A monitoring method and system for six-sided top press

Abstract

The present invention relates to the technical field of engineering equipment monitoring, and discloses a monitoring method and system for a six-sided top press. The method comprises: acquiring acoustic wave signals of at least three acoustic wave sensors deployed on an acoustic wave sensor array of the six-sided top press according to a collection time period, preprocessing the at least three acoustic wave signals to determine a top pressure acoustic wave signal of the six-sided top press, judging whether to adjust the top pressure acoustic wave signal according to a signal-to-noise ratio, analyzing the top pressure target acoustic wave signal to determine suspected acoustic wave data, determining defect acoustic wave data of the six-sided top press based on an acoustic wave recognition model and the suspected acoustic wave data, comparing the defect acoustic wave data with a historical defect acoustic wave data set, determining an 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. The present invention ensures the reliability of monitoring by adjusting the top pressure acoustic wave signal.

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 science and technology, the demand for diamonds has posed a severe challenge. The six-sided top press is the main equipment used in the production of superhard materials such as diamond. Its stable operation directly affects production efficiency and diamond quality. Currently, the monitoring of the six-sided top press mainly relies on periodic manual inspections. The manual inspection intervals are long, making it difficult to timely capture changes in the six-sided top press during operation. Secondly, when using acoustic wave sensors to monitor the six-sided top press, due to the strict requirements on the quality, stability, and integrity of the monitoring signal, the acoustic wave sensors cannot meet the needs of real-time monitoring and early warning, and cannot achieve effective early warning of 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 problem that the monitoring of the six-sided top press mainly relies on periodic manual inspection, the time interval of manual inspection is long, and it is difficult to capture the changes in the operation of the six-sided top press in time, and the acoustic wave sensor is difficult to meet the needs of real-time monitoring and early warning, and it is impossible to achieve effective early warning of the equipment.

[0005] In one aspect, the present invention provides a monitoring method for a six-sided top press, comprising:

[0006] Acquire acoustic wave signals from at least three acoustic wave sensors deployed on an acoustic wave sensor array of a six-sided top press according to a collection time period;

[0007] pre-processing at least three of the acoustic wave signals to determine a top pressure acoustic wave signal of the six-sided top press, determining a signal-to-noise ratio based on the top pressure acoustic wave signal, determining whether to adjust the top pressure acoustic wave signal based on the signal-to-noise ratio, and determining a top pressure target acoustic wave signal of the six-sided top press based on the determination result;

[0008] Analyzing the target acoustic wave signal of the top pressing machine to determine suspected acoustic wave data, and determining defect acoustic wave data of the six-sided top pressing machine based on an acoustic wave recognition model and the suspected acoustic wave data;

[0009] The defect acoustic wave data is compared with a historical defect acoustic wave data set, and an alarm mode of the six-sided top press is determined based on the comparison result. Based on the environment of the six-sided top press, it is determined whether to adjust the alarm mode, and an alarm is issued to the six-sided top press according to the adjusted alarm mode.

[0010] Further, the acoustic wave signal is pre-processed to determine the top pressure acoustic wave signal of the six-sided top press, a signal-to-noise ratio is determined based on the top pressure acoustic wave signal, and whether to adjust the top pressure acoustic wave signal is determined based on the signal-to-noise ratio, and the top pressure target acoustic wave signal of the six-sided top press is determined based on the judgment result, including:

[0011] The preprocessing is signal denoising;

[0012] Obtaining a square mean of the top pressure acoustic wave signal to determine a signal power of the top pressure acoustic wave signal, determining a top pressure acoustic wave signal for shutting down the six-sided top press, and determining a noise power based on the power of the top pressure acoustic wave signal for shutting down the six-sided top press;

[0013] determining the signal-to-noise ratio based on the signal power and the noise power;

[0014] Comparing the signal-to-noise ratio with a signal-to-noise ratio threshold, and determining whether to adjust the top pressure acoustic wave signal according to the comparison result;

[0015] When the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, determining that no adjustment is made to the top pressure acoustic wave signal, and determining the top pressure acoustic wave signal as the top pressure target acoustic wave signal;

[0016] 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 sound wave signal is to be adjusted, and the adjusted top pressure sound wave signal is determined as the top pressure target sound wave signal.

