Treatment bed collision detection method, device and equipment and storage medium
By constructing the correlation relationship between the treatment bed motion trajectory parameters and motor current, predicting the current difference, the problem of blind spots in the treatment bed detection is solved, the collision detection accuracy is improved and the hardware cost is reduced.
Patent Information
- Application Number
- CN202411061027.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-12-10
AI Technical Summary
In the existing treatment bed collision detection methods, the accuracy and installation position limitation of the sensing detection device lead to a blind spot for detection, and the collision in all spatial ranges in the treatment bed cavity cannot be fully detected, resulting in low collision detection accuracy.
By constructing the correlation between the parameters of the motion trajectory of the treatment bed, load weight and motor current, predict the current of the motor in the non-collision situation, compare the difference between the actual current and the predicted current, judge the collision if it exceeds the preset range, and control the treatment The bed moves back to the starting position in the opposite direction.
The collision detection of any spatial location in the treatment bed cavity is realized, the collision detection accuracy is improved, the detection of blind spots is missed, and the hardware cost is reduced.
Smart Images
Figure CN119097331A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of medical technology, and in particular to a treatment bed collision detection method, device, equipment and storage medium. Background Art
[0002] During radiation detection and radiation therapy, the detection of the diseased part of the patient lying on the treatment bed or the transportation of the patient to the radiation therapy chamber of the radiation device for radiation therapy is achieved by moving the position of the treatment bed. In order to detect the collision between the load or the treatment bed and the treatment chamber when the treatment bed moves on a large scale, an induction detection device will be set in the chamber to detect the external force generated by the collision, and determine the collision when the external force is detected, so as to implement the corresponding safety operation when the collision is detected, so as to avoid further misoperation of the treatment bed. However, in the above-mentioned collision detection method, the accuracy of the collision detection result is limited by the accuracy, installation position and installation space of the induction detection device itself, and there is a detection blind spot, which can only detect the collision external force within a part of the space range, and the collision occurring within the detection blind spot space range cannot be detected. Therefore, the accuracy of the collision detection result is low. Summary of the invention
[0003] The present invention provides a treatment bed collision detection method, device, equipment and storage medium to at least solve the technical problem in the related art that, due to the limitations of the accuracy, installation position and installation space of the induction detection device itself, only the collision external force within a part of the space range can be detected, and the collision occurring within the detection blind area space range cannot be detected, thereby resulting in low accuracy of the collision detection result. The technical solution of the present invention is as follows:
[0004] According to a first aspect of an embodiment of the present invention, a treatment bed collision detection method is provided, the method comprising: predicting the current of the motor under current motion trajectory parameters, current load weight and current treatment parameters according to the correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor under a non-collision condition of the treatment bed to obtain a predicted current; and obtaining an actual current of the motor; the current of the motor provides a driving force for the movement of the treatment bed, and when the current difference between the actual current and the predicted current exceeds a preset current difference range, controlling the treatment bed to move in the opposite direction back to a movement starting position of the treatment bed.
[0005] The above-mentioned preset current difference range is characterized by the range of change of the motor current when no collision occurs to the treatment bed.
[0006] When the current difference between the actual current and the predicted current exceeds the preset current difference range, it indicates that the current of the motor has surged due to the collision of the treatment bed.
[0007] In a possible implementation, according to the correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor under the non-collision condition of the treatment bed, the current of the motor under the current motion trajectory parameters, the current load weight and the current treatment parameters is predicted to obtain the predicted current, including: constructing a dynamic model characterizing the correlation based on the motor operation parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed; inputting the current motion trajectory parameters, the current load weight and the current treatment parameters into the dynamic model to obtain the predicted current; wherein the motor operation parameters include the motor torque constant, the motor current, the motor external disturbance and the motor friction; the motion trajectory parameters include the position, speed and acceleration of the treatment bed; the treatment parameters include the inclination angle and the weight of the treatment bed; the load weight is linearly related to the inclination angle.
[0008] In another possible implementation, a dynamic model characterizing the association relationship is constructed based on the motor operating parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed, including: when the motor operating parameters indicate that the treatment bed is operating in five-dimensional directions, based on the motor operating parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed, a dynamic model is constructed along the horizontal rotation direction and along the vertical rotation direction; wherein the five-dimensional direction includes a horizontal transverse direction, a horizontal longitudinal direction, a vertical direction, a horizontal rotation direction and a vertical rotation direction.
[0009] In another possible implementation, according to the correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor on the treatment bed in a non-collision condition, the current of the motor under the current motion trajectory parameters, the current load weight and the current treatment parameters is predicted to obtain the predicted current, including: constructing an initial model that characterizes the initial correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor on the treatment bed in a non-collision condition; training the initial model using the historical motion trajectory parameters, historical load weight and historical treatment parameters of the treatment bed as input sample data, and using the corresponding historical current of the motor on the treatment bed in a non-collision condition as output sample data for indicating model parameters for correcting the initial model, to obtain a preset model that characterizes the correlation; and inputting the current motion trajectory parameters, the current load weight and the current treatment parameters into the preset model to obtain the predicted current.
