Monitoring method and system for cubic press

Abstract

The invention relates to the technical field of engineering equipment monitoring, and discloses a monitoring method and system for a cubic press, and the method comprises the steps: obtaining sound wave signals of at least three sound wave sensors disposed on a sound wave sensing array of the cubic press according to a collection time period, preprocessing the at least three sound wave signals to determine a top pressure sound wave signal of the cubic press, judging whether to adjust the top pressure sound wave signal according to a signal-to-noise ratio, analyzing a top pressure target sound wave signal, determining suspected sound wave data, determining defect sound wave data of the cubic press based on a sound wave identification model and the suspected sound wave data, and determining the defect sound wave data of the cubic press according to the defect sound wave data. The defect sound wave data is compared with the historical defect sound wave data set, the alarm mode of the cubic press is determined according to the comparison result, whether the alarm mode is adjusted or not is judged based on the environment of the cubic press, and the monitoring reliability is ensured by adjusting the top pressure sound wave signals.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering equipment monitoring, and in particular, to a monitoring method and system for a six-sided top press. Background Art

[0002] With the development of technology, the demand for diamond has posed a severe challenge. The six-sided top press is the main equipment for producing superhard materials such as diamond, and its stable operation directly affects the production efficiency and the quality of diamond. At present, the monitoring of the six-sided top press mainly relies on periodic manual inspection methods. The time interval of manual inspection is relatively long, making it difficult to capture the changing conditions during the operation of the six-sided top press in a timely manner. Secondly, when using acoustic wave sensors to monitor the six-sided top press, due to the relatively strict requirements for the quality, stability, and integrity of the monitoring signals, it is difficult for acoustic wave sensors to meet the needs of real-time monitoring and early warning, and it is impossible to effectively warn the equipment.

[0003] Therefore, it is necessary to design a monitoring method and system for a six-sided top press to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes a monitoring method and system for a six-sided top press, aiming to solve the problems that the monitoring of the six-sided top press mainly relies on periodic manual inspection methods, the time interval of manual inspection is relatively long, it is difficult to capture the changing conditions during the operation of the six-sided top press in a timely manner, and acoustic wave sensors are difficult to meet the needs of real-time monitoring and early warning, and it is impossible to effectively warn the equipment.

[0005] On the one hand, the present invention proposes a monitoring method for a six-sided top press, including:[[]] Obtaining acoustic wave signals of at least three acoustic wave sensors deployed on the acoustic wave sensor array of the six-sided top press according to the acquisition time period; Preprocessing at least three of the acoustic wave signals to determine the top pressure acoustic wave signal of the six-sided top press, determining the signal-to-noise ratio according to the top pressure acoustic wave signal, and judging whether to adjust the top pressure acoustic wave signal according to the signal-to-noise ratio, and determining the top pressure target acoustic wave signal of the six-sided top press according to the judgment result; Analyzing the top pressure target acoustic wave signal to determine suspected acoustic wave data, and determining the defective acoustic wave data of the six-sided top press based on the acoustic wave recognition model and the suspected acoustic wave data; Comparing the defective acoustic wave data with the historical defective acoustic wave data set, determining the alarm mode of the six-sided top press according to the comparison result, and judging whether to adjust the alarm mode based on the environment of the six-sided top press, and sending an alarm to the six-sided top press according to the adjusted alarm mode.

[0006] Further, when preprocessing the acoustic wave signal to determine the top pressure acoustic wave signal of the cubic press, determining the signal-to-noise ratio according to the top pressure acoustic wave signal, and judging whether to adjust the top pressure acoustic wave signal according to the signal-to-noise ratio, and determining the top pressure target acoustic wave signal of the cubic press according to the judgment result, it includes: The preprocessing is signal denoising; Obtain the mean square value of the top pressure acoustic wave signal to determine the signal power of the top pressure acoustic wave signal, determine the top pressure acoustic wave signal when the cubic press is turned off, and determine the noise power according to the power of the top pressure acoustic wave signal when the cubic press is turned off; Determine the signal-to-noise ratio based on the signal power and the noise power; Compare the signal-to-noise ratio with the signal-to-noise ratio threshold, and judge whether to adjust the top pressure acoustic wave signal according to the comparison result; When the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, it is determined that the top pressure acoustic wave signal is not adjusted, and the top pressure acoustic wave signal is determined as the top pressure target acoustic wave signal; When the signal-to-noise ratio is less than or equal to the signal-to-noise ratio threshold, it is determined that the top pressure acoustic wave signal is adjusted, and the adjusted top pressure acoustic wave signal is determined as the top pressure target acoustic wave signal.

[0007] Further, when it is determined that the top pressure acoustic wave signal is adjusted, it includes: Obtain the Doppler frequency of the top pressure acoustic wave signal, and compare the Doppler frequency with historical data to determine the adjustment value of the Doppler frequency; The historical data includes several historical Doppler frequencies and several phase compensation values, and each historical Doppler frequency corresponds to a phase compensation value; When there is a historical Doppler frequency in the historical data that is the same as the Doppler frequency, the phase compensation value corresponding to the historical Doppler frequency is determined as the adjustment value of the Doppler frequency; When there is no historical Doppler frequency in the historical data that is the same as the Doppler frequency, obtain the similarity between the Doppler frequency and each historical Doppler frequency, and determine the phase compensation value corresponding to the historical Doppler frequency with the maximum similarity as the adjustment value of the Doppler frequency.