[0017] Furthermore, when determining to adjust the top pressure sound wave signal, it includes:

[0018] Acquiring the Doppler frequency of the top pressure acoustic wave signal, and comparing the Doppler frequency with historical data to determine an adjustment value of the Doppler frequency;

[0019] The historical data includes a plurality of historical Pulser frequencies and a plurality of phase compensation values, and each historical Pulser frequency corresponds to a phase compensation value;

[0020] When there is a historical Doppler frequency identical to the Doppler frequency in the historical data, determining the phase compensation value corresponding to the historical Doppler frequency as the adjustment value of the Doppler frequency;

[0021] When there is no historical Doppler frequency identical to the Doppler frequency in the historical data, similarity between the Doppler frequency and each historical Doppler frequency is obtained, and a phase compensation value corresponding to the historical Doppler frequency with the maximum similarity is determined as the adjustment value of the Doppler frequency.

[0022] Furthermore, when analyzing the pressure target acoustic wave signal to determine the suspected acoustic wave data, the following steps are included:

[0023] The top pressure target acoustic wave signal in the acquisition time period is analyzed to determine a time domain value of the top pressure target acoustic wave signal, and whether the top pressure target acoustic wave signal is the suspected acoustic wave data is determined according to the time domain value.

[0024] Furthermore, when judging whether the top pressure target sound wave signal is the suspected sound wave data according to the time domain value and the frequency domain value, the method includes:

[0025] Obtaining a time domain maximum value and a time domain minimum value of the top pressure target acoustic wave signal;

[0026] 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, the top pressure target sound wave signal is determined to be the suspected sound wave data; otherwise, the top pressure target sound wave signal is determined not to be the suspected sound wave data.

[0027] Furthermore, 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, the method includes:

[0028] Obtain the sound wave dataset and sample it according to the sampling ratio to obtain the training set and test set;

[0029] Obtaining a decision tree model, training the decision tree model according to the training set, and evaluating the trained decision tree model according to the test set;

[0030] 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, the training is stopped, and the currently trained decision tree model is determined as the acoustic wave recognition model; otherwise, a grid search is used to find the model parameters of the decision tree model, and the decision tree model is continued to be trained according to the model parameters until the evaluation value is greater than or equal to the evaluation value of the previously trained decision tree model;

[0031] The suspected sound wave data is substituted into the sound wave recognition model to determine the defect sound wave data.

[0032] Furthermore, when comparing the defect acoustic wave data with a historical defect acoustic wave data set and determining the alarm mode of the six-sided top press according to the comparison result, the method includes:

[0033] When data identical to the defect acoustic wave data exists in the historical defect acoustic wave data set, the defect acoustic wave data is added to the historical defect acoustic wave data set, and the alarm mode of the six-sided top press is determined according to the number of occurrences of the data;

[0034] When the historical defect acoustic wave data set does not contain data identical to the defect acoustic wave data, the defect acoustic wave data is added to the historical defect acoustic wave data set and an alarm is issued to prompt manual verification.

[0035] Furthermore, when determining the alarm mode of the six-sided top press according to the number of occurrences of the data, it includes:

[0036] Preset a first preset number of occurrences of data and a second preset number of occurrences of data, wherein the first preset number of occurrences of data is greater than the second preset number of occurrences of data;

[0037] When the number of occurrences of the data is greater than or equal to the first preset number of occurrences of the data, the alarm mode is determined to be a first-level warning;

[0038] When the number of occurrences of the data is less than the first preset number of occurrences of the data and greater than the second preset number of occurrences of the data, the alarm mode is determined to be a level 2 warning;

[0039] When the number of occurrences of the data is less than or equal to the second preset number of occurrences of the data, the alarm mode is determined to be a level three warning;

[0040] The urgency of the first-level warning, second-level warning and third-level warning decreases in sequence.

[0041] Furthermore, when determining whether to adjust the alarm mode based on the environment of the six-sided top press, the method includes:

[0042] Acquiring environmental parameters of the six-sided top press and determining standard environmental parameters of the six-sided top press;

[0043] Counting the number of environmental parameters that are not equal to standard environmental parameters;

[0044] When the number of environmental parameters is greater than or equal to the environmental parameter number threshold, the alarm mode is raised by one level;

[0045] When the number of environmental parameters is less than the environmental parameter number threshold, the alarm mode is reduced by one level.