[0010] In another possible implementation, when the current difference between the actual current and the predicted current exceeds the preset current difference range, before the treatment bed is controlled to move in the opposite direction back to the starting position of the treatment bed, the method includes: determining the current position information of the treatment bed and the load and the target current threshold under the current load weight according to the mapping relationship between the position information of the treatment bed and the load, the load weight and the current threshold; the current threshold represents the current difference between the upper limit current and the lower limit current reached by the motor current when the treatment bed and the load operate normally under the position information and the load weight of the treatment bed and the load in a non-collision situation; determining the opposite of the current threshold as the lower limit threshold of the preset current difference range, and determining the current threshold as the upper limit threshold of the preset current difference range, to obtain the preset current difference range; wherein the actual current of the motor is the current data after filtering by the Butterworth filter.
[0011] In another possible implementation, based on the correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor in a non-collision condition of the treatment bed, the current of the motor under the current motion trajectory parameters, the current load weight and the current treatment parameters is predicted, and after the predicted current is obtained, the method further includes: when the current difference between the actual current and the predicted current is within a preset current difference range, controlling the treatment bed to continue to operate according to the current operation trajectory parameters.
[0012] In another possible implementation, the method further includes: when the current difference between the actual current and the predicted current exceeds a preset current difference range, issuing an indication message indicating that there is a collision risk between the treatment bed or the load, and / or locking the control interface used to control the operation of the treatment bed.
[0013] According to a second aspect of an embodiment of the present invention, a treatment bed collision detection device is provided, the device comprising: a prediction unit, configured to predict the current of the motor under current motion trajectory parameters, current load weight and current treatment parameters according to the correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor under a non-collision condition of the treatment bed, so as to obtain a predicted current; an acquisition unit, configured to acquire the actual current of the motor; the current of the motor provides a driving force for the movement of the treatment bed; and a control unit, configured to control the treatment bed to move in the opposite direction back to a movement starting position of the treatment bed when the current difference between the actual current and the predicted current exceeds a preset current difference range.
[0014] In a possible implementation, the prediction unit is specifically used to: construct a dynamic model that characterizes the association relationship based on the motor operation parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed; input the current motion trajectory parameters, the current load weight and the current treatment parameters into the dynamic model to obtain the predicted current; wherein the motor operation parameters include the motor torque constant, the motor current, the motor external disturbance and the motor friction; the motion trajectory parameters include the position, speed and acceleration of the treatment bed; the treatment parameters include the inclination angle of the treatment bed and the weight of the treatment bed; the load weight is linearly related to the inclination angle.
[0015] In another possible implementation, the prediction unit is specifically used to: when the motor operating parameters indicate that the treatment bed is operating in five-dimensional directions, based on the motor operating parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed, construct a dynamic model along the horizontal rotation direction and along the vertical rotation direction; wherein the five-dimensional direction includes a horizontal transverse direction, a horizontal longitudinal direction, a vertical direction, a horizontal rotation direction and a vertical rotation direction.
[0016] In another possible implementation, the prediction unit is specifically used to: construct an initial model that characterizes the initial correlation relationship between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor on the treatment bed in a non-collision condition; use the historical motion trajectory parameters, historical load weight and historical treatment parameters of the treatment bed as input sample data, and use the corresponding historical current of the motor on the treatment bed in a non-collision condition as output sample data for indicating model parameters for correcting the initial model, train the initial model, and obtain a preset model that characterizes the correlation relationship; input the current motion trajectory parameters, current load weight and current treatment parameters into the preset model to obtain a predicted current.
[0017] In another possible implementation, when the current difference between the actual current and the predicted current exceeds the preset current difference range, before the treatment bed is controlled to move in the opposite direction back to the starting position of the treatment bed, the acquisition unit is further used to: determine the current position information of the treatment bed and the load and the target current threshold under the current load weight according to the mapping relationship between the position information of the treatment bed and the load, the load weight and the current threshold; the current threshold represents the current difference between the upper limit current and the lower limit current reached by the motor current when the treatment bed and the load operate normally under the position information and the load weight of the treatment bed and the load in a non-collision situation; determine the opposite of the current threshold as the lower limit threshold of the preset current difference range, and determine the current threshold as the upper limit threshold of the preset current difference range, to obtain the preset current difference range; wherein the actual current of the motor is the current data after filtering by the Butterworth filter.
[0018] In another possible implementation, the control unit is further configured to: when the current difference between the actual current and the predicted current is within a preset current difference range, control the treatment bed to continue operating according to the current operating trajectory parameters.
[0019] In another possible implementation, the control unit is further used to: when the current difference between the actual current and the predicted current exceeds a preset current difference range, issue an indication message indicating that there is a risk of collision between the treatment bed or the load, and / or, associate and lock a control interface used to control the operation of the treatment bed.
[0020] According to a third aspect of an embodiment of the present invention, a treatment couch is provided. The treatment couch includes a bed plate and a supporting component, and is used to implement the treatment couch collision detection method according to the first aspect and any possible implementation thereof.
