Punching machine tool health assessment method and punching machine tool

Abstract

The method comprises the steps of obtaining vibration data of a punching machine tool bearing, obtaining rotating speed data of the punching machine tool bearing, and conducting health assessment on the punching machine tool bearing based on the vibration data and the rotating speed data of the punching machine tool bearing. According to the health assessment method for the punching machine, the health of the punching machine can be accurately and timely assessed locally.

Description

Technical Field

[0001] This disclosure relates to machining equipment, and more particularly to a health assessment method for a stamping machine tool and the stamping machine tool itself. Background Technology

[0002] A stamping machine, also known as a punch press or die forging press, is a machine that uses pressure to deform materials, shaping them into various required structures. The functions of a stamping machine include punching, shearing, metal forming, deep drawing, and forging. Stamping machines are typically used in conjunction with dies and are essential equipment for producing metal mechanical parts. A stamping machine may include an electric motor, bearings, a drive system, and a slide block.

[0003] Stamping machine tools are critical manufacturing equipment in the production of machinery such as automobiles. Bearing failures in stamping machine tools can cause production interruptions and result in significant economic losses. Currently, to maintain the healthy operation of stamping machine tools, maintenance engineers can assess mechanical equipment malfunctions by measuring relevant data when the stamping machine is stopped. However, the assessment of stamping machine tools by maintenance engineers is subject to considerable uncertainty, depending on their qualifications. Traditional periodic manual maintenance is labor-intensive and costly, and cannot detect faults in a timely and accurate manner.

[0004] In addition, due to data security concerns, owners of stamping machines may not want to upload the processing data of their stamping machines to servers or the cloud.

[0005] Therefore, a method is desired that can assess the health of stamping machines locally. Summary of the Invention

[0006] The embodiments of this disclosure disclose a health assessment method for a stamping machine tool, including: obtaining vibration data of a stamping machine tool bearing, obtaining rotational speed data of a stamping machine tool bearing, and performing a health assessment of the stamping machine tool bearing based on the vibration data and rotational speed data of the stamping machine tool bearing.

[0007] According to the method of the embodiments of the present disclosure, vibration data of the stamping machine bearing is obtained by a vibration sensor installed at the support of the stamping machine bearing, and rotational speed data of the stamping machine bearing is obtained by a tachometer installed at the support of the stamping machine bearing.

[0008] The method according to embodiments of this disclosure further includes: performing effective data extraction on vibration data and rotational speed data, wherein the effective data extraction includes: obtaining vibration data and rotational speed data of a target working condition among multiple working conditions.

[0009] According to the method of embodiments of this disclosure, the plurality of working conditions correspond to different stamping machine tool processing speed ranges.

[0010] According to the method of the embodiments of this disclosure, the effective data acquisition further includes: filtering out external disturbance signals from the vibration data and speed data of the target working condition to obtain filtered vibration data and filtered speed data, wherein the external disturbance signals include stamping signals of the stamping machine tool processing, and removing outliers from the filtered vibration data and filtered speed data.

[0011] According to the method of the embodiments of this disclosure, wherein the vibration data includes acceleration data, and the health assessment of the stamping machine bearing based on the vibration data and rotational speed data of the stamping machine bearing includes: obtaining one or more of the following by performing data conversion on the vibration data: spectral data of acceleration data, velocity data, spectral data of velocity data, envelope data of acceleration, and spectral data of the envelope data of acceleration.

[0012] According to the method of the embodiments of this disclosure, the health assessment of the stamping machine bearing based on the vibration data and rotational speed data of the stamping machine bearing further includes: extracting features from the acceleration data and the spectral data of the acceleration data, the velocity data and the spectral data of the velocity data, the envelope data of the acceleration and the spectral data of the envelope data of the acceleration, and the rotational speed data to obtain one or more of the following: the rotational frequency and its harmonics of the stamping machine bearing, the gear meshing frequency and its harmonics, and the bearing failure frequency and its harmonics.

[0013] According to the method of embodiments of this disclosure, the health assessment of the stamping machine bearing based on vibration data and rotational speed data includes assessing the health of the stamping machine through a trained anomaly detection model and a trained fault diagnosis model, wherein the trained anomaly detection model is configured to determine whether a fault has occurred in the machine tool, and the trained fault diagnosis model is configured to determine the type of fault that has occurred in the stamping machine tool.

