Pig red internal organ stripping control method and device based on state machine, equipment and medium

Abstract

This application discloses a method, apparatus, equipment, and medium for controlling the separation of pig viscera based on a state machine, relating to the field of food processing automation technology. The method includes: collecting and connecting tissue state information; dividing risk zones according to preset mechanical rules as the current state of the state machine; invoking corresponding strategies for control execution and obtaining tissue response information; and transitioning to a new state and repeating the process when transition conditions are met, until separation is complete. By determining the mechanical state zones and dynamically adjusting the strategy, non-destructive separation is achieved.

Description

Technical Field

[0001] This invention relates to the field of food processing automation technology, and in particular to a method, apparatus, equipment and medium for controlling the separation of pig viscera based on a state machine. Background Technology

[0002] Pig viscera generally refers to the red organs produced during slaughter and processing, including but not limited to the heart, liver, lungs, and spleen. These organs are often interconnected by connective tissue, blood vessels, or membranous structures. These connecting tissues are characterized by their softness, fragility, and significant variations depending on the location; during the disassembly process, the stress state, morphology, and connection strength of the connecting tissues continuously change.

[0003] Existing automated or semi-automatic viscera stripping technologies mainly fall into two categories: one relies on fixed action procedures (e.g., fixed sequence, fixed trajectory, or fixed action parameters); the other employs simple closed-loop control (PID control) based on a single mechanical feedback (traction force), maintaining a constant force threshold by fine-tuning the speed or stopping traction. The first type of solution completely ignores the dynamic changes in the connection state, exhibiting extremely poor adaptability. While the second type possesses some feedback adjustment capability, its control logic and objective remain singular and fixed throughout the stripping process (e.g., always maintaining a reactive logic of "constant force traction" or "stopping upon exceeding the limit"). This single-mode continuous fine-tuning is insufficient to effectively address the strong nonlinearity, time-varying characteristics, and abrupt state changes nearing damage exhibited by the connective tissue of pig viscera during stripping. Specifically, this manifests as: low efficiency when the tissue is in a low-risk state; and when entering medium- or high-risk states, because the control mode remains fundamentally unchanged, parameter fine-tuning alone cannot timely and effectively suppress the risk of damage, easily leading to problems such as connective tissue damage, increased stripping failure rate, and insufficient stripping consistency. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a state machine-based control method, apparatus, device, and medium for the separation of pig blood viscera, which can classify and determine the changes in the mechanical state of tissue connections during the separation process and dynamically adjust the separation strategy accordingly to achieve non-destructive separation. The specific solution is as follows: In a first aspect, this application discloses a state machine-based control method for the separation of pig blood viscera, including: Sensors mounted on the peeling actuator collect status information of the connecting tissues between the pig's red viscera to be peeled; wherein, the status information includes current mechanical performance information and geometric status information; According to the preset mechanical judgment rules and based on the state information, the current dissection state of the pig red viscera to be dissected is divided into corresponding risk level zones, so as to use the risk level zones as the current state of the state machine; wherein, the state of the state machine includes preset low risk state, preset medium risk state, preset high risk state and preset abnormal protection state. Based on the current state, the corresponding stripping operation control strategy is invoked and executed to control the stripping execution mechanism to perform stripping actions in order to obtain organizational response information fed back during the execution process; When the organizational response information meets the preset state transition conditions, the state machine is triggered to transition from the current state to the target state, and the target state is updated to the new current state. Then, the process jumps to execute the step of calling and executing the corresponding stripping operation control strategy based on the current state to control the stripping execution mechanism to perform the stripping action and obtain the organizational response information fed back during the execution process, until the stripping is completed.

[0005] Optionally, the step of collecting status information of the connecting tissues between the pig's internal organs to be separated through sensors installed on the peeling execution mechanism includes: The mechanical sensors installed on the peeling actuator collect information on the current mechanical properties of the connecting tissues between the pig's red viscera to be peeled. Geometric state information of the connecting tissues between the pig's red viscera to be peeled is collected by a displacement detector installed on the peeling actuator; Accordingly, the step of dividing the current dissection status of the pig's red viscera to be dissected into corresponding risk level zones based on preset mechanical judgment rules and the state information includes: Based on the state information, mechanical trend characteristics are determined to characterize the mechanical state of the connecting tissue; wherein, the mechanical trend characteristics include the rate of change of force and / or the rate of change of stiffness; If the mechanical trend characteristic quantity is greater than or equal to the preset warning threshold, the current peeling state of the pig red viscera to be peeled is determined to be a risk level zone one risk level higher than the previous peeling state; wherein, the previous peeling state includes a preset low risk state, a preset medium risk state, and a preset high risk state.

[0006] Optionally, determining the mechanical trend characteristic quantity for characterizing the mechanical state of the connective tissue based on the state information includes: Within a preset sliding window, the rate of change of force or the rate of change of stiffness of continuous sampling are monitored to obtain mechanical trend characteristic quantities used to characterize the mechanical state of the connection tissue.

[0007] Optionally, the step of dividing the current dissection status of the pig's red viscera to be dissected into corresponding risk level zones according to preset mechanical judgment rules and based on the state information includes: Obtain visual feature information of the connected tissue; wherein, the visual feature information includes local tissue thinning, necking, or risk of blood vessel stretching; When the visual feature information meets the preset visual risk conditions, the current peeling state is determined as a preset high-risk level partition, and / or the partitioning result based on the mechanical trend feature quantity is weighted and corrected.