[0021] According to a fourth aspect of an embodiment of the present invention, a medical device is provided, wherein the medical system device includes a treatment bed, and the treatment bed includes a bed board and a supporting component, which is used to implement the treatment bed collision detection method as described in the first aspect and any possible implementation manner thereof.
[0022] According to a fifth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by a processor of a medical device, the medical device is enabled to perform a treatment bed collision detection method such as the first aspect and any possible implementation thereof.
[0023] According to a sixth aspect of an embodiment of the present application, a computer program product is provided, the computer program product comprising computer instructions, which, when executed on a medical device, causes the medical device to execute the treatment bed collision detection method of the first aspect and any possible implementation thereof.
[0024] The technical solution provided by the embodiment of the present invention brings at least the following beneficial effects: by using the correlation between the multi-dimensional parameters of the treatment bed and the motor current when the treatment bed and the load are in a non-collision state, the motor current of the treatment bed and the normal movement without collision under the current multi-dimensional parameters is predicted. At the same time, the actual current of the motor in the current running state is obtained, so as to determine that the actual current changes greatly by comparing the current difference between the actual current and the predicted current, and the current change amount exceeds the current change range when the treatment bed moves normally, that is, the motor current has surged, and the reason for the surge in current is caused by the collision between the treatment bed and the load, so as to accurately detect the collision of the treatment bed.
[0025] In the above-mentioned collision detection method, the current difference between the motor when the treatment bed collides and when it does not collide is very different. By comparing the current difference between the actual current of the motor and the predicted current when there is no collision with the preset current difference range, the current surge caused by the collision at any spatial position in the treatment bed cavity and the large current change can be accurately detected without being restricted by the detection space area. In this way, the collision within all spatial ranges in the treatment bed cavity can be accurately and comprehensively detected, improving the collision detection accuracy and avoiding the missed detection of collisions due to the existence of detection blind spots in related technologies. At the same time, in the technical solution of this application, additional external force detection sensing devices are also omitted, reducing hardware costs and saving application resources.
[0026] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute improper limitations on the present application.
[0028] Figure 1 is a schematic diagram of a treatment bed collision detection device according to an exemplary embodiment;
[0029] Figure 2 is a flow chart showing a method for detecting a collision of a treatment bed according to an exemplary embodiment;
[0030] Figure 3 is a block diagram of a treatment bed collision detection device according to an exemplary embodiment;
[0031] Figure 4 is a schematic diagram of a medical device according to an exemplary embodiment. DETAILED DESCRIPTION
[0032] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.
[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.
[0034] In addition, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0035] Before introducing in detail the treatment bed collision detection method provided in the embodiment of the present application, a brief introduction is first given to the application scenarios and implementation architecture involved in the embodiment of the present application.
[0036] First, the application scenarios of the embodiments of the present application are described below.
[0037] During radiation detection and radiation therapy, the detection of the diseased part of the patient lying on the treatment bed or the transportation of the patient to the radiation therapy chamber of the radiation device for radiation therapy is achieved by moving the position of the treatment bed. In order to detect the collision between the load or the treatment bed and the treatment chamber when the treatment bed moves on a large scale, an induction detection device will be set in the chamber to detect the external force generated by the collision, and determine the collision when the external force is detected, so as to implement the corresponding safety operation when the collision is detected, so as to avoid further misoperation of the treatment bed. However, in the above-mentioned collision detection method, the accuracy of the collision detection result is limited by the accuracy, installation position and installation space of the induction detection device itself, and there is a detection blind spot, which can only detect the collision external force within a part of the space range, and the collision occurring within the detection blind spot space range cannot be detected. Therefore, the accuracy of the collision detection result is low.
[0038] In response to the above problems, the present application provides a method for detecting collision of a treatment bed, which uses the correlation between the multi-dimensional parameters of the treatment bed and the motor current when the treatment bed and the load are in a non-collision state to predict the motor current when the treatment bed and the load are in a normal non-collision state under the current multi-dimensional parameters. At the same time, the actual current of the motor in the current operating state is obtained, and the current difference between the actual current and the predicted current is compared to exceed the preset current difference range to determine that the actual current changes greatly, and the current change amount has exceeded the current change range when the treatment bed moves normally, that is, the motor current has surged, and the reason for the surge in current is caused by the collision between the treatment bed and the load, thereby accurately detecting the collision of the treatment bed.
[0039] In the above-mentioned collision detection method, the current difference between the motor when the treatment bed collides and when it does not collide is very different. By comparing the current difference between the actual current of the motor and the predicted current when there is no collision with the preset current difference range, the current surge caused by the collision at any spatial position in the treatment bed cavity and the large current change can be accurately detected without being restricted by the detection space area. In this way, the collision within all spatial ranges in the treatment bed cavity can be accurately and comprehensively detected, improving the collision detection accuracy and avoiding the missed detection of collisions due to the existence of detection blind spots in related technologies. At the same time, in the technical solution of this application, additional external force detection sensing devices are also omitted, reducing hardware costs and saving application resources.
[0040] Secondly, the implementation architecture involved in this application is briefly introduced below.