[0008] Further, when analyzing the top pressure target acoustic wave signal to determine suspected acoustic wave data, it includes: Analyze the top pressure target acoustic wave signal in the acquisition time period to determine the time domain value of the top pressure target acoustic wave signal, and judge whether the top pressure target acoustic wave signal is the suspected acoustic wave data according to the time domain value.

[0009] Further, when determining whether the top pressure target acoustic wave signal is the suspected acoustic wave data according to the time domain value and the frequency domain value, it includes: Obtain the time domain maximum value and the time domain minimum value of the top pressure target acoustic wave signal; When the time domain maximum value is greater than the time domain maximum threshold and the time domain minimum value is less than the time domain minimum threshold, determine that the top pressure target acoustic wave signal is the suspected acoustic wave data; otherwise, determine that the top pressure target acoustic wave signal is not the suspected acoustic wave data.

[0010] Further, when determining the defective acoustic wave data of the six-side top press based on the acoustic wave recognition model and the suspected acoustic wave data, it includes: Obtain an acoustic wave data set and sample it according to a sampling ratio to obtain a training set and a test set; Obtain a decision tree model, train the decision tree model according to the training set, and evaluate the trained decision tree model according to the test set; If the evaluation value of the currently trained decision tree model is greater than or equal to the evaluation value of the previously trained decision tree model, stop training and determine the currently trained decision tree model as the acoustic wave recognition model; otherwise, use grid search to find the model parameters of the decision tree model and continue to train the decision tree model according to the model parameters until it is greater than or equal to the evaluation value of the previously trained decision tree model; Substitute the suspected acoustic wave data into the acoustic wave recognition model to determine the defective acoustic wave data.

[0011] Further, when comparing the defective acoustic wave data with the historical defective acoustic wave data set and determining the alarm mode of the six-side top press according to the comparison result, it includes: When there is data in the historical defective acoustic wave data set that is the same as the defective acoustic wave data, add the defective acoustic wave data to the historical defective acoustic wave data set and determine the alarm mode of the six-side top press according to the number of times the data appears; When there is no data in the historical defective acoustic wave data set that is the same as the defective acoustic wave data, add the defective acoustic wave data to the historical defective acoustic wave data set and give an alarm to remind for manual verification.

[0012] Further, when determining the alarm mode of the six-side top press according to the number of times the data appears, it includes: Preset a first preset number of times the data appears and a second preset number of times the data appears, and the first preset number of times the data appears is greater than the second preset number of times the data appears; When the number of times the data appears is greater than or equal to the first preset number of times the data appears, determine the alarm mode as a first-level early warning; When the occurrence times of the data are less than the first preset occurrence times of the data and greater than the second preset occurrence times of the data, the alarm mode is determined as the secondary early warning; When the occurrence times of the data are less than or equal to the second preset occurrence times of the data, the alarm mode is determined as the tertiary early warning; The emergency levels of the primary early warning, secondary early warning, and tertiary early warning decrease in sequence.

[0013] Further, when determining whether to adjust the alarm mode based on the environment of the six-sided top press, it includes: Obtain the environmental parameters of the six-sided top press and determine the standard environmental parameters of the six-sided top press; Count the number of environmental parameters whose environmental parameters are not equal to the standard environmental parameters; When the number of environmental parameters is greater than or equal to the environmental parameter quantity threshold, upgrade the alarm mode by one level; When the number of environmental parameters is less than the environmental parameter quantity threshold, downgrade the alarm mode by one level.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: By collecting the acoustic wave signals of at least three acoustic wave sensors through an acoustic wave sensing array, the comprehensiveness of signal collection is improved. At the same time, the collected acoustic wave signals are preprocessed and the signal-to-noise ratio is determined according to the top pressure acoustic wave signal, and the top pressure acoustic wave signal is dynamically adjusted according to the signal-to-noise ratio, improving the overall quality of the signal, avoiding misjudgment caused by poor signal quality, and improving the reliability of monitoring. Using the acoustic wave recognition model to analyze the suspected acoustic wave data to determine the defective acoustic wave data, avoiding relying on the periodic manual inspection method, intelligently identifying the potential defective acoustic wave data of the six-sided top press, reducing the risk of production interruption caused by the failure of the six-sided top press, dynamically determining the alarm mode and making corresponding adjustments in combination with the environment, being able to detect the defect signs of the six-sided top press in time and effectively respond to the complex and changeable industrial environment, thereby improving the accuracy and reliability of monitoring and providing a reliable guarantee for the stable operation of the six-sided top press.