[0008] Optionally, the step of invoking and executing the corresponding stripping operation control strategy based on the current state to control the stripping execution mechanism to perform stripping actions and obtain organizational response information fed back during the execution process includes: If the current state is a preset low-risk state, then the continuous traction strategy is invoked, and the stripping execution mechanism is controlled to perform continuous traction stripping actions at a preset high speed and a preset high traction force limit, so as to obtain the organizational response information fed back during the execution process; If the current state is a preset medium-risk state, the segmented traction strategy is invoked, and the stripping execution mechanism is controlled to perform the segmented traction stripping action according to the preset medium speed, preset large segment step size, preset medium traction force upper limit, and preset high change rate upper limit, so as to obtain the organizational response information fed back during the execution process. If the current state is a preset high-risk state, then the micro-stepping traction strategy is invoked, and the stripping execution mechanism is controlled to perform intermittent traction stripping actions according to a preset low speed, preset small segment step length, preset low traction force upper limit, and preset low change rate upper limit, so as to obtain the organizational response information fed back during the execution process. If the current state is a preset abnormal state, a protective rollback strategy is invoked from the preset strategy library, and the stripping execution mechanism is controlled to perform rollback and pause stripping actions to obtain organizational response information fed back during the execution process.

[0009] Optionally, the step of the organization response information satisfying a preset state transition condition includes: If the current traction force, current stiffness change rate, or current force change rate in the response information exceeds the corresponding preset out-of-bounds threshold, then the out-of-bounds trigger state transition condition is met. If the trend characteristic of the current force change rate or the trend characteristic of the current stiffness change rate in the response information exceeds the corresponding preset warning threshold, then the state transition condition for triggering the trend warning is met. If the force-displacement relationship in the response information is not within the preset range, then the state transition condition triggered by deviation is met; If the visual features in the response information meet the preset high-risk visual conditions, then the state transition condition for triggering visual risk is met.

[0010] Optionally, the process of updating the target state to a new current state and then jumping to execute the corresponding stripping operation control strategy based on the current state further includes: Set a stable window. When a preset number of consecutive sampling points in the stable window in the update result meet the preset downgrading condition, the downgrading switch is executed. If a preset number of consecutive sampling points in the stable window of the update result meet the preset upgrade conditions, then the upgrade switch is executed.

[0011] Secondly, this application discloses a state machine-based control device for separating and dissecting pig viscera, comprising: The information acquisition module is used to acquire the status information of the connecting tissues between the pig's red viscera to be separated through sensors installed on the peeling execution mechanism; wherein, the status information includes current mechanical performance information and geometric status information; The partitioning module is used to divide the current dissection state of the pig's red viscera to be dissected into corresponding risk level partitions according to preset mechanical judgment rules and based on the state information, so as to use the risk level partitions as the current state of the state machine; wherein, the state of the state machine includes preset low risk state, preset medium risk state, preset high risk state and preset abnormal protection state. The strategy execution module is used to invoke and execute the corresponding stripping operation control strategy based on the current state, so as to control the stripping execution mechanism to perform stripping actions and obtain organizational response information fed back during the execution process; The stripping module is used to trigger the state machine to transition from the current state to the target state when the organizational response information meets the preset state transition, and update the target state to the new current state. Then, it jumps to execute the step of calling and executing the corresponding stripping operation control strategy based on the current state to control the stripping execution mechanism to perform the stripping action to obtain the organizational response information fed back during the execution process, until the stripping is completed.

[0012] Thirdly, this application discloses an electronic device, including: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the aforementioned state machine-based control method for separating pig viscera.

[0013] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned state machine-based method for controlling the separation of pig viscera.

[0014] As can be seen, this application discloses a method for collecting state information of the connecting tissues between the viscera to be peeled by sensors installed on the peeling execution mechanism; wherein, the state information includes current mechanical performance information and geometric state information; according to preset mechanical judgment rules and based on the state information, the current peeling state of the viscera to be peeled is divided into corresponding risk level zones, and the risk level zones are used as the current state of the state machine; wherein, the state machine states include preset low-risk state, preset medium-risk state, preset high-risk state, and preset abnormal protection state; based on the current state, the corresponding peeling operation control strategy is invoked and executed to control the peeling execution mechanism to perform peeling actions to obtain tissue response information fed back during the execution; when the tissue response information meets the preset state transition conditions, the state machine is triggered to transition from the current state to the target state, and the target state is updated to the new current state, and then the step of invoking and executing the corresponding peeling operation control strategy based on the current state to control the peeling execution mechanism to perform peeling actions to obtain tissue response information fed back during the execution is executed, until the peeling is completed. Therefore, by collecting mechanical and geometric information about the connective tissue to be stripped, the state information of the connective tissue can be obtained. Then, by using preset mechanical judgment rules and state information, the current stripping state can be divided into different risk level zones. This allows for the identification of different stages of the tissue from relaxation to tension to near-breakage. This zone mechanism directly corresponds to the strong nonlinear and time-varying characteristics exhibited by the connective tissue during the stripping process, avoiding the poor adaptability problem caused by the traditional method of using a single mode to handle the entire process. Once the zone is determined, the matching control strategy is invoked to execute the stripping action. Since different risk levels (low risk, medium risk, and high risk) correspond to drastically different control modes, efficient operation can be performed when the tissue is at low risk, and a gentle, protective operation can be promptly switched when it enters medium or high risk, reducing the risk of tissue damage due to inappropriate strategies and ensuring the consistency of the stripping process. In addition, response information continues to be collected after the strategy is executed, and the target zone and strategy are automatically updated when the preset zone switching conditions are met. This allows for dynamic adjustment of control behavior based on real-time changes in the tissue state, and even early switching of strategies through trend warnings before risks occur. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0016] Figure 1This application discloses a flowchart of a state machine-based control method for the separation of pig red viscera; Figure 2 This application discloses a schematic diagram of tissue biomechanical partitioning for connecting tissues; Figure 3 This application discloses a mapping diagram between tissue biomechanical partitioning and a set of stripping operation strategies; Figure 4 This application discloses a schematic diagram of a partition switching trigger condition; Figure 5 This application discloses a flowchart of a specific state machine-based control method for the separation of pig red viscera; Figure 6 This application discloses a schematic diagram of a state machine-based control device for separating and controlling pig viscera. Figure 7 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] Pig viscera generally refers to the red organs produced during slaughter and processing, including but not limited to the heart, liver, lungs, and spleen. These organs are often interconnected by connective tissue, blood vessels, or membranous structures. These connecting tissues are characterized by their softness, fragility, and significant variations depending on the location; during the disassembly process, the stress state, morphology, and connection strength of the connecting tissues continuously change.

