Safety Of Equipment Operation Research Articles

Reserving embedding space for new fault types: A new continual learning method for bearing fault diagnosis

In complex operating environments, rotating equipment may continually generate new fault categories, affecting the safety of equipment operation, and the number of collected fault samples is limited, which make it difficult to establish a reliable diagnostic model. Few-shot continual learning (FSCL) can continuously learn and summarize fault knowledge from limited samples. These traditional FSCL models, when learning from limited samples of new types of bearing faults, exhibit model overfitting and catastrophic forgetting issues after self-updating (new model). This phenomenon significantly limits the reliability of traditional models. This paper presents a new approach coined as reserving embedding space for new fault types (RESNFT) for continual learning of newly occurred bearing faults for machinery fault diagnosis, which includes several key and new ideas. Preliminary, a class prototype (prototype vector) is derived to replace a classifier weight. Then, embedding space reserved by forcibly assigning real fault samples to both real and virtual categories can mitigate catastrophic forgetting. Finally, virtual faults formed by sample mixing guide new fault samples to the reserved embedding space, and realize continuous classification of new faults. Results show that the RESNFT can effectively alleviate the catastrophic forgetting and overfitting problems, and it is superior to other existing methods.

Parameter sharing fault data generation method based on diffusion model under imbalance data

Abstract Rotating machinery will inevitably fail under long-term heavy load working conditions. Obtaining enough data to train the deep learning model can enable managers to detect and deal with related failures in time, which greatly improves the safety of equipment operation. Mechanical fault samples are often much smaller than healthy samples. Traditional data enhancement methods mostly change the original data, but cannot improve the diversity of its features, so that the number of fault samples becomes larger, but the features remain unchanged. Aiming at the above problems, a diffusion model based on parameter sharing and inverted bottleneck residual structure (DDPM) is proposed. Firstly, the diffusion process gradually covers the original data with Gaussian noise, to learn the corresponding fault characteristics of the original data. In the diffusion process, the parameter sharing attention mechanism is embedded in the learning process of the diffusion process. Then, the feature extraction module is constructed by using the inverted bottleneck residual structure to enhance the learning ability of the network. After obtaining the fault characteristics of the original data, the reverse process of the results restores the Gaussian noise to data with different fault characteristics through the same steps as the diffusion process. By comparing the results of various generation models and analysing the characteristics of the generated data, the feasibility and universality of the proposed method in data augmentation tasks are verified.

Applying Systems Thinking to Research into Risk Factors Influencing Earthmoving Equipment Operation Safety in Construction Sites

Earthmoving operations in the construction process are complex environments that involve interactions between equipment, the workforce, and materials within an overarching construction plan. Over the past two decades, researchers in construction have focused on improving the safety of construction earthmoving equipment due to their omnipresence in the construction environment. Although previous studies have explored safety risks and the causes of accidents involving construction earthmoving equipment, their approaches were common and lacked a comprehensive perspective. Hence, this systematic literature review applies Rasmussen’s (1997) risk management framework using a systems thinking approach to identify and classify the risk factors influencing earthmoving equipment operation safety in construction sites. Utilizing a multistep methodology, this research first identifies 38 risk factors pertinent to earthmoving equipment operations and then classifies them based on systems thinking. Social network analysis (SNA) is employed to analyze the data. The results show that most research on earthmoving equipment safety focuses on monitoring construction sites, but very little on government and regulatory roles. When considering the interdependencies of risk factors, safety training is the most important factor, followed by the largely overlooked earthmoving machinery characteristics and manufacturer’s performance. The results of this review inform both the research community and industry practitioners regarding the less-understood aspects of earthmoving equipment operation safety and future research directions.

Research on Key Technologies for Intelligent Analysis of Escalator Risk Management in Large Transportation Hub

Transportation hubs are an important component of urban transportation systems, and their special equipment such as elevators and escalators have characteristics such as high working pressure, high frequency of use, and complex load changes. Once an accident occurs, it will have immeasurable impacts on public life safety and social stability. Building a smart large-scale transportation hub special equipment management system is the cornerstone of “smart city” construction, reducing equipment failure and accident rates, improving operational efficiency and service quality, as well as reducing operating costs and improving the economic benefits of enterprises. This article discusses the risk management of special equipment in transportation hubs from several aspects, including quality control of equipment maintenance and upkeep, investigation and risk assessment of equipment hazards, training on equipment operation safety, improvement and inspection of safety management systems, and emergency response to accidents. A risk governance intelligent analysis model with five levels of description model, judgment model, prediction model, decision model, and value model has been proposed as an indicator to evaluate whether the process of intelligent analysis of special equipment risk governance is “intelligent”.