[0014] The method according to embodiments of this disclosure further includes: downloading a general anomaly detection model from a server, training the general anomaly detection model locally to obtain a trained anomaly detection model, downloading a general fault diagnosis model from a server, and training the general fault diagnosis model locally to obtain a trained fault diagnosis model.

[0015] According to the method of the embodiments of this disclosure, the bearing failure frequencies and their harmonics include: inner ring defect frequency BPFI and its harmonics, outer ring defect frequency BPFO and its harmonics, ball defect frequency BSP and its harmonics, and cage defect frequency FTF and its harmonics.

[0016] According to the method of embodiments of this disclosure, a general anomaly detection model and a general fault diagnosis model are trained using vibration data and rotational speed data in a boosting manner.

[0017] The method according to an embodiment of the present disclosure further includes performing a health assessment on the press machine bearing at predetermined time intervals, wherein the vibration data used for the health assessment of the press machine bearing is the average value of vibration data collected during multiple collection time intervals in the 24 hours prior to the time point of the health assessment, and the rotational speed data used for the health assessment of the press machine bearing is the average value of rotational speed data collected during multiple collection time intervals in the 24 hours prior to the time point of the health assessment.

[0018] This disclosure discloses a stamping machine tool, comprising: a bearing configured to support a transmission mechanism for transmitting power from an electric motor to a slide block via the transmission mechanism, causing the slide block to perform a stamping action; a vibration sensor mounted on a support of the bearing and configured to acquire vibration data of the bearing; a tachometer mounted on the support of the bearing and configured to acquire rotational speed data of the bearing; and a processor coupled to the vibration sensor and the tachometer, executing program code stored in a memory to perform a health assessment of the stamping machine tool bearing based on the vibration data and rotational speed data of the stamping machine tool bearing.

[0019] This disclosure provides an embodiment of a health assessment device for a stamping machine tool, comprising: a vibration sensor installed at a bearing support of the stamping machine tool and configured to obtain vibration data of the stamping machine tool bearing; a tachometer installed at the bearing support of the stamping machine tool and configured to obtain rotational speed data of the stamping machine tool bearing; and a processor coupled to the vibration sensor and the tachometer and configured to perform a health assessment of the stamping machine tool bearing based on the vibration data and rotational speed data of the stamping machine tool bearing.

[0020] This disclosure provides an embodiment of a stamping machine tool health assessment system, comprising: a server configured to store a general anomaly detection model and a general fault diagnosis model; a stamping machine tool health assessment device, the stamping machine tool health assessment device comprising: a vibration sensor installed at a bearing support of the stamping machine tool and configured to obtain vibration data of the stamping machine tool bearing; a tachometer installed at the bearing support of the stamping machine tool and configured to obtain rotational speed data of the stamping machine tool bearing; and a processor coupled to the vibration sensor and the tachometer, configured to: download the general anomaly detection model and the general fault diagnosis model from the server; train the general anomaly detection model and the general fault diagnosis model locally to obtain trained anomaly detection model and trained fault diagnosis model; and perform a health assessment of the stamping machine tool bearing based on the vibration data and rotational speed data of the stamping machine tool bearing using the trained anomaly detection model and trained fault diagnosis model.

[0021] Embodiments of this disclosure disclose one or more non-transitory storage media having instructions stored thereon that, when executed by a processor, cause the processor to perform the method described above.

[0022] According to the health assessment method, machine tool, device, system, and storage medium of this disclosure, an accurate and timely health assessment of the machine tool can be performed locally based on bearing vibration data and rotational speed data. By performing real-time or near-real-time health assessments, performance degradation or malfunctions of the machine tool can be detected promptly, thereby reducing the probability of unexpected downtime and minimizing potential losses. Preprocessing the vibration and rotational speed data yields more accurate and effective data, making the health assessment of the machine tool more precise. Using a locally downloaded machine learning model for health assessment eliminates the need to upload the machine tool's processing data to a server or cloud, thus ensuring data security. Attached Figure Description

[0023] The above and other aspects, features, and advantages of specific embodiments of the present disclosure will become clearer from the following description taken in conjunction with the accompanying drawings, in which:

[0024] Figure 1 This is an example flowchart of a health assessment method for a stamping machine tool according to an embodiment of the present disclosure.