[0019] Existing automated or semi-automatic viscera stripping technologies mainly fall into two categories: one relies on fixed action procedures (e.g., fixed sequence, fixed trajectory, or fixed action parameters); the other employs simple closed-loop control (PID control) based on a single mechanical feedback (traction force), maintaining a constant force threshold by fine-tuning the speed or stopping traction. The first type of solution completely ignores the dynamic changes in the connection state, exhibiting extremely poor adaptability. While the second type possesses some feedback adjustment capability, its control logic and objective remain singular and fixed throughout the stripping process (e.g., always maintaining a reactive logic of "constant force traction" or "stopping upon exceeding the limit"). This single-mode continuous fine-tuning is insufficient to effectively address the strong nonlinearity, time-varying characteristics, and abrupt state changes nearing damage exhibited by the connective tissue of pig viscera during stripping. Specifically, this manifests as: low efficiency when the tissue is in a low-risk state; and when entering medium- or high-risk states, because the control mode remains fundamentally unchanged, parameter fine-tuning alone cannot timely and effectively suppress the risk of damage, easily leading to problems such as connective tissue damage, increased stripping failure rate, and insufficient stripping consistency.

[0020] To address this, the present invention provides a state machine-based control scheme for the separation of pig blood viscera. This scheme can determine the partitioning based on the changes in the mechanical state of tissue connections during the separation process and dynamically adjust the separation strategy accordingly for non-destructive separation, thereby reducing the risk of damage and improving the success rate and consistency of separation.

[0021] like Figure 1 As shown, this invention provides a state machine-based control method for the separation of pig viscera, comprising: Step S11: Collect the status information of the connecting tissues between the pig's red viscera to be separated by a sensor installed on the peeling actuator; wherein, the status information includes current mechanical performance information and geometric status information.

[0022] In this embodiment, the current mechanical performance information of the connecting tissues between the pig's red viscera to be separated is collected by a mechanical sensor installed on the peeling execution mechanism; it can be understood that the mechanical state information (current mechanical performance information) characterizing the connection state of the connecting tissues between the pig's red viscera to be separated is collected by a mechanical sensor (e.g., tension and compression sensor) installed on the peeling execution mechanism (manipulator, traction gripper).

[0023] In this embodiment, a displacement detector installed on the peeling actuator collects geometric state information of the connecting tissues between the pig's red viscera to be peeled; it can be understood that a displacement detection device (such as a photoelectric encoder or laser displacement meter) installed on the peeling actuator (manipulator, traction gripper) collects geometric state information characterizing the connection state of the connecting tissues between the pig's red viscera to be peeled.

[0024] Step S12: According to the preset mechanical judgment rules and based on the state information, the current dissection state of the pig red viscera to be dissected is divided into corresponding risk level zones, so as to use the risk level zones as the current state of the state machine; wherein, the state of the state machine includes a preset low-risk state, a preset medium-risk state, a preset high-risk state, and a preset abnormal protection state.

[0025] In this embodiment, mechanical trend features characterizing the mechanical state of the connecting tissue are determined based on the state information. These mechanical trend features include the rate of change of force and / or the rate of change of stiffness. Specifically, the rate of change of force or the rate of change of stiffness is monitored within a preset sliding window to obtain the mechanical trend features characterizing the mechanical state of the connecting tissue. It is understood that the state information includes at least one or more of traction force-related quantities and displacement-related quantities, preferably including traction force (F(t)), displacement (x(t)), traction velocity (v(t)), and the curve features derived therefrom. Let the fixed sampling period be... (For example =10ms), at each sampling time Obtain the original state information: traction force Displacement Traction speed It can be obtained through displacement difference: To construct the mechanical features used for partition determination and to suppress measurement noise and transient disturbances, optionally, the raw information can be preprocessed and feature calculated: the raw force sequence { Perform moving average filtering; the window length can be chosen as... =5, resulting in the smoothed force sequence { Subsequent calculations are all based on the smoothed sequence. For the sake of brevity, the following text will still use} Furthermore, the equivalent stiffness characterizes the local slope of the force-displacement curve, reflecting the tightness of the joint structure. First-order backward difference calculation is used. ; Where, Δ F Δ represents the change in traction force during the current sampling period. x For the corresponding displacement change, when Δ x When it approaches 0, use a preset minimum positive number. ε Substitute to prevent division by zero (e.g., ε =10 -6 ).

[0026] The rate of change of force reflects abrupt changes in the stress state and is key to predictive regional determination. The calculation is as follows: ; Energy accumulation can be used to determine whether the overall work done is abnormal. The trapezoidal rule is used as an approximation. ; To perform predictive region determination, a sliding window is required. Observe the changing trend of the feature quantity within (e.g., containing 10 sampling points). For example, within the calculation window. mean Or determine the number of points that continuously exceed the threshold.

[0027] The above calculations are performed in real time during each sampling period, forming a feature vector. This serves as the input for the partition determination module.

[0028] In this embodiment, if the mechanical trend feature quantity is greater than or equal to a preset warning threshold, the current peeling state of the pig's red viscera to be peeled is determined to be a risk level partition one risk level higher than the previous peeling state; wherein, the previous peeling state includes a preset low-risk state, a preset medium-risk state, and a preset high-risk state. It can be understood that the partitioning determination module actually divides the continuous feature space... Mapped to discrete risk levels {P1, P2, P3}. This implementation uses a rule-based judgment method based on threshold comparison, the key being the determination of the threshold. All judgment thresholds and strategy parameters are obtained through the following calibration process: First, sample preparation and data acquisition. Specifically, select M groups (e.g., M≥30) of representative pig viscera samples, covering different connection sites (e.g., heart-liver connection, liver-lung connection). Under a controllable initial posture, perform stripping with a set of conservative fixed parameters (low speed, small step size), while simultaneously acquiring high-fidelity F(t) and x(t) data at high speed. Second, event labeling. Specifically, experienced operators or through subsequent video analysis, label the acquired data stream with events, where key event labels include: Tag S (Stable): The stage where peeling is smooth and the tissue shows no obvious deformation.

