A production efficiency global optimization method applied to an industrial production line

Abstract

The application relates to the field of industrial optimization, and particularly discloses a production efficiency global optimization method applied to an industrial production line, which comprises the following steps: collecting vibration frequency of a processing device and differential current data of a servo system of the processing device in real time during operation of the processing device, extracting vibration and current abnormal characteristic values through discrete wavelet transform and fast Fourier transform respectively, inputting a multi-dimensional running state characteristic vector into a trained deep learning efficiency evaluation model for fusion analysis, outputting a current efficiency coefficient of the processing device and dividing the efficiency level, triggering a corresponding power improvement strategy according to the efficiency level, and realizing closed-loop control from state perception to active intervention. The application improves the efficiency identification precision and self-adaptive response capability of the processing device under complex working conditions, and has good practicability and popularization value.

Description

Technical Field

[0001] This invention relates to the field of industrial optimization, specifically to a method for global optimization of production efficiency applied to industrial production lines. Background Technology

[0002] Industrial production lines are a production method in industry that improves efficiency through division of labor and cooperation. They consist of traction components, load-bearing components, drive devices, tensioning devices, redirection devices, and support components. As core equipment performing complex tasks, industrial production lines need to operate stably for extended periods under high-intensity, high-load, or unstructured environments. The reliability of their mechanical and electrical systems directly affects operational and system efficiency. Therefore, constructing an efficient and intelligent condition monitoring and efficiency evaluation mechanism has become an important means to ensure the efficient operation of processing equipment systems. In recent years, fusion analysis methods based on sensor data and artificial intelligence algorithms have been increasingly applied to the efficiency evaluation and interactive control of processing equipment, significantly improving the system's intelligence level and adaptive capabilities.

[0003] The existing technology has the following shortcomings: An industrial production line consists of multiple processing devices, and its efficiency improvement is limited by these devices. The power that can be increased by each processing device is different, and existing technologies have limited ability to identify this, making it difficult to determine the efficiency improvement potential of the processing devices and thus difficult to optimize the entire industrial production line in a targeted manner. Summary of the Invention

[0004] To address the aforementioned technical problems, this paper provides a method for global optimization of production efficiency in industrial production lines. This technical solution resolves the issues raised in the background section.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for global optimization of production efficiency applied to industrial production lines includes the following steps: S1: During the operation of the industrial production line, the vibration frequency of the processing equipment and the differential current data of the servo system of the processing equipment are collected in real time. S2: Analyze the vibration frequency and calculate the abnormal characteristic value of the vibration frequency based on the change amplitude of the vibration frequency, which is used to determine whether the processing equipment is normal. S3: Analyze the differential current and calculate the abnormal characteristic value of the differential current based on the stability of the differential current, which is used to assess whether there is an abnormality in the motor winding. S4: Construct a multi-dimensional operating state feature vector from the abnormal vibration frequency feature value and the abnormal differential current feature value, and input it into the trained deep learning efficiency evaluation model for fusion analysis; S5: Determine the current efficiency level of the processing equipment based on the model output results, and trigger the corresponding power boosting strategy based on the efficiency level.

[0006] As a further aspect of the present invention: the determination of whether the processing equipment is functioning properly specifically includes: During the operation of the industrial production line, the vibration frequency data of the processing equipment is collected in real time, the vibration frequency is analyzed, and the abnormal characteristic value of the vibration frequency is calculated based on the change amplitude of the vibration frequency. It is then determined whether the abnormal characteristic value of the vibration frequency is greater than or equal to a preset threshold. If it is, the processing equipment is abnormal; otherwise, the processing equipment is normal.

[0007] As a further aspect of the present invention: the process for obtaining the abnormal vibration frequency characteristic value is as follows: Obtain vibration frequency data of the processing equipment and preprocess the vibration frequency data; The processed vibration frequency data is then standardized. Discrete wavelet transform is applied to the standardized vibration frequency data to decompose the data into detail coefficients and approximation coefficients at multiple scales. Wavelet basis and decomposition level are used to obtain the high-frequency components of the vibration frequency data at each scale. For each detail coefficient, calculate the corresponding amplitude: The overall vibration frequency anomaly characteristic value is obtained by weighted averaging of the fluctuation amplitudes corresponding to all detail coefficients.