[0015] On the other hand, the present application also provides a monitoring system for a six-sided top press, which is applied to the above-mentioned monitoring method for a six-sided top press, and includes: An acquisition module, configured to acquire the acoustic wave signals of at least three acoustic wave sensors deployed on the acoustic wave sensing array of the six-sided top press according to the acquisition time period; A processing module, configured to preprocess at least three of the acoustic wave signals to determine the top pressure acoustic wave signal of the six-sided top press, determine the signal-to-noise ratio according to the top pressure acoustic wave signal, and determine whether to adjust the top pressure acoustic wave signal according to the signal-to-noise ratio, and determine the top pressure target acoustic wave signal of the six-sided top press according to the judgment result; An identification module, configured to analyze the top - pressing target acoustic wave signal, determine suspected acoustic wave data, and based on an acoustic wave identification model and the suspected acoustic wave data, determine the defective acoustic wave data of the six - side top press; An alarm module, configured to compare the defective acoustic wave data with a historical defective acoustic wave data set, determine the alarm mode of the six - side top press according to the comparison result, and based on the environment of the six - side top press, determine whether to adjust the alarm mode, and issue an alarm to the six - side top press according to the adjusted alarm mode.

[0016] It can be understood that the above - mentioned monitoring method and system for a six - side top press have the same beneficial effects, which will not be elaborated here. Description of the Drawings

[0017] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 It is a flowchart of a monitoring method for a six - side top press provided by an embodiment of the present invention; Figure 2 It is a functional block diagram of a monitoring system for a six - side top press provided by an embodiment of the present invention. Detailed Embodiments

[0018] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be completely conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. Hereinafter, the present invention will be described in detail with reference to the drawings and in combination with the embodiments.

[0019] In some embodiments of the present application, referring to Figure 1 as shown, a monitoring method for a six - side top press includes: S100: Obtain acoustic wave signals of at least three acoustic wave sensors deployed on the acoustic wave sensing array of the six - side top press according to the acquisition time period.

[0020] S200: Preprocess at least three acoustic signals to determine the top-pressure acoustic signal of the cubic press, determine the signal-to-noise ratio based on the top-pressure acoustic signal, and judge whether to adjust the top-pressure acoustic signal according to the signal-to-noise ratio. Determine the target top-pressure acoustic signal of the cubic press according to the judgment result.

[0021] S300: Analyze the target top-pressure acoustic signal to determine suspected acoustic data, and determine the defective acoustic data of the cubic press based on the acoustic recognition model and the suspected acoustic data.

[0022] S400: Compare the defective acoustic data with the historical defective acoustic data set, determine the alarm mode of the cubic press according to the comparison result, and judge whether to adjust the alarm mode based on the environment of the cubic press. Send an alarm to the cubic press according to the adjusted alarm mode.

[0023] Specifically, deploy an acoustic sensor array on the cubic press. The acoustic sensor array is composed of multiple acoustic sensors arranged in a certain geometric structure. The acoustic sensor array can be set to array structures such as triangular, circular, cross-shaped, etc., which are not specifically limited here. The acoustic signals collected by a single acoustic sensor may not contain the acoustic information generated by the cubic press, while multiple acoustic sensors can complement each other, improving the comprehensiveness and reliability of signal collection. The acquisition time period is determined by the actual application situation of the cubic press and experimental data. For example, assuming that the sampling rate of the acoustic signal is 20 kHz and the length of each frame is 400 points, then 80 ms is the length of 4 frames of acoustic signals. When there are defects or other situations in the cubic press, the length of the acoustic signal generated instantaneously will be approximately 4 - 6 frames. Therefore, the acquisition time period can be set to 120 ms, that is, the length of 6 frames. Preprocess the at least three collected acoustic signals to remove interference factors such as noise in the acoustic signal noise, so as to determine the top-pressure acoustic signal of the cubic press. The signal-to-noise ratio reflects the proportional relationship between the effective component and the noise component in the signal. By measuring the signal-to-noise ratio, judge the quality of the top-pressure acoustic signal, and thus decide whether to adjust the top-pressure acoustic signal to improve the overall quality of the signal. Finally, determine the target top-pressure acoustic signal to avoid misjudgment caused by poor signal quality. Analyze the target top-pressure acoustic signal to identify the suspected acoustic data that may be abnormal. The acoustic recognition model is trained with a large amount of data and can quickly and accurately identify defect features. Substitute the suspected acoustic data into the acoustic recognition model to judge whether the suspected acoustic data belongs to the defective acoustic data, avoiding the method of relying on periodic manual inspections.

[0024] It is understandable that the determined defective acoustic wave data is compared with the historical defective acoustic wave data set, which contains the defective acoustic wave data corresponding to various defects that occurred in the previous six-sided top press. By comparing, the corresponding alarm mode is determined. At the same time, considering the operating environment of the six-sided top press, such as factors like temperature and humidity, it is judged whether the alarm mode needs to be adjusted according to the environmental conditions. Finally, an alarm is issued according to the adjusted alarm mode, so that the alarm can conform to the actual operating conditions of the six-sided top press. By preprocessing the acoustic wave signals collected by multiple acoustic wave sensors and adjusting the signal-to-noise ratio and other operations, the signal quality of the top pressure target acoustic wave signal is improved, making up for the deficiency that the acoustic wave sensors are difficult to meet the requirements of real-time monitoring and early warning, realizing the effective early warning of the six-sided top press, ensuring the stable operation of the six-sided top press, and thus improving the stability of monitoring.