[0029] Tag R (Risk Imminent): Before actual tissue damage occurs, there is a stage where the stress increases rapidly, there is shaking, or the tissue appears to be noticeably thinner or stretched.

[0030] Label B (Damage): The point in time when tissue tears or breaks.

[0031] Then feature extraction and statistics are performed. Specifically, for all event segments labeled S and R, the statistical values ​​of their corresponding feature quantities F, k, and r (such as mean, maximum value, 95th percentile, etc.) are extracted.

[0032] Furthermore, the P3 threshold (F2,k2,r0) F 2, k2, r 0) The determination method is as follows: Analyze all R event segments, and take the 90th - 95th percentiles of F and k as the candidate values of F2 and k2. Analyze the r value distribution at the moment before the B event, and take its 80th percentile as the out - of - bounds change rate threshold r 0 candidate value. On this basis, multiply by a safety margin coefficient of 0.7 - 0.9 to obtain the final F2, k2, r0. This is aimed at early identification before the risk occurs. The determination method of the P1 / P2 threshold (F1, k1) is as follows: Analyze all S event segments, and take the 80th - 85th percentiles of F and k as F1 and k1. At the same time, analyze the F and k values near the starting point of the R event to ensure that F1 < F2 and k1 < k2, so as to form a clear transition zone (P2) in the feature space. The determination method of the warning threshold is as follows(<s r pre , q pre ) Determine: Analyze the data in the initial stage of the R event segment when F and k have not yet reached F2 and k2, and count its r and Δ k distribution, and take its 70th percentile as the warning threshold r pre and q pre . Obviously, it needs to satisfy r pre < r0.

[0033] Correspondingly, the basic zoning rule is: If F1 ≤ F i < F2 or k 1 ≤ k i < k < 2, then the basic zoning result is P2; if Fi ≥ F2 or k i ≥ k 2 or r i ≥ r 0, then the basic zoning result is P3.

[0034] Furthermore, after obtaining the above - mentioned mechanical trend characteristic quantities, the determination conditions for trend warning using the mechanical trend characteristic quantities are as follows: In a sliding window with a length of N w (for example, N w = 8), check r i or the calculated Δ k i . The trend warning condition is: If the r i ≥ r preIf it holds, regardless of the current basic partition result, the current partition is predictively determined to be of a higher risk level (for example, if the basis is P1, it is determined to be P2; if the basis is P2, it is determined to be P3). If the basis is already P3, strengthen the high-risk determination or directly trigger the protection strategy. This mechanism realizes "downshifting in advance". Output the final partition label P ∈ {P1, P2, P3} and the trigger flag (such as "basis P2", "trend warning to P3"). Respectively count the distribution ranges of operation parameters such as the traction speed, step size, and pause time used when successfully completing the peeling within the S and R (but not damaged) event segments, and take the median or a more conservative value to form the initial parameter sets {P T1 , P T2 , P T3}. The fallback parameters Δx back , t back etc. can be set according to the mechanical characteristics of the actuator and the calibration experience.

[0035] Furthermore, for the real-time partition determination condition: during the operation phase, the following determination process is executed in each sampling period: Basic partition determination: If F i <F1 and k i <k1 and r i < r pre , then the basic partition result is P1.

[0036] In this embodiment, for the partition determination, comprehensive determination can also be performed through multimodal fusion. In this embodiment, a comprehensive modality determination of mechanical characteristics and visual characteristics is adopted. Specifically, obtain the visual characteristic information of the connective tissue; wherein, the visual characteristic information includes local thinning of the tissue, necking, or risk of blood vessel tension; when the visual characteristic information meets the preset visual risk condition, determine the current peeling state as a preset high-risk level partition, and / or perform weighted correction on the partition result output based on the mechanical trend feature quantity. It can be understood that the image information of the connective tissue is obtained through a visual sensor to identify high-risk visual characteristics such as significant thinning of the film, local necking, or blood vessel tension. When both a clear mechanical risk trend and a visual high-risk feature are detected, it can be preferentially determined as a high breakage risk partition (P3), or trigger earlier strategy intervention, thereby providing redundant safety guarantees. Specifically, the visual characteristic information may include risk characterizations such as local thinning, necking, and blood vessel tension of the connective tissue, and its output can be a flag bit V ∈ {0, 1} or a confidence level p v ∈ [0, 1]. The fusion determination conditions include: Forced correction: When V = 1 or p v ≥ p th , directly correct the partition result to P3; Weighted scoring: Construct the risk score \(R = w\) m R m + w v R v , where \(R\) m is calculated from \(F\), \(k\), \(r\), \(\Delta k\), and \(R\) v is calculated from visual features. When \(R\geq R\) th , enter P3.

[0037] By taking visual risk as a correction term or a mandatory term for the mechanical judgment area, high-risk connection states can be identified in advance when the mechanical quantity has not yet significantly exceeded the boundary, thereby improving the success rate and stability of non-destructive peeling. In this way, in the implementation method of multi-modal fusion determination, visual features are not output as an independent determination result, but participate in the decision-making of the judgment area as a correction factor or a mandatory term for the determination of tissue mechanical zoning. When visual analysis detects high-risk morphological features such as obvious necking, local significant thinning, or abnormal tensile stress of blood vessels in the connecting tissue, even if the current mechanical feature quantity has not reached the high-risk threshold, the zoning result can be corrected to a higher risk level, or a protective peeling strategy can be directly triggered, so as to intervene in advance before the mechanical index is significantly abnormal and further reduce the risk of sudden breakage.