[0025] Figure 2 This is an example flowchart of another health assessment method for a stamping machine tool according to an embodiment of the present disclosure.

[0026] Figure 3A This is an example diagram showing vibration data for a target operating condition that includes external disturbance signals.

[0027] Figure 3B This is an example diagram of filtered vibration data obtained by removing external disturbance signals from vibration data under the target operating condition.

[0028] Figure 4 This is an example illustration of removing outliers from filtered vibration data according to embodiments of the present disclosure.

[0029] Figure 5 This is an example schematic diagram of a health assessment score generated according to an embodiment of this disclosure.

[0030] Figure 6 This is an example schematic diagram of a stamping machine tool according to an embodiment of the present disclosure.

[0031] Figure 7 This is an example schematic diagram of a health assessment device for a stamping machine tool according to an embodiment of the present disclosure.

[0032] Figure 8 This is an example schematic diagram of a health assessment system for a stamping machine tool according to an embodiment of the present disclosure. Detailed Implementation

[0033] Before proceeding with the detailed description below, it may be advantageous to define certain words and phrases used throughout this disclosure. The terms “comprising” and “including” and their derivatives mean, but are not limited to, “including”. The phrase “at least one”, when used with a list of items, means that different combinations of one or more of the listed items may be used, and that only one item in the list may be required. For example, “at least one of A, B, and C” includes any one of the following combinations: A, B, C, A and B, A and C, B and C, A and B and C.

[0034] Definitions of other specific words and phrases are provided throughout this disclosure. Those skilled in the art will understand that, in many, if not most, cases, such definitions apply to the prior and future use of the words and phrases thus defined.

[0035] The various embodiments of the principles of this disclosure described below with reference to the accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this disclosure in any way. Those skilled in the art will understand that the principles of this disclosure can be implemented in any suitably arranged system or device. In some cases, the actions described in this disclosure can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific order or sequential sequence to achieve the desired result. In certain embodiments, multitasking and parallel processing may be advantageous.

[0036] The text and accompanying drawings are provided by way of example only to aid in understanding this disclosure. They should not be construed as limiting the scope of the claims appended to this disclosure in any way. Throughout the drawings, the same reference numerals generally indicate the same elements. Although certain embodiments and examples have been provided, it will be apparent to those skilled in the art, based on the content of this disclosure, that changes may be made to the illustrated embodiments and examples without departing from the scope of this disclosure.

[0037] Figure 1 This is an example flowchart of a health assessment method for a stamping machine tool according to an embodiment of the present disclosure.

[0038] In S101, vibration data of the stamping machine tool bearing can be obtained. For example, vibration data of the stamping machine tool bearing can be obtained through a vibration sensor. Vibration data may include acceleration data, etc.

[0039] Vibration sensors may include, but are not limited to, mechanical vibration sensors, optical vibration sensors, and electrical vibration sensors (such as inductive vibration sensors, eddy current vibration sensors, capacitive vibration sensors, resistance strain gauge vibration sensors, and piezoelectric vibration sensors). In one embodiment, the vibration sensor may be mounted on the support of a stamping machine bearing.

[0040] In S102, the rotational speed data of the stamping machine tool bearing can be obtained. For example, the rotational speed data of the stamping machine tool bearing can be obtained through a tachometer.

[0041] The tachometer may include, but is not limited to, centrifugal tachometers, magnetic tachometers, electric tachometers, magneto-electric tachometers, and flash tachometers. In one embodiment, the tachometer may be mounted on the support of the bearing of a stamping machine tool.

[0042] In S103, a health assessment of the press bearing can be performed based on its vibration and rotational speed data. For example, a health assessment of the press bearing can be performed based on its vibration and rotational speed data to output a score indicating the health status of the press bearing.

[0043] Figure 2 This is an example flowchart of another health assessment method for a stamping machine tool according to an embodiment of the present disclosure.

[0044] In S201, vibration data of the press machine bearing can be obtained. For example, vibration data of the press machine bearing can be obtained using a vibration sensor installed at the support of the press machine bearing. The vibration data may include acceleration data, etc.

[0045] In S202, the rotational speed data of the stamping machine bearing can be obtained. For example, the rotational speed data of the stamping machine bearing can be obtained by a tachometer installed at the support of the stamping machine bearing.

[0046] In S203, effective data extraction can be performed on vibration data and rotational speed data. Effective data extraction may include obtaining vibration data and rotational speed data of a target operating condition from multiple operating conditions, filtering out external disturbance signals from the vibration data and rotational speed data of the target operating condition, and removing outliers from the filtered vibration data and filtered rotational speed data.

[0047] Effective data extraction can include obtaining vibration and rotational speed data for a target operating condition across multiple operating conditions. For example, the obtained vibration and rotational speed data can be data from various different operating conditions. These various operating conditions can include commissioning conditions and normal machining conditions. Data for the normal machining condition can be extracted from the obtained vibration and rotational speed data. The normal machining condition can include various specific machining conditions; for example, these specific machining conditions may correspond to different machining speed ranges (e.g., the cycle speed of a stamping machine), or they may correspond to different workpieces being processed. Vibration and rotational speed data for a target operating condition across multiple operating conditions can be obtained. The target operating condition can be the normal machining condition or one or more of the various specific machining conditions.

[0048] In one embodiment, the target operating condition can be identified using rotational speed data. The machining condition can be identified based on the rotational speed of the press machine tool bearings; for example, a faster bearing rotational speed corresponds to a faster machining speed. The operating condition of the machine tool is determined based on the rotational speed range within which the bearing rotational speed falls. In another embodiment, the operating condition of the press machine tool can be determined based on scheduling data stored within the press machine tool. For example, the machining speed or the workpiece being machined can be determined by retrieving the scheduling data stored in the press machine tool, thereby determining the operating condition of the press machine tool.

[0049] Effective data extraction can include filtering out external disturbance signals from vibration and rotational speed data of the target operating condition. External disturbance signals can be filtered from the vibration and rotational speed data of the target operating condition to obtain filtered vibration and rotational speed data. External disturbance signals can primarily include stamping signals from the stamping process of a stamping machine. External disturbance signals can also include vibration signals generated by related components of the stamping machine due to the processing signals of the stamping machine. In one embodiment, a sliding window algorithm can be used to filter out external disturbance signals from the vibration and rotational speed data of the target operating condition.

[0050] Figure 3A This is an example diagram of vibration data for a target operating condition that includes external disturbance signals. Figure 3B This is an example diagram of filtered vibration data from the vibration data of the target working condition, after removing external disturbance signals.

[0051] Reference Figure 3A and Figure 3B Describe an example of filtering out external disturbance signals from vibration data under a target operating condition. For example... Figure 3A As shown, in the frequency domain data of vibration data including external disturbance signals, the highest amplitude of the vibration data is approximately 10 mm / s, and the highest amplitude occurs at a frequency of approximately 40 Hz; in the time domain data of vibration data including external disturbance signals, the highest amplitude of the vibration data is approximately 38 mm / s. Figure 3BAs shown, in the frequency domain data of the filtered vibration data (excluding external disturbance signals), the highest amplitude of the vibration data is approximately 0.68 mm / s, occurring at a frequency of approximately 30 Hz. Furthermore, the distribution of the frequency domain data of the filtered vibration data (excluding external disturbance signals) differs significantly from that of the vibration data containing external disturbance signals. In the time domain data of the filtered vibration data (excluding external disturbance signals), the highest amplitude of the vibration data is approximately 3 mm / s. By filtering out larger external disturbance signals from the vibration data of the target operating condition, more accurate bearing vibration data can be obtained for subsequent analysis. Although... Figure 3A and Figure 3B Only an example of vibration data is shown, but those skilled in the art will understand that a similar effect can be achieved by filtering out external disturbance signals from the rotational speed data of the target operating condition.

[0052] Figure 4 This is an example diagram illustrating the removal of outliers from filtered vibration data according to embodiments of the present disclosure.

[0053] like Figure 4 As shown, the statistical threshold and statistical mean of the vibration data can be determined. Values ​​above the statistical threshold can be identified as outliers. By removing outliers from the vibration data, more accurate bearing vibration data can be obtained for subsequent analysis. Figure 4 The table shows the statistical threshold as the upper limit; another statistical threshold can also be set as the lower limit, depending on actual needs. Although Figure 4 Only an example of vibration data is shown, but those skilled in the art will understand that similar effects can be obtained by removing outliers from filtered rotational speed data.

