CN117532403A - CNC processing quality real-time detection method based on multi-sensor fusion - Google Patents
CNC processing quality real-time detection method based on multi-sensor fusion Download PDFInfo
- Publication number
- CN117532403A CN117532403A CN202311771596.0A CN202311771596A CN117532403A CN 117532403 A CN117532403 A CN 117532403A CN 202311771596 A CN202311771596 A CN 202311771596A CN 117532403 A CN117532403 A CN 117532403A
- Authority
- CN
- China
- Prior art keywords
- sensor
- time
- real
- data
- cnc
- 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 51
- 238000012545 processing Methods 0.000 title claims abstract description 46
- 230000004927 fusion Effects 0.000 title claims abstract description 41
- 238000011897 real-time detection Methods 0.000 title claims abstract description 17
- 238000012544 monitoring process Methods 0.000 claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 15
- 238000005520 cutting process Methods 0.000 claims abstract description 10
- 238000005457 optimization Methods 0.000 claims description 12
- 239000000463 material Substances 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000013500 data storage Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 238000010845 search algorithm Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 2
- 238000003754 machining Methods 0.000 abstract description 15
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000010801 machine learning Methods 0.000 abstract description 3
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000003672 processing method Methods 0.000 abstract 1
- 238000004519 manufacturing process Methods 0.000 description 28
- 230000006872 improvement Effects 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Abstract
A real-time detection method based on multi-sensor fusion CNC processing quality utilizes a Computer Numerical Control (CNC) system and a multi-sensor fusion algorithm to be combined, so that the quality of a workpiece is monitored in real time in the processing process, and the product is ensured to meet a preset standard. The system comprises a plurality of sensors such as a visual sensor, a force sensor, a temperature sensor and the like, and can acquire various parameters and characteristics in the processing process in real time. In the method, a visual sensor is used for capturing the appearance characteristics of a workpiece, a force sensor is used for monitoring cutting force and pressure change in the machining process, and a temperature sensor is used for detecting temperature change of a machining area. The data of the sensors are comprehensively analyzed through a multi-sensor fusion algorithm. The algorithm is based on a multi-sensor data fusion technology, and utilizes advanced signal processing and machine learning methods to realize real-time monitoring and analysis of various quality indexes in the processing process.
Description
Technical Field
The invention relates to the technical field of real-time detection of machining quality, in particular to a real-time detection method of machining quality based on multi-sensor fusion CNC.
Background
In modern manufacturing, electric machines are one of the key devices that are widely used in various fields. However, the quality of the motor directly affects the performance and stability of the device, and therefore, ensuring the quality of the motor process is a critical task in the manufacturing industry. Conventional CNC machining quality inspection typically relies on a single sensor, such as a vision sensor for appearance inspection, a force sensor for monitoring cutting forces, and the like. However, the quality of the motor is affected by a variety of factors, and it is difficult for the data of a single sensor to fully and accurately reflect the actual state of the machining process. To address this challenge, multi-sensor fusion techniques have evolved.
The multi-sensor fusion technique aims to acquire more comprehensive and accurate information by integrating data of a plurality of sensors. The CNC processing quality real-time detection method based on multi-sensor fusion fully utilizes the advantages of the multi-sensor. In the processing process, the method combines a plurality of sensors such as a visual sensor, a force sensor, a temperature sensor and the like, and integrates and analyzes the data acquired by each sensor in real time through an intelligent multi-sensor fusion algorithm. The algorithm is based on deep learning and machine learning technologies, can efficiently process sensor data, and realizes multi-azimuth monitoring of workpieces, including appearance characteristics, cutting force, temperature and the like. The method can meet the production requirement in real time and has high accuracy and reliability. When the system detects a potential quality problem, it can quickly react to an alarm and take appropriate action, such as adjusting machining parameters, changing tool paths, etc., to ensure that the product quality meets the criteria. The method has strong self-adaptability, can adapt to workpieces of different materials, shapes and processing technologies, and provides a highly intelligent and extremely high-accuracy real-time processing quality detection solution for the field of motor manufacturing.
In conclusion, the CNC processing quality real-time detection method based on multi-sensor fusion has extremely important application prospect in the field of motor manufacturing, not only improves production efficiency, but also ensures product quality, and brings brand new opportunities for development of modern manufacturing industry.