[0038] In this embodiment, the risk level zoning is as Figure 2 shown, specifically including P1 (low resistance and stiffness, stable response, large continuous traction window), P2 (medium resistance / stiffness, sensitive to parameters, suitable for deceleration and can introduce support / limitation), P3 (high-risk states such as sudden increase in resistance / stiffness or excessive change rate, or in predictive zoning, the trend \(r\geq r\) pre or \(dk / dt\geq q\) 。 pre , suitable for gentle segmented traction and strict constraint). Specifically, the criteria for P1, P2, and P3 are as follows: P1: satisfy \((F < F1)\) and \((k < k1)\) and \((r < r\) pre ); P2: satisfy \((F1\leq F < F2)\) and / or \((k1\leq k < k2)\); P3: satisfy \((F\geq F2)\) or \((k\geq k2)\) or \((r\geq r0)\). Therefore, P1 low risk, P2 medium risk, P3 high risk, and abnormal protection are correspondingly obtained, and then the zoning output after judgment is used as the current state of the state machine. The states of the state machine include: the policy state corresponding to P1, the policy state corresponding to P2, the policy state corresponding to P3, and the protective fallback state (T4). The above set of peeling operation strategies is used to map the risk level zoning (P1 / P2 / P3) to executable peeling actions and control parameters. Each strategy includes at least an action type and control parameter constraints. The control parameters include, but are not limited to, the traction direction or path, traction speed (\(v\)), displacement step (\(\Delta x\)), pause time (\(t\) hold ), upper limit of traction force (\(F\) lim ), upper limit of change rate (\(r\) lim)、Support / Limit State (S), etc.

[0039] Step S13: Based on the current state, call and execute the corresponding peeling operation control strategy to control the peeling actuator to perform the peeling action, so as to obtain the tissue response information feedback during the execution process.

[0040] In this embodiment, a mapping relationship between the state and the strategy is pre-constructed based on the above control strategy, such as Figure 3 shown. The specific mapping relationship is as follows: P1 corresponds to T1 (fast continuous traction), P2 corresponds to T2 (decelerated steady traction + support optional), P3 corresponds to T3 (gentle segmented traction + strict constraint); when P3 persists or a risk anomaly occurs, enter T4 (retreat - rejudgment - re-enter).

[0041] In this embodiment, if the current state is a preset low-risk state, then call the continuous traction strategy, and control the peeling actuator to perform the peeling action of continuous traction according to the preset high speed and preset high traction upper limit, so as to obtain the tissue response information feedback during the execution process; it can be understood that, based on the above constructed mapping relationship, when the current state is the P1 low-risk state, then call the T1 strategy, and under this strategy, the action type and control parameters (v = v1, F lim = F 1,lim ; switch when the judgment area enters the P2 / P3 range or a trend warning is triggered) control the peeling actuator to perform the peeling action, and obtain the tissue response information feedback during the execution process.

[0042] In this embodiment, if the current state is a preset medium-risk state, then call the segmented traction strategy, and control the peeling actuator to perform the peeling action of segmented traction according to the preset medium speed, preset large segmented step size, preset medium traction upper limit, and preset high change rate upper limit, so as to obtain the tissue response information feedback during the execution process; it can be understood that when the current state is the P2 medium-risk state, then call the T2 strategy, and under this strategy, the action type and control parameters (v = v2 < v1, Δx = Δx2, optional (t hold = t2); set (F lim = F 2,lim ), (r lim = r2), support / limit (S = S on ) optional; switch back to T1 when the transfer to the P1 stable window is satisfied, and switch to T3 when entering P3) control the peeling actuator to perform the peeling action, and obtain the tissue response information feedback during the execution process.

[0043] In this embodiment, if the current state is a preset high-risk state, a micro-stepping traction strategy is invoked, and the stripping execution mechanism is controlled to perform intermittent traction stripping actions according to a preset low speed, preset small segment step size, preset low traction force upper limit, and preset low rate of change upper limit, in order to obtain tissue response information fed back during the execution process; it can be understood that if the current state is a P3 high-risk state, the T3 strategy is invoked, and the action type and control parameters (v=v3) under this strategy are used. v2, Δx = Δx3 < Δx2, t hold =t3; Set the strictest (F) lim =F 3,lim ), (r lim =r3), preferred (S=S) on If necessary, trigger T4) to control the stripping execution mechanism to perform the stripping action and obtain the organizational response information fed back during the execution process.

[0044] In this embodiment, if the current state is a preset abnormal state, a protective rollback strategy is invoked from the preset strategy library, and the stripping execution mechanism is controlled to perform rollback and pause stripping actions to obtain organizational response information fed back during the execution process. It can be understood that if the current state is an abnormal state, the T4 strategy is invoked, and the action type and control parameters under this strategy (rollback displacement (Δx)) are specified. back ) or pause after partially releasing traction (t) back In the re-decision window (W) re Re-collect and determine the region within T2 or T3; the maximum number of retries (N) can be set. max ).

[0045] Step S14: When the organization response information meets the preset state transition conditions, the state machine is triggered to transition from the current state to the target state, and the target state is updated to the new current state. Then, the process jumps to execute the step of calling and executing the corresponding stripping operation control strategy based on the current state to control the stripping execution mechanism to perform the stripping action in order to obtain the organization response information fed back during the execution process, until the stripping is completed.

[0046] In this embodiment, if the current traction force, current stiffness change rate, or current force change rate in the response information exceeds the corresponding preset out-of-bounds threshold, the out-of-bounds trigger state transition condition is met; if the trend characteristic of the current force change rate or the trend characteristic of the current stiffness change rate in the response information exceeds the corresponding preset warning threshold, the trend warning trigger state transition condition is met; if the force-displacement relationship in the response information is not within a preset range, the deviation trigger state transition condition is met; if the visual characteristics in the response information meet the preset visual high-risk condition, the visual risk trigger state transition condition is met.