[0025] In some embodiments of the present application, when preprocessing the acoustic wave signal to determine the top pressure acoustic wave signal of the six-sided top press, determining the signal-to-noise ratio according to the top pressure acoustic wave signal, and judging whether to adjust the top pressure acoustic wave signal according to the signal-to-noise ratio, and determining the top pressure target acoustic wave signal of the six-sided top press according to the judgment result, it includes: preprocessing for signal denoising, obtaining the mean square value of the top pressure acoustic wave signal to determine the signal power of the top pressure acoustic wave signal, determining the top pressure acoustic wave signal for shutting down the six-sided top press, and determining the noise power according to the power of the top pressure acoustic wave signal for shutting down the six-sided top press. Based on the signal power and the noise power, the signal-to-noise ratio is determined. The signal-to-noise ratio is compared with the signal-to-noise ratio threshold, and according to the comparison result, it is judged whether to adjust the top pressure acoustic wave signal. When the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, it is determined not to adjust the top pressure acoustic wave signal, and the top pressure acoustic wave signal is determined as the top pressure target acoustic wave signal. When the signal-to-noise ratio is less than or equal to the signal-to-noise ratio threshold, it is determined to adjust the top pressure acoustic wave signal, and the adjusted top pressure acoustic wave signal is determined as the top pressure target acoustic wave signal.

[0026] Specifically, first, the acoustic wave signal is denoised to determine the top pressure acoustic wave signal of the six-sided top press. When denoising the signal, band-pass filtering or wavelet transform is used for denoising. After the signal denoising is completed, the signal-to-noise ratio of the top pressure acoustic wave signal is determined. The signal-to-noise ratio is determined by the following formula:

[0027] Among them, SNR represents the signal-to-noise ratio, P represents the signal power, and P0 represents the noise power. The signal power is calculated by obtaining the mean square value of the top pressure acoustic wave signal. Determining the top pressure acoustic wave signal power when the six-sided top press is turned off and using it as the noise power is because when the six-sided top press stops running, the collected acoustic wave signal is basically the inherent noise of the six-sided top press. Determining the signal-to-noise ratio based on the signal power and the noise power can intuitively reflect the quality of the signal. When the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, it indicates that the proportion of effective components in the signal is high and the quality is good, and no adjustment is required. When the signal-to-noise ratio is less than or equal to the signal-to-noise ratio threshold, it means that the influence of noise is large and the top pressure acoustic wave signal needs to be adjusted. By comparing the signal-to-noise ratio with the pre-set signal-to-noise ratio threshold, the top pressure acoustic wave signal can be dynamically adjusted according to the actual signal quality, so as to achieve an optimized phase compensation under different signal-to-noise ratio conditions. On the one hand, the effective signal is retained, and on the other hand, the interference of noise is further suppressed, thereby improving the signal quality of the top pressure target acoustic wave signal.

[0028] In some embodiments of the present application, when determining to adjust the top pressure acoustic wave signal, it includes: obtaining the Doppler frequency of the top pressure acoustic wave signal, comparing the Doppler frequency with historical data, and determining the adjustment value of the Doppler frequency. The historical data includes several historical Doppler frequencies and several phase compensation values, and each historical Doppler frequency corresponds to a phase compensation value. When there is a historical Doppler frequency in the historical data that is the same as the Doppler frequency, the phase compensation value corresponding to the historical Doppler frequency is determined as the adjustment value of the Doppler frequency. When there is no historical Doppler frequency in the historical data that is the same as the Doppler frequency, the similarity between the Doppler frequency and each historical Doppler frequency is obtained, and the phase compensation value corresponding to the historical Doppler frequency with the maximum similarity is determined as the adjustment value of the Doppler frequency.

[0029] Specifically, the Doppler frequency reflects the frequency change of the acoustic wave signal caused by relative motion during propagation. The historical data contains the corresponding relationships between several historical Doppler frequencies and phase compensation values, which are obtained based on the analysis and summary of the operation data of the six-sided top press. When there is a historical Doppler frequency in the historical data that is the same as the current Doppler frequency, the corresponding phase compensation value is directly determined as the adjustment value. Determining the phase compensation value based on past historical experience can directly adapt to the current situation, thus achieving rapid adjustment. If there is a historical Doppler frequency in the historical data that is the same as the Doppler frequency, the average value of the phase compensation values corresponding to each historical Doppler frequency can be directly used as the adjustment value. When there is no identical Doppler frequency in the historical data, the similarity between the Doppler frequency and each historical Doppler frequency is calculated. The similarity can be determined using the Euclidean distance or cosine similarity to quantify the "similarity degree" between Doppler frequencies. The phase compensation value corresponding to the historical Doppler frequency with the maximum similarity is selected as the adjustment value. This is because similar Doppler frequencies mean that the six-sided top press is in a similar operating state. Through a data-driven approach, subjective speculation is avoided, and the signal quality of the top-pressure target acoustic wave signal is improved, laying a foundation for subsequent defect analysis.