[0008] As a further aspect of the present invention: the evaluation of whether the motor windings are abnormal specifically includes: During the operation of the industrial production line, the differential current data of the servo system is collected in real time, the differential current is analyzed, and the abnormal characteristic value of the differential current is calculated based on the stability of the differential current. It is then determined whether the abnormal characteristic value of the differential current is greater than or equal to a preset threshold. If it is, the motor winding is abnormal; otherwise, the motor winding is normal.

[0009] As a further aspect of the present invention: the process for obtaining the differential current anomaly characteristic value is as follows: The differential current of the servo system is acquired in real time and transmitted to the data processing unit for storage. The acquired differential current is subjected to a fast Fourier transform to convert the differential current from the time domain to the frequency domain, and the frequency component and amplitude component are obtained. Calculate the total energy within the normal frequency range and the energy within the abnormal frequency range based on the spectral amplitude components; Calculate the differential current abnormal characteristic value based on the energy in the normal frequency range and the abnormal frequency range.

[0010] As a further aspect of the present invention: the construction of a multi-dimensional operating state feature vector from the abnormal vibration frequency feature value and the abnormal differential current feature value, and inputting it into the trained deep learning efficiency evaluation model for fusion analysis, specifically includes: The abnormal vibration frequency and differential current feature values ​​during the interaction process of the industrial production line are obtained. The abnormal vibration frequency and differential current feature values ​​are constructed into a comprehensive feature vector, which is used as the input of the deep learning efficiency evaluation model to minimize the error between the predicted efficiency coefficient of the industrial production line and the actual efficiency coefficient of the industrial production line. This serves as the training objective of the model. Based on the trained deep learning efficiency evaluation model, the efficiency coefficient of the industrial production line is output. The deep learning efficiency evaluation model is a long short-term memory network.

[0011] As a further aspect of the present invention: the training process of the deep learning efficiency evaluation model is as follows: During the model training phase, a large amount of vibration frequency data of processing equipment and differential current data of servo system under different operating conditions of industrial production lines are first collected, and their actual operating status labels are recorded simultaneously as training samples. The raw data is preprocessed, standardized, and feature extracted to obtain the corresponding vibration frequency anomaly feature values ​​and differential current anomaly feature values, which are then used to construct a multidimensional operating state feature vector. The feature vector is used as input, and the actual efficiency coefficient of the processing equipment is used as output label. A long short-term memory network is used to construct a sequence prediction model. The model training is completed by continuously adjusting the model parameters through the backpropagation algorithm to minimize the error between the model's predicted output and the actual efficiency level. The trained deep learning efficiency evaluation model is used to evaluate the efficiency of the current operating state of the processing equipment in real time and output the corresponding efficiency coefficient.

[0012] As a further aspect of the present invention: the step of determining the current efficiency level of the processing equipment based on the model output results specifically includes: The efficiency coefficient generated by the processing equipment during normal operation within a preset time interval from the current time is taken as the historical efficiency coefficient, and the output power of the processing equipment that generates the maximum historical efficiency coefficient is taken as the characteristic power of the processing equipment. The efficiency level of the processing equipment is obtained by dividing the characteristic power of the processing equipment by the current output power of the processing equipment.

[0013] As a further aspect of the present invention: the step of triggering a corresponding power boosting strategy based on the efficiency level specifically includes: The minimum efficiency level of at least one processing device currently in operation is used as the factor to be increased, and the power of at least one processing device is increased by a factor equal to the factor to be increased.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention acquires real-time vibration frequency data from processing equipment and differential current signals from the servo system, combined with advanced signal processing algorithms, including discrete wavelet transform and fast Fourier transform, to achieve high-precision sensing of the mechanical and electrical states of the processing equipment during operation. Specifically, by performing multi-scale decomposition of the vibration signal based on wavelet transform, extracting detail coefficients, and calculating its fluctuation amplitude, it can effectively capture minute vibration anomalies in motors under non-stationary conditions, significantly improving the ability to identify early efficiency issues such as motor wear, loosening, or load imbalance. Simultaneously, through frequency domain conversion and energy distribution analysis of the differential current signal, it can accurately detect weak current distortions in the motor windings caused by factors such as short circuits and poor contact, enhancing the system's sensitivity and discrimination ability to electrical anomalies. Compared with traditional methods based on time-domain statistics or single spectrum analysis, this scheme has significant advantages in noise suppression, feature distinguishability, and dynamic response performance. It not only improves the robustness of signal processing, but also enables a refined assessment of the operating status of key components of processing equipment under complex working conditions. This allows for accurate prediction of the efficiency improvement potential of the processing equipment based on its current operating status, and further enables global optimization of the industrial production line based on the prediction results. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a global optimization method for production efficiency applied to an industrial production line according to the present invention. Figure 2 This is a flowchart illustrating the process of obtaining abnormal vibration frequency characteristic values ​​according to the present invention. Figure 3 This is a flowchart illustrating the process of obtaining the differential current anomaly characteristic value according to the present invention. Figure 4 This is a flowchart illustrating the training process of the deep learning efficiency evaluation model of the present invention. Figure 5 This is a schematic diagram of the process of determining the current efficiency level of the processing equipment based on the model output results of the present invention. Detailed Implementation