Disclosure of Invention
In order to solve the technical problems, the invention provides a real-time detection method for processing quality based on multi-sensor fusion CNC, which can monitor and analyze the quality of a workpiece in real time and automatically adjust and optimize processing parameters.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a CNC processing quality real-time detection method based on multi-sensor fusion comprises the following specific steps:
1) Collecting and preprocessing sensor data;
in the step, a proper sensor is selected to collect the required data, after the data collection is completed, the collected data is stored, and a database mode is adopted to ensure that the data storage mode can meet the data quantity and the access requirement;
2) Processing a multi-sensor fusion algorithm;
after the data acquisition and pretreatment are completed, the data are further processed by adopting a multi-sensor fusion algorithm in the step so as to monitor the processing quality of CNC in real time, and the step is combined with an improved Z-Score formula for extended Kalman filtering; in this process, Z-Score is used to evaluate the deviation between a measured value and its expected value, while EKF is used to estimate future states from past observations and models;
3) Monitoring and analyzing in real time;
the real-time monitoring and analysis are divided into two steps of monitoring alarm and data analysis, and after the analysis is completed, the model must be automatically regulated and feedback controlled, and at the same time the corresponding conditions are recorded and reported, and the steps are as follows;
wherein step 3) real-time monitoring and analysis comprises the following sub-processes:
monitoring and alarming in real time;
data storage and analysis;
automatic adjustment and feedback control;
recording and reporting;
4) Adjusting and optimizing processing parameters;
in the step, the automatic adjustment and optimization of CNC processing parameters are involved, so that the consistency and quality of products are ensured, an optimization algorithm is introduced in the adjustment of the processing parameters for further improving the quality and efficiency of the products, and a CNC parallel search algorithm is adopted, so that the optimal combination can be searched in a parameter space.
As a further improvement of the present invention, the Z-Score algorithm of the modified version in step 2) is formulated as:
wherein v represents the measurement of the sensor; e (sensor) represents the expected value of the sensors, which each sensor may have, representing the measured value expected under normal conditions; sigma (sensor) represents the standard deviation of the sensors, and the standard deviation of each sensor reflects the distribution of the measured values; t then represents the sensor weight, thereby determining its contribution to anomaly detection.
As a further improvement of the present invention, the optimized EKF state prediction formula in the step 2) is expressed as:
wherein x is k|k-1 Is the result of a state estimate update. X is x k|k-1 Is an estimated state x using the previous time k-1 at time k k|k-1 And control input u k Predicted status; alpha is a correction factor to balance losses or errors between the Z-score and the EKF; f is a state transfer function describing how the state of the whole processing quality real-time monitoring system evolves with time; u (u) k The control input at time k is information from a sensor or an external input.
As a further improvement of the present invention, the formula of the CNC parallel search algorithm in the step 4) is as follows:
wherein N represents a specific number of workpieces; m is the number of CNC machine tools; v max Expressed as the maximum cutting speed of each material; v tool_max Expressed as the maximum cutting speed per tool; x is x ij Tool for indicating use of workpiece iThe decision variable for j, i.e. 1, indicates use and 0 indicates no use.
The beneficial effects are that:
conventional CNC machining quality inspection methods typically require off-line inspection after machining is complete, while real-time inspection methods based on multi-sensor fusion allow for real-time monitoring of the quality of the workpiece during machining. Through instant feedback, production personnel can rapidly identify potential problems and make adjustments, so that production efficiency is improved, waiting time in the production process is reduced, and manufacturing cycle is accelerated.
Through real-time monitoring and automatic adjustment, the method can reduce the generation of waste products and defective products to the greatest extent. In addition, the method optimizes the selection of processing parameters, improves the utilization rate of materials, and reduces the waste of materials, thereby reducing the production cost and increasing the production benefit.
The CNC processing quality real-time detection method based on multi-sensor fusion combines a deep learning technology, and achieves intelligent processing and analysis of a large amount of data. The intelligent level of the production process is improved, powerful support is provided for the development of an intelligent manufacturing system in the future, and the manufacturing industry is promoted to move towards the intelligent and automatic directions.
The method provided by the application has strong self-adaptability and can adapt to the workpiece requirements of different materials, shapes and processing technologies. This flexibility allows manufacturers to more easily adapt to changes in market demand, rapidly switch production lines, provide a variety of products, and enhance the competitiveness of the enterprise.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of the model training of the present invention;
FIG. 3 is a diagram of a method optimization architecture of the present invention.
Detailed Description
The invention is described in further detail below with reference to the attached drawings and detailed description:
FIG. 1 is a system flow chart of a real-time detection method for CNC machining quality based on multi-sensor fusion.
Step S1: and (5) collecting and preprocessing sensor data.