[0030] In some embodiments of the present application, when analyzing the top-pressure target acoustic wave signal to determine suspected acoustic wave data, it includes: analyzing the top-pressure target acoustic wave signal in the acquisition time period to determine the time-domain value of the top-pressure target acoustic wave signal, and judging whether the top-pressure target acoustic wave signal is suspected acoustic wave data according to the time-domain value.

[0031] In some embodiments of the present application, when judging whether the top-pressure target acoustic wave signal is suspected acoustic wave data according to the time-domain value and frequency-domain value, it includes: obtaining the maximum time-domain value and the minimum time-domain value of the top-pressure target acoustic wave signal. When the maximum time-domain value is greater than the maximum time-domain threshold and the minimum time-domain value is less than the minimum time-domain threshold, it is determined that the top-pressure target acoustic wave signal is suspected acoustic wave data; otherwise, it is determined that the top-pressure target acoustic wave signal is not suspected acoustic wave data.

[0032] Specifically, the time-domain value refers to the characteristic parameter of the signal in the time domain. The time-domain characteristics of the top-pressure target acoustic signal directly reflect the instantaneous characteristics of the signal. When there are defects in the six-sided top press, the generated top-pressure target acoustic signal often exhibits sudden change characteristics in the time domain, such as a sudden increase or decrease in amplitude. By obtaining the time-domain maximum value and the time-domain minimum value of the top-pressure target acoustic signal and comparing them with the time-domain maximum threshold and the time-domain minimum threshold, these abnormal characteristics can be quickly identified. The time-domain maximum threshold and the time-domain minimum threshold are determined based on the characteristics of the top-pressure target acoustic signal when the six-sided top press is operating normally. When the top-pressure target acoustic signal is not suspected acoustic data, it indicates that the six-sided top press is in a normal working state and there is no need to determine the alarm mode. When the time-domain maximum value is greater than the time-domain maximum threshold and, at the same time, the time-domain minimum value is less than the time-domain minimum threshold, it indicates that there are certain fluctuations and abnormal changes in the top-pressure target acoustic signal. This change is likely related to the defects or faults of the six-sided top press. For example, the loosening of the internal structure of the six-sided top press may cause the amplitude of the top-pressure target acoustic signal to increase rapidly within a short period of time, exceeding the normal range, which can provide data screening for subsequent in-depth analysis based on the acoustic recognition model, thereby reducing the amount of redundant data processed by the subsequent model and improving the monitoring efficiency.

[0033] In some embodiments of the present application, when determining the defective acoustic data of the six-sided top press based on the acoustic recognition model and the suspected acoustic data, it includes: obtaining an acoustic data set and sampling it according to a sampling ratio to obtain a training set and a test set, obtaining a decision tree model, training the decision tree model according to the training set, evaluating the trained decision tree model according to the test set. If the evaluation value of the currently trained decision tree model is greater than or equal to the evaluation value of the previously trained decision tree model, then stop training and determine the currently trained decision tree model as the acoustic recognition model. Otherwise, use grid search to find the model parameters of the decision tree model and continue to train the decision tree model according to the model parameters until it is greater than or equal to the evaluation value of the previously trained decision tree model, and substitute the suspected acoustic data into the acoustic recognition model to determine the defective acoustic data.

[0034] Specifically, the acoustic wave dataset includes the defect acoustic wave data corresponding to various defects that occurred in the previous cubic press, such as peak index, pulse index, margin index, skewness index, and kurtosis index in the time domain. The acoustic wave dataset is sampled according to a sampling ratio to obtain a training set and a test set. The sampling ratio is usually 7:3 and can be adjusted according to the data volume in the acoustic wave dataset. The training set is used to train the decision tree model, and the test set is used to evaluate the performance of the trained model. The decision tree model is selected as the initial model, which contains internal nodes, branches, and leaf nodes and aims to capture complex relationships in the data. The data in the training set is used to train the decision tree model. In each training, the model tries to learn the patterns and relationships in the data to improve its prediction or classification ability. After each training, the data in the test set is used to evaluate the model to determine the evaluation value. The evaluation indicators include accuracy, loss function value, recall rate, etc., which are used to measure the performance of the model.

[0035] It can be understood that if the evaluation value of the currently trained decision tree model is greater than or equal to the evaluation value of the decision tree model after the previous training, it indicates that the model performance has improved or remained stable. At this time, the training can be stopped, and it is considered that the model has reached a satisfactory performance level. Otherwise, it indicates that the model performance has declined. Grid search is used to find the model parameters (hyperparameters) of the decision tree model. Grid search exhaustively searches for model parameters in the parameter space. The determined model parameters are used to adjust the currently trained decision tree model, and then the training continues, which helps the model approach the global optimal solution more stably. Finally, an acoustic wave recognition model that can identify defect acoustic wave data is determined, thus ensuring the stability and reliability of the monitoring.

