Electric bed intelligent test method and system based on visual analysis

Abstract

The invention discloses an electric bed intelligent test method and system based on visual analysis, and the method comprises the steps: carrying out the multi-part spatial positioning and displacement track analysis of an electric bed through a machine vision module in a first test period, generating displacement monitoring data, and evaluating a deviation node; motor operation parameters are synchronously collected, and a multi-dimensional data item set is constructed in combination with displacement data; an FP-Growth association algorithm is adopted to mine an implicit association rule between displacement abnormity and motor parameters, when it is judged that a specific displacement deviation is associated with motor state parameters, an abnormal association node is generated, an abnormal displacement-motor parameter group is defined, and finally a subsequent test scheme is dynamically optimized based on the abnormal characteristic parameter group. And a closed-loop test process of'detection-diagnosis-adaptation 'is formed. According to the invention, adaptive adjustment of the test scheme is realized, and the intelligent degree of quality detection of the electric bed and the tracing efficiency of abnormal factors are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent analysis of electric beds, and more specifically, to an intelligent test method and system for electric beds based on visual analysis. Background Art

[0002] Traditional electric bed test methods rely on manual operation and subjective judgment, and have problems such as low efficiency, poor accuracy, and single coverage scenarios. In the case of electric beds in multiple scenarios and complex usage conditions, it is easy to have situations such as control deviation and inaccurate lifting. The traditional test process is difficult to effectively evaluate abnormal conditions and regulate production, lacking a process of using machine vision for efficient deviation analysis and test regulation. At the same time, there is a lack of correlation analysis between the control deviation of the electric bed and the motor operation process, and potential abnormal control parameters cannot be effectively mined.

[0003] Therefore, there is an urgent need for an intelligent test method for electric beds based on visual analysis. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and provides an intelligent test method and system for electric beds based on visual analysis.

[0005] The first aspect of the present invention provides an intelligent test method for electric beds based on visual analysis, including:

[0006] S1: In the first test cycle, set multiple test nodes, test the target electric bed based on a preset plan, perform multi-site positioning and displacement analysis on the target electric bed based on the machine vision module, and obtain displacement monitoring data;

[0007] S2: Evaluate the displacement deviation according to the displacement monitoring data and set abnormal nodes;

[0008] S3: Through the motor module, obtain the motor monitoring data of the target electric bed, set a data item according to each parameter, generate multiple data items according to the displacement monitoring data and the motor monitoring data, analyze the correlation between the data items through the FP-Growth association algorithm, and obtain associated data items;

[0009] S4: If the associated data items include displacement and motor parameters, and the corresponding test node is an abnormal node, then mark the corresponding node as an abnormal associated node, and dynamically set an abnormal displacement-motor parameter group based on the abnormal associated node;

[0010] S5: Dynamically set the test plan according to the abnormal displacement-motor parameter group, and combine the abnormal associated nodes to generate a dynamic test plan.

[0011] In this solution, the specific content of S1 is:

[0012] In the first test cycle, multiple test nodes are set to ensure that the intervals between each test node are consistent;

[0013] Based on a preset plan, the target electric bed is tested. During the test process, video data of the target electric bed is obtained through a machine vision module;

[0014] Key frames are extracted from the video data, and the key frame images are preprocessed by smoothing, denoising, and normalizing;

[0015] The key frame images include multi-angle image frames of the target electric bed;

[0016] Based on the YOLOv7 model, feature extraction and target recognition are performed on the key frame images. Based on the various parts of the target electric bed, identification and positioning are carried out, and target movement monitoring is performed. Parameters of multiple test nodes are recorded based on the movement speed, movement amplitude, rotation angle, and movement trajectory of each part to obtain displacement monitoring data.

[0017] In this scheme, the specific content of S2 is as follows:

[0018] Through the displacement monitoring data, it is compared with the expected displacement parameters of each part of the bed body, and a preset weight is set for the displacement parameters to calculate the displacement weighted deviation rate of multiple test nodes;

[0019] It is judged whether the displacement weighted deviation rate is greater than the preset deviation rate. If so, the corresponding test node is marked as an abnormal node.