Approaches to Sustainable Energy Management in Ensuring Safety of Power Equipment Operation

The study considers ways to ensure the quality of the functioning of power equipment as one of the directions for ensuring the safety of energy complexes in the period of “green transformation”. Based on the analysis, it is established that for an effective “green” transformation, it is necessary to ensure the energy safety of equipment operation, which is possible by developing effective science-based approaches to technical diagnostics of the state of power systems and individual equipment. The main objective of the study is to develop a Safety Management Model for Life Term Operation of power equipment, which takes into account changes in its condition at different stages of operation and allows for the prediction of further safe operation. The paper proposes an approach to researching the technical condition of power equipment, taking into account the deformations that occur during operation. The results of the calculation of stress intensity coefficients for longitudinal and transverse-postulated cracks in different modes are presented. Based on the calculated and experimentally obtained values, an approach to predicting the operating life of power equipment with regard to changes in technical characteristics is proposed. The results of the calculations showed that by changing the allowable load on the material of the energy equipment to 35 kgf/mm2, the estimated operational lifespan could be extended until 2035, ensuring all necessary safety conditions. It has been proven that with effective management and continuous safety diagnostics, nuclear power plants have the potential to operate beyond their standard design life of up to 30–40 years. This approach allows for the quality and safe operation of power equipment in the context of the transition to sustainable energy.

Study on the interaction mechanism between degradation behavior of grease and evolution of friction interface properties under static storage conditions

Long-term static storage of the ball screws result in interactive degradation of the grease and the friction interface, affecting the safety of equipment operation. In this study, the physical structure of the grease under static storage was found to be a sensitive factor for degradation. Subsequently the interaction mechanism between degradation of grease and the evolution of interface property was revealed. The aggregation and adsorption behaviors of thickener-base oil, thickener-metal interface, and base oil-metal interface were investigated by the molecular dynamic simulation. Further, interface characteristics and grease degradation respectively affect the value and duration of the growth phase of friction. This study can provide guidance for the phenomenon of increased starting torque of equipment relying on ballscrew after long-term standby.

Attention-Based Bilinear Feature Fusion Method for Bearing Fault Diagnosis

The bearing is the key component of rotating mechanical equipment, so the fault diagnosis of bearings is important to improve the reliability and safety of equipment operation. In recent years, feature fusion method has been extensively explored in the health monitoring and fault diagnosis of bearings. However, almost all the existing feature-fusion-based fault diagnosis methods extract features from different signals independently and concatenating them simply. It will lead to the failure of achieving the expected diagnostic accuracy because the complementary fault information is not fully mined and fused. This article proposes a novel bearing fault diagnosis approach based on mutual attention and bilinear model to address these issues. The features extracted from different input are interactive through mutual attention and are fused by the bilinear model, so the complementary fault features are effectively extracted and fine-grained fused. Experiments are conducted on the Paderborn bearing dataset to verify the effectiveness of the proposed method. Results show that the proposed method can effectively extract complementary fault features from different signals and deeply fuse them, and its diagnosis accuracy is up to 99.86%. Its performance is much better than that of simple concatenation and the feature fusion methods proposed in the reference.

Research on the Spillover Effect of Different Types of Technological Innovation on New Energy Industry: Taking China’s Solar Photovoltaic as an Example

Technological innovation has always played a very important role in the development of new energy industries. This paper takes the solar photovoltaic industry as an object of study, taking into account the diffusion of technological advances and the different roles of different technological innovations, and uses a spatial econometric SDM model to analyze the spillover effects of different types of technological advances on the solar industry in China. It is found that for the PV industry, efficiency-enhancing technological advances have the most significant impact, with efficiency-enhancing technologies contributing significantly to the annual electricity production of the PV industry; safety-enhancing technological advances having the second highest impact on the industry’s development; and cost-reducing technological advances have no significant impact on the industry. The study also found that due to the positive externalities of technological innovation, the spillover effect of technological innovation between regions has a significant impact on the development of the regional solar PV industry. In the long term, the direct effect of efficiency-enhancing technological innovation on the development of the PV industry is significantly positive, while the direct effect of safety-enhancing technological innovation on the development of the PV industry is significantly negative. Therefore, in the future, China’s solar energy industry should combine the capital investment of different types of science and technology into research and development, fully consider the impact of regional and technological spillover on industrial development, use technological innovation spillover to promote technological exchange and progress, and continuously improve the level of equipment operation safety, output efficiency, and electricity cost.

Operation Optimization Study of Integrated Energy System with Electric and Thermal Coupling Characteristics

The differences in inertia effects on multiple energy sources cause an imbalance between energy supply and load demand. Therefore, an operation optimization method for a comprehensive energy system with electric and thermal coupling characteristics is proposed. This method adopts the thermal system to reduce the system operation cost and improve operational reliability. Firstly, the method takes the energy transmission network of IES as the basis and establishes the model of the heating pipeline. Secondly, the method also takes the lowest total operating cost of the system as the goal, combines the power balance and equipment operation safety and other constraints, considers the electro-thermal coupling characteristics, establishes the corresponding IES operation optimization model, and applies the genetic algorithm to solve it. Finally, the simulation results show that the method can effectively reduce the system operation cost while ensuring the smooth and safe operation of the equipment based on the optimization model.

Methodology of Designing Sealing Systems for Highly Loaded Rotary Machines

Higher parameters of centrifugal machines are constantly required, such as the pressure of the medium to be sealed and the speed of rotation of the shaft. However, as the parameters increase, it becomes more and more difficult to ensure the effectiveness of sealing. In addition, sealing systems affect the overall safety of equipment operation, especially vibration. In order to harmonize the sealing functions and increase the dynamic rigidity of the rotors of centrifugal machines, a method for modeling complex sealing systems has been developed. Non-contact seals are considered as hydrostatic–dynamic bearings that can effectively dampen rotor oscillations. A general approach to the analysis of non-contact seals as automatic control systems and an algorithm for constructing their dynamic characteristics at the design stage were proposed for the first time. Models of “rotor-gap seal”, impulse seal and “rotor–hydraulic face” systems, and seal-supports of a shaftless pump have been studied to assess the effect of these seal systems on the oscillatory characteristics of the rotor. Analytical dependencies are obtained for calculating the dynamic characteristics and stability limits of seals as hydromechanical systems. The directions for improving the safety of operation of critical pumping equipment due to a targeted increase in the rigidity of non-contact seals are determined, which leads to an increase in the vibration resistance of the rotor and the environ-mental safety of centrifugal machines. The paper proposes a method for designing sealing systems based on the configuration of sealing components in order to achieve harmonization between sealing and vibration reliability, taking into account oscillatory processes due to hydrodynamic sealing characteristics.

Decision-making Algorithm for Improving the Lifetime of Signal Equipment

The safety of equipment operation is important for the operation of rail transits. The lifetime of equipment and its improvement methods have become one of the key issues in the operation and maintenance of rail transits. Based on the fuzzy comprehensive evaluation process and evaluation result data, the decision-making algorithm for improving the lifetime of the equipment was discussed, including the strategy recommendation algorithm based on assessed data and the strategy matching algorithm based on case reasoning. Taking the actual data of onboard ATC equipment of Line 11 in a city as an example, the effectiveness of the two methods was verified. The methods in the study can support the decision-making process for maintenance departments.

Performance evaluation of a novel intelligent distributed mounting system for marine mechanical equipment

Machinery mounting system is one of the most significant vibration and noise attenuation technology for marine mechanical equipment. A novel intelligent mounting system having distributed intermediate mass light in weight, intelligent in function and small in installation space is presented. The performance of the novel distributed mounting system is analysed using a simplified but efficient theoretical model. The influences of system designing parameters including weight of intermediate mass, stiffness of isolators and mechanical impedance of foundation on vibration isolation efficiency are analysed. A scale experimental prototype was established to verify the accuracy of theoretical analysis. Conclusions of theoretical and experimental analysis reveal that stiffness of isolators should be chosen as small as possible under the premise of stability of system. The intermediate mass should be chosen within a reasonable range based on the index requested on isolation efficiency because substantial increase on intermediate mass will not lead to substantial increase on vibration isolation efficiency which is different from conventional methods to obtain considerable isolation efficiency. And intelligent safety mechanism designed to ensure the ultimate operation safety of equipment was introduced. The novel intelligent mounting system is qualified with the need of practical projects on vibration isolation efficiency and reliability standard, providing a new way for vibration engineer to choose when making mounting plan for marine machinery equipment.

Abnormal vibration analysis and treatment for No. 3 bearing bush of ultra - supercritical 1000MW turbine

When a power plant ultra-supercritical 1000MW steam turbine generator set was started in a cold state, the vibration value of NO.3 bearing bush exceeded the alarm value. Based on the mechanism of vibration, the fault diagnosis and troubleshooting of excessive vibration of the NO.3 bearing bush were carried out by consulting the historical operation trend and checking the maintenance records, and the cause of the fault was accurately analyzed. By adopting effective measures such as setting up the heating system of the middle pressure cylinder and setting up the starting steam parameters reasonably, the problem of excessive vibration value of the NO.3 bearing bush was completely solved and the hidden danger of equipment operation safety was eliminated.