[0047] In this embodiment, as Figure 4 As shown, when any one or more of the above four transition conditions are met, the corresponding switching direction rule for switching to the target state is: if the risk increases, the switching direction tends to be mild (T1→T2→T3), by reducing (v), decreasing (Δx), and tightening (F). lim / r lim ), and reduce risk by activating support / limit levels; when risk falls back and is within a stable window (W stable If the conditions are consistently met within a given period, a gradual switchback to a high-efficiency strategy is allowed to avoid jitter. When a sudden and sustained increase in force / rate of change occurs, P3 fails to reduce risk, or both visual risk and trend warnings appear simultaneously, the process proceeds to T4, executing a rollback (Δx). back ) and pause (t) back ), in (W re Re-collect and determine the region within T2 or T3; the maximum number of retries (N) can be set. max If the limit is exceeded, an error will be output and manual intervention will be initiated (optional safety procedure).

[0048] In this embodiment, the process of updating the target state to a new current state and then jumping to execute the corresponding stripping operation control strategy based on the current state further includes: setting a stable window; when a preset number of consecutive sampling points in the stable window in the update result meet a preset downgrading condition, a downgrading switch is executed; when a preset number of consecutive sampling points in the stable window in the update result meet a preset upgrading condition, an upgrading switch is executed. It is understood that, to avoid frequent strategy switching due to fluctuations in partitioning determination around the threshold, sliding window smoothing, double threshold hysteresis, and a stable window W can be used. stable And so on. Specifically, the system can set a stable window W. stable When the judgment result is consecutive N s Downgrading is only allowed when all sampling points meet the downgrading condition; when the judgment result is consecutive N s Upgrading is only allowed when all sampling points meet the upgrading conditions. Optionally, different thresholds (hysteresis) can be used for upgrading and downgrading to further suppress jitter. The above anti-jitter mechanism can reduce the risk of mechanical jitter and damage caused by frequent acceleration / deceleration or frequent retraction at the actuator.

[0049] As can be seen, this application discloses a method for collecting state information of the connecting tissues between the viscera to be peeled by sensors installed on the peeling execution mechanism; wherein, the state information includes current mechanical performance information and geometric state information; according to preset mechanical judgment rules and based on the state information, the current peeling state of the viscera to be peeled is divided into corresponding risk level zones, and the risk level zones are used as the current state of the state machine; wherein, the state machine states include preset low-risk state, preset medium-risk state, preset high-risk state, and preset abnormal protection state; based on the current state, the corresponding peeling operation control strategy is invoked and executed to control the peeling execution mechanism to perform peeling actions to obtain tissue response information fed back during the execution; when the tissue response information meets the preset state transition conditions, the state machine is triggered to transition from the current state to the target state, and the target state is updated to the new current state, and then the step of invoking and executing the corresponding peeling operation control strategy based on the current state to control the peeling execution mechanism to perform peeling actions to obtain tissue response information fed back during the execution is executed, until the peeling is completed. Therefore, by collecting mechanical and geometric information about the connective tissue to be stripped, the state information of the connective tissue can be obtained. Then, by using preset mechanical judgment rules and state information, the current stripping state can be divided into different risk level zones. This allows for the identification of different stages of the tissue from relaxation to tension to near-breakage. This zone mechanism directly corresponds to the strong nonlinear and time-varying characteristics exhibited by the connective tissue during the stripping process, avoiding the poor adaptability problem caused by the traditional method of using a single mode to handle the entire process. Once the zone is determined, the matching control strategy is invoked to execute the stripping action. Since different risk levels (low risk, medium risk, and high risk) correspond to drastically different control modes, efficient operation can be performed when the tissue is at low risk, and a gentle, protective operation can be promptly switched when it enters medium or high risk, reducing the risk of tissue damage due to inappropriate strategies and ensuring the consistency of the stripping process. In addition, response information continues to be collected after the strategy is executed, and the target zone and strategy are automatically updated when the preset zone switching conditions are met. This allows for dynamic adjustment of control behavior based on real-time changes in the tissue state, and even early switching of strategies through trend warnings before risks occur.

[0050] like Figure 5 As shown, a preferred embodiment of the state machine-based control method for separating pig viscera according to the present invention is described in detail. This method achieves precise and non-destructive separation of pig viscera by dynamically driving state machine switching through real-time sensing of tissue mechanical properties. The control process mainly includes five stages: state information acquisition, tissue mechanical partitioning determination, strategy mapping and invocation, execution of the segmentation action, and response monitoring and switching. The flowchart of each step is as follows: Step S101: State Information Acquisition. During the disassembly and actuation of the actuator, the mechanical and kinematic state information of the connected tissue is acquired in real time using high-frequency sampling. Specifically, the acquired raw parameters include: the force F(t) currently applied to the tissue, the displacement x(t) of the actuator, and the actuation velocity v(t). Based on these raw data, the system calculates derived characteristic quantities in real time, including: instantaneous stiffness k=dF / dx, reflecting the tissue's resistance to deformation under the current tensile state, used to determine the tissue's brittleness or toughness; force rate of change r=dF / dt, reflecting the rate of change of force, which can be used to detect whether the tissue is about to tear; and cumulative energy E= Fdx: Reflects the total work done on the organization from the initial contact to the current moment, used to assess the organization's fatigue level or tolerance limit. These multi-dimensional state information together constitute a complete feature vector describing the current organizational connectivity state.

[0051] Step S102: Tissue mechanical zoning determination. The real-time state obtained in step S101 is mapped to preset risk zones. Based on built-in preset mechanical judgment rules, the system performs real-time assessment of the current tissue's mechanical state and divides it into three main risk level zones: P1 (low-risk zone), P2 (medium-risk zone), and P3 (high-risk zone). Each zone corresponds to a different range of tissue mechanical characteristic thresholds. It is important to note that this step not only includes real-time determination based on current data but also introduces a trend warning mechanism. The system analyzes the changing trends of derived features (such as k and r) to predict the risk level the tissue may enter in the very short term. For example, even if the current force value is still within the P2 range, if the stiffness k drops sharply and the force rate r rises rapidly, the system can determine that it is about to enter the P3 zone, thus achieving advanced prediction. The determination result (P1 / P2 / P3 or predicted transition) will be used as the current state output of the state machine.