[0046] 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 sensor 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; the top pressure acoustic wave signal is dynamically adjusted according to the signal-to-noise ratio, thereby improving the overall quality of the signal, avoiding misjudgment due to poor signal quality, and improving the reliability of monitoring. The acoustic wave recognition model is used to analyze the suspected acoustic wave data and determine the defective acoustic wave data, thereby avoiding reliance on periodic manual inspection methods, 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 based on the environment, which can not only timely detect the signs of defects of the six-sided top press, but also effectively cope with 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.

[0047] 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, comprising:

[0048] an acquisition module configured to acquire acoustic wave signals from at least three acoustic wave sensors deployed on an acoustic wave sensor array of a six-sided top press according to an acquisition time period;

[0049] a processing module configured to pre-process at least three of the acoustic wave signals to determine a top pressure acoustic wave signal of the six-sided top press, determine a signal-to-noise ratio based on the top pressure acoustic wave signal, determine whether to adjust the top pressure acoustic wave signal based on the signal-to-noise ratio, and determine a top pressure target acoustic wave signal of the six-sided top press based on the determination result;

[0050] an identification module configured to analyze the target acoustic wave signal of the top pressing machine to determine suspected acoustic wave data, and determine defect acoustic wave data of the six-sided top pressing machine based on an acoustic wave identification model and the suspected acoustic wave data;

[0051] The alarm module is configured to compare the defect acoustic wave data with a historical defect acoustic wave data set, determine an 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, and issue an alarm to the six-sided top press according to the adjusted alarm mode.

[0052] It is understandable that the above-mentioned monitoring method and system for a six-sided top press have the same beneficial effects, which will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0054] Figure 1 A flow chart of a monitoring method for a six-sided top press provided in an embodiment of the present invention;

[0055] Figure 2 This is a functional block diagram of a monitoring system for a six-sided top press provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying 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 to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0057] In some embodiments of the present application, see Figure 1 As shown, a monitoring method for a six-sided top press includes:

[0058] S100: Acquire acoustic wave signals of at least three acoustic wave sensors deployed on an acoustic wave sensor array of a six-sided top press according to a collection time period.

[0059] S200: Preprocessing at least three acoustic wave signals to determine a top pressure acoustic wave signal of the six-sided top press, determining a signal-to-noise ratio based on the top pressure acoustic wave signal, and judging whether to adjust the top pressure acoustic wave signal based on the signal-to-noise ratio, and determining a top pressure target acoustic wave signal of the six-sided top press based on the judgment result.

[0060] S300: Analyze the target acoustic wave signal of the top pressing machine to determine suspected acoustic wave data, and determine defect acoustic wave data of the six-sided top pressing machine based on the acoustic wave recognition model and the suspected acoustic wave data.

[0061] S400: Compare the defect acoustic wave data with the historical defect acoustic wave 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, and issue an alarm to the six-sided top press according to the adjusted alarm mode.

[0062] Specifically, an acoustic sensor array is deployed on the six-sided top press. The acoustic sensor array consists of multiple acoustic sensors arranged in a specific geometric configuration. The acoustic sensor array can be configured in triangular, circular, or cross configurations, without specific limitations. The acoustic signal collected by a single acoustic sensor may not contain the acoustic information generated by the six-sided top press. However, multiple acoustic sensors can complement each other, improving the comprehensiveness and reliability of signal acquisition. The acquisition period is determined by the actual application of the six-sided top press and experimental data. For example, assuming a 20kHz acoustic signal sampling rate and 400 points per frame, 80ms represents the duration of four acoustic signal frames. When a six-sided top press experiences a defect, the instantaneous acoustic signal lasts approximately four to six frames, so the acquisition period can be set to 120ms, or six frames. At least three collected acoustic signals are preprocessed to remove noise and other interfering factors, thereby determining the acoustic signal of the six-sided top press. The signal-to-noise ratio reflects the ratio of the effective component to the noise component in the signal. By measuring the signal-to-noise ratio, the quality of the top pressure acoustic wave signal is judged, thereby deciding whether to adjust the top pressure acoustic wave signal to improve the overall quality of the signal. Finally, the top pressure target acoustic wave signal is determined to avoid misjudgment due to poor signal quality. The top pressure target acoustic wave signal is analyzed to identify suspected acoustic wave data that may contain abnormalities. The acoustic wave recognition model has been trained with a large amount of data and can quickly and accurately identify defect features. The suspected acoustic wave data is substituted into the acoustic wave recognition model to determine whether the suspected acoustic wave data is defective acoustic wave data, avoiding reliance on periodic manual inspections.