In this step, the appropriate sensor will be selected to collect the required data. The sensor is connected to a data acquisition device such as a microcontroller, a single board computer or a data acquisition card. The data acquisition device is set up to start recording sensor data, this step being accomplished by Python programming for data acquisition during a predetermined time interval or upon event triggering. The sensors are then installed in the appropriate locations to ensure accuracy of the data, which requires consideration of the location, orientation and environmental conditions of the sensors. After the data acquisition is completed, the acquired data is stored. The application adopts a database mode, and ensures that the data storage mode can meet the data quantity and the access requirement.
Data preprocessing is an important step to ensure the quality and usability of the acquired data. The following is the data preprocessing task related to this application:
denoising: noise due to sensor errors, environmental disturbances, or other factors is identified and removed.
And (3) calibrating: calibration is performed based on the sensor characteristics to ensure accuracy of the measurement.
Interpolation: filling in missing data that may be generated due to equipment failure or data loss.
And (3) filtering: filtering techniques are applied to smooth the data, removing high frequency noise.
Data format conversion: the data is converted to the required format for subsequent analysis and visualization.
Abnormal value detection: outliers are identified and processed to prevent them from affecting the analysis results.
It should be noted that outlier detection is a significant point in the preprocessing process, and it is eliminated to make the training result of the multi-sensor fusion algorithm more accurate. Before the multi-sensor fusion algorithm starts, it is necessary to propose an improved anomaly detection algorithm based on the data and algorithm conditions of the present application, the following being an improved version of the Z-Score algorithm:
wherein v represents the measurement of the sensor; e (sensor) represents the expected value of the sensors, which each sensor may have, representing the measured value expected under normal conditions; sigma (sensor) represents the standard deviation of the sensors, and the standard deviation of each sensor can reflect the distribution of the measured values; t then represents the sensor weight, thereby determining its contribution to anomaly detection. For some more important sensors, the weight value may be set higher.
Detailed information about data acquisition and pre-processing is recorded, including sensor specifications, calibration procedures, data processing algorithms and parameters. This helps ensure that the data is reusable and interpretable. After the preprocessing step is completed, preprocessed high-quality sensor data is obtained, which provides a reliable basis for subsequent data analysis and application.
Step S2: and (5) processing a multi-sensor fusion algorithm.
Fig. 2 is a model training flowchart of a real-time detection method for machining quality based on multi-sensor fusion CNC.
After the data acquisition and pretreatment are completed, the data are further processed by adopting a multi-sensor fusion algorithm in the step, so that the processing quality of CNC is monitored in real time. The multi-sensor information fusion technology is like the process of comprehensively processing information by the brain of a person, performs multi-level and multi-space information complementation and optimization combination processing on various sensors, and finally generates consistency interpretation on an observation environment. In the process, multisource data is fully utilized for reasonable allocation and use, and the final target of information fusion is based on separated observation information obtained by each sensor, so that more useful information is derived through multi-level and multi-aspect combination of the information. This not only takes advantage of the co-operation of multiple sensors, but also integrates the processing of data from other sources to enhance the intelligence of the overall sensor system. The theoretical method is generally divided into two main types, namely Kalman filtering and artificial neural networks, and the application adopts Extended Kalman Filtering (EKF) to fuse the information of multiple sensors.
The data fusion is to combine the data of different sensors by using a multi-sensor fusion algorithm so as to improve the accuracy and the robustness of estimation, and the factors such as uncertainty, weight distribution, time delay and the like among the sensors need to be considered. The extended Kalman filtering is combined with the improved Z-Score formula; in this process, Z-Score is used to evaluate the deviation between a measured value and its expected value, while EKF is used to estimate future states from past observations and models, the following is a specifically given optimized version of EKF state prediction formula:
wherein x is k|k-1 Is the result of a state estimate update. X is x k|k-1 Is an estimated state x using the previous time k-1 at time k k|k-1 And control input u k Predicted status; alpha is a correction factor to balance losses or errors between the Z-score and the EKF; f is a state transfer function describing how the state of the whole processing quality real-time monitoring system evolves with time; u (u) k Is the control input at time k, which is information from a sensor or an external input.
In the method, after the basic steps of the multi-sensor fusion algorithm are completed, the evaluation and verification and the real-time updating of the fusion algorithm are also needed. And evaluating the fused data by using proper performance indexes, wherein the indexes such as root mean square error, precision, recall rate and the like are adopted. Verification and testing is then required to ensure that the effect of the fusion algorithm is in line with expectations, i.e. the fusion algorithm is continually updated based on new sensor data and system status to achieve real-time multi-sensor fusion.
Step S3: and (5) monitoring and analyzing in real time.
