoid function is (0, 1), and the sigmoid function is expressed as follows:
in the above formula, the first and second carbon atoms are,
and
are respectively provided withRepresenting the ith input layer and the ith output layer, in an automatic coding network, an activation function sigma acts on the input layer and carries out coding operation on the input layer to obtain a hidden vector h of a hidden layer; the concealment vector is decoded r in the output layer to obtain an output vector a, expressed as:
the input to the ith hidden layer is X,
e r (m), where N is the total number of datasets and m is the dimension of each dataset, where
A code representing a hidden layer;
representing the decoding weights of the output layer; b1 and b2 represent the encoded and decoded offset values, respectively; representing the output of the jth neuron in the hidden layer,
an input representing an ith sample;
s2.1.2: fusing a plurality of SAEs together by using the deviation value to obtain a Square Prediction Error (SPE) value and an SPE trend curve, and estimating a threshold line (a) according to the conventional data batch on the basis of the conventional data batch processing
) And calculating the SPE value according to the test data, wherein the formula is as follows:
wherein, k represents the sensor number and the residual matrixR can be represented by X and A and is represented by: x = A + R and X = A + R,
(ii) a In order to estimate the threshold value at any time,
requiring computation in the SPE, the SPE distribution can be defined as:
wherein, α represents the confidence of chi-square distribution variable, and is generally 0.05; h represents the average of SPEs in the dataset; v represents the variance value of the SPEs in the dataset;
s2.1.3: combining the SPE value of the multi-channel sensor to obtain a trend curve of the system;
s2.1.4: comparison
And
the service life of the cutter is judged according to the image curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110122854.7A CN112858901A (en) | 2021-01-29 | 2021-01-29 | System and method for monitoring operation state and service life prediction of cutter in real time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110122854.7A CN112858901A (en) | 2021-01-29 | 2021-01-29 | System and method for monitoring operation state and service life prediction of cutter in real time |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112858901A true CN112858901A (en) | 2021-05-28 |
Family
ID=75987852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110122854.7A Pending CN112858901A (en) | 2021-01-29 | 2021-01-29 | System and method for monitoring operation state and service life prediction of cutter in real time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112858901A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113867263A (en) * | 2021-08-27 | 2021-12-31 | 大唐互联科技(武汉)有限公司 | Intelligent cutter management system based on cloud edge cooperation and machine learning |
| CN113927370A (en) * | 2021-09-22 | 2022-01-14 | 南京理工大学 | Multi-source signal-based real-time cloud monitoring system and method for residual life of tool for production line |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109499908A (en) * | 2018-11-10 | 2019-03-22 | 东莞理工学院 | A kind of vision detection system for machine components |
| CN110472800A (en) * | 2019-08-23 | 2019-11-19 | 山东浪潮通软信息科技有限公司 | A kind of machine tool method for predicting residual useful life based on LSTM+CNN |
| CN111475921A (en) * | 2020-03-13 | 2020-07-31 | 重庆邮电大学 | Tool residual life prediction method based on edge calculation and L STM network |
| CN111964718A (en) * | 2020-08-11 | 2020-11-20 | 重庆大学 | Multi-source information fusion environment monitoring device and system thereof |
| CN112187932A (en) * | 2020-09-29 | 2021-01-05 | 长江勘测规划设计研究有限责任公司 | Intelligent monitoring and early warning method for small and medium reservoir dam based on edge calculation |
| US20220146462A1 (en) * | 2019-07-05 | 2022-05-12 | Chongqing University Of Posts And Telecommunications | Method for predicting remaining life of numerical control machine tool |
-
2021
- 2021-01-29 CN CN202110122854.7A patent/CN112858901A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109499908A (en) * | 2018-11-10 | 2019-03-22 | 东莞理工学院 | A kind of vision detection system for machine components |
| US20220146462A1 (en) * | 2019-07-05 | 2022-05-12 | Chongqing University Of Posts And Telecommunications | Method for predicting remaining life of numerical control machine tool |
| CN110472800A (en) * | 2019-08-23 | 2019-11-19 | 山东浪潮通软信息科技有限公司 | A kind of machine tool method for predicting residual useful life based on LSTM+CNN |
| CN111475921A (en) * | 2020-03-13 | 2020-07-31 | 重庆邮电大学 | Tool residual life prediction method based on edge calculation and L STM network |
| CN111964718A (en) * | 2020-08-11 | 2020-11-20 | 重庆大学 | Multi-source information fusion environment monitoring device and system thereof |
| CN112187932A (en) * | 2020-09-29 | 2021-01-05 | 长江勘测规划设计研究有限责任公司 | Intelligent monitoring and early warning method for small and medium reservoir dam based on edge calculation |
Non-Patent Citations (1)
| Title |
|---|
| JIANWEN GUO ETC.: "Mechanical fault time series prediction by using EFMSAE-LSTM neural", MEASUREMENT, pages 1 - 12 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113867263A (en) * | 2021-08-27 | 2021-12-31 | 大唐互联科技(武汉)有限公司 | Intelligent cutter management system based on cloud edge cooperation and machine learning |
| CN113927370A (en) * | 2021-09-22 | 2022-01-14 | 南京理工大学 | Multi-source signal-based real-time cloud monitoring system and method for residual life of tool for production line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110221558B (en) | Electro-hydraulic servo valve online fault diagnosis gateway based on edge computing technology | |
| CN110347116B (en) | Machine tool state monitoring system and monitoring method based on operation data flow | |
| US20230213895A1 (en) | Method for Predicting Benchmark Value of Unit Equipment Based on XGBoost Algorithm and System thereof | |
| CN117234785B (en) | Centralized control platform error analysis system based on artificial intelligence self-query | |
| CN112858901A (en) | System and method for monitoring operation state and service life prediction of cutter in real time | |
| CN111340110B (en) | Fault early warning method based on industrial process running state trend analysis | |
| CN114997313B (en) | Abnormality detection method for ocean on-line monitoring data | |
| CN111273607B (en) | Spark-based numerical control machine tool running state monitoring method | |
| CN117393076B (en) | Intelligent monitoring method and system for heat-resistant epoxy resin production process | |
| CN116991130A (en) | Intelligent automatic control system and method for petrochemical production | |
| CN117421994A (en) | Edge application health monitoring method and system | |
| CN113486571A (en) | Method for predicting residual service life of machining equipment | |
| CN114611764B (en) | Abnormal monitoring and early warning method for industrial water of enterprises in specific area | |
| CN117943892A (en) | Cutter monitoring data prediction optimization method based on time sequence data analysis | |
| CN117668493A (en) | Tobacco equipment fault prediction method and system | |
| CN113609672A (en) | Incremental model-based digital twin system coevolution method | |
| CN117829453A (en) | Intelligent equipment production and management integrated system | |
| CN116383645A (en) | Intelligent system health degree monitoring and evaluating method based on anomaly detection | |
| CN110659681B (en) | Time sequence data prediction system and method based on pattern recognition | |
| CN111813631A (en) | Resource situation visualization and analysis method for cloud data center | |
| CN114528278B (en) | Classification method of intelligent unit body mixed decision model based on information physical fusion | |
| Miao et al. | Research on Operation Status Prediction of Production Equipment Based on Digital Twins and Multidimensional Time Series | |
| CN117892212B (en) | Distributed heterogeneous energy station situation awareness monitoring method | |
| CN117804811B (en) | Health diagnosis system and method for deep neural network port machinery equipment of attention mechanism | |
| CN118311914B (en) | Production line data acquisition control method and system for intelligent workshop |
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 |