[0063] It is understandable that the determined defect acoustic wave data is compared with the historical defect acoustic wave data set, which contains the defect acoustic wave data corresponding to various defects in the six-sided top press in the past. The corresponding alarm mode is determined by comparison. At the same time, the operating environment of the six-sided top press, such as temperature and humidity, is taken into consideration. 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 fit the actual operating conditions of the six-sided top press. By preprocessing the acoustic wave signals collected by multiple acoustic wave sensors, adjusting the signal-to-noise ratio and other operations, the signal quality of the top pressure target acoustic wave signal is improved, which makes up for the deficiency of the acoustic wave sensor in meeting the real-time monitoring and early warning needs, realizes the effective early warning of the six-sided top press, ensures the stable operation of the six-sided top press, and thus improves the stability of monitoring.

[0064] In some embodiments of the present application, the acoustic wave signal is preprocessed to determine the top pressure acoustic wave signal of the six-sided top press, the signal-to-noise ratio is determined according to the top pressure acoustic wave signal, and it is judged whether to adjust the top pressure acoustic wave signal according to the signal-to-noise ratio, and the top pressure target acoustic wave signal of the six-sided top press is determined according to the judgment result, including: preprocessing for signal denoising, obtaining the square mean 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 of closing the six-sided top press, and closing the top pressure acoustic wave of the six-sided top press according to the top pressure acoustic wave signal of the six-sided top press. The power of the signal is determined, the noise power is determined, the signal-to-noise ratio is determined based on the signal power and the noise power, the signal-to-noise ratio is compared with the signal-to-noise ratio threshold, and whether to adjust the top pressure sound wave signal is determined 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 sound wave signal is not adjusted, and the top pressure sound wave signal is determined as the top pressure target sound 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 sound wave signal is adjusted, and the adjusted top pressure sound wave signal is determined as the top pressure target sound wave signal.

[0065] Specifically, the acoustic wave signal is first denoised to determine the top pressure acoustic wave signal of the six-sided top press. When performing signal denoising, bandpass filtering or wavelet transformation 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 using the following formula:

[0066]

[0067] Where SNR represents the signal-to-noise ratio, P represents the signal power, and P0 represents the noise power. The signal power is calculated by taking the square mean of the top pressure acoustic wave signal. The top pressure acoustic wave signal power when the six-sided top press is shut down is determined and used as the noise power because when the six-sided top press stops operating, the sound wave signal collected is basically the inherent noise of the six-sided top press. Determining the signal-to-noise ratio based on the signal power and noise power can intuitively reflect the signal quality. When the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, it indicates that the signal has a high proportion of effective components and good quality, and no adjustment is required. When the signal-to-noise ratio is less than or equal to the signal-to-noise ratio threshold, it indicates that the noise influence is significant 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, thereby achieving 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.

[0068] In some embodiments of the present application, when determining whether to adjust the top pressure sound wave signal, it includes: obtaining the Doppler frequency of the top pressure sound wave signal, and comparing 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, each historical Doppler frequency corresponds to a phase compensation value, when there is a historical Doppler frequency that is the same as the Doppler frequency in the historical data, 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 that is the same as the Doppler frequency in the historical data, 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.

[0069] Specifically, the Doppler frequency reflects the frequency change of the sound wave signal caused by the relative motion during the propagation process. The historical data contains the correspondence between several historical Doppler frequencies and phase compensation values, which is based on the analysis and summary of the operating data of the six-sided top press. When there is a historical Doppler frequency that is the same as the current Doppler frequency in the historical data, the corresponding phase compensation value is directly determined as the adjustment value. The phase compensation value determined based on past historical experience can be directly adapted to the current situation, thereby achieving rapid adjustment. If there is a historical Doppler frequency that is the same as the Doppler frequency in the historical data, the average of the phase compensation values ​​corresponding to each historical Doppler frequency can be directly used as the adjustment value. When the same Doppler frequency does not exist in the historical data, the similarity between the Doppler frequency and each historical Doppler frequency is calculated. The similarity can be determined using Euclidean distance or cosine similarity to quantify the "similarity" between the Doppler frequencies. The phase compensation value of the historical Doppler frequency corresponding to 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 data-driven methods, subjective conjecture is avoided, the signal quality of the top press target acoustic wave signal is improved, and the foundation is laid for subsequent defect analysis.