The real-time monitoring and analysis are divided into two steps of monitoring alarm and data analysis, and after the analysis is completed, the model must be automatically regulated and feedback controlled, and at the same time the correspondent condition can be recorded and reported, and its steps are as follows.
Real-time monitoring and alarming:
once the workpiece state model is established, the system can monitor the processing process of the workpiece in real time. The system will compare with the workpiece state model to check if there is an anomaly or an abnormal condition. If the system detects any anomalies, it will trigger an alarm, informing the operator or automatically stop the production line to prevent quality problems.
Data storage and analysis:
all the acquired data will typically be stored for use in subsequent analysis. These data can be used for retrospective and analysis to find potential production problems or to improve the production process.
Automatic adjustment and feedback control:
based on the results of the real-time monitoring, the system can automatically adjust the production process to correct the problem. It includes adjusting parameters, reducing workpiece speed, modifying tool bits or material supply to ensure that the quality of the workpiece meets regulatory standards.
Recording and reporting:
the system will typically record all real-time monitored and analyzed data for later analysis and reporting. These records can be used for quality control and improvement of the production flow, not only for quality traceability, but also for formulating finer processing strategies and production plans to increase production efficiency and quality levels.
In general, the steps of real-time monitoring and analysis ensure the quality control and the improvement of production efficiency in the production process, and the system can discover and solve the quality problem in time through a multi-sensor fusion algorithm, so that the defective rate is reduced, the product quality is improved, the production cost is reduced, and the production process is more efficient and economical.
Step S4: and (5) adjusting and optimizing processing parameters.
Fig. 3 shows an algorithm optimization architecture diagram based on a multi-sensor fusion CNC processing quality real-time detection method.
In this application, this step involves automatically adjusting and optimizing CNC machining parameters to ensure product consistency and quality. The following is a specific tuning and optimization procedure and selection of the corresponding optimization algorithm.
Establishing a feedback loop: the real-time monitoring data is fed back to the control part of the system for parameter adjustment and optimization. This may be achieved by machine learning and control algorithms.
Parameter adjustment: based on the monitoring results, the system can automatically adjust parameters of the CNC machining equipment, such as cutter speed, cutting depth, feeding speed and the like, in response to changes in workpiece state, thereby ensuring machining process stability and consistency.
Selection of an optimization algorithm in the parameter adjustment process: in order to further improve the quality and efficiency of the product, an optimization algorithm is introduced in the adjustment of the processing parameters. The application adopts CNC parallel search algorithm, which can search the best combination in the parameter space. The following is a specific formula of CNC parallel search algorithm in parameter adjustment process:
wherein N represents a specific number of workpieces; m is the number of CNC machine tools; v max Expressed as the maximum cutting speed of each material; v tool_max Expressed as the maximum cutting speed per tool; x is x ij The decision variable indicating the use of tool j by workpiece i, i.e., 1 indicates use and 0 indicates no use.
The above description is only of the preferred embodiment of the present invention, and is not intended to limit the present invention in any other way, but is intended to cover any modifications or equivalent variations according to the technical spirit of the present invention, which fall within the scope of the present invention as defined by the appended claims.
Claims (4)
1. A real-time detection method for CNC processing quality based on multi-sensor fusion is characterized in that: the method comprises the following specific steps:
1) Collecting and preprocessing sensor data;
in the step, a proper sensor is selected to collect the required data, after the data collection is completed, the collected data is stored, and a database mode is adopted to ensure that the data storage mode can meet the data quantity and the access requirement;
2) Processing a multi-sensor fusion algorithm;
after the data acquisition and pretreatment are completed, the data are further processed by adopting a multi-sensor fusion algorithm in the step so as to monitor the processing quality of CNC in real time, and the step is combined with an improved Z-Score formula for extended Kalman filtering; in this process, Z-Score is used to evaluate the deviation between a measured value and its expected value, while EKF is used to estimate future states from past observations and models;
3) Monitoring and analyzing in real time;
the real-time monitoring and analysis are divided into two steps of monitoring alarm and data analysis, and after the analysis is completed, the model must be automatically regulated and feedback controlled, and at the same time the corresponding conditions are recorded and reported, and the steps are as follows;
wherein step 3) real-time monitoring and analysis comprises the following sub-processes:
monitoring and alarming in real time;
data storage and analysis;
automatic adjustment and feedback control;
recording and reporting;
4) Adjusting and optimizing processing parameters;
in the step, the automatic adjustment and optimization of CNC processing parameters are involved, so that the consistency and quality of products are ensured, an optimization algorithm is introduced in the adjustment of the processing parameters for further improving the quality and efficiency of the products, and a CNC parallel search algorithm is adopted, so that the optimal combination can be searched in a parameter space.