A turbine energy storage utilization evaluate method in thermal power unit

In China, the improvement of thermal power unit's operational flexibility is an important way to solve the clean energy absorption problem. The comprehensive utilization of steam turbine energy storage is an effective way to improve the load regulation performance of thermal power unit. A turbine energy storage utilization comprehensive evaluate method is presented. In the method the unit performance influence and equipment safety influence of energy storage are normalizes as a single object optimization problem. The comprehensive index calculation result is used in online optimization of storage power utilizing range limiting. Test result shows that the comprehensive index calculation method can help restrain the negative influence of turbine energy storage utilization on equipment operation safety, thereby improves availability of the energy storage system and improves the operating flexibility of thermal power unit.

Aging State Detection of Viscoelastic Sandwich Structure Based on ELMD and Sensitive IA Spectrum Entropy

Viscoelastic sandwich structure is playing an important role in mechanical equipment, but therein viscoelastic material inevitably suffers from aging which affects structural service performance and the whole performance of equipment. Therefore, the aging state detection of viscoelastic sandwich structure based on vibration response signal is essential for monitoring the health state of structure and guaranteeing the operation safety of equipment. However, the weakness of structural vibration response variation caused by material aging make this task challenging. In this paper, a novel method based on ensemble local mean decomposition (ELMD) and sensitive IA spectrum entropy is proposed for this task. As an adaptive nonlinear and non-stationary signal processing method, ELMD is introduced to decompose the structural vibration response signal, and a series of instantaneous amplitudes (IAs) are obtained. Then, the spectrum entropies of these IAs are developed to quantitatively assess the aging state of viscoelastic sandwich structure. However, the IA spectrum entropies have different sensitivities to the aging state. Therefore, the most sensitive IA spectrum entropy is selected with a distance evaluation technique to detect the aging state of viscoelastic sandwich structure. In order to demonstrate the effectiveness of the proposed method, the experimental device of a viscoelastic sandwich structure is designed, and different structural aging states are created through the accelerated aging of viscoelastic material. The results show the outstanding performance of the proposed method.

Evaluation of dependability indicators of NK, NKV and NPS type pumps

One of the strategic areas of development of all oil refineries (OR) in the Russian Federation is the improvement of equipment dependability and safety. The regulatory framework often does not take into consideration the design features of devices which, on the one hand, standardizes the service conditions, but, on the other hand, may cause inefficient maintenance of individual types of equipment. Due to the unpreparedness of the Russian oil refining complex to migration from scheduled preventive maintenance to condition-based maintenance, a large number of obsolete equipment and unceasing growth of technology complexity in modern ORs, it is required to improve and update the statistical and analytical base of dependability indicators of the equipment in operation. Russian and foreign experience of OR operation shows that damaged OR pump equipment can cause significant material damage and human casualties. A fair share of faults and failures that can cause accidents in ORs is concentrated in pump and compressor facilities. Ensuring safety of equipment operation and ORs as a whole requires reducing the probability of accidents. To that effect, technical condition monitoring facilities are deployed and equipment diagnostics are performed. A priori information analysis is also an option. Results. The article presents the results of documental inspection of performed maintenance of NK, NKV and NPS type pumps of a Russian OR conducted for the purpose of improving dependability and safety of pump operation. Probabilistic and statistical methods were used. The article presents an analysis of dependability indicators based on Gomertz-Makeham parametric distribution. This distribution is widely used in survival analysis and characterizes both system deterioration, and the influence of factors that do not depend on operation time. The authors analyze maintenance operations and repair cycles, identify the least dependable pump components and most frequent repair operations, show the influence of total operation time on pump dependability indicators. For the inspected pumps, the availability factors, utilization factors and average time between maintenance have been defined. The analysis identified that the availability factor of pumps depends not only on the average time between maintenance (that in turn depends on the frequency of required maintenance), but also on the utilization factor of the pumps. Beside the conventional dependability indicators, i.e probability of no-failure and failure rate, based on pump failure rate analysis ultimate times to failure for the inspected pumps were identified. Ultimate time to failure is the operation time beyond which gradual deterioration process significantly accelerates and causes a growth of the number and/or quality of partial failures. A significant accumulation of partial failures results in the loss of function or destruction of equipment. This dependability indicator is the most important in insuring the normal operation from the point of view of operating services. Conclusions. The article shows taht the identification of the ultimate time to failure for improved dependability and reliability of equipment operation must involve regular updates of input data in order to identify the beginning of the process of equipment “aging” for prevention of accidents caused by out-of-limit tear and wear of equipment.