[0036] In some embodiments of the present application, when comparing the defect acoustic wave data with the historical defect acoustic wave dataset and determining the alarm mode of the cubic press according to the comparison result, it includes: when there is data in the historical defect acoustic wave dataset that is the same as the defect acoustic wave data, the defect acoustic wave data is added to the historical defect acoustic wave dataset, and the alarm mode of the cubic press is determined according to the occurrence times of the data; when there is no data in the historical defect acoustic wave dataset that is the same as the defect acoustic wave data, the defect acoustic wave data is added to the historical defect acoustic wave dataset and an alarm is issued to remind for manual verification.

[0037] It can be understood that by comparing with the historical defect acoustic wave dataset, abnormal situations that may exist can be quickly identified, reducing the response time to common defect states. By analyzing the occurrence times of defect acoustic wave data, possible persistent problems or periodic faults can be identified, thereby triggering an alarm mode and improving the monitoring efficiency of the six-sided top press. For new defect acoustic wave data that has not been recorded, an alarm is immediately triggered to ensure that potential problems of the six-sided top press receive timely attention and handling. At the same time, the new defect acoustic wave data is added to the historical defect acoustic wave dataset. The data-driven alarm mechanism ensures the working state of the six-sided top press. When new defect acoustic wave data is detected, an alarm is immediately issued and a prompt for manual verification is given to ensure that each new defect acoustic wave data can be carefully checked, enabling relevant personnel to capture new changes in the six-sided top press during operation and avoiding relying on periodic manual inspection methods, thus ensuring the monitoring efficiency and reliability.

[0038] In some embodiments of the present application, when determining the alarm mode of the six-sided top press according to the occurrence times of data, it includes: presetting a first preset data occurrence time and a second preset data occurrence time, where the first preset data occurrence time is greater than the second preset data occurrence time. When the data occurrence time is greater than or equal to the first preset data occurrence time, the alarm mode is determined as a first-level early warning. When the data occurrence time is less than the first preset data occurrence time and greater than the second preset data occurrence time, the alarm mode is determined as a second-level early warning. When the data occurrence time is less than or equal to the second preset data occurrence time, the alarm mode is determined as a third-level early warning. The urgency of the first-level early warning, second-level early warning, and third-level early warning decreases in sequence.

[0039] In some embodiments of the present application, when determining whether to adjust the alarm mode based on the environment of the six-sided top press, it includes: obtaining the environmental parameters of the six-sided top press and determining the standard environmental parameters of the six-sided top press, counting the number of environmental parameters whose environmental parameters are not equal to the standard environmental parameters. When the number of environmental parameters is greater than or equal to the environmental parameter quantity threshold, the alarm mode is upgraded by one level. When the number of environmental parameters is less than the environmental parameter quantity threshold, the alarm mode is downgraded by one level.

[0040] Specifically, the occurrence times of the first preset data are preferably 10 times, and the occurrence times of the second preset data are preferably 5 times. The alarm mode is divided into three levels. When the occurrence times of the data are greater than or equal to the occurrence times of the first preset data, it indicates that there are persistent problems or periodic faults in the six-sided top press, triggering the highest-level first-level warning. When the occurrence times of the data are less than the occurrence times of the first preset data and greater than the occurrence times of the second preset data, it indicates that there are certain persistent problems or periodic faults in the six-sided top press, which need attention, and then the intermediate-level second-level warning is triggered. When the occurrence times of the data are less than or equal to the occurrence times of the second preset data, it indicates that there are fewer persistent problems or periodic faults in the six-sided top press, and the alarm mode is determined as the third-level warning. Dynamically determining the alarm mode according to the occurrence times of the data avoids waste of monitoring resources. Obtain the environmental parameters of the six-sided top press and compare them with the standard environmental parameters. The environmental parameters represent parameters such as temperature, humidity, air pressure, and dust, and the standard environmental parameters are determined by the actual usage instructions of the six-sided top press. Further optimize the alarm mode according to the number of statistical environmental parameters. The more the number of environmental parameters, the greater the difference between the current environmental situation of the six-sided top press and the standard, which will increase the risk of defects in the six-sided top press. At this time, the alarm mode is upgraded by one level to ensure that potential faults are not missed in a complex environment. The threshold of the number of environmental parameters is preferably 3. If the alarm mode is already the first-level warning, then continue to maintain the first-level warning. On the contrary, when the number of environmental parameters is less, it indicates that the environmental parameters are basically within the normal range, and the alarm level is appropriately reduced. If the alarm mode is already the third-level warning, then continue to maintain the third-level warning. Combining the number of environmental parameters and the occurrence times of the data can not only detect the defect signs of the six-sided top press in time, but also effectively cope with the complex and changeable industrial environment, thus improving the accuracy and reliability of monitoring and providing a reliable guarantee for the stable operation of the six-sided top press.