2. The multi-sensor fusion CNC processing quality real-time detection method based on claim 1 is characterized by comprising the following steps:
the Z-Score algorithm formula of the modified version in the step 2) is expressed as follows:
wherein v represents the measurement of the sensor; e (sensor) represents the expected value of the sensors, which each sensor may have, representing the measured value expected under normal conditions; sigma (sensor) represents the standard deviation of the sensors, and the standard deviation of each sensor reflects the distribution of the measured values; t then represents the sensor weight, thereby determining its contribution to anomaly detection.
3. The multi-sensor fusion CNC processing quality real-time detection method based on claim 1 is characterized by comprising the following steps:
the optimized version EKF state prediction formula in the step 2) is expressed as follows:
wherein x is k|k-1 Is the result of a state estimate update. X is x k|k-1 Is an estimated state x using the previous time k-1 at time k k|k-1 And control input u k Predicted status; alpha is a correction factor to balance losses or errors between the Z-score and the EKF; f is a state transfer function describing how the state of the whole processing quality real-time monitoring system evolves with time; u (u) k The control input at time k is information from a sensor or an external input.
4. The multi-sensor fusion CNC processing quality real-time detection method based on claim 1 is characterized by comprising the following steps:
the formula of the CNC parallel search algorithm in the step 4) is as follows:
wherein N represents a specific number of workpieces; m is the number of CNC machine tools; v max Expressed as the maximum cutting speed of each material; v tool_max Expressed as the most of each toolA large cutting speed; x is x ij The decision variable indicating the use of tool j by workpiece i, i.e., 1 indicates use and 0 indicates no use.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311771596.0A CN117532403A (en) | 2023-12-21 | 2023-12-21 | CNC processing quality real-time detection method based on multi-sensor fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311771596.0A CN117532403A (en) | 2023-12-21 | 2023-12-21 | CNC processing quality real-time detection method based on multi-sensor fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117532403A true CN117532403A (en) | 2024-02-09 |
Family
ID=89790176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311771596.0A Pending CN117532403A (en) | 2023-12-21 | 2023-12-21 | CNC processing quality real-time detection method based on multi-sensor fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117532403A (en) |
-
2023
- 2023-12-21 CN CN202311771596.0A patent/CN117532403A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11237539B2 (en) | System and method for operational-data-based detection of anomaly of a machine tool | |
| AU2002246994B2 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| CN107614214B (en) | Trouble-shooter and method for diagnosing faults | |
| CN111459778A (en) | Operation and maintenance system abnormal index detection model optimization method and device and storage medium | |
| JP2004524609A (en) | Adaptive modeling of changing states in predictive state monitoring | |
| JP6832327B2 (en) | Data-driven method for automatic detection of anomalous workpieces during the production process | |
| CN112692646B (en) | Intelligent assessment method and device for tool wear state | |
| AU2002246994A1 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| US10684608B2 (en) | Abnormality detection apparatus and machine learning device | |
| US20200004221A1 (en) | Method and system for tool life monitoring and management in a cnc environment | |
| CN113253037B (en) | Current ripple-based edge cloud cooperative equipment state monitoring method and system and medium | |
| CN113723781A (en) | Product quality defect judgment system and method based on SPC analysis | |
| CN112183919A (en) | Quality prediction system and quality prediction method | |
| KR102474332B1 (en) | Prediction method of machine health stability in smart factory system, and recording medium thereof | |
| CN112859741A (en) | Method and system for evaluating operation reliability of sequential action units of machine tool | |
| CN117532403A (en) | CNC processing quality real-time detection method based on multi-sensor fusion | |
| EP3869286A1 (en) | System and method for detecting turbine underperformance and operation anomaly | |
| KR20180074473A (en) | Pre-sensing apparatus for abnormal of coiling equipment | |
| CN117272844B (en) | Method and system for predicting service life of distribution board | |
| CN114971599B (en) | Food manufacturing processing technological parameter setting method, device, equipment and medium | |
| CN117057676B (en) | Multi-data fusion fault analysis method, equipment and storage medium | |
| DE102020203606A1 (en) | MONITORING AN OPERATING PROCESS USING A FAULT PREDICTION MODEL | |
| CN114943524A (en) | Equipment production state monitoring system and working method thereof | |
| CN114693143A (en) | Health state evaluation method, system, equipment and medium of numerical control machine tool | |
| von Collani et al. | Improving and maintaining process profitability |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |