Maximum Power Spectral Density Research Articles

Sample entropy-based quantitative assessment of the arc magnetic field spectrum for improved arc welding quality

Arc magnetic field analysis is a valuable approach for assessing the stability of the arc welding process, yet existing methods lack the ability to effectively quantify the disorder within the process. Through an investigation into the characteristics of the arc magnetic field signal, it was observed that the occurrence of low-frequency random fluctuations in arc magnetic field power, induced by unstable factors such as bubbles or short circuits, contributed to increased complexity and randomness in the arc magnetic field signals. To visualise the arc magnetic field signals in a time-frequency domain, a spectrogram was employed, revealing a strong correlation between the distribution of maximum power spectral density (PSD) in the spectrogram and the stability of the arc welding process. Furthermore, a novel method based on sample entropy was introduced to provide a quantitative measure of this relationship. A comprehensive quantitative assessment indicator called arc magnetic field sample entropy (AMFSE) was proposed. This indicator effectively mitigates the influence of varying parameters on the quantitative results, enabling a more accurate and consistent representation of the stability of the arc welding process. The proposed method was validated through testing, yielding an accuracy rate exceeding 90%.

K-wire is more damaging than standard or acrylic drill bits when evaluating torsional properties of rabbit (Oryctolagus cuniculi) femurs.

The objective of this study is to compare drilling variables and torsional mechanical properties of rabbit femora after bicortical drilling with a 1.5-mm standard surgical drill bit, acrylic drill bit, and K-wire. 24 pairs of rabbit femora. After drilling under controlled axial displacement rate, each bone was biaxially loaded in compression followed by rapid external torsion to failure. Maximum axial thrust force, maximum drill torque, integral of force and displacement, change in temperature, maximum power spectral density of the torque signal, torque vibration, and torque and angle at the yield and failure points were collected. Pre- and postyield stiffness, yield and failure energies, and postyield energy were calculated. The work required to drill through the cis- and transcortices (integral of force and displacement) was greater for the K-wire, followed by the acrylic and then standard drill bits, respectively. The K-wire demonstrated higher maximum torque than the drill bits at the ciscortex, and the force of drilling was significantly greater. The vibration data was greater with the acrylic and standard drill bits than the K-wire. There was no difference in torsional strength between drilling types. Mechanical differences exist between different drill bits and K-wire and demonstrate that the K-wire is overall more damaging than the surgical drill bit.

Asphalt Pavement Transverse Cracking Detection Based on Vehicle Dynamic Response

Transverse cracking is thought of as the typical distress of asphalt pavements. A faster detection technique can provide pavement performance information for maintenance administrations. This paper proposes a novel vehicle-vibration-based method for transverse cracking detection. A theoretical model of a vehicle-cracked pavement vibration system was constructed using the d’Alembert principle. A testing system installed with a vibration sensor was put in and applied to a testing road. Then, parameter optimization of the Short-time Fourier transform (STFT) was conducted. Transverse cracking and normal sections were processed by the optimized STFT algorithm, generating two ideal indicators. The maximum power spectral density and the relative power spectral density, which were extracted from 3D time–frequency maps, performed well. It was found that the power spectral density caused by transverse cracks was above 100 dB/Hz. The power spectral density at normal sections was below 80 dB/Hz. The distribution of the power spectral density for the cracked sections is more discrete than for normal sections. The classification model based on the above two indicators had an accuracy, true positive rate, and false positive rate of 94.96%, 92.86%, and 4.80%, respectively. The proposed vehicle-vibration-based method is capable of accurately detecting pavement transverse cracking.

Evidence for human-centric in-vehicle lighting: part 3-Illumination preferences based on subjective ratings, eye-tracking behavior, and EEG features.