[0070] In some embodiments of the present application, when analyzing the top pressure target acoustic wave signal and determining the suspected acoustic wave data, it includes: analyzing the top pressure target acoustic wave signal during the acquisition time period, determining 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 based on the time domain value.

[0071] In some embodiments of the present application, when judging whether the top pressure target sound wave signal is suspected sound wave data based on the time domain value and the frequency domain value, it includes: obtaining the time domain maximum value and the time domain minimum value of the top pressure target sound 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, the top pressure target sound wave signal is judged to be suspected sound wave data; otherwise, the top pressure target sound wave signal is judged not to be suspected sound wave data.

[0072] Specifically, the time domain value refers to the characteristic parameters of the signal in the time domain. The time domain characteristics of the top pressure target acoustic wave signal directly reflect the instantaneous characteristics of the signal. When defects occur in the six-sided top press, the top pressure target acoustic wave signal generated will often show mutation characteristics in the time domain, such as a sudden increase or decrease in amplitude. By obtaining the time domain maximum and time domain minimum values ​​of the top pressure target acoustic wave signal and comparing them with the time domain maximum and time domain minimum thresholds, 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 wave signal during normal operation of the six-sided top press. When the top pressure target acoustic wave signal is not suspected acoustic wave 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 the time domain minimum value is less than the time domain minimum threshold, it indicates that the top pressure target acoustic wave signal has certain fluctuations and abnormal changes. This change is likely to be related to defects or failures of the six-sided top press. For example, loose internal structure of the six-sided top press may cause the amplitude of the top pressure target acoustic wave signal to increase sharply in a short period of time, exceeding the normal range. It can provide data screening for subsequent in-depth analysis based on the acoustic wave recognition model, thereby reducing the amount of redundant data processed by the subsequent model and improving monitoring efficiency.

[0073] In some embodiments of the present application, when determining the defective acoustic wave data of a six-sided top press based on an acoustic wave recognition model and suspected acoustic wave data, the method includes: obtaining an acoustic wave data set and sampling according to a sampling ratio to obtain a training set and a test set, obtaining a decision tree model, and training the decision tree model based on the training set, and evaluating the trained decision tree model based on 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, the training is stopped, and the currently trained decision tree model is determined as the acoustic wave recognition model. Otherwise, a grid search is used to find the model parameters of the decision tree model, and the decision tree model is continued to be trained according to the model parameters until it is greater than or equal to the evaluation value of the previously trained decision tree model, and the suspected acoustic wave data is substituted into the acoustic wave recognition model to determine the defective acoustic wave data.

[0074] Specifically, the acoustic wave dataset includes defect acoustic wave data corresponding to various defects that occurred in the six-sided top press in the past, 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 the sampling ratio to obtain the training set and test set. The sampling ratio is usually 7:3, which can be adjusted according to the amount of data 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. This model contains internal nodes, branches, and leaf nodes to capture the complex relationships in the data. The decision tree model is trained using the data in the training set. In each training, the model will try to learn the patterns and relationships in the data to improve its prediction or classification capabilities. After each training, the model is evaluated using the data in the test set 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.

[0075] It can be understood that if the evaluation value of the decision tree model after the current training is greater than or equal to the evaluation value of the decision tree model after the previous training, it means 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 means that the performance of the model has declined. The model parameters (hyperparameters) of the decision tree model are found by grid search. The grid search adjusts the currently trained decision tree model with the determined model parameters by exhaustively searching the model parameters in the parameter space, and then continues the training. This helps the model to more stably approach the global optimal solution, and finally determine an acoustic wave recognition model that can identify defect acoustic wave data, thereby ensuring the stability and reliability of monitoring.

[0076] In some embodiments of the present application, when comparing the defect acoustic wave data with the historical defect acoustic wave data set and determining the alarm mode of the six-sided top press according to the comparison result, it includes: when the historical defect acoustic wave data set contains data identical to the defect acoustic wave data, the defect acoustic wave data is added to the historical defect acoustic wave data set, and the alarm mode of the six-sided top press is determined according to the number of times the data occurs; when the historical defect acoustic wave data set contains data identical to the defect acoustic wave data, the defect acoustic wave data is added to the historical defect acoustic wave data set and an alarm is issued to remind manual verification.