[0054] Return to reference Figure 2 In S204, feature extraction can be performed on the valid data. Data transformation and feature extraction can be performed on the valid data to obtain features that can be used for training machine learning models or for bearing health assessment.

[0055] Data transformation can be performed on valid data. For example, vibration data can include vibration acceleration data. Vibration data including acceleration data can be transformed to obtain vibration velocity data and acceleration envelope data. Further data transformation can be performed on the vibration acceleration data, vibration velocity data, and acceleration envelope data to obtain spectral data of acceleration data, spectral data of velocity data, and spectral data of acceleration envelope data.

[0056] Feature extraction can be performed on the effective data after data conversion. For example, feature extraction can be performed on acceleration data and its spectrum, velocity data and its spectrum, acceleration envelope data and its spectrum, and rotational speed data to obtain one or more of the following: the rotational frequency and its harmonics of a stamping machine bearing, the gear meshing frequency and its harmonics, and the bearing failure frequency and its harmonics. For example, the rotational frequency and its harmonics of a stamping machine bearing can be obtained based on rotational speed data. The gear meshing frequency and its harmonics of the gears in contact with the bearing can be obtained by feature extraction on the converted data. The bearing failure frequency and its harmonics can represent the vibration frequency and its harmonics of the corresponding components in the bearing, and changes in the vibration frequency and its harmonics of the corresponding components in the bearing can be correlated with bearing failures. For example, the bearing failure frequency and its harmonics can include the inner ring defect frequency BPFI and its harmonics, the outer ring defect frequency BPFO and its harmonics, the ball defect frequency BSP and its harmonics, and the cage defect frequency FTF and its harmonics. Changes in the inner ring defect frequency BPFI and its harmonics can be correlated with failures in the inner ring of the bearing. Variations in the outer ring defect frequency (BPFO) and its harmonics can be associated with outer ring failure in bearings. Variations in the ball defect frequency (BSP) and its harmonics can be associated with ball failure in bearings. Variations in the cage defect frequency (FTF) and its harmonics can be associated with cage failure in bearings.

[0057] In S205, a health assessment of the stamping machine bearing can be performed based on the extracted features. For example, the health assessment of the stamping machine bearing can be performed based on a machine learning model. The machine learning model can be trained based on the extracted features. For example, a general machine learning model can be downloaded from a server and trained locally to obtain a trained machine learning model. The machine learning model can include an anomaly detection model and a fault diagnosis model. The anomaly diagnosis model can be used to determine whether a fault has occurred in the stamping machine, and the fault diagnosis model can be used to determine the type of fault that has occurred in the stamping machine. In some embodiments, the general anomaly detection model and the general fault diagnosis model downloaded from the server can correspond to the normal machining conditions of the stamping machine. In some embodiments, the general anomaly detection model and the general fault diagnosis model downloaded from the server can correspond to one or more specific machining conditions within the normal machining conditions. The general anomaly detection model and the general fault diagnosis model can be trained using the features obtained in S204 to obtain and store the trained anomaly detection model and the trained fault diagnosis model.

[0058] In one embodiment, the anomaly detection model may include distribution-based machine learning methods (such as 3sigma, Z-score, boxplot, etc.), distance-based machine learning methods (such as K-nearest neighbor (KNN)), density-based machine learning methods (such as Local Outlier Factor (LOF), Connectivity-Based Outlier Factor (COF), Stochastic Outlier Selection (SOS), etc.), clustering-based machine learning methods (such as Density-Based Spatial Clustering of Applications with Noise (DBSCAN), etc.), tree-based machine learning methods (such as Isolation Forest (iForest), etc.), dimensionality reduction-based machine learning methods (such as Principal Component Analysis (PCA), Autoencoder, etc.), and classification-based machine learning methods (such as One-Class Support Vector Machine). Anomaly detection models utilizing machine learning include SVM (such as SVM) and prediction-based machine learning methods (such as Moving Average, Autoregressive Integrated Moving Average model (ARIMA)). While the example embodiments illustrate some anomaly detection models utilizing machine learning, those skilled in the art should understand that the above description is merely exemplary and not exhaustive, and other existing or future models for anomaly detection can be used to determine whether a stamping machine has malfunctioned, all of which are within the scope of this disclosure.

[0059] In one embodiment, the fault diagnosis model may include decision trees, random forests, logistic regression, naive Bayes, etc. While the example embodiments illustrate some fault diagnosis models utilizing machine learning, those skilled in the art should understand that the above description is merely exemplary and not exhaustive, and other existing or future-developed models for fault diagnosis can be used to determine the type of fault occurring in the stamping machine, all of which are within the scope of this disclosure.

[0060] Generally, training anomaly detection and fault diagnosis models requires a large amount of training data and consumes significant computing resources, including CPU and RAM, and the training process is very lengthy, potentially lasting several days. In the embodiments of this disclosure, vibration and rotational speed data can be used to train general anomaly detection and fault diagnosis models via boosting. The boosting algorithm generates a weak learner based on the training samples, then adjusts the sample distribution based on the weak learner's performance, i.e., increasing the weight of erroneous samples to give them more attention in subsequent training. After adjusting the weights on the training set, a new weak learner is generated, and this process is repeated until a certain number of weak learners are generated. Finally, the outputs of these multiple weak learners are combined using a combination strategy. By using the boosting algorithm, the training time for anomaly detection and fault diagnosis models can be shortened to a few hours, such as 4 hours.

[0061] Health assessments of press machine bearings can be performed using trained machine learning models. For example, a trained anomaly detection model can be used to determine if a press machine has malfunctioned, and a trained fault diagnosis model can be used to determine the type of fault. Health assessments of press machine bearings can be performed at predetermined time intervals (e.g., hourly). Each health assessment can be based on the average of bearing vibration and rotational speed data collected over multiple acquisition periods within the preceding 24 hours. For example, bearing vibration and rotational speed data can be collected every half hour in acquisition periods such as 1 minute. This avoids the influence of sudden changes in certain data values. False alarm rates can be effectively avoided by collecting rolling historical data to generate statistical results. In one embodiment, anomaly detection can be performed based on rolling historical data, and a bearing health assessment score based on the anomaly detection results can be displayed. When the health assessment score falls below a threshold, further fault diagnosis can be performed.

[0062] Figure 5 This is an example schematic diagram of a health assessment score generated according to an embodiment of the present disclosure.

[0063] like Figure 5 As shown, the health of the bearing can be continuously assessed over a period of 2000 hours. By displaying the bearing's health assessment score to the user in real time, the user can gain a more comprehensive understanding of the bearing's health status and thus prepare for maintenance and repair activities in advance when necessary.

[0064] Figure 6 This is an example schematic diagram of a stamping machine tool according to an embodiment of the present disclosure.

[0065] like Figure 6 As shown, the stamping machine tool 600 may include a bearing 601, a vibration sensor 602, a tachometer 603, a processor 604, a motor 605, a slider 606, and a worktable 607.

[0066] The bearing 601 can be configured to support the transmission mechanism to transmit power from the motor 605 to the slider 606 through the transmission mechanism, so that the slider 606 performs a stamping action to cooperate with the worktable 607 to process the workpiece.

[0067] Vibration sensor 602 can be mounted on the support of bearing 601 and configured to obtain vibration data of bearing. Vibration sensor 602 may include, but is not limited to, mechanical vibration sensors, optical vibration sensors, and electrical vibration sensors (such as inductive vibration sensors, eddy current vibration sensors, capacitive vibration sensors, resistance strain gauge vibration sensors, and piezoelectric vibration sensors).

[0068] Tachometer 603 can be mounted on the support of bearing 602 and configured to obtain bearing rotational speed data. Tachometer 603 may include, but is not limited to, centrifugal tachometer, magnetic tachometer, electrodynamic tachometer, magneto-electric tachometer, and flash tachometer.

[0069] The processor 604 can be coupled to the vibration sensor 602 and the tachometer 603. For example, the processor 604 can be coupled to the vibration sensor 602 and the tachometer 603 via a cable or wireless connection. The cable connection may include a cable for transmitting analog signals (e.g., voltage, 4-20mA current) or digital signals (pulse, CAN, RS485, etc.). Cable connections are more suitable for applications requiring high-performance data acquisition and high reliability. Wireless connections may include various configurations and protocols, including Bluetooth. TM ,Bluetooth TM LE's short-range communication protocols include sub-GHz, wireless HART, infrared links, ZigBee, RFID, WiFi, the Internet, the World Wide Web, intranets, virtual private networks, wide area networks, local area networks, private networks using communication protocols proprietary to one or more companies, Ethernet, and HTTP, as well as various combinations thereof. Wireless connectivity is more suitable for requirements such as ease of installation and small size. The processor 604 can execute program code stored in memory to perform a health assessment of the press machine bearing based on vibration and rotational speed data.