[0016] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0017] Reference Figure 1As shown, a method for global optimization of production efficiency applied to industrial production lines includes the following steps: S1: During the operation of the industrial production line, the vibration frequency of the processing equipment and the differential current data of the servo system of the processing equipment are collected in real time. S2: Analyze the vibration frequency and calculate the abnormal characteristic value of the vibration frequency based on the change amplitude of the vibration frequency, which is used to determine whether the processing equipment is normal. S3: Analyze the differential current and calculate the abnormal characteristic value of the differential current based on the stability of the differential current, which is used to assess whether there is an abnormality in the motor winding. S4: Construct a multi-dimensional operating state feature vector from the abnormal vibration frequency feature value and the abnormal differential current feature value, and input it into the trained deep learning efficiency evaluation model for fusion analysis; S5: Determine the current efficiency level of the processing equipment based on the model output results, and trigger the corresponding power boosting strategy based on the efficiency level.

[0018] In S1, during the operation of the industrial production line, the vibration frequency of the processing equipment and the differential current data of the servo system of the processing equipment are collected in real time, specifically including: An industrial production line contains multiple processing devices, each with different operating conditions. Long-term operation can cause changes in their maximum rated power. Therefore, the maximum rated power cannot be used as a reference alone. It is necessary to estimate the maximum rated power based on the operating conditions, which is the output power of the processing device that generates the highest historical efficiency coefficient. This allows us to determine the efficiency improvement potential of the processing device. However, the improvement potential of each processing device is different. In order to improve the overall efficiency of the industrial production line, we need to proceed according to the minimum improvement potential of the processing devices. Otherwise, if we proceed according to the maximum improvement potential, it will exceed the improvement potential of almost all processing devices. As a result, most processing devices will operate under overload, making it difficult to maintain stable operation and reducing the service life of the industrial production line. The processing equipment in the industrial production line is controlled by a servo system, which in turn is controlled by a motor. Therefore, the stability of the motor is evaluated by using its vibration and current, and the power increase is predicted based on the stability. This is because the closer the power is to the maximum usable power, the lower the stability. Therefore, this can be modeled and estimated using the model. During the operation of the industrial production line, the data acquisition module acquires the motor vibration signal in real time through a high-sensitivity vibration sensor deployed at the processing equipment, and converts the analog signal into a digital signal for processing. The vibration sensor adopts a triaxial accelerometer to collect vibration frequency data in the X, Y, and Z directions respectively, with a sampling frequency of not less than 1kHz, to ensure accurate capture of the vibration characteristics of the motor under different loads and motion states.

[0019] Meanwhile, the system monitors the differential current of the servo system in real time through a current detection circuit. The current detection circuit includes a high-precision Hall current sensor, which is installed in the power supply circuit of the servo motor to collect the current difference between the current flowing into and out of the motor. The collected differential current signal is filtered and amplified by the signal conditioning module and then sent to the embedded data acquisition unit for analog-to-digital conversion. The sampling period is no more than 1ms, thereby obtaining high time resolution differential current data for subsequent abnormal feature extraction and analysis.