[0020] In this scheme, the specific content of S3 is as follows:

[0021] Through the motor module, the motor parameters are monitored and recorded in the first test cycle to obtain motor monitoring data;

[0022] The motor parameters include the effective value of current, current harmonic components, voltage, rotation speed, and vibration frequency;

[0023] In the motor monitoring data, each motor parameter is used as a data item, and in the displacement monitoring data, each movement parameter is used as a data item to generate a data item set;

[0024] Based on the FP-Growth association algorithm, each data item in the data item set is scanned and its support degree is calculated, and frequent items are screened out based on the minimum support degree;

[0025] An initial FP tree structure is constructed, the frequent items of adjacent nodes are combined to construct a transaction item set, the transaction item set is sorted in descending order based on the support degree, and the sorted transaction items are inserted into the FP tree in turn to complete the construction of the FP tree;

[0026] In a recursive form, perform frequent item set mining on the FP tree, and mark the frequent item sets obtained by each screening as associated data items until all frequent item set mining is completed, obtaining multiple associated data items.

[0027] In this solution, S4 is specifically as follows:

[0028] For an associated data item, if there are both displacement parameters and motor parameters at the same time, extract the corresponding multiple associated parameters, and mark the test nodes corresponding to the multiple associated parameters as associated nodes;

[0029] If the associated nodes are the same nodes or adjacent nodes, and the associated nodes all belong to abnormal nodes, then mark the associated nodes as abnormal associated nodes;

[0030] Taking the abnormal associated nodes as the reference points, based on the preset time span, obtain the displacement parameters and motor parameters within the preset time range, and perform associated storage on the parameters to obtain the abnormal displacement-motor parameter group.

[0031] In this solution, S5 is specifically as follows:

[0032] For an abnormal displacement-motor parameter group, dynamically set the test content, combine the proportion of the abnormal associated nodes in the test nodes, and set the test time period to generate a dynamic test plan;

[0033] Based on multiple abnormal displacement-motor parameter groups, generate multiple dynamic test plans.

[0034] The second aspect of the present invention also provides a vision-based intelligent test system for an electric bed, which includes: a memory and a processor. The memory includes a vision-based intelligent test program for an electric bed. When the vision-based intelligent test program for an electric bed is executed by the processor, the following steps are implemented:

[0035] S1: In the first test cycle, set multiple test nodes, test the target electric bed based on a preset plan, perform multi-site positioning and displacement analysis on the target electric bed based on the machine vision module, and obtain displacement monitoring data;

[0036] S2: Evaluate the displacement deviation according to the displacement monitoring data and set abnormal nodes;

[0037] S3: Through the motor module, obtain the motor monitoring data of the target electric bed, set a data item according to each parameter, generate multiple data items according to the displacement monitoring data and the motor monitoring data, analyze the correlation between the data items through the FP-Growth association algorithm, and obtain associated data items;

[0038] S4: If the associated data items include displacement and motor parameters, and the corresponding test node is an abnormal node, then mark the corresponding node as an abnormal associated node, and dynamically set the abnormal displacement-motor parameter group based on the abnormal associated node;

[0039] S5: Dynamically set the test plan according to the abnormal displacement-motor parameter group, and combine with the abnormal associated node to generate a dynamic test plan.

[0040] The third aspect of the present invention also provides a computer-readable storage medium, which includes an intelligent test program for an electric bed based on visual analysis. When the intelligent test program for an electric bed based on visual analysis is executed by a processor, the steps of the intelligent test method for an electric bed based on visual analysis as described in any one of the above are implemented.

[0041] The present invention discloses an intelligent test method and system for an electric bed based on visual analysis, including in the first test cycle, using a machine vision module to perform multi-site spatial positioning and displacement trