AI-Based Condition Monitoring of Hydraulic Valves in Zonal Hydraulics Using Simulated Electric Motor Signals

Zonal hydraulics, in particular Direct Driven Hydraulics (DDH), is an emerging transmission and actuation technique that is proposed to be used for electrification of heavy-duty mobile machinery. In addition to the already demonstrated advantages of DDH, which include high efficiency, compactness, and ease of maintenance, it is also capable of condition monitoring. The condition monitoring features can be obtained through indirect analysis of the existing electric motor signals (voltage and current) using artificial intelligence-based algorithms rather than by adding extra sensors, which are normally required for conventional realization. In this paper, the valve condition monitoring method of the DDH through electrical motor signals is explored at an early development stage. Firstly, the hydraulic valve models, which involve the valve fault behaviors, are added to the basic DDH model. Secondly, healthy and faulty scenarios for the valves are simulated, and the data are generated. Thirdly, the preliminary artificial intelligence-based condition monitoring classifier is developed using the simulation data, including feature extraction, algorithm training, testing, and comparison of accuracy. The effects of modeling error on developing the condition monitoring function are analyzed. In conclusion, the preliminary outcomes for the valve condition monitoring of the DDH are achieved by taking advantage of modeling and simulation and by utilizing the existing electric motor signals.

Gated feedforward inhibition in the frontal cortex releases goal-directed action

Cortical circuits process sensory information and generate motor signals in animals performing perceptual tasks. However, it is still unclear how sensory inputs generate motor signals in the cortex to initiate goal-directed action. Here, we identified a visual-to-motor inhibitory circuit in the anterior cingulate cortex (ACC) that induced action initiation in mice performing visual Go/No-go tasks. Interestingly, higher activity in sensory neurons and faster suppression in motor neurons of the ACC predicted faster reaction times. Notably, optogenetic activation of visual inputs in the ACC evoked strong suppression of neighboring motor neurons by activating fast-spiking sensory neurons and drove task-relevant actions in mice via activating striatal neurons. Finally, the ACC network activity maintained low during spontaneous and perceptual actions and increased during action cancellation in response to the stop signals. Collectively, our data demonstrate that visual salience in the frontal cortex exerts gated feedforward inhibition to release goal-directed actions.

The Translesional Spinal Network and Its Reorganization after Spinal Cord Injury

Evidence from preclinical and clinical research suggest that neuromodulation technologies can facilitate the sublesional spinal networks, isolated from supraspinal commands after spinal cord injury (SCI), by reestablishing the levels of excitability and enabling descending motor signals via residual connections. Herein, we evaluate available evidence that sublesional and supralesional spinal circuits could form a translesional spinal network after SCI. We further discuss evidence of translesional network reorganization after SCI in the presence of sensory inputs during motor training. In this review, we evaluate potential mechanisms that underlie translesional circuitry reorganization during neuromodulation and rehabilitation in order to enable motor functions after SCI. We discuss the potential of neuromodulation technologies to engage various components that comprise the translesional network, their functional recovery after SCI, and the implications of the concept of translesional network in development of future neuromodulation, rehabilitation, and neuroprosthetics technologies.

Recurrent processes support a cascade of hierarchical decisions

Perception depends on a complex interplay between feedforward and recurrent processing. Yet, while the former has been extensively characterized, the computational organization of the latter remains largely unknown. Here, we use magneto-encephalography to localize, track and decode the feedforward and recurrent processes of reading, as elicited by letters and digits whose level of ambiguity was parametrically manipulated. We first confirm that a feedforward response propagates through the ventral and dorsal pathways within the first 200 ms. The subsequent activity is distributed across temporal, parietal and prefrontal cortices, which sequentially generate five levels of representations culminating in action-specific motor signals. Our decoding analyses reveal that both the content and the timing of these brain responses are best explained by a hierarchy of recurrent neural assemblies, which both maintain and broadcast increasingly rich representations. Together, these results show how recurrent processes generate, over extended time periods, a cascade of decisions that ultimately accounts for subjects’ perceptual reports and reaction times.