[0020] In S2, the vibration frequency is analyzed, and based on the amplitude of the vibration frequency change, abnormal characteristic values ​​of the vibration frequency are calculated to determine whether the processing equipment is functioning normally. Specifically, this includes: During the operation of the industrial production line, the vibration frequency data of the processing equipment is collected in real time, the vibration frequency is analyzed, and the abnormal characteristic value of the vibration frequency is calculated based on the change amplitude of the vibration frequency. It is then determined whether the abnormal characteristic value of the vibration frequency is greater than or equal to a preset threshold. If it is, the processing equipment is abnormal; otherwise, the processing equipment is normal.

[0021] Reference Figure 2 As shown, the process for obtaining the abnormal vibration frequency characteristic value is as follows: Obtain vibration frequency data of the processing equipment and preprocess the vibration frequency data; The processed vibration frequency data is then standardized. Discrete wavelet transform is applied to the standardized vibration frequency data to decompose the data into detail coefficients and approximation coefficients at multiple scales. Using wavelet basis and decomposition level, the high-frequency components of the vibration frequency data at each scale are obtained. The calculation expression is as follows: ; In the formula, The approximation coefficient represents the low-frequency component. Indicates the number of detail coefficients. Indicates the first These detail coefficients represent the high-frequency components. A dataset representing the high-frequency components of vibration frequency data at each scale; For each detail coefficient, calculate the corresponding amplitude: ; In the formula, Indicates the first The magnitude of each detail coefficient, This represents the maximum value of the detail coefficient. This represents the minimum value of the detail coefficient; The overall vibration frequency anomaly characteristic value is obtained by weighted averaging of the fluctuation amplitudes corresponding to all detail coefficients, and the calculation expression is as follows: ; in, Indicates the abnormal characteristic value of vibration frequency. This represents the total number of detail coefficients.

[0022] It should be noted that this invention introduces discrete wavelet transform to decompose the standardized vibration frequency data into multiple scales during vibration frequency analysis. Detail coefficients at each scale are extracted, and their fluctuation amplitudes are calculated. Then, a weighted average is used to obtain the vibration frequency anomaly characteristic value. This method can effectively capture minute vibration anomalies in processing equipment during operation, improving the sensitivity and accuracy of efficiency identification. Compared to traditional time-domain or frequency-domain analysis methods, this scheme utilizes wavelet transform's excellent localization characteristics for non-stationary signals, enabling a more comprehensive reflection of the time-frequency domain characteristics of vibration signals, thereby achieving a refined assessment of the processing equipment's condition. This technology not only improves the accuracy of monitoring the processing equipment's operating status but also enhances the early warning capability of mechanical efficiency, demonstrating significant technological advancement and practical innovation.

[0023] In S3, the differential current is analyzed. Based on the stability of the differential current, abnormal characteristic values ​​of the differential current are calculated to assess whether there are any abnormalities in the motor windings. Specifically, this includes: During the operation of the industrial production line, the differential current data of the servo system is collected in real time, the differential current is analyzed, and the abnormal characteristic value of the differential current is calculated based on the stability of the differential current. It is then determined whether the abnormal characteristic value of the differential current is greater than or equal to a preset threshold. If it is, the motor winding is abnormal; otherwise, the motor winding is normal.

[0024] Reference Figure 3 As shown, the process for obtaining the differential current anomaly characteristic value is as follows: Real-time acquisition of differential current of servo system The differential current is then transmitted to the data processing unit for storage. in, Indicates time; For the collected differential current Perform a Fast Fourier Transform to convert the differential current from the time domain to the frequency domain and obtain the frequency components. and amplitude components , The calculation expression for the amplitude component is as follows: ; in, Represents the real part of the spectrum. Represents the imaginary part of the spectrum. Indicates frequency; According to the spectral amplitude component The total energy within the normal frequency range and the energy within the abnormal frequency range are calculated using the following expression: ; In the formula, Indicates frequency range Internal energy Indicates the frequency range; Based on the energy levels within the normal and abnormal frequency ranges, the differential current anomaly characteristic value is calculated using the following expression: ; In the formula, This represents the abnormal characteristic value of the differential current. Indicates the range of abnormal frequencies. Indicates the total frequency range. This represents the energy within the abnormal frequency range. This represents the energy within the total frequency range.