[0041] Figure 1 is a schematic diagram of a medical device provided by this application. Figure 1 As shown, the medical device includes a treatment bed 12, a Y-axis transmission mechanism 15 moving in the horizontal longitudinal direction, a Z-axis transmission mechanism 16 moving in the vertical direction, an X-axis transmission mechanism 17 moving in the horizontal transverse direction, a treatment head 18 and a treatment cavity 19. Based on this, three-dimensional treatment is achieved.
[0042] In some embodiments, the medical device may further include a yaw axis transmission mechanism 13 for yaw motion around the vertical rotation direction along the isocenter 11, and a pitch axis transmission mechanism 14 for pitch motion around the horizontal lateral rotation direction along the isocenter 11. Based on this, five-dimensional treatment is achieved.
[0043] In some embodiments, the above-mentioned medical equipment may be a radiotherapy device, or may be a radiological examination device during treatment or examination, such as CT, PET-CT, robotic surgery equipment, etc.
[0044] Optionally, the treatment bed is connected to the support component via a driving component, and the driving component includes a motor. The driving component is used to drive the support component to move. The current of the motor provides driving force for the movement of the treatment bed.
[0045] The motor may be a servo motor, including a servo controller, and the current value of the motor current is obtained from the servo controller.
[0046] The support component is used to support and fix the treatment bed 12. The support component can move longitudinally, transversely, and vertically, and can also rotate isocentrically along the isocenter or non-isocentrically along the non-isocenter, so as to move the load (i.e., the patient) of the treatment bed 12 in any direction during treatment.
[0047] The above-mentioned medical equipment requires multiple motion axes to move simultaneously when achieving fast and accurate radiotherapy. However, there is a problem in the above-mentioned treatment process. When the patient's lesion is in a relatively biased position, the treatment bed 12 needs to move and deflect on a larger scale to align the lesion with the radiation focus (such as the isocenter 11). This causes the actual movement distance of the treatment bed 12 to exceed the cavity space range of the radiotherapy cavity 19, which may cause the patient's body and other objects to collide with the treatment cavity 19. In order to ensure the safety of the patient, when the patient's body and other objects collide with the treatment cavity 19, timely feedback should be obtained, and the treatment bed should move to the initial position and generate an interlock. Therefore, it is necessary to perform collision detection on the control system of the treatment bed in real time to ensure safety.
[0048] The treatment bed collision detection method provided in the embodiment of the present application can be applied to the above-mentioned medical equipment. For ease of understanding, the treatment bed collision detection method provided in the present application is specifically introduced below in conjunction with the accompanying drawings.
[0049] Figure 2 is a flow chart of a treatment bed collision detection method according to an exemplary embodiment. Figure 2 As shown, the treatment bed collision detection method includes the following steps.
[0050] S21, predicting the current of the motor under the current motion trajectory parameters, the current load weight and the current treatment parameters according to the correlation between the motion trajectory parameters, the load weight and the treatment parameters of the treatment bed and the current of the motor under the non-collision condition of the treatment bed, and obtaining the predicted current.
[0051] The correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor when the treatment bed is not in collision can be obtained in any of the following three ways.
[0052] The first acquisition method is to store the historical currents of the motor corresponding to different historical motion trajectory parameters, historical load weights, and historical treatment parameters in a preset table. By looking up the table and based on the interpolation algorithm, the linear relationship between the current motion trajectory parameters, the current load weight and the current of the motor under the current treatment parameters is obtained.
[0053] Exemplarily, a linear relationship is determined between the current motion trajectory parameter, the current load weight, and the two historical currents corresponding to the two historical motion trajectory parameters, the two historical load weights, and the two historical treatment parameters adjacent to the current treatment parameter, and then the current motion trajectory parameter, the current load weight, and the current treatment parameter are inserted into the linear relationship to obtain the predicted current.
[0054] It should be noted that if the current motion trajectory parameters, the current load weight and the current treatment parameters exist in the preset table, the corresponding historical current in the preset table is directly used as the preset current.
[0055] The second acquisition method is to use training sample data to obtain its association relationship.
[0056] Specifically, firstly, an initial model is constructed to characterize the initial correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment couch and the current of the motor of the treatment couch in a non-collision situation.
[0057] Secondly, filter the input and output sample data. Input sample data: historical motion trajectory parameters, historical load weight, and historical treatment parameters of the treatment bed. Output sample data includes the historical current of the motor corresponding to the input sample data when the treatment bed is not in a collision condition. The historical current is used to indicate the model parameters for correcting the initial model.
[0058] Finally, the input sample data is input into the initial model to obtain the initial current output by the initial model; the initial current is subtracted from the historical current corresponding to the input sample data to obtain a comparison difference. When the comparison difference is greater than the preset difference, the model parameters of the initial model are updated; the input sample data is then input into the initial model after the model parameters are updated to obtain the initial current output by the initial model again, and the initial current obtained again is subtracted from the historical current corresponding to the input sample data to obtain a new comparison difference, and whether to re-update the model parameters of the initial model is determined according to the comparison difference, and this is repeated until the comparison difference is less than or equal to the preset difference, then the updating of the model parameters of the initial model is stopped, and the initial model of the model parameters corresponding to the comparison difference when the comparison difference is less than or equal to the preset difference is used as the preset model to characterize the association relationship.