[0052] Step S103: Strategy Mapping and Invocation. Based on the partition determination result output in step S102, this step is responsible for invoking the matching stripping operation control strategy. The system has a pre-built strategy library that corresponds one-to-one with the risk partition: when the partition is determined to be P1, strategy T1 is invoked, using a larger step size and higher speed to pursue efficiency; when the partition is determined to be P2, strategy T2 is invoked, appropriately reducing the speed and increasing the force monitoring frequency to balance efficiency and safety; when the partition is determined to be P3, strategy T3 is invoked, using a very small step size and very low speed to strip the partition, prioritizing the integrity of the organization. In addition, the strategy library also includes an emergency strategy T4, which is triggered when abnormal fluctuations (sensor signal jumps) or continuous risk accumulation (long-term exposure to the boundary between P2 and P3) are detected. Strategy T4 will pause the operation and enter the safety assessment subroutine.

[0053] Step S104: Execute the segmentation action. This step is the concrete physical implementation of the strategy. Based on the control strategy (T1 / T2 / T3 / T4) selected in step S103, the system sends refined control commands to the segmentation execution mechanism. The control parameter set includes: execution speed v, single step displacement Δx, and action hold time t. hold Force upper limit threshold F lim Upper limit threshold of force variation r lim And the safety step size S.

[0054] During execution, the system also incorporates two auxiliary mechanisms to ensure stability and reliability: anti-jitter mechanism W stable The signals acquired by the sensor are filtered to prevent misjudgments caused by mechanical vibration or momentary interference. Retry limit N max When an action fails to achieve the expected result or triggers an exception, the system allows a limited number of retries to prevent process interruption due to unforeseen factors.

[0055] Step S105: Response Monitoring and Switching. This step constitutes the feedback loop in closed-loop control. During the execution of step S104, the system continuously monitors the organization's response status. Monitoring trigger conditions include: force value or force rate exceeding limits, activation of trend warning signals, deviation of the action trajectory from the preset path, and abnormal visual feedback. Once the preset state transition conditions are met, the system will trigger the state machine to transition from the current state to the target state. The specific execution logic is as follows: Retreat: The actuator slightly retracts to a safe position to release organizational stress; Re-determination: Jumps back to step S102 and re-determines the mechanical partitioning based on the latest state information; Retry: Based on the new determination result, the strategy mapping and segmentation actions are re-executed. This cycle of execution, monitoring, retreat, and re-determination will continue until the stripping task is successfully completed.

[0056] In summary, this embodiment achieves refined and intelligent control of the process of separating pig blood viscera through the above-described process. By real-time partitioning and dynamic strategy adjustment of the tissue mechanical state, it effectively ensures the non-destructive separation of the product.

[0057] like Figure 6 As shown, the present invention also provides a state machine-based control device for separating and controlling pig viscera, comprising: The information acquisition module 11 is used to acquire the status information of the connecting tissues between the pig's red viscera to be separated through sensors installed on the peeling execution mechanism; wherein, the status information includes current mechanical performance information and geometric status information; The partitioning module 12 is used to divide the current dissection state of the pig's red viscera to be dissected into corresponding risk level partitions according to preset mechanical judgment rules and based on the state information, so as to use the risk level partitions as the current state of the state machine; wherein, the state of the state machine includes preset low risk state, preset medium risk state, preset high risk state and preset abnormal protection state. The strategy execution module 13 is used to invoke and execute the corresponding stripping operation control strategy based on the current state, so as to control the stripping execution mechanism to perform stripping actions and obtain organizational response information fed back during the execution process; The stripping module 14 is used to trigger the state machine to transition from the current state to the target state when the organizational response information meets the preset state transition, and update the target state to the new current state. Then, it jumps to execute the step of calling and executing the corresponding stripping operation control strategy based on the current state to control the stripping execution mechanism to perform the stripping action to obtain the organizational response information fed back during the execution process, until the stripping is completed.

[0058] Therefore, it is evident that the overall architecture, through state perception, partitioning, strategy mapping, and dynamic switching, can proactively switch between fundamentally different control strategy modes based on the phased changes in the connected organization's state, solving the fundamental problem that existing single control modes cannot adapt to dynamic changes throughout the entire process. By monitoring trend characteristics, it can provide early warnings before force or stiffness reaches the damage threshold and trigger strategy downgrading, achieving a breakthrough from passive reaction to proactive prevention.

[0059] Furthermore, embodiments of this application also disclose an electronic device, Figure 7 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0060] Figure 7 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the state machine-based pig viscera removal control method disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0061] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0062] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0063] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0064] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device 20 to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system 221 can be Windows Server, Netware, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the state machine-based pig viscera removal control method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.

[0065] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned state machine-based control method for separating and dissecting pig viscera. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0066] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0067] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly in hardware, software modules executed by a processor, or a combination of both. The software module may be located in random access memory (RAM), memory, read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, removable disks, CD-ROMs (Compact Disc-Read Only Memory), or any other form of storage medium known in the art.

[0068] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0069] The solution provided by the present invention has been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A state machine based pig red gut peel control method, characterized by, include: Sensors mounted on the peeling actuator collect status information of the connecting tissues between the pig's red viscera to be peeled; wherein, the status information includes current mechanical performance information and geometric status information; According to the preset mechanical judgment rules and based on the state information, the current dissection state of the pig red viscera to be dissected is divided into corresponding risk level zones, so as to use the risk level zones as the current state of the state machine; wherein, the state of the state machine includes preset low risk state, preset medium risk state, preset high risk state and preset abnormal protection state. Based on the current state, the corresponding stripping operation control strategy is invoked and executed to control the stripping execution mechanism to perform stripping actions in order to obtain organizational response information fed back during the execution process; When the organizational response information meets the preset state transition conditions, the state machine is triggered to transition from the current state to the target state, and the target state is updated to the new current state. Then, the process jumps to execute the step of calling and executing the corresponding stripping operation control strategy based on the current state to control the stripping execution mechanism to perform the stripping action and obtain the organizational response information fed back during the execution process, until the stripping is completed.