[0025] It should be noted that this invention introduces a Fast Fourier Transform (FFT) to convert the time-domain signal into a frequency-domain signal during the analysis of the differential current in the servo system. This further distinguishes the energy distribution within the normal frequency range from that within the abnormal frequency range, and calculates the abnormal characteristic value of the differential current based on the energy ratio between the two. This method can effectively identify minute current distortions in the motor windings caused by short circuits, open circuits, or poor contact, thereby achieving accurate assessment of the motor's electrical condition. Compared to traditional mean or variance statistical methods, this scheme improves the discriminability of efficiency characteristics through frequency-domain energy analysis, exhibiting higher sensitivity and stability, especially in early electrical efficiency detection. This technology not only enhances the operating efficiency of the processing equipment drive system but also expands the application depth of current monitoring in industrial production line condition sensing, demonstrating significant technological innovation and engineering practicality.

[0026] In S4, the abnormal vibration frequency feature values ​​and the abnormal differential current feature values ​​are constructed into a multi-dimensional operating state feature vector, which is then input into the trained deep learning efficiency evaluation model for fusion analysis. Specifically, this includes: The process of constructing a multi-dimensional operating state feature vector from the abnormal vibration frequency feature values ​​and the abnormal differential current feature values, and inputting it into the trained deep learning efficiency evaluation model for fusion analysis, specifically includes: The abnormal vibration frequency and differential current feature values ​​during the interaction process of the industrial production line are obtained. The abnormal vibration frequency and differential current feature values ​​are constructed into a comprehensive feature vector, which is used as the input of the deep learning efficiency evaluation model to minimize the error between the predicted efficiency coefficient of the industrial production line and the actual efficiency coefficient of the industrial production line. This serves as the training objective of the model. Based on the trained deep learning efficiency evaluation model, the efficiency coefficient of the industrial production line is output. The deep learning efficiency evaluation model is a long short-term memory network.

[0027] Reference Figure 4 As shown, the training process of the deep learning efficiency evaluation model is as follows: During the model training phase, a large amount of vibration frequency data of processing equipment and differential current data of servo system under different operating conditions of industrial production lines are first collected, and their actual operating status labels are recorded simultaneously as training samples. The raw data is preprocessed, standardized, and feature extracted to obtain the corresponding vibration frequency anomaly feature values ​​and differential current anomaly feature values, which are then used to construct a multidimensional operating state feature vector. The feature vector is used as input, and the actual efficiency coefficient of the processing equipment is used as output label. A long short-term memory network is used to construct a sequence prediction model. The model training is completed by continuously adjusting the model parameters through the backpropagation algorithm to minimize the error between the model's predicted output and the actual efficiency level. The trained deep learning efficiency evaluation model is used to evaluate the efficiency of the current operating state of the processing equipment in real time and output the corresponding efficiency coefficient.

[0028] The efficiency coefficient generated by the processing equipment during normal operation within a preset time interval from the current time is taken as the historical efficiency coefficient, and the output power of the processing equipment that generates the maximum historical efficiency coefficient is taken as the characteristic power of the processing equipment. The efficiency level of the processing equipment is obtained by dividing the characteristic power of the processing equipment by the current output power of the processing equipment.

[0029] Here, the preset time is set based on experience, mainly according to the change of the maximum power of the processing equipment during normal operation. That is, the change of the maximum power of the processing equipment during normal operation within the preset time is negligible. The preset time can be generated through the following steps: Set a large time interval, and collect the maximum power of the processing equipment during normal operation multiple times within this time interval; If the difference between the maximum power of the processing equipment under normal operation collected multiple times is less than the allowable error, then the length of the time interval is taken as the preset time. Otherwise, the time interval is shortened by a preset margin, which is a very small margin. The previous step is repeated for the shortened time interval until the preset time can be obtained. The historical efficiency coefficient is obtained by using the preset time obtained therefrom. The historical efficiency coefficient can be continuously updated, and based on this, the characteristic power of the current processing equipment can be obtained, that is, the maximum power of the current processing equipment during normal operation.

[0030] Reference Figure 5 As shown, in S5, the current efficiency level of the processing equipment is determined based on the model output, and a corresponding power boosting strategy is triggered based on the efficiency level, specifically including: The minimum efficiency level of at least one processing device currently in operation is used as the factor to be increased, and the power of at least one processing device is increased by a factor equal to the factor to be increased.