[0077] It is understandable that by comparing with the historical defect acoustic wave data set, possible abnormal conditions can be quickly identified, reducing the response time to common defect states. By analyzing the number of occurrences of the defect acoustic wave data, possible persistent problems or periodic failures can be identified, thereby triggering the alarm mode and improving the monitoring efficiency of the six-sided top press. For new unrecorded defect acoustic wave data, an alarm is immediately triggered to ensure that potential problems of the six-sided top press receive timely attention and processing. At the same time, the new defect acoustic wave data is added to the historical defect acoustic wave data set. The data-driven alarm mechanism guarantees the working status of the six-sided top press. When new defect acoustic wave data is detected, an alarm is immediately issued and a prompt is given for manual verification to ensure that each new defect acoustic wave data can be carefully checked, so that relevant personnel can capture new changes in the operation of the six-sided top press, avoiding reliance on periodic manual inspection methods, thereby ensuring the efficiency and reliability of monitoring.

[0078] In some embodiments of the present application, when determining the alarm mode of the six-sided top press according to the number of data occurrences, it includes: pre-setting a first preset data occurrence number and a second preset data occurrence number, the first preset data occurrence number is greater than the second preset data occurrence number, when the data occurrence number is greater than or equal to the first preset data occurrence number, the alarm mode is determined to be a first-level warning, when the data occurrence number is less than the first preset data occurrence number and greater than the second preset data occurrence number, the alarm mode is determined to be a second-level warning, when the data occurrence number is less than or equal to the second preset data occurrence number, the alarm mode is determined to be a third-level warning, and the urgency of the first-level warning, the second-level warning and the third-level warning decreases in sequence.

[0079] 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 that are not equal to the standard environmental parameters, when the number of environmental parameters is greater than or equal to the environmental parameter number threshold, raising the alarm mode by one level, and when the number of environmental parameters is less than the environmental parameter number threshold, lowering the alarm mode by one level.

[0080] Specifically, the number of occurrences of the first preset data is preferably 10 times, and the number of occurrences of the second preset data is preferably 5 times. The alarm mode is divided into three levels. When the number of occurrences of the data is greater than or equal to the number of occurrences of the first preset data, it indicates that there are persistent problems or periodic failures in the six-sided top press, and the highest level one warning is triggered. When the number of occurrences of the data is less than the number of occurrences of the first preset data and greater than the number of occurrences of the second preset data, it indicates that there are certain persistent problems or periodic failures in the six-sided top press, which requires attention, and the middle level two warning is triggered. When the number of occurrences of the data is less than or equal to the number of occurrences of the second preset data, it indicates that the six-sided top press has fewer persistent problems or periodic failures, and the alarm mode is determined to be a three-level warning. The alarm mode is dynamically determined according to the number of occurrences of the data, thereby avoiding waste of monitoring resources. The environmental parameters of the six-sided top press are obtained and compared with the standard environmental parameters. The environmental parameters represent parameters such as temperature, humidity, air pressure and dust. The standard environmental parameters are determined by the actual operating instructions of the six-sided top press. The alarm mode is further optimized according to the number of statistical environmental parameters. The more environmental parameters there are, the greater the difference between the current environmental conditions of the six-sided top press and the standard environment, 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 a level one warning, the level one warning is maintained. On the contrary, when the number of environmental parameters is smaller, it indicates that the environmental parameters are basically within the normal range, and the alarm level is appropriately lowered. If the alarm mode is already a level three warning, the level three warning is maintained. Combining the number of environmental parameters with the number of data occurrences can not only timely detect the signs of defects of the six-sided top press, but also effectively cope with 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.

[0081] In summary, the beneficial effects of the present invention are: by collecting the acoustic wave signals of at least three acoustic wave sensors through the acoustic wave sensor 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; the top pressure acoustic wave signal is dynamically adjusted according to the signal-to-noise ratio, thereby improving the overall quality of the signal, avoiding misjudgment due to poor signal quality, and improving the reliability of monitoring. The acoustic wave recognition model is used to analyze the suspected acoustic wave data and determine the defective acoustic wave data, thereby avoiding reliance on periodic manual inspection methods, 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 based on the environment, which can not only timely detect the defect signs of the six-sided top press, but also effectively cope with the complex and changeable industrial environment, thereby improving the accuracy and reliability of monitoring, and providing reliable guarantee for the stable operation of the six-sided top press.