Sensorimotor signals underlying space perception: an investigation based on self-touch

Perception of space has puzzled scientists since antiquity and is among the foundational questions of scientific psychology. Classical “local sign” theories assert that perception of spatial extent ultimately derives from efferent signals specifying the intensity of motor commands. Everyday cases of self-touch, such as stroking the left forearm with the right index fingertip, provide an important platform for studying spatial perception, because of the tight correlation between motor and tactile extents. Nevertheless, if the motor and sensory information in self-touch were artificially decoupled, these classical theories would clearly predict that motor signals– especially if self-generated rather than passive – should influence spatial perceptualjudgements, but not vice versa. We tested this hypothesis by quantifying the contribution of tactile, kinaesthetic, and motor information to judgements of spatial extent. In a self-touch paradigm involving two coupled robots in a master-slave configuration, voluntary movements of the right-hand produced simultaneous tactile stroking on the left forearm. Crucially, the coupling between robots was manipulated so that tactile stimulation could be shorter, equal, or longer in extent than the movement that caused it. Participants judged either the extent of the movementor the extent of the tactile stroke. By controlling sensorimotor gains in this way, we quantified how motor signals influence tactile spatial perception and vice versa. Perception of tactile extent was strongly biased by the amplitude of the movement performed. Importantly, touch also affected the perceived extent of movement. Finally, the effect of movement on touch was significantly stronger when movements were actively-generated compared to when the participant’s right hand was passively moved by the experimenter. Overall, these results suggest that motor signals indeed dominate the construction of spatial percepts, at least when the normal tight correlation between motor and sensory signals is broken. Importantly, however, thisdominance is not total, as classical theory might suggest.

Corollary Discharge Versus Efference Copy: Distinct Neural Signals in Speech Preparation Differentially Modulate Auditory Responses

Actions influence sensory processing in a complex way to shape behavior. For example, during actions, a copy of motor signals—termed “corollary discharge” (CD) or “efference copy” (EC)—can be transmitted to sensory regions and modulate perception. However, the sole inhibitory function of the motor copies is challenged by mixed empirical observations as well as multifaceted computational demands for behaviors. We hypothesized that the content in the motor signals available at distinct stages of actions determined the nature of signals (CD vs. EC) and constrained their modulatory functions on perceptual processing. We tested this hypothesis using speech in which we could precisely control and quantify the course of action. In three electroencephalography (EEG) experiments using a novel delayed articulation paradigm, we found that preparation without linguistic contents suppressed auditory responses to all speech sounds, whereas preparing to speak a syllable selectively enhanced the auditory responses to the prepared syllable. A computational model demonstrated that a bifurcation of motor signals could be a potential algorithm and neural implementation to achieve the distinct functions in the motor-to-sensory transformation. These results suggest that distinct motor signals are generated in the motor-to-sensory transformation and integrated with sensory input to modulate perception.

Corollary Discharge versus Efference Copy: Distinct Neural Signals in Speech Preparation Differentially Modulate Auditory Responses

Actions influence sensory processing in a complex way to shape behavior. For example, during actions, a copy of motor signals—termed corollary discharge (CD) or efference copy (EC)—can be transmitted to sensory regions and modulate perception. However, the sole inhibitory function of the motor copies is challenged by mixed empirical observations as well as multifaceted computational demands for behaviors. We hypothesized that the content in the motor signals available at distinct stages of actions determined the nature of signals (CD vs. EC) and constrained their modulatory functions on perceptual processing. We tested this hypothesis using speech in which we could precisely control and quantify the course of action. In three electroencephalography (EEG) experiments using a novel delayed articulation paradigm, we found that preparation without linguistic contents suppressed auditory responses to all speech sounds, whereas preparing to speak a syllable selectively enhanced the auditory responses to the prepared syllable. A computational model demonstrated that a bifurcation of motor signals could be a potential algorithm and neural implementation to achieve the distinct functions in the motor-to-sensory transformation. These results suggest that distinct motor signals are generated in the motor-to-sensory transformation and integrated with sensory input to modulate perception.