[0031] When upgrading, it is necessary to ensure that the power of the processing equipment after the upgrade does not exceed the maximum allowable power under its current operating state. Therefore, it is necessary to select the minimum value of the current operating efficiency level of at least one processing equipment for upgrading. After the upgrade, each processing equipment can operate normally. At the same time, it is also easy to know that this is the maximum multiple of efficiency improvement. Therefore, this is the way to maximize the upgrading of the industrial production line.

[0032] The working principle of this invention: This invention provides a method for global optimization of production efficiency in industrial production lines, aiming to achieve real-time monitoring and efficiency evaluation of the operating status of key components of processing equipment. This method collects vibration frequency data of the processing equipment and differential current signals of the servo system in real time during operation, extracts abnormal feature values ​​from both, and constructs a multi-dimensional operating status feature vector. This vector is then input into a trained deep learning efficiency evaluation model for fusion analysis, thereby determining the current efficiency level of the processing equipment and triggering corresponding early warning and control strategies. Specifically, vibration frequency data is collected by a high-sensitivity triaxial accelerometer deployed on the processing equipment, with a sampling frequency of no less than 1 kHz; differential current is collected by a Hall current sensor, filtered and amplified, and then converted from analog to digital, with a sampling period of no more than 1 ms. For the vibration frequency data, discrete wavelet transform is used to decompose it at multiple scales, extract detail coefficients, and calculate the fluctuation amplitude. Finally, a weighted average is used to obtain abnormal vibration frequency feature values ​​to identify whether the processing equipment has abnormal states such as wear, looseness, or imbalance. For differential current data, a Fast Fourier Transform (FFT) is used to convert it into a frequency domain signal. The energy ratio between the normal and abnormal frequency ranges is then calculated to obtain differential current anomaly characteristic values, which are used to determine whether the motor windings have experienced electrical inefficiencies. These two characteristic values ​​are combined into a comprehensive feature vector, which is input into an efficiency evaluation model built on a Long Short-Time Memory (LSTM) network. The model, trained on a large amount of historical data, can accurately output the current efficiency coefficient of the processing equipment and classify it into efficiency levels. Based on different efficiency levels, intelligent perception, evaluation, and control of the processing equipment's operating status are achieved, significantly improving the efficiency and reliability of the processing equipment system, making it suitable for long-term stable operation in complex environments.

[0033] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0034] Furthermore, this solution also proposes a storage medium on which a computer-readable program is stored. When the computer-readable program is invoked, the aforementioned global optimization method for production efficiency applied to industrial production lines is executed.

[0035] It is understandable that the storage medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid-state drive (SSD).

[0036] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for global optimization of production efficiency applied to industrial production lines, characterized in that, Includes the following steps: S1: During the operation of the industrial production line, the vibration frequency of the processing equipment and the differential current data of the servo system of the processing equipment are collected in real time. S2: Analyze the vibration frequency and calculate the abnormal characteristic value of the vibration frequency based on the change amplitude of the vibration frequency, which is used to determine whether the processing equipment is normal. S3: Analyze the differential current and calculate the abnormal characteristic value of the differential current based on the stability of the differential current, which is used to assess whether there is an abnormality in the motor winding. S4: Construct a multi-dimensional operating state feature vector from the abnormal vibration frequency feature value and the abnormal differential current feature value, and input it into the trained deep learning efficiency evaluation model for fusion analysis; S5: Determine the current efficiency level of the processing equipment based on the model output results, and trigger the corresponding power boosting strategy based on the efficiency level.

2. The method for global optimization of production efficiency applied to industrial production lines according to claim 1, characterized in that, The determination of whether the processing equipment is functioning properly specifically includes: During the operation of the industrial production line, the vibration frequency data of the processing equipment is collected in real time, the vibration frequency is analyzed, and the abnormal characteristic value of the vibration frequency is calculated based on the change amplitude of the vibration frequency. It is then determined whether the abnormal characteristic value of the vibration frequency is greater than or equal to a preset threshold. If it is, the processing equipment is abnormal; otherwise, the processing equipment is normal.