[0059] In the second acquisition method, the historical motion trajectory parameters, historical load weight, and historical treatment parameters of the treatment bed are used as input sample data, and the historical current of the corresponding motor in the treatment bed under non-collision conditions is used as output sample data for indicating the model parameters of the modified initial model, and the initial model is trained to obtain a preset model that characterizes the association relationship. This acquisition method is accurate and efficient.
[0060] Based on this, the current motion trajectory parameters, current load weight and current treatment parameters are input into the above preset model to obtain the predicted current.
[0061] The third acquisition method is to construct a dynamic model that characterizes the correlation relationship based on the dynamic model of the treatment bed described by the motor operation parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed.
[0062] Optionally, for a three-dimensional treatment bed or a five-dimensional treatment bed, a dynamic model characterizing the correlation relationship can be constructed based on the motor operating parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed; the current motion trajectory parameters, current load weight and current treatment parameters are input into the dynamic model to obtain the predicted current.
[0063] Among them, the motor operating parameters include motor torque constant, motor current, motor external disturbance and motor friction; the motion trajectory parameters include the position, speed and acceleration of the treatment bed; the treatment parameters include the inclination angle and weight of the treatment bed; the load weight is linearly related to the inclination angle.
[0064] Furthermore, considering that the X, Y, and Z axes in the five-dimensional treatment bed have little effect on the judgment result, they can be simplified during modeling, so only the dynamic modeling along the horizontal lateral rotation direction and the vertical rotation direction needs to be performed.
[0065] It can be understood that, since the acceleration and deceleration of the X-axis and Z-axis of the treatment bed in the five-dimensional treatment bed are both affected by the yaw axis and the pitch axis, the dynamic model along the horizontal rotation direction and the vertical rotation direction can reflect the dynamic model of the treatment bed.
[0066] Specifically, when the motor operating parameters indicate that the treatment bed is running in five-dimensional directions, it is described as a five-dimensional treatment bed. Based on the motor operating parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed, a dynamic model in the horizontal rotation direction and the vertical rotation direction is constructed.
[0067] Among them, the five-dimensional directions include horizontal transverse direction, horizontal longitudinal direction, vertical direction, horizontal rotation direction and vertical rotation direction.
[0068] S22, obtain the actual current of the motor.
[0069] The current from the motor provides the driving force for the movement of the treatment bed.
[0070] In some embodiments, due to the existence of friction and disturbance during the operation of the motor, the current generally contains noise. Therefore, the current output by the motor is input into a Butterworth filter to filter the output current data to obtain a more accurate actual current.
[0071] S23, when the current difference between the actual current and the predicted current exceeds the preset current difference range, the treatment bed is controlled to move in the reverse direction back to the movement starting position of the treatment bed.
[0072] The above-mentioned preset current difference range is characterized by the range of change of the motor current when no collision occurs to the treatment bed.
[0073] When the current difference between the actual current and the predicted current exceeds the preset current difference range, it indicates that the current of the motor has surged due to the collision of the treatment bed.
[0074] Specifically, in view of the current of the motor used to drive the movement of the treatment bed when the treatment bed collides, compared with the motor current when the treatment bed is operating normally without collision, its current will surge to a larger current value in the positive and negative directions. The correlation between the dimensional parameters of the treatment bed and the current of the motor when the treatment bed is not in collision is used to predict the motor current of the motor in normal operation under the current parameters, and obtain the predicted current when the treatment bed does not collide. At the same time, the actual current of the motor in the current operating state is obtained. When the current difference between the actual current and the predicted current exceeds the preset difference range, it means that the current of the motor has surged, so that the treatment bed is detected to have collided. And when a collision is detected, the treatment bed is controlled to move in the opposite direction back to the starting position of the movement of the treatment bed to ensure the safety of loads such as patients on the treatment bed.
[0075] Compared with the related art that relies on the sensing device set on the treatment bed for collision detection, the above method is not limited by the detection direction and detection space. When a collision occurs in the direction of any spatial dimension, it can produce a current surge, that is, it will cause a current difference between the actual current and the predicted current.
[0076] With respect to the above step S23, when the current difference between the actual current and the predicted current is within the preset current difference range, it indicates that the treatment bed has not collided, and the treatment bed is controlled to continue to run according to the current running trajectory parameters to ensure the normal operation of the treatment bed.
[0077] As a warning method, when the current difference between the actual current and the predicted current exceeds the preset current difference range, an indication message is issued to indicate that there is a risk of collision between the treatment bed and the load, so as to remind the user that there is a high risk of collision between the treatment bed and the load, and to take appropriate safety measures. At the same time, the control interface used to control the operation of the treatment bed can also be locked to prevent the user from continuing to perform erroneous operations when the treatment bed collides with the load, thereby eliminating the corresponding safety hazards.
[0078] The collision detection method is described below by taking the correlation relationship between the dynamic model construction of the pitch axis and the yaw axis of the five-dimensional treatment bed as an example.