[0070] Figure 7 This is an example schematic diagram of a health assessment device for a stamping machine tool according to an embodiment of the present disclosure.

[0071] like Figure 7 As shown, the stamping machine tool health assessment device 700 may include a vibration sensor 701, a tachometer 702, and a processor 703. Figure 7 Zhongyu Figure 6 Descriptions of the same components will not be repeated.

[0072] Vibration sensor 701 can be installed at the bearing support of a stamping machine tool and can be configured to obtain vibration data of the stamping machine tool bearing.

[0073] The tachometer 702 can be installed at the bearing support of the stamping machine tool and can be configured to obtain the rotational speed data of the stamping machine tool bearing.

[0074] The processor 703 can be coupled to the vibration sensor 701 and the tachometer 702, and can be configured to perform a health assessment of the press bearing based on the vibration data and rotational speed data of the press bearing.

[0075] Figure 8 This is an example schematic diagram of a health assessment system for a stamping machine tool according to an embodiment of the present disclosure.

[0076] like Figure 8 As shown, the stamping machine tool health assessment system 800 may include a stamping machine tool health assessment device 700 and a server 810. Figure 8 Zhongyu Figure 7 Descriptions of the same components will not be repeated.

[0077] Server 810 can be configured to store a general anomaly detection model and a general fault diagnosis model.

[0078] The health assessment device 700 for a stamping machine tool may include a vibration sensor 701, a tachometer 702, and a processor 703.

[0079] Vibration sensor 701 can be installed at the bearing support of a stamping machine tool and can be configured to obtain vibration data of the stamping machine tool bearing.

[0080] The tachometer 702 can be installed at the bearing support of the stamping machine tool and can be configured to obtain the rotational speed data of the stamping machine tool bearing.

[0081] The processor 703 can be coupled to the vibration sensor 701 and the tachometer 702, and can be configured to download a general anomaly detection model and a general fault diagnosis model from a server (e.g., via a communication module). The processor 703 can train the general anomaly detection model and the general fault diagnosis model locally to obtain trained anomaly detection models and trained fault diagnosis models. Based on the vibration data and rotational speed data of the stamping machine bearing, a health assessment of the stamping machine bearing is performed using the trained anomaly detection model and the trained fault diagnosis model.

[0082] The connection between the press machine health assessment device 700 and the server 810 can be via the communication module of the press machine health assessment device 700 and / or various configurations and protocols. The communication module can use various cellular communication technologies, such as GSM, CDMA, UMTS, EV-DO, WiMAX, LTE, or 5G cellular technology, as well as other cellular technologies developed in the future. Various configurations and protocols include short-range communication protocols such as Bluetooth. TM ,Bluetooth TM LE, sub GHz, wireless HART, infrared link, ZigBee, radio frequency identification (RFID), WiFi, Internet, World Wide Web, intranet, virtual private network, wide area network, local area network, private network using communication protocols proprietary to one or more companies, Ethernet and HTTP, and various combinations thereof.

[0083] As will be understood by those skilled in the art, without departing from the scope of the invention, Figure 8 The health assessment device 700 for the stamping machine tool can be replaced by the stamping machine tool 600.

[0084] although Figures 6-8 Memory is not shown, but those skilled in the art will understand that a processor may include one or more memories on which instructions and / or data are stored. Furthermore, although... Figures 6-8 Functionally, the processor and sensor are shown as being within a single box; however, those skilled in the art will understand that the processor and sensor may actually comprise multiple processors and multiple sensors of the same type, which may or may not be housed in the same physical enclosure. Therefore, references to a processor or sensor will be understood to include references to a collection of processors operating in parallel or not in parallel, and to a collection of sensors of the same type.

[0085] This invention provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, cause the processor to perform a stamping machine health assessment method according to an embodiment of this disclosure.