[0041] In summary, the beneficial effects of the present invention are as follows: By collecting the acoustic signals of at least three acoustic sensors through the acoustic sensing array, the comprehensiveness of signal collection is improved. At the same time, the collected acoustic signals are preprocessed and the signal-to-noise ratio is determined according to the top pressure acoustic signal, and the top pressure acoustic signal is dynamically adjusted according to the signal-to-noise ratio, improving the overall quality of the signal and avoiding misjudgment caused by poor signal quality, and improving the reliability of monitoring. Using the acoustic recognition model to analyze the suspected acoustic data to determine the defective acoustic data, avoiding relying on periodic manual inspection methods, intelligently identifying the potential defective acoustic data of the six-sided top press, reducing the risk of production interruption caused by the failure of the six-sided top press, dynamically determining the alarm mode and making corresponding adjustments in combination with the environment, which can not only detect the defect signs of the six-sided top press in time, but also effectively cope with the complex and changeable industrial environment, thus improving the accuracy and reliability of monitoring and providing a reliable guarantee for the stable operation of the six-sided top press.

[0042] In another preferred embodiment based on the above embodiments, refer to Figure 2 As shown, this embodiment provides a monitoring system for a six-sided top press, which is used to apply the above-mentioned monitoring method for a six-sided top press, including: An acquisition module, configured to acquire acoustic wave signals of at least three acoustic wave sensors deployed on the acoustic wave sensor array of the six-sided top press according to an acquisition time period; A processing module, configured to preprocess at least three acoustic wave signals to determine the top pressure acoustic wave signal of the six-sided top press, determine the signal-to-noise ratio according to the top pressure acoustic wave signal, and determine whether to adjust the top pressure acoustic wave signal according to the signal-to-noise ratio, and determine the top pressure target acoustic wave signal of the six-sided top press according to the judgment result; An identification module, configured to analyze the top pressure target acoustic wave signal to determine suspected acoustic wave data, and determine the defective acoustic wave data of the six-sided top press based on the acoustic wave identification model and the suspected acoustic wave data; An alarm module, configured to compare the defective acoustic wave data with the historical defective acoustic wave data set, determine the alarm mode of the six-sided top press according to the comparison result, and determine whether to adjust the alarm mode based on the environment of the six-sided top press, and issue an alarm to the six-sided top press according to the adjusted alarm mode.

[0043] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0044] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in one Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0045] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the processes Figure 1 one or more processes and / or blocks Figure 1 specified in the block or blocks.

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes Figure 1 one or more processes and / or blocks Figure 1 specified in the block or blocks.

[0047] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the specific embodiments of the present invention can still be modified or equivalently replaced, and any modification or equivalent replacement without departing from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A monitoring method for a six-sided top press, characterized in that, Including: Obtain the acoustic signals of at least three acoustic sensors deployed on the acoustic sensing array of the six-sided top press according to the acquisition time period; Preprocess at least three of the acoustic signals to determine the top-pressure acoustic signal of the six-sided top press, determine the signal-to-noise ratio according to the top-pressure acoustic signal, and judge whether to adjust the top-pressure acoustic signal according to the signal-to-noise ratio. Determine the top-pressure target acoustic signal of the six-sided top press according to the judgment result; Analyze the top-pressure target acoustic signal to determine suspected acoustic data, and determine the defective acoustic data of the six-sided top press based on the acoustic recognition model and the suspected acoustic data; Compare the defective acoustic data with the historical defective acoustic data set, determine the alarm mode of the six-sided top press according to the comparison result, and judge whether to adjust the alarm mode based on the environment of the six-sided top press. Alarm the six-sided top press according to the adjusted alarm mode.

2. The monitoring method for a six-sided top press according to claim 1, characterized in that, When preprocessing the acoustic signal to determine the top-pressure acoustic signal of the six-sided top press, determining the signal-to-noise ratio according to the top-pressure acoustic signal, and judging whether to adjust the top-pressure acoustic signal according to the signal-to-noise ratio, and determining the top-pressure target acoustic signal of the six-sided top press according to the judgment result, it includes: The preprocessing is signal denoising; Obtain the mean square value of the top-pressure acoustic signal to determine the signal power of the top-pressure acoustic signal, determine the top-pressure acoustic signal for turning off the six-sided top press, and determine the noise power according to the power of the top-pressure acoustic signal for turning off the six-sided top press; Determine the signal-to-noise ratio based on the signal power and the noise power; Compare the signal-to-noise ratio with the signal-to-noise ratio threshold, and judge whether to adjust the top-pressure acoustic signal according to the comparison result; When the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, it is determined that the top-pressure acoustic signal is not adjusted, and the top-pressure acoustic signal is determined as the top-pressure target acoustic signal; When the signal-to-noise ratio is less than or equal to the signal-to-noise ratio threshold, it is determined that the top-pressure acoustic signal is adjusted, and the adjusted top-pressure acoustic signal is determined as the top-pressure target acoustic signal.

3. The monitoring method for a six-sided top press according to claim 2, characterized in that, When it is determined that the top-pressure acoustic signal is adjusted, it includes: Obtain the Doppler frequency of the top-pressure acoustic signal, and compare the Doppler frequency with historical data to determine the adjustment value of the Doppler frequency; The historical data includes a plurality of historical Doppler frequencies and a plurality of phase compensation values, and each historical Doppler frequency corresponds to a phase compensation value; When there is a historical Doppler frequency in the historical data that is the same as the Doppler frequency, the phase compensation value corresponding to the historical Doppler frequency is determined as the adjustment value of the Doppler frequency; When there is no historical Doppler frequency in the historical data that is the same as the Doppler frequency, obtain the similarity between the Doppler frequency and each historical Doppler frequency, and determine the phase compensation value of the historical Doppler frequency corresponding to the maximum similarity as the adjustment value of the Doppler frequency.