[0079] Second, the linear relationship between motor torque and current is expressed by formula (2).
[0080]
[0081] Among them, T c is the motor torque constant, which can be obtained directly from the motor manual. Output current vector for each motor.
[0082] make Formula (3) obtained from formula (1) and formula (2) is as follows.
[0083]
[0084] The current value i(t) of the servo motor at different movement times t is collected in real time through the I / O interface of the servo amplifier.
[0085] Third, due to the existence of friction and disturbance during the operation of the motor, the current generally contains noise. Therefore, this application designs a Butterworth filter to filter the current data. The transfer function of the Butterworth filter is shown in formula (4).
[0086]
[0087] Fourthly, based on different loads and different load positions, a more appropriate current threshold is selected. The difference between the model predicted current and the sampled current is obtained to obtain the difference of the motor current as formula (5).
[0088]
[0089] Fifth, the absolute value of the motor current difference τ(t) is taken and compared with the threshold.
[0090] Sixth, when the difference τ(t) of the motor current is greater than the preset threshold, an alarm is issued, the treatment bed moves in the opposite direction to the origin, an interlock occurs, and the current treatment process ends, otherwise the next step will be continued.
[0091] Optionally, as an implementation, the preset current difference range may be a preset static preset current difference range, or may be determined based on the treatment bed position, load position and load weight in order to obtain higher accuracy, and the specific determination process is as follows. That is, when the current difference between the actual current and the predicted current exceeds the preset current difference range, the treatment bed is controlled to move in the reverse direction back to the starting position of the treatment bed, and the following steps are specifically performed.
[0092] First, according to the mapping relationship between the position information of the treatment bed and the load, the load weight and the current threshold, the current position information of the treatment bed and the load and the target current threshold under the current load weight are determined. The current threshold represents the current difference between the upper limit current and the lower limit current reached by the motor current when the treatment bed and the load are operating normally under the position information of the treatment bed and the load and the load weight without collision.
[0093] In this way, based on the fact that the current threshold is affected by the position information of the treatment bed and the load and the weight of the load, and considering that the current thresholds corresponding to different positions and different loads are different, the current threshold can be determined more accurately, thereby determining a more accurate preset current difference range based on the current threshold.
[0094] Secondly, the opposite number of the current threshold is determined as the lower threshold of the preset current difference range, and the current threshold is determined as the upper threshold of the preset current difference range, so as to obtain the preset current difference range.
[0095] In order to ensure that the actual current obtained is more accurate, the actual current of the motor is set to the current data after filtering by the Butterworth filter.
[0096] Through the above implementation, the relationship between the multi-dimensional parameters of the treatment bed and the motor current when the treatment bed and the load are in a non-collision state is used to predict the motor current when the treatment bed and the load are in a normal non-collision state under the current multi-dimensional parameters. At the same time, the actual current of the motor in the current operating state is obtained, and the current difference between the actual current and the predicted current exceeds the preset current difference range to determine that the actual current changes greatly, and the current change amount has exceeded the current change range when the treatment bed moves normally, that is, the motor current has surged, and the reason for the surge in current is caused by the collision between the treatment bed and the load, so as to accurately detect the collision of the treatment bed.
[0097] Through the above-mentioned collision detection method, the current difference between the motor when the treatment bed collides and when it does not collide is very different. By comparing the current difference between the actual current of the motor and the predicted current when there is no collision with the preset current difference range, the current surge caused by the collision at any spatial position in the treatment bed cavity and the large current change can be accurately detected without being restricted by the detection space area. In this way, the collision within all spatial ranges in the treatment bed cavity can be accurately and comprehensively detected, improving the collision detection accuracy and avoiding the missed collision due to the existence of detection blind spots in related technologies. At the same time, in the technical solution of this application, additional external force detection sensing devices are also omitted, reducing hardware costs and saving application resources.
[0098] In order to achieve the above functions, the treatment bed collision detection device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0099] The present application also provides a method Figure 3 A treatment bed collision detection device is shown, which includes a prediction unit 301, an acquisition unit 302 and a control unit 303.
[0100] The prediction unit 301 is used to predict the motor current under the current motion trajectory parameters, current load weight and current treatment parameters according to the correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor under the non-collision condition of the treatment bed, and obtain the predicted current. The acquisition unit 302 is used to acquire the actual current of the motor; the motor is driven
[0101] The control unit 303 is used to control the treatment bed to move in the reverse direction back to the movement starting position of the treatment bed when the current difference between the actual current and the predicted current exceeds the preset current difference range.
[0102] In a possible implementation, the prediction unit 301 is specifically used to: construct a dynamic model that characterizes the association relationship based on the motor operation parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed; input the current motion trajectory parameters, the current load weight and the current treatment parameters into the dynamic model to obtain a predicted current; wherein the motor operation parameters include the motor torque constant, the motor current, the motor external disturbance and the motor friction; the motion trajectory parameters include the position, speed and acceleration of the treatment bed; the treatment parameters include the inclination angle of the treatment bed and the weight of the treatment bed; the load weight is linearly related to the inclination angle.