[0086] Computer-readable storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0087] According to the health assessment method, machine tool, device, system, and storage medium of this disclosure, accurate and timely health assessments of the machine tool can be performed locally based on bearing vibration and rotational speed data. By performing real-time or near-real-time health assessments, performance degradation or malfunctions of the machine tool can be detected promptly, thereby reducing the probability of unexpected downtime and minimizing potential losses. Preprocessing the vibration and rotational speed data yields more accurate and effective data, making the health assessment of the machine tool more precise. Using a locally downloaded machine learning model for health assessment eliminates the need to upload the machine tool's processing data to a server or cloud, thus ensuring data security.

[0088] The text and accompanying drawings are provided by way of example only to aid in understanding this disclosure. They should not be construed as limiting the scope of this disclosure in any way. Although certain embodiments and examples have been provided, it will be clear to those skilled in the art, based on the content disclosed herein, that changes can be made to the illustrated embodiments and examples without departing from the scope of this disclosure.

[0089] Although this disclosure has been described with reference to exemplary embodiments, various changes and modifications may be suggested to those skilled in the art. This disclosure is intended to cover such changes and modifications that fall within the scope of the appended claims.

[0090] Any description in this invention should not be construed as implying that any particular element, step, or function is an essential element that must be included within the scope of the claims. The scope of the patent subject matter is defined only by the claims.

Claims

1. A method for health assessment of a stamping machine tool, comprising: Obtain vibration data of the bearings of the stamping machine tool. Obtain the rotational speed data of the bearings in the stamping machine tool, and A health assessment of the stamping machine tool bearings is conducted based on vibration and rotational speed data.

2. The method according to claim 1, wherein, Vibration data of the stamping machine bearing is obtained by a vibration sensor installed at the support of the stamping machine bearing. The rotational speed data of the stamping machine bearing is obtained by a tachometer installed on the support of the stamping machine bearing.

3. The method according to claim 1, further comprising: Effective data extraction is performed on vibration data and rotational speed data, the effective data extraction including: Vibration and rotational speed data for the target operating condition are obtained from multiple operating conditions.

4. The method according to claim 3, wherein, The multiple operating conditions correspond to different processing speed ranges of the stamping machine tool.

5. The method according to claim 3, wherein, The acquisition of valid data also includes: External disturbance signals are filtered out from the vibration and rotational speed data under the target operating condition to obtain filtered vibration and rotational speed data. The external disturbance signals include stamping signals from the stamping machine tool processing. Remove outliers from the filtered vibration data and filtered rotational speed data.

6. The method according to claim 1, wherein, The vibration data includes acceleration data, and the health assessment of the stamping machine bearing based on the vibration and rotational speed data includes: By performing data conversion on the vibration data, one or more of the following can be obtained: spectral data of acceleration data, spectral data of velocity data, spectral data of velocity data, envelope data of acceleration, and spectral data of the envelope data of acceleration.

7. The method according to claim 6, wherein, Health assessment of stamping machine tool bearings based on vibration and rotational speed data also includes: By extracting features from acceleration data and its spectrum, velocity data and its spectrum, acceleration envelope data and its spectrum, and rotational speed data, one or more of the following can be obtained: the rotational frequency and its harmonics of the stamping machine bearing, the gear meshing frequency and its harmonics, and the bearing fault frequency and its harmonics.

8. The method according to claim 1, wherein, Health assessment of stamping machine tool bearings based on vibration and rotational speed data includes health assessment of the machine tool through trained anomaly detection and fault diagnosis models. The trained anomaly detection model is configured to determine whether a stamping machine has malfunctioned. The trained fault diagnosis model is configured to determine the type of fault occurring in the stamping machine.

9. The method according to claim 8, further comprising: Download the general anomaly detection model from the server, and train it locally to obtain the trained anomaly detection model. Download the general fault diagnosis model from the server and train it locally to obtain the trained fault diagnosis model.

10. A stamping machine tool, comprising: The bearing is configured to support the transmission mechanism, which transmits power from the electric motor to the slider via the transmission mechanism, causing the slider to perform the stamping action. A vibration sensor is mounted on the support of the bearing and configured to acquire vibration data of the bearing. A tachometer, mounted on the support of the bearing, is configured to obtain the bearing's rotational speed data. The processor is coupled to a vibration sensor and a tachometer, and executes program code stored in memory to perform a health assessment of the press bearing based on vibration and speed data.

Images