[0082] In another preferred embodiment based on the above embodiment, 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:

[0083] an acquisition module configured to acquire acoustic wave signals from at least three acoustic wave sensors deployed on an acoustic wave sensor array of a six-sided top press according to an acquisition time period;

[0084] a processing module configured to pre-process the at least three acoustic wave signals to determine a top pressure acoustic wave signal of the six-sided top press, determine a signal-to-noise ratio based on the top pressure acoustic wave signal, determine whether to adjust the top pressure acoustic wave signal based on the signal-to-noise ratio, and determine a top pressure target acoustic wave signal of the six-sided top press based on the determination result;

[0085] an identification module configured to analyze the acoustic wave signal of the top pressing target, determine suspected acoustic wave data, and determine defective acoustic wave data of the six-sided top pressing machine based on the acoustic wave identification model and the suspected acoustic wave data;

[0086] The alarm module is configured to compare the defect acoustic wave data with the historical defect acoustic wave 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, and issue an alarm to the six-sided top press according to the adjusted alarm mode.

[0087] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0089] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A monitoring method for a six-sided top press, characterized in that: include: Acquire acoustic wave signals from at least three acoustic wave sensors deployed on an acoustic wave sensor array of a six-sided top press according to a collection time period; pre-processing at least three of the acoustic wave signals to determine a top pressure acoustic wave signal of the six-sided top press, determining a signal-to-noise ratio based on the top pressure acoustic wave signal, determining whether to adjust the top pressure acoustic wave signal based on the signal-to-noise ratio, and determining a top pressure target acoustic wave signal of the six-sided top press based on the determination result; Analyzing the target acoustic wave signal of the top pressing machine to determine suspected acoustic wave data, and determining defect acoustic wave data of the six-sided top pressing machine based on an acoustic wave recognition model and the suspected acoustic wave data; comparing the defect acoustic wave data with a historical defect acoustic wave data set, determining an alarm mode of the six-sided top press according to the comparison result, determining whether to adjust the alarm mode based on an environment of the six-sided top press, and issuing an alarm to the six-sided top press according to the adjusted alarm mode; Preprocessing the acoustic wave signal to determine the top pressure acoustic wave signal of the six-sided top press, determining a signal-to-noise ratio based on the top pressure acoustic wave signal, and judging whether to adjust the top pressure acoustic wave signal based on the signal-to-noise ratio, and determining the top pressure target acoustic wave signal of the six-sided top press based on the judgment result, including: The preprocessing is signal denoising; Obtaining a square mean of the top pressure acoustic wave signal to determine a signal power of the top pressure acoustic wave signal, determining a top pressure acoustic wave signal for shutting down the six-sided top press, and determining a noise power based on the power of the top pressure acoustic wave signal for shutting down the six-sided top press; determining the signal-to-noise ratio based on the signal power and the noise power; Comparing the signal-to-noise ratio with a signal-to-noise ratio threshold, and determining 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, determining that no adjustment is made to the top pressure acoustic wave signal, and determining the top pressure acoustic wave signal 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, determining to adjust the top pressure acoustic wave signal, and determining the adjusted top pressure acoustic wave signal as the top pressure target acoustic wave signal; When determining to adjust the top pressure sound wave signal, it includes: Acquiring the Doppler frequency of the top pressure acoustic wave signal, and comparing the Doppler frequency with historical data to determine an adjustment value of the Doppler frequency; The historical data includes a plurality of historical Pulser frequencies and a plurality of phase compensation values, and each historical Pulser frequency corresponds to a phase compensation value; When there is a historical Doppler frequency identical to the Doppler frequency in the historical data, determining the phase compensation value corresponding to the historical Doppler frequency as the adjustment value of the Doppler frequency; When there is no historical Doppler frequency identical to the Doppler frequency in the historical data, similarity between the Doppler frequency and each historical Doppler frequency is obtained, and a phase compensation value corresponding to the historical Doppler frequency with the maximum similarity is determined as the adjustment value of the Doppler frequency.