[0103] In another possible implementation, the prediction unit 301 is specifically used to: when the motor operating parameters indicate that the treatment bed is running in five-dimensional directions, based on the motor operating parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed, construct a dynamic model in the horizontal rotation direction and the vertical rotation direction; wherein the five-dimensional direction includes a horizontal transverse direction, a horizontal longitudinal direction, a vertical direction, a horizontal rotation direction and a vertical rotation direction.
[0104] In another possible implementation manner, the prediction unit 301 is specifically used to: construct an initial model that characterizes the initial correlation relationship between the motion trajectory parameters, load weight and treatment parameters of the treatment couch and the current of the motor on the treatment couch in a non-collision condition; train the initial model using the historical motion trajectory parameters, historical load weight and historical treatment parameters of the treatment couch as input sample data, and using the corresponding historical current of the motor on the treatment couch in a non-collision condition as output sample data for indicating model parameters for correcting the initial model, to obtain a preset model that characterizes the correlation relationship; and input the current motion trajectory parameters, current load weight and current treatment parameters into the preset model to obtain a predicted current.
[0105] In another possible implementation manner, when the current difference between the actual current and the predicted current exceeds the preset current difference range, before the treatment bed is controlled to move in the opposite direction back to the starting position of the treatment bed, the acquisition unit 302 is further used to: determine the current position information of the treatment bed and the load and the target current threshold under the current load weight according to the mapping relationship between the position information of the treatment bed and the load, the load weight and the current threshold; the current threshold represents the current difference between the upper limit current and the lower limit current reached by the motor current when the treatment bed and the load operate normally under the position information and the load weight of the treatment bed and the load in a non-collision situation; determine the opposite of the current threshold as the lower limit threshold of the preset current difference range, and determine the current threshold as the upper limit threshold of the preset current difference range, to obtain the preset current difference range; wherein the actual current of the motor is the current data filtered by the Butterworth filter.
[0106] In another possible implementation, the control unit 303 is further configured to: when the current difference between the actual current and the predicted current is within a preset current difference range, control the treatment bed to continue to operate according to the current operation trajectory parameters.
[0107] In another possible implementation, the control unit 303 is further used to: when the current difference between the actual current and the predicted current exceeds a preset current difference range, issue an indication message indicating that there is a collision risk between the treatment bed or the load, and / or, associate and lock a control interface used to control the operation of the treatment bed.
[0108] Regarding the device in the above embodiment, the specific manner in which each unit module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.
[0109] Figure 4 is a schematic diagram of a medical device provided by this application. Figure 4 The medical device 60 may include at least one processor 601 and a memory 603 for storing processor executable instructions. The processor 601 is configured to execute instructions in the memory 603 to implement the treatment bed collision detection method in the following embodiment.
[0110] In addition, the medical device 60 may further include a communication bus 602 , at least one communication interface 604 , an input device 606 , and an output device 605 .
[0111] The processor 601 may be a central processing unit (CPU), a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.
[0112] Communication bus 602 may include a pathway for transmitting information between the above-mentioned components.
[0113] The communication interface 604 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.
[0114] The input device 606 is used to receive input signals and the output device 605 is used to output signals.
[0115] The memory 603 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processing unit through a bus. The memory may also be integrated with the processing unit.
[0116] The memory 603 is used to store instructions for executing the solution of the present application, and the execution is controlled by the processor 601. The processor 601 is used to execute the instructions stored in the memory 603, so as to realize the functions in the method of the present application.
[0117] In a specific implementation, as an embodiment, the processor 601 may include one or more CPUs, such as Figure 4 CPU0 and CPU1 in.
[0118] In a specific implementation, as an embodiment, the medical device 60 may include multiple processors, such as Figure 4 601 and processor 607 in FIG. Each of these processors may be a single-CPU processor or a multi-CPU processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).
[0119] The medical device Figure 4 The system includes: a processor 601 and a memory 603 for storing executable instructions of the processor 601; wherein the processor 601 is configured to execute the executable instructions to implement a treatment bed collision detection method as in any possible implementation method described above. The same technical effect can be achieved, and to avoid repetition, it will not be described here.
[0120] The embodiment of the present application also provides a computer-readable storage medium, when the instructions in the computer-readable storage medium are executed by the processor of the treatment bed collision detection device or medical equipment, the treatment bed collision detection device or medical equipment can execute the treatment bed collision detection method of any possible implementation method as described above. And the same technical effect can be achieved, so it will not be repeated here to avoid repetition.
[0121] The embodiment of the present application also provides a computer program product, including a computer program or instruction, which is executed by a processor to perform a treatment bed collision detection method in any of the above possible implementations. The same technical effect can be achieved, and to avoid repetition, it will not be described here.
[0122] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.
[0123] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A treatment bed collision detection method, characterized in that: The method comprises: According to the correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor under the non-collision condition of the treatment bed, the current of the motor under the current motion trajectory parameters, the current load weight and the current treatment parameters are predicted to obtain the predicted current; and the actual current of the motor is obtained; the current of the motor provides driving force for the movement of the treatment bed; When the current difference between the actual current and the predicted current exceeds a preset current difference range, the treatment couch is controlled to move in the reverse direction back to a movement starting position of the treatment couch.