3. The method for global optimization of production efficiency applied to industrial production lines according to claim 2, characterized in that, The process for obtaining the abnormal vibration frequency characteristic value is as follows: Obtain vibration frequency data of the processing equipment and preprocess the vibration frequency data; The processed vibration frequency data is then standardized. Discrete wavelet transform is applied to the standardized vibration frequency data to decompose the data into detail coefficients and approximation coefficients at multiple scales. Wavelet basis and decomposition level are used to obtain the high-frequency components of the vibration frequency data at each scale. For each detail coefficient, calculate the corresponding amplitude: The overall vibration frequency anomaly characteristic value is obtained by weighted averaging of the fluctuation amplitudes corresponding to all detail coefficients.

4. The method for global optimization of production efficiency applied to an industrial production line according to claim 3, characterized in that, The assessment of whether there is an abnormality in the motor windings specifically includes: During the operation of the industrial production line, the differential current data of the servo system is collected in real time, the differential current is analyzed, and the abnormal characteristic value of the differential current is calculated based on the stability of the differential current. It is then determined whether the abnormal characteristic value of the differential current is greater than or equal to a preset threshold. If it is, the motor winding is abnormal; otherwise, the motor winding is normal.

5. The method for global optimization of production efficiency applied to an industrial production line according to claim 4, characterized in that, The process for obtaining the differential current anomaly characteristic value is as follows: The differential current of the servo system is acquired in real time and transmitted to the data processing unit for storage. The acquired differential current is subjected to a fast Fourier transform to convert the differential current from the time domain to the frequency domain, and the frequency component and amplitude component are obtained. Calculate the total energy within the normal frequency range and the energy within the abnormal frequency range based on the spectral amplitude components; Calculate the differential current abnormal characteristic value based on the energy in the normal frequency range and the abnormal frequency range.

6. The method for global optimization of production efficiency applied to an industrial production line according to claim 5, characterized in that, The process of constructing a multi-dimensional operating state feature vector from the abnormal vibration frequency feature values ​​and the abnormal differential current feature values, and inputting it into the trained deep learning efficiency evaluation model for fusion analysis, specifically includes: The abnormal vibration frequency and differential current feature values ​​during the interaction process of the industrial production line are obtained. The abnormal vibration frequency and differential current feature values ​​are constructed into a comprehensive feature vector, which is used as the input of the deep learning efficiency evaluation model to minimize the error between the predicted efficiency coefficient of the industrial production line and the actual efficiency coefficient of the industrial production line. This serves as the training objective of the model. Based on the trained deep learning efficiency evaluation model, the efficiency coefficient of the industrial production line is output. The deep learning efficiency evaluation model is a long short-term memory network.

7. The method for global optimization of production efficiency applied to an industrial production line according to claim 6, characterized in that, The training process of the deep learning efficiency evaluation model is as follows: During the model training phase, a large amount of vibration frequency data of processing equipment and differential current data of servo system under different operating conditions of industrial production lines are first collected, and their actual operating status labels are recorded simultaneously as training samples. The raw data is preprocessed, standardized, and feature extracted to obtain the corresponding vibration frequency anomaly feature values ​​and differential current anomaly feature values, which are then used to construct a multidimensional operating state feature vector. The feature vector is used as input, and the actual efficiency coefficient of the processing equipment is used as output label. A long short-term memory network is used to construct a sequence prediction model. The model training is completed by continuously adjusting the model parameters through the backpropagation algorithm to minimize the error between the model's predicted output and the actual efficiency level. The trained deep learning efficiency evaluation model is used to evaluate the efficiency of the current operating state of the processing equipment in real time and output the corresponding efficiency coefficient.

8. The method for global optimization of production efficiency applied to an industrial production line according to claim 7, characterized in that, The determination of the current efficiency level of the processing equipment based on the model output results specifically includes: The efficiency coefficient generated by the processing equipment during normal operation within a preset time interval from the current time is taken as the historical efficiency coefficient, and the output power of the processing equipment that generates the maximum historical efficiency coefficient is taken as the characteristic power of the processing equipment. The efficiency level of the processing equipment is obtained by dividing the characteristic power of the processing equipment by the current output power of the processing equipment.

9. The method for global optimization of production efficiency applied to an industrial production line according to claim 8, characterized in that, The power boosting strategy triggered according to the efficiency level specifically includes: The minimum efficiency level of at least one processing device currently in operation is used as the factor to be increased, and the power of at least one processing device is increased by a factor equal to the factor to be increased.

Images