2. The state machine based pig red internal organ stripping control method of claim 1, wherein, The process involves collecting status information of the connecting tissues between the pig's internal organs to be separated through sensors installed on the peeling actuator, including: The mechanical sensors installed on the peeling actuator collect information on the current mechanical properties of the connecting tissues between the pig's red viscera to be peeled. Geometric state information of the connecting tissues between the pig's red viscera to be peeled is collected by a displacement detector installed on the peeling actuator; Accordingly, the step of dividing the current dissection status of the pig's red viscera to be dissected into corresponding risk level zones based on preset mechanical judgment rules and the state information includes: Based on the state information, mechanical trend characteristics are determined to characterize the mechanical state of the connecting tissue; wherein, the mechanical trend characteristics include the rate of change of force and / or the rate of change of stiffness; If the mechanical trend characteristic quantity is greater than or equal to the preset warning threshold, the current peeling state of the pig red viscera to be peeled is determined to be a risk level zone one risk level higher than the previous peeling state; wherein, the previous peeling state includes a preset low risk state, a preset medium risk state, and a preset high risk state.

3. The state machine based pig red internal organ stripping control method of claim 2, wherein, The determination of mechanical trend characteristic quantities for characterizing the mechanical state of connected tissues based on the state information includes: Within a preset sliding window, the rate of change of force or the rate of change of stiffness of continuous sampling are monitored to obtain mechanical trend characteristic quantities used to characterize the mechanical state of the connection tissue.

4. The state machine based pig red internal organ stripping control method of claim 2, wherein, The process of classifying the current dissection status of the pig's blood viscera to be dissected into corresponding risk level zones based on preset mechanical judgment rules and the state information includes: Obtain visual feature information of the connected tissue; wherein, the visual feature information includes local tissue thinning, necking, or risk of blood vessel stretching; When the visual feature information meets the preset visual risk conditions, the current peeling state is determined as a preset high-risk level partition, and / or the partitioning result based on the mechanical trend feature quantity is weighted and corrected.

5. The state machine based pig red internal organ stripping control method of claim 2, wherein, The step of invoking and executing the corresponding stripping operation control strategy based on the current state to control the stripping execution mechanism to perform stripping actions and obtain organizational response information fed back during the execution process includes: If the current state is a preset low-risk state, then the continuous traction strategy is invoked, and the stripping execution mechanism is controlled to perform continuous traction stripping actions at a preset high speed and a preset high traction force limit, so as to obtain the organizational response information fed back during the execution process; If the current state is a preset medium-risk state, the segmented traction strategy is invoked, and the stripping execution mechanism is controlled to perform the segmented traction stripping action according to the preset medium speed, preset large segment step size, preset medium traction force upper limit, and preset high change rate upper limit, so as to obtain the organizational response information fed back during the execution process. If the current state is a preset high-risk state, then the micro-stepping traction strategy is invoked, and the stripping execution mechanism is controlled to perform intermittent traction stripping actions according to a preset low speed, preset small segment step length, preset low traction force upper limit, and preset low change rate upper limit, so as to obtain the organizational response information fed back during the execution process. If the current state is a preset abnormal state, a protective rollback strategy is invoked from the preset strategy library, and the stripping execution mechanism is controlled to perform rollback and pause stripping actions to obtain organizational response information fed back during the execution process.

6. The state machine based pig red-belly de-stripping control method of claim 1, wherein, The condition that the organization's response information meets the preset state transition conditions includes: If the current traction force, current stiffness change rate, or current force change rate in the response information exceeds the corresponding preset out-of-bounds threshold, then the out-of-bounds trigger state transition condition is met. If the trend characteristic of the current force change rate or the trend characteristic of the current stiffness change rate in the response information exceeds the corresponding preset warning threshold, then the state transition condition for triggering the trend warning is met. If the force-displacement relationship in the response information is not within the preset range, then the state transition condition triggered by deviation is met; If the visual features in the response information meet the preset high-risk visual conditions, then the state transition condition for triggering visual risk is met.

7. The state machine based pig red-belly de-stripping control method of claim 1, wherein, The process of updating the target state to the new current state and then jumping to execute the corresponding stripping operation control strategy based on the current state further includes: Set a stable window. When a preset number of consecutive sampling points in the stable window in the update result meet the preset downgrading condition, the downgrading switch is executed. If a preset number of consecutive sampling points in the stable window of the update result meet the preset upgrade conditions, then the upgrade switch is executed.

8. A state machine based pig red belly stripping control apparatus, characterized by, include: The information acquisition module is used to acquire the status information of the connecting tissues between the pig's red viscera to be separated through sensors installed on the peeling execution mechanism; wherein, the status information includes current mechanical performance information and geometric status information; The partitioning module is used to divide the current dissection state of the pig's red viscera to be dissected into corresponding risk level partitions according to preset mechanical judgment rules and based on the state information, so as to use the risk level partitions as the current state of the state machine; wherein, the state of the state machine includes preset low risk state, preset medium risk state, preset high risk state and preset abnormal protection state. The strategy execution module is used to invoke and execute the corresponding stripping operation control strategy based on the current state, so as to control the stripping execution mechanism to perform stripping actions and obtain organizational response information fed back during the execution process; The stripping module is used to trigger the state machine to transition from the current state to the target state when the organizational response information meets the preset state transition, and update the target state to the new current state. Then, it jumps to execute the step of calling and executing the corresponding stripping operation control strategy based on the current state to control the stripping execution mechanism to perform the stripping action to obtain the organizational response information fed back during the execution process, until the stripping is completed.

9. An electronic device, comprising: include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the state machine-based pig viscera stripping control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the state machine-based pig viscera stripping control method as described in any one of claims 1 to 7.

Images