2. The monitoring method for a six-sided top press according to claim 1, characterized in that: When analyzing the top pressure target acoustic wave signal to determine suspected acoustic wave data, the following steps are included: The top pressure target acoustic wave signal in the acquisition time period is analyzed to determine a time domain value of the top pressure target acoustic wave signal, and whether the top pressure target acoustic wave signal is the suspected acoustic wave data is determined according to the time domain value.

3. The monitoring method for a six-sided top press according to claim 2, characterized in that: When judging whether the top pressure target sound wave signal is the suspected sound wave data according to the time domain value and the frequency domain value, the method includes: Obtaining a time domain maximum value and a 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, the top pressure target sound wave signal is determined to be the suspected sound wave data; otherwise, the top pressure target sound wave signal is determined not to be the suspected sound wave data.

4. The monitoring method for a six-sided top press according to claim 3, 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, the method includes: Obtain the sound wave dataset and sample it according to the sampling ratio to obtain the training set and test set; Obtaining a decision tree model, training the decision tree model according to the training set, and 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, the training is stopped, and the currently trained decision tree model is determined as the acoustic wave recognition model; otherwise, a grid search is used to find the model parameters of the decision tree model, and the decision tree model is continued to be trained according to the model parameters until the evaluation value is greater than or equal to the evaluation value of the previously trained decision tree model; The suspected sound wave data is substituted into the sound wave recognition model to determine the defect sound wave data.

5. The monitoring method for a six-sided top press according to claim 4, characterized in that: When comparing the defect acoustic wave data with a historical defect acoustic wave data set and determining the alarm mode of the six-sided top press according to the comparison result, the method includes: When data identical to the defect acoustic wave data exists in the historical defect acoustic wave data set, the defect acoustic wave data is added to the historical defect acoustic wave data set, and the alarm mode of the six-sided top press is determined according to the number of occurrences of the data; When the historical defect acoustic wave data set does not contain data identical to the defect acoustic wave data, the defect acoustic wave data is added to the historical defect acoustic wave data set and an alarm is issued to prompt manual verification.

6. The monitoring method for a six-sided top press according to claim 5, characterized in that: When determining the alarm mode of the six-sided top press according to the number of occurrences of the data, it includes: Preset a first preset number of occurrences of data and a second preset number of occurrences of data, wherein the first preset number of occurrences of data is greater than the second preset number of occurrences of data; When the number of occurrences of the data is greater than or equal to the first preset number of occurrences of the data, the alarm mode is determined to be a first-level warning; When the number of occurrences of the data is less than the first preset number of occurrences of the data and greater than the second preset number of occurrences of the data, the alarm mode is determined to be a level 2 warning; When the number of occurrences of the data is less than or equal to the second preset number of occurrences of the data, the alarm mode is determined to be a level three warning; The urgency of the first-level warning, second-level warning and third-level warning decreases in sequence.

7. The monitoring method for a six-sided top press according to claim 6, characterized in that: When determining whether to adjust the alarm mode based on the environment of the six-sided top press, the method includes: Acquiring environmental parameters of the six-sided top press and determining standard environmental parameters of the six-sided top press; Counting the number of environmental parameters that are not equal to standard environmental parameters; When the number of environmental parameters is greater than or equal to the environmental parameter number threshold, the alarm mode is raised by one level; When the number of environmental parameters is less than the environmental parameter number threshold, the alarm mode is reduced by one level.

8. A monitoring system for a six-sided top press, used for applying the monitoring method for a six-sided top press according to any one of claims 1 to 7, characterized in that: include: an acquisition module configured to acquire acoustic wave signals from at least three acoustic wave sensors deployed on an acoustic wave sensor array of a six-sided top press according to an acquisition time period; a processing module configured to pre-process at least three of the acoustic wave signals to determine a top pressure acoustic wave signal of the six-sided top press, determine a signal-to-noise ratio based on the top pressure acoustic wave signal, determine whether to adjust the top pressure acoustic wave signal based on the signal-to-noise ratio, and determine a top pressure target acoustic wave signal of the six-sided top press based on the determination result; an identification module configured to analyze the target acoustic wave signal of the top pressing machine to determine suspected acoustic wave data, and determine defect acoustic wave data of the six-sided top pressing machine based on an acoustic wave identification model and the suspected acoustic wave data; The alarm module is configured to compare the defect acoustic wave data with a historical defect acoustic wave data set, determine an 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, and issue an alarm to the six-sided top press according to the adjusted alarm mode.

Images