2. The treatment bed collision detection method according to claim 1, characterized in that: The method predicts the current of the motor under the current motion trajectory parameters, the current load weight and the current treatment parameters according to the correlation between the motion trajectory parameters, the load weight and the treatment parameters of the treatment bed and the current of the motor under the non-collision condition of the treatment bed to obtain the predicted current, including: Based on the motor operation parameters and the motion trajectory parameters of the treatment bed, the load weight and the treatment parameters, a dynamic model characterizing the association relationship is constructed; Inputting the current motion trajectory parameters, the current load weight and the current treatment parameters into the kinetic model to obtain the predicted current; Among them, the motor operation parameters include motor torque constant, motor current, motor external disturbance and motor friction; the motion trajectory parameters include the position, speed and acceleration of the treatment bed; the treatment parameters include the inclination angle and weight of the treatment bed; the load weight is linearly related to the inclination angle.
3. The treatment bed collision detection method according to claim 2, characterized in that: The step of constructing a dynamic model representing the association relationship based on the motor operation parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed includes: When the motor operating parameters indicate that the treatment bed is moving in five-dimensional directions, the dynamic model is constructed along the horizontal rotation direction and the vertical rotation direction based on the motor operating parameters and the motion trajectory parameters, load weight and treatment parameters of the treatment bed; wherein the five-dimensional directions include a horizontal transverse direction, a horizontal longitudinal direction, a vertical direction, a horizontal rotation direction and a vertical rotation direction.
4. The treatment bed collision detection method according to claim 1, characterized in that: The method predicts the current of the motor under the current motion trajectory parameters, the current load weight and the current treatment parameters according to the correlation between the motion trajectory parameters, the load weight and the treatment parameters of the treatment bed and the current of the motor under the non-collision condition of the treatment bed to obtain the predicted current, including: Constructing an initial model that characterizes the initial correlation between the motion trajectory parameters, load weight and treatment parameters of the treatment bed and the current of the motor of the treatment bed in a non-collision condition; The initial model is trained using historical motion trajectory parameters, historical load weight, and historical treatment parameters of the treatment bed as input sample data, and the corresponding historical current of the motor of the treatment bed in a non-collision situation as output sample data for indicating model parameters for correcting the initial model, so as to obtain a preset model representing the association relationship; The current motion trajectory parameters, the current load weight and the current treatment parameters are input into the preset model to obtain the predicted current.
5. The treatment bed collision detection method according to any one of claims 1 to 4, characterized in that: Before controlling the treatment bed to move in the reverse direction back to the movement starting position of the treatment bed when the current difference between the actual current and the predicted current exceeds the preset current difference range, the method includes: According to the mapping relationship between the position information of the treatment bed and the load, the load weight and the current threshold, the current position information of the treatment bed and the load and the target current threshold under the current load weight are determined; the current threshold represents the current difference between the upper limit current and the lower limit current reached by the motor current when the treatment bed and the load operate normally under the position information and the load weight of the treatment bed and the load in a non-collision situation; Determine the opposite number of the current threshold as the lower threshold of the preset current difference range, and determine the current threshold as the upper threshold of the preset current difference range, to obtain the preset current difference range; The actual current of the motor is current data filtered by a Butterworth filter.
6. The treatment bed collision detection method according to any one of claims 1 to 4, characterized in that: After predicting the current of the motor under the current motion trajectory parameters, the current load weight and the current treatment parameters according to the correlation between the motion trajectory parameters, the load weight and the treatment parameters of the treatment bed and the current of the motor under the non-collision condition of the treatment bed to obtain the predicted current, the method further includes: When the current difference between the actual current and the predicted current is within the preset current difference range, the treatment bed is controlled to continue running according to the current running trajectory parameters.
7. The treatment bed collision detection method according to any one of claims 1 to 4, characterized in that: The method further comprises: When the current difference between the actual current and the predicted current exceeds a preset current difference range, an indication message is issued to indicate that there is a collision risk between the treatment bed and the load, and / or a control interface for controlling the operation of the treatment bed is associated and locked.
8. A treatment bed collision detection device, characterized in that: The device comprises: a prediction unit, configured to predict the current of the motor under the current motion trajectory parameters, the current load weight and the current treatment parameters according to the correlation between the motion trajectory parameters, the load weight and the treatment parameters of the treatment bed and the current of the motor under the non-collision condition of the treatment bed, so as to obtain a predicted current; an acquisition unit, used to acquire an actual current of the motor; the current of the motor provides a driving force for the movement of the treatment bed; and a control unit, used to control the treatment bed to move in a reverse direction back to a movement starting position of the treatment bed when a current difference between the actual current and the predicted current exceeds a preset current difference range.
9. A medical device, characterized in that: The medical device comprises a treatment couch, and is configured to execute the treatment couch collision detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor, the treatment bed collision detection method according to any one of claims 1 to 7 can be performed.