4. The monitoring method for a six-sided press according to claim 3, characterized in that When analyzing the top-pressure target acoustic signal to determine suspected acoustic data, it includes: Analyze the top pressure target acoustic wave signal in the acquisition time period to determine the time domain value of the top pressure target acoustic wave signal, and judge whether the top pressure target acoustic wave signal is the suspected acoustic wave data according to the time domain value.

5. The monitoring method for a six-sided top press according to claim 4, characterized in that, When judging whether the top pressure target acoustic wave signal is the suspected acoustic wave data according to the time domain value and the frequency domain value, it includes: Obtain the maximum time domain value and the minimum time domain value of the top pressure target acoustic wave signal; When the maximum time domain value is greater than the maximum time domain threshold and the minimum time domain value is less than the minimum time domain threshold, determine that the top pressure target acoustic wave signal is the suspected acoustic wave data, otherwise, determine that the top pressure target acoustic wave signal is not the suspected acoustic wave data.

6. The monitoring method for a six-sided press according to claim 5, characterized in that, When determining the defective acoustic wave data of the six-sided top press based on the acoustic wave recognition model and the suspected acoustic wave data, it includes: Obtain the acoustic wave data set and sample it according to the sampling ratio to obtain the training set and the test set; Obtain the decision tree model, train the decision tree model according to the training set, and evaluate the trained decision tree model according to the test set; If the evaluation value of the currently trained decision tree model is greater than or equal to the evaluation value of the previously trained decision tree model, stop training and determine the currently trained decision tree model as the acoustic wave recognition model, otherwise, use grid search to find the model parameters of the decision tree model and continue to train the decision tree model according to the model parameters until it is greater than or equal to the evaluation value of the previously trained decision tree model; Substitute the suspected acoustic wave data into the acoustic wave recognition model to determine the defective acoustic wave data.

7. The monitoring method for a six-side top press according to claim 6, wherein When comparing the defective acoustic wave data with the historical defective acoustic wave data set and determining the alarm mode of the six-sided top press according to the comparison result, it includes: When there is data in the historical defective acoustic wave data set that is the same as the defective acoustic wave data, add the defective acoustic wave data to the historical defective acoustic wave data set, and determine the alarm mode of the six-sided top press according to the number of times the data appears; When there is no data in the historical defective acoustic wave data set that is the same as the defective acoustic wave data, add the defective acoustic wave data to the historical defective acoustic wave data set and give an alarm to remind for manual verification.

8. The monitoring method for a six-sided press according to claim 7, characterized in that When determining the alarm mode of the six-sided top press according to the number of times the data appears, it includes: Preset the first preset number of times the data appears and the second preset number of times the data appears, and the first preset number of times the data appears is greater than the second preset number of times the data appears; When the number of times the data appears is greater than or equal to the first preset number of times the data appears, determine the alarm mode as a first-level warning; When the number of times the data appears is less than the first preset number of times the data appears and greater than the second preset number of times the data appears, determine the alarm mode as a second-level warning; When the number of times the data appears is less than or equal to the second preset number of times the data appears, determine the alarm mode as a third-level warning; The emergency levels of the first-level warning, the second-level warning, and the third-level warning decrease in turn.

9. The monitoring method for a six-sided press according to claim 8, characterized in that, When judging whether to adjust the alarm mode based on the environment of the six-sided top press, it includes: Obtain the environmental parameters of the six-sided top press and determine the standard environmental parameters of the six-sided top press; Count the number of environmental parameters whose environmental parameters are not equal to the standard environmental parameters; When the number of environmental parameters is greater than or equal to the environmental parameter quantity threshold, raise the alarm mode by one level; When the number of environmental parameters is less than the environmental parameter quantity threshold, lower the alarm mode by one level.

10. A monitoring system for a six-sided top press, which is used to apply the monitoring method for a six-sided top press according to any one of claims 1-9, characterized in that, Including: An acquisition module configured to obtain acoustic signals of at least three acoustic sensors deployed on an acoustic sensing array of a six-sided top press according to an acquisition time period; A processing module configured to preprocess at least three of the acoustic signals to determine the top pressure acoustic signal of the six-sided top press, determine the signal-to-noise ratio according to the top pressure acoustic signal, and determine whether to adjust the top pressure acoustic signal according to the signal-to-noise ratio, and determine the top pressure target acoustic signal of the six-sided top press according to the judgment result; An identification module configured to analyze the top pressure target acoustic signal to determine suspected acoustic data, and determine the defective acoustic data of the six-sided top press based on an acoustic identification model and the suspected acoustic data; An alarm module configured to compare the defective acoustic data with a historical defective acoustic data set, determine the alarm mode of the six-sided top press according to the comparison result, and determine whether to adjust the alarm mode based on the environment of the six-sided top press, and issue an alarm to the six-sided top press according to the adjusted alarm mode.

Images