Abstract: The present invention discloses a method for onset time detection of a time-domain acoustic emission signal based on histogram distance. The method comprises the following steps: acquiring an acoustic emission signal; dividing the signal into two intervals with a sliding point k as the demarcation point; obtaining the relative frequency histograms of two adjacent intervals; obtaining histogram distance of the relative frequency histograms of two adjacent intervals; moving the sliding point k to the next element to obtain two new intervals and generating new histograms of the two new intervals and calculating the histogram distance of two new intervals; searching for the point which gives the maximum value of the histogram distances, and the corresponding time to this point is regarded as the onset time.

Abstract: Disclosed are a ship arrival prediction system and a ship arrival prediction method. The system includes a data acquisition module for acquiring historical sample data of a ship arrival; a data processing module connected with the data acquisition module and used for processing the historical sample data and converting the processed data into a two-dimensional matrix; a spatial temporal graph convolution layer module connected with the data processing module and used for modeling the converted data and obtaining optimal model parameters through training operations; and a full connection module connected with the spatial temporal graph convolution layer module and used for carrying out a dimensional reconstruction on an output result of the spatial temporal graph convolution layer module and outputting to obtain a predictive value of the ship arrival in each port.

Abstract: The present invention discloses a method of reducing octane loss in catalytic cracking of gasoline in S-Zorb plant. The method comprises following steps: a. Collecting equipment data and adjusting differences thereamong to construct initial data sample set; b. Collating data sample set; c. Employing local linear embedding to reduce dimension of independent variables, and trimming the independent variables to obtain reserved independent variables; d. Calculating correlation coefficients of the reserved independent variables and removing variables with too high correlation coefficients to obtain main variables; e. Constructing a BP neural network model of the main variables to obtain optimal octane loss prediction model; f. Employing the optimal octane loss prediction model to obtain a predicted optimal operating condition for each main variable. The present invention has advantage of reducing octane loss and improving quality of refined oil.

Abstract: The present invention discloses a method for onset time detection of acoustic emission signals based on histogram distance. The method comprises the following steps: acquiring an acoustic emission signal; dividing the signal into two intervals with a sliding point k as the demarcation point; obtaining the relative frequency histograms of two adjacent intervals; obtaining histogram distance of the relative frequency histograms of two adjacent intervals; moving the sliding point k to the next element to obtain two new intervals and generating new histograms of the two new intervals and calculating the histogram distance of two new intervals; searching for the point which gives the maximum value of the histogram distances, and the corresponding time to this point is regarded as the onset time.

Abstract: The present invention discloses a method for identifying travel classification based on smartphone travel surveys. The method takes individual volunteers as the object, GPS information collected by smartphones and instant recall verification features of respondents as the data source. First, travel features, individual features, and family features are determined by GPS data and questionnaire information of volunteers. Then, a training data set is determined by the equal proportion method. Finally, an artificial neural network combined with a particle swarm optimization algorithm is used to detect travel classification from the survey data. The method described in the invention can realize automatic identification of six travel classifications. It is conducive to replace the traditional resident travel survey with the advanced survey method under the environment of big data. At the same time, it provides data foundation for urban management and planning.

Abstract: The present invention discloses a method of reducing octane loss in catalytic cracking of gasoline in S-Zorb plant. The method comprises following steps: a. Collecting equipment data and adjusting differences thereamong to construct initial data sample set; b. Collating data sample set; c. Employing local linear s embedding to reduce dimension of independent variables, and trimming the independent variables to obtain reserved independent variables; d. Calculating correlation coefficients of the reserved independent variables and removing variables with too high correlation coefficients to obtain main variables; e. Constructing a BP neural network model of the main variables to obtain optimal octane loss prediction model; f. Employing the optimal octane loss prediction model to obtain a predicted optimal operating condition for each main variable. The present invention is different from traditional chemical mechanism method at aspect of building FCC technology process.

Abstract: A method for determining the excitation frequency of vibratory stress relief by employing a system for determining the excitation frequency of vibratory stress relief is disclosed, comprising the steps of: connecting the component to the system for determining excitation frequency of vibratory stress relief; selecting a group of preferred excitation frequency of the vibratory stress relief according to the results of numerical simulation; obtaining the reference voltage peak of the sinusoidal signal from the preferred excitation frequency, and transforming the sinusoidal signal into an excitation signal for vibratory stress relief treatment; converting the vibration signal of the component during vibratory stress relief treatment into voltage signal to obtain the actual voltage peak; comparing the actual voltage peak with the reference voltage peak, and selecting the frequency with the maximum difference of voltage peak as the excitation frequency for the vibratory stress relief treatment.

Abstract: A high-frequency vibration welding conditioning system for achieving better metal material properties is disclosed, which comprises a host computer, a signal generator, a power amplifier, a high-frequency vibrator, a high-frequency vibration energy amplification and transfer device, an acceleration sensor, and a cooling module, the host computer controlling the signal generator to output a sinusoidal excitation signal which is independently and continuously adjustable in amplitude and frequency, the sinusoidal excitation signal being inputted to the high-frequency vibrator via the power amplifier.

Abstract: The present invention discloses a method of constructing a high-frequency vibratory stress relief device for eliminating residual stress of a small work-piece.

Abstract: A system for determining the excitation frequency of vibratory stress relief is disclosed, comprising a host computer system, an arbitrary waveform generation card, a driver, a vibration exciter, an acceleration sensor, a charge amplifier, a data acquisition card, and a support device. The vibration exciter is mounted on the surface of a component, and the component is supported by the elastic support device; the host computer system comprises a finite element numerical simulation module, a preferred excitation frequency determination module, a reference voltage peak setting module, an excitation signal synthesis module, a voltage signal acquisition module, a Fourier transform module, an actual voltage peak acquisition module, and a voltage peak difference storage module.

Abstract: A high-frequency vibration welding conditioning system for achieving better metal material properties is disclosed, which comprises a host computer, a signal generator, a power amplifier, a high-frequency vibrator, a high-frequency vibration energy amplification and transfer device, an acceleration sensor, and a cooling module, the host computer controlling the signal generator to output a sinusoidal excitation signal which is independently and continuously adjustable in amplitude and frequency, the sinusoidal excitation signal being inputted to the high-frequency vibrator via the power amplifier.