Studying the possibility of separate and joint combustion of Estonian shales and oil shale retort gas at thermal power plants

Results from investigations of joint and separate combustion of shale with a low heating value and oil shale retort gas (OSRG) are presented. The question about the possibility of further using shale as basic fuel is presently placed on the agenda. This matter is connected with the fact that the environmental regulations are imposing increasingly more stringent limits on emissions of harmful substances and that a decrease in the shale heating value is predicted. An adequate mathematical model of one of the TP-101 boilers installed at the Estonian power plant was developed and verified for carrying out investigations. Criteria for determining the reliability, efficiency, and environmental safety of equipment operation were formulated based on the operating chart, regulatory documents, and environmental requirements. Assessment of the possibility of boiler operation and the boiler unit as a whole in firing shale with a low calorific value has shown that despite fulfilling the required superheated steam parameters, quite a number of limitations relating to reliable operation of the boiler are not complied with. In addition, normal operation of forced-draft equipment and mills is possible only at low loads. For operation with joint combustion of shale and OSRG, the fractions of degraded-quality shale and OSRG (by heat) at which reliable and efficient operation of the boiler and boiler unit is ensured in the entire working range of loads with fulfilling the environmental standards are determined. Proposals on modifying the equipment for joint combustion of shale and OSRG are formulated. Boiler operation with firing OSRG as main fuel was modeled for three versions of furnace waterwall thermal efficiency with a view to estimate possible changes of boiler operation in carrying out waterwall cleaning operations. Calculation results have shown that operation of the boiler and boiler unit meeting the elaborated criteria is possible in the entire working range of loads with essentially increased the air excess factor at the furnace outlet in low load modes.

Improving Construction Equipment Operation Safety from a Human-centered Perspective

Construction equipment-related accidents are a major cause of workplace fatalities and injuries in the construction industry. Particularly, visibility issue (i.e. blind spots) has been recognized as one of the primary reasons for construction equipment related accidents and injuries. Although attempts have been made to alleviate the problem by providing external assistance to operators and laborers, being struck by objects and equipment remains the third leading cause of construction fatalities (behind falls and transportation incidents) for the past decade. Therefore, an in-depth understanding of how operators respond to the external assistance has great potential to improve operation safety from a human-centered perspective. This paper highlights a promising method of employing external views that provides additional spatial information to overcome the visibility problem. Challenges are discussed in human spatial ability-related aspects such as the additional spatial information may increase mental workload and introduce difficulties in processing the information. At last, potential research directions and experiments are discussed.

Small Sample Reliability Analysis of Automatic Ultrasonic Testing of Austenitic Steel Defect

Reliability analysis of the procedure of ultrasonic technique before inspection has been proved to be essential to ensure the equipment operation safety. The conventional evaluation methods are based on statistical models and a remarkable sample size is needed to get a accurate result. In this work, the Bootstrap model for small sample data is established based on the re-sampling technique. The probability of detection (POD) curves in different conditions are calculated based on the Bootstrap model, and used for quantitative analysis the influence of inspection parameter on stainless steel auto ultrasonic testing result. The calculated result based on bootstrap model is compared with which based on model assisted POD method. The results indicate that Bootstrap model is an efficient tool for the reliability analysis of inspection with small sample data, and insure the inspection result.

Digital monitoring and health diagnosis for mechanical equipment operation safety based on fiber Bragg grating sensor

This paper introduces fiber Bragg grating (FBG) based on a fiber optic grating sensor developed to be embedded on mechanical equipment for digital monitoring and health diagnosis. The theoretical and experimental researches on the new-style FBG sensor (FBGS) technology, high-speed demodulation, and data transmission are discussed. The transmission characteristics between the FBG and the detection interface, modeling and compensation method for online distributed multi-parameter digital monitoring and methods for data processing, synchronous sampling, and long-term dynamic digital monitoring using embedded technology are also presented. The acquired information by an FBGS can be used for the optimization of maintenance schedules and refinement of mechanical equipment design. It is a challenge to gather real-time data from components working at high speed and in a severe environment of high temperature, high pressure, and high rotation speed. Currently, there are no sensors or technologies available for digital monitoring and health diagnosis under this rigorous situation for use in mechanical engineering operation safety. As a result, this paper introduces an online distributed and integrated digital monitoring system and health diagnosis. The new principle and new method will contribute to modern measurements in science and technology, mechanical engineering, and large mechanical equipment operation safety.