Within this third part of our mini-series, searching for the best and worst automotive in-vehicle lighting settings, we aim to extend our previous finding about white light illumination preferences by adding local cortical area activity as one key indicator. Frontal electrical potential asymmetry, measured using an electroencephalogram (EEG), is a highly correlated index for identifying positive and negative emotional behavior, primarily in the alpha band. It is rarely understood to what extent this observation can be applied to the evaluation of subjective preference or dislike based on luminaire variations in hue, chroma, and lightness. Within a controlled laboratory study, we investigated eight study participants who answered this question after they were shown highly immersive 360° image renderings. By so doing, we first subjectively defined, based on four different external driving scenes varying in location and time settings, the best and worst luminaire settings by changing six unlabeled luminaire sliders. Emotional feedback was collected based on semantic differentials and an emotion wheel. Furthermore, we recorded 120 Hz gaze data to identify the most important in-vehicle area of interest during the luminaire adaptation process. In the second study session, we recorded EEG data during a binocular observation task of repeated images arbitrarily paired by previously defined best and worst lighting settings and separated between all four driving scenes. Results from gaze data showed that the central vehicle windows with the left-side orientated colorful in-vehicle fruit table were both significantly longer fixed than other image areas. Furthermore, the previously identified cortical EEG feature describing the maximum power spectral density could successfully separate positive and negative luminaire settings based only on cortical activity. Within the four driving scenes, two external monotonous scenes followed trendlines defined by highly emotionally correlated images. More interesting external scenes contradicted this trend, suggesting an external emotional bias stronger than the emotional changes created by luminaires. Therefore, we successfully extended our model to define the best and worst in-vehicle lighting with cortical features by touching the field of neuroaesthetics.

Preliminary Results on Low Frequency Passive Seismic (LFPS) Study in Lake Toba

Sumatra Island is an island located in the subduction zone of the Indo-Australian plate towards Eurasia. The geological structure on the island of Sumatra is the Semangko Fault. There is active volcanic activity, such as the Bukit Barisan Mountains, which makes Sumatra Island vulnerable to volcanic eruptions. The study was conducted in Lake Toba, North Sumatra, using earthquake data from the IRIS station. The purpose of this study is to investigate the amplitude in determining the presence of fluid reservoirs (magma) and to analyze the volcanics of the Lake Toba region using the Low Frequency Passive Seismic (LFPS) method by utilizing attributes such as maximum amplitude Vertical-to-Horizontal Spectral Ratio (VHSR), maximum amplitude of Power Spectral Density (PSD) Z, and the maximum amplitude spectrum of the Z component, which are used as indicators to connect the subsurface fluid reservoir by looking at the spectrum curve. Previous research has linked the presence of a reservoir to the peak amplitude spectrum in the vertical component in the frequency range 1-6 Hz. Based on the research results from the analysis of all attribute parameters obtained, the maximum anomaly of the maximum VHSR amplitude spectrum, the maximum PSD Z amplitude, and the maximum Z component amplitude spectrum indicate that the location with the highest subsurface fluid reservoir potential is in the Northwest-Southeast around Lake Toba and Samosir island. These results support previous research. Volcanic activity in Lake Toba is relatively lower because the amplitude spectrum values of all attribute parameters are not too high.

Epileptic seizure detection combining power spectral density and high-frequency oscillations

Detection of pre-seizure signs in epileptic signals may help patients to survive the seizure with minimal damage. This study aims to detect epileptic seizure patterns using EEG datasets of five patients. The signals' maximum power spectral density (PSD) and high-frequency oscillations (HFOs) signals are investigated. The PSDs of all patients' signals are calculated, and the subbands of the maximum PSD are examined. It is observed that 95%, 85%, 85%, 75%, and 80% of the channels of the five patients are in the sum of delta and theta subbands of the maximum PSD, respectively. All patients' maximum power frequency subbands of F4 and T3 channels included only delta and theta subbands. Furthermore, frequency increase rates of pre-ictal and ictal signals are investigated, and increasing PSDs of ripples and fast ripples are then calculated. A much higher-frequency ripple follows the low-frequency ripple in 75%, 75%, 65%, 85%, and 75% of the channels of the first, second, third, fourth, and fifth patients, respectively. For the pre-ictal data, a much higher frequency ripple is not seen, followed by a low-frequency ripple in 90%, 85%, 75%, 90%, and 90% of all channels of five patients, respectively. In addition, in this study, the frequency of signals is observed to be 80 Hz and above in the Fp2, C4, P4, O2, and Pz channels, which are common to all patients. Consequently, examining PSD and HFO signals ensures the detection of the differences between the data sets and detects the epileptic seizure patterns in all five patients.

High-power supercontinuum lasers with a flat blue spectrum through pump modulation: a numerical study.

We numerically investigate high-power, modulational instability-based supercontinuum sources. Such sources have spectra that reach the infrared material absorption edge and as a result the spectrum has a strong narrow blue peak (dispersive wave group velocity matched to solitons at the infrared loss edge) followed by a significant dip in the neighboring longer-wavelength region. In a wide range of applications one prefers a broader and more flat blue part within a certain minimum and maximum power spectral density. From the perspective of fiber degradation it would be desirable to achieve this at reduced pump peak powers. We show that it is possible to improve the flatness by more than a factor of 3 by modulating the input peak power, although this comes at the expense of slightly higher relative intensity noise. Specifically, we consider a standard 6.6 W, 80 MHz supercontinuum source with a 455 nm blue edge, which uses 7 ps pump pulses. We then modulate its peak power to generate a pump pulse train having two and three different sub-pulses.

Performance study of semi-active seat suspension added by quasi-zero stiffness structure under various vibratory roller models

To enhance the vibratory roller’s comfort, three different types of seat suspension including the seat’s semi-active suspension system (SASS) controlled by the FLC-PID controller, seat’s passive suspension system (PSS) added by the quasi-zero stiffness structure (QZSS), and seat’s SASS added by the QZSS are proposed. Three different vehicle dynamic models including a one-dimensional (1D) model, two-dimensional (2D) model, and three-dimensional (3D) model are established to evaluate the performance and stability of the seat’s suspension systems under different operating conditions. The root mean square (RMS) acceleration and power spectral density (PSD) acceleration of the seat have been selected as the evaluation indexes. The mathematical model and numerical simulation method are then tested via the experiment to enhance the reliability of the research results. The research result shows that the seat’s vibration characteristic using 1D, 2D, and 3D models is the same. However, the seat’s RMS acceleration and maximum PSD acceleration using the 1D model are increased by 30.6% and 61.7% in comparison with the 3D model, whereas the seat’s acceleration and PSD acceleration using the 3D model are like the measured results. Thus, the use of the vehicle model greatly influences the research result. By adding the QZSS into the seat’s SASS, the seat’s RMS and maximum PSD accelerations are greatly reduced in comparison with all seat’s PSS, seat’s SASS without the QZSS, and seat’s PSS added by QZSS. Therefore, the seat’s SASS added by the QZSS should be applied to further enhance the vibratory roller’s comfort.

Leveraging Accelerometry as a Prognostic Indicator for Increase in Opioid Withdrawal Symptoms.

Treating opioid use disorder (OUD) is a significant healthcare challenge in the United States. Remaining abstinent from opioids is challenging for individuals with OUD due to withdrawal symptoms that include restlessness. However, to our knowledge, studies of acute withdrawal have not quantified restlessness using involuntary movements. We hypothesized that wearable accelerometry placed mid-sternum could be used to detect withdrawal-related restlessness in patients with OUD. To study this, 23 patients with OUD undergoing active withdrawal participated in a protocol involving wearable accelerometry, opioid cues to elicit craving, and non-invasive Vagal Nerve Stimulation (nVNS) to dampen withdrawal symptoms. Using accelerometry signals, we analyzed how movements correlated with changes in acute withdrawal severity, measured by the Clinical Opioid Withdrawal Scale (COWS). Our results revealed that patients demonstrating sinusoidal-i.e., predominantly single-frequency oscillation patterns in their motion almost exclusively demonstrated an increase in the COWS, and a strong relationship between the maximum power spectral density and increased withdrawal over time, measured by the COWS (R = 0.92, p = 0.029). Accelerometry may be used in an ambulatory setting to indicate the increased intensity of a patient's withdrawal symptoms, providing an objective, readily-measurable marker that may be captured ubiquitously.

Study of the Statistical Characteristics of Artificial Source Signals Based on the CSES

The ground-based artificial source electromagnetic signal transmitted to space will form a pair of intensity regions over the station and its conjugate point. In order to study the position and intensity of the strongest points in the two regions, the power-spectrum density (PSD) of the electric field on board the Zhangheng-1 satellite (CSES) was selected when it passed over the NWC artificial source transmitting station. The selected frequency is centered at 19.8 kHz with a bandwidth of 200 Hz. The strongest point is defined as the location with the maximum power spectral density of ±10° around the NWC station within 5 days, which is the revisiting period of the CSES. The results show that statistical characteristics of strongest points vary as day/night, local/conjugate point, longitude/latitude, and different components of electric field vectors. In terms of longitude deviation, it is mostly westward offset at night and on both sides in the day over the NWC but opposite at the conjugate point. In terms of latitude deviations, it is equator-ward at night and the same during the day with a smaller deviation. While over the conjugate point, it is northward offset in the day and both at night with a bigger offset. In terms of intensity, it is stable without obvious seasonal changes over the NWC and its conjugate point. The intensity of PSD is higher at night than during the day. For the PSD intensity of the three components, the descending order over the NWC is Ead, Eab, and Ecd at night and Ecd, Ead, and Eab in the day, and the opposite is true for over the conjugate point.

VGA With Voltage Feedback, Constant Bandwidth and a High Degree of Independence Between Amplifier and Gain Controller

The following paper is devoted to an amplifier with gain control (Variable Gain Amplifier). The role of amplification and gain control is addressed separately from the very beginning, to achieve the greatest possible independence of the required parameters both for the amplifier itself (gain size, bandwidth, noise figure) and for the gain controller (energy consumption control, distortion). The core of the amplifier consists of an operational amplifier with voltage feedback (VFB) in an inverting circuit, to the feedback of which a gain regulator executed with a diode bridge is connected in parallel. The analysis of the simplified circuit model shows that it is possible to obtain a variable-gain amplifier that maintains its bandwidth. The control of the gain is continuous and only one element, the variable resistance, is sufficient for its control. This resistance can be achieved by a number of components, either by a rheostat, by the resistance of the FET transistor channel (the FET control is related to GND, which is advantageous), or by the resulting dynamic resistance of the diode bridge. Continuous control with one element preserving the bandwidth of an operational amplifier with VFB is unique and the authors are unaware of any other similar solution. If maximum gain is required, the diode bridge is disconnected and does not contribute to the resulting noise of the VGA amplifier. Because the diode bridge is connected between the output of the operational amplifier and its inverting input, and because the inverting input is current controlled, the diode bridge processes only a portion of the output voltage of the amplifier, thus preventing more noticeable distortion. The distortion is further suppressed due to the simultaneous action of four diodes in the bridge, whose characteristics are reciprocal for the signal path. The presented construction is relatively simple and can be a topic not only for other microelectronic structures, but also for applications from discrete components. The achieved parameters of the presented connection are as follows: gain change 0 to 20 dB, constant bandwidth 7 MHz, distance III. harmonics min. 30 dB at an output voltage of 0.5 V, maximum power spectral density at the output 25 ∙10-15 V2Hz-1.

Comparison of apple firmness prediction models based on non‐destructive acoustic signal

AbstractThis paper aimed to explore the non‐destructive detection of apple firmness based on portable acoustic signals for consumers. The acoustic eigenvalues processed by Time‐domain, Fourier Transform (FT), and Hilbert Huang Transform (HHT) are used to analyse the correlations with apple firmness. The apple firmness prediction models are established through Multiple Linear Regression (MLR) and Artificial Neural Network (ANN). The results proved that the acoustic eigenvalues of wave index form and total energy of 8–9 kHz correlated with apple firmness (P < 0.05), the significant acoustic eigenvalues of sound intensity, amplitude difference, max frame energy, maximum power spectral density, power spectral density characteristics and total energy of 0–1 kHz significantly correlated with apple firmness (P < 0.01). The average relative error of ANN model was significantly lower than that of MLR model (P < 0.05). Compared with Time‐FT, the acoustic eigenvalues processed by a combination of Time‐FT‐HHT possessed a superior effect on the prediction model established by ANN of apple firmness.

A Digitally Controlled Multichannel Spectrally Efficient Low-Power Transceiver for Ultra-Wideband Cognitive Radio Applications

A multichannel transceiver design with low hardware complexity, flexibility and efficient spectrum use intended for Impulse Radio (IR) Ultra-Wideband (UWB) apertures, is proposed in this paper. The transceiver supports 14 channels and is implemented in TSMC CMOS process. The transmitter adopts a symmetrical triangular narrow pulse generator, a multiband LC-VCO, a mixer and a Variable-Gain Amplifier. A digital control of transmitter output power and carrier frequency is achieved by a current-steering Digital-to-Analog Converter (CS-DAC). The receiver follows the noncoherent Energy Detection (ED) scheme including Low-Noise Amplifier (LNA) which takes the benefits of the body biasing technique to further reduce power consumption, squarer and comparator. The LNA achieves high gain of up to 30[Formula: see text]dB allowing to enhance the receiver sensitivity which is [Formula: see text]83.7[Formula: see text]dBm at 25[Formula: see text]Mbps. The transmitter provides output pulses with a width of 3[Formula: see text]ns, a pulse repetition rate of 20[Formula: see text]ns and a maximum Power Spectral Density (PSD) of [Formula: see text]42[Formula: see text]dBm/MHz. The power consumptions of transmitter and receiver are 35.6[Formula: see text]pJ/bit and 0.207[Formula: see text]nJ/bit at 25[Formula: see text]Mbps, respectively. Maximizing utilization of the scarce wireless spectrum, enhancing spectral flexibility and efficiency and reducing power consumption are the main contributions brought by this work, enabling this transceiver to be able to deal with the current debate on producing single multifunctional Cognitive Radio (CR) UWB systems.

Transient Modeling and Recovery of Non-Stationary Fault Signature for Condition Monitoring of Induction Motors

This paper presents the modeling and the broken rotor bar fault diagnostics by time–frequency analysis of the motor current under an extended startup transient time. The transient current-based nonstationary signal is retrieved and investigated for its time–frequency response to segregate the rotor faults and spatial harmonics. For studying the effect of reduced voltage on various parameters and the theoretical definition of the fault patterns, the winding function analysis (WFA)-based model is presented first. Moreover, an algorithm to improve the spectrum legibility is proposed. It is shown that by efficient utilization of the attenuation filter and consideration of the area containing the maximum power spectral density, the diagnostic algorithm gives promising results. The results are based on the machine’s analytical model and the measurements taken from the laboratory setup.

Real-Time EEG Signal Classification for Monitoring and Predicting the Transition Between Different Anaesthetic States.

Quantitative identification of the transitions between anaesthetic states is very essential for optimizing patient safety and quality care during surgery but poses a very challenging task. The state-of-the-art monitors are still not capable of providing their manifest variables, so the practitioners must diagnose them based on their own experience. The present paper proposes a novel real-time method to identify these transitions. Firstly, the Hurst method is used to pre-process the de-noised electro-encephalograph (EEG) signals. The maximum of Hurst's ranges is then accepted as the EEG real-time response, which induces a new real-time feature under moving average framework. Its maximum power spectral density is found to be very differentiated into the distinct transitions of anaesthetic states and thus can be used as the quantitative index for their identification.

New Reconstruction Method for Needle Contrast Optimization in B-Mode Ultrasound Image by Extracting RF Signal Parameters in Frequency Domain

Ultrasound-guided needle insertion has become standard in medical interventional procedures. Regardless of its advantages, it still has crucial problems related to needle visibility. Some technical factors affect the visibility with non-linear characteristic, i.e. frequency, insertion angle and depth. Here, backscattered signal parameters from measurement were compared to a simulation of a resonance scattering model. Raw radio frequency (RF) data were reconstructed with a new method to represent unique information on total backpropagation from the needle, which consists of non-resonance and resonance scattering components. The result suggests that reconstruction of the needle in B-mode images should be derived from the maximum power spectral density and the energy spectral density to optimize the contrast of the needle. In measurements with the center frequency at 1.87 MHz, the effect of resonance scattering on the total backpropagation around critical angles could be observed more clearly with this method than with standard reconstruction based on the signal envelope. The simulation showed that the fractional bandwidth of the spectrum of the backscattered pressure field centered at 1.87 MHz was relatively optimal at 40% to 100%. So that the simulation of the resonance scattering model can be used to predict the backscattered response from the needle, it must be able to confirm it to the real conditions of RF data with random characteristics. Therefore, extraction of the backscattered pressure field in a simulation with fractional bandwidth should be a concern.

High-power single mode GaSb-based 2 μm superluminescent diode with double-pass gain

We report a broadband superluminescent diode operating around a 2 μm wavelength, optimized for high-power broadband operation. The high power operation is achieved by using a GaInSb/AlGaAsSb heterostructure positioned in a ridge waveguide with a J-shaped layout to form a double-pass geometry. To avoid lasing at high current while enabling high gain, a cavity suppression element is used. This combination allows demonstration of an output power as high as 120 mW for continuous-wave (CW) operation at room temperature, with a spectral full width at half maximum of about 43 nm. The maximum power spectral density was measured to be 1.8 mW/nm, which is about a fourfold increase compared to the state-of-the-art results for this wavelength range. To avoid heating, the diode was also driven with low duty-cycle current pulses; in this case, a peak power of more than 300 mW was achieved without any sign of roll-over (power was limited by the current injected). For CW operation, the central emission wavelength could be tuned by current injection between 1900 nm at 200 mA and 2027 nm at 2000 mA. Devices produce a Gaussian output beam that is suitable for coupling to single mode waveguides.

Numerical simulation of UV LEDs with GaN and BGaN single quantum well

The objective of this work is to simulate a single quantum well ultraviolet light emitting diode (LED) based on AlGaN/GaN/AlGaN and AlGaN/BGaN/AlGaN, by using TCAD Silvaco simulator. The first structure has a GaN quantum well taken between two layers, of n-AlGaN and p-AlGaN. The second one has a BGaN quantum well instead of GaN. We fix the concentration of the boron in BGaN to only 1% and we vary the thickness of GaN and BGaN quantum well layer from 7 to 20 nm, for the two structures. As results, we obtain respectively for GaN-LED and BGaN-LED, a maximum current of 0.52 and 0.27 mA, a maximum power spectral density of 1.935 and 6.7 W cm−1 eV−1, a maximum spontaneous emission of 3.34 × 1028 and 3.43 × 1028 s−1 cm−3 eV−1, and a maximum Light output power of 0.56 and 0.89 mW.

Design of Dual Band Wireless Power and Data Through RF Transmission for Biomedical Implants

In this paper, a new data and power recovery architecture for biomedical microsystem implants is proposed. Our contribution aims to overcome problems resulted by the trade-off between transmission data rate and power consumption for systems using the same or the separate inductive link to transmit data and power to the implanted part. The dual separate channels of RF powering and data recovery parts are designed to achieve the back telemetry data and power supply. The RF power recovery system is based on a 4-MHz RF link signal. It provides a regulated 3.3 V for the stimulating stage and 0.9 V for data recovery stage. The receiver based on a non-coherent topology consists of a 3–5-GHz low-noise amplifier (LNA), a squarer, an integrator, and a high-speed decision stage. The LNA of cascaded by cascode inductive source degenerative approach is proposed to decrease the noise figure when respecting linearity and stability conditions. It dissipates 8.89 mA from the 0.9-V power supply. The pulse generator produces an output signal with a maximum power spectral density (PSD) of − 66 dBm/MHz. The power consumption of the data transmission system is approximately equal to 0.664 mW for the emitter and 9.17 mW for the receiver. Simulation results show that this configuration can achieve a 125-Mbps data rate and − 82 dBm at 125-Mbps receiving sensitivity. This topology was designed in 0.18-μm RF-CMOS technology.

Numerical Optimization and Cyber-Physical- Social Computing for Vibrations of the Elliptical Treadmill Based on GSO-BPNN Model

The finite element method was used to compute the vibration characteristics of the elliptical treadmill, and the computational results were then compared with those of the experimental test to verify its correctness. The vibrations of the elliptical treadmill were optimized by glowworm swarm optimization back propagation neural network (GSO-BPNN) model to obtain an elliptical treadmill with the minimum mass and vibration. The experimental test was completed using the intelligent sensor device, and the collected signal will be processed by people. Therefore, in this paper, the numerical computation involved the cyber-physical-social system. The computational results proved that: Tri-axial excitation forces presented an obvious periodicity. Power spectral density was mainly distributed within 10–20 Hz. Power spectral densities of the elliptical treadmill with different materials were also mainly distributed within 10–20 Hz. In addition, the maximum peak value of power spectral densities of the elliptical treadmill with aluminum alloy was 2.1 g2/Hz, while the maximum peak value of power spectral densities of the elliptical treadmill with magnesium alloy was 1.7 g2/Hz. Compared with a steel elliptical treadmill, the maximum power spectral density of an aluminum elliptical treadmill was decreased by 19.2%, and the maximum power spectral density of a magnesium elliptical treadmill was decreased by 34.6%. Therefore, using magnesium alloy to make the elliptical treadmill can obtain a comparatively better structure. Vibration displacement, velocity and acceleration in Z direction were obviously more than those in X and Y directions and presented certain periodicity because excitation forces in Z direction were also the largest. GSO-BPNN model was compared with BP neural network model and genetic algorithm-BP neural network model. They adopted the same neural network topology structure to conduct a multi-objective optimization for the power spectral density and acceleration of the elliptical treadmill. GSO-BPNN not only improved the optimized accuracy, but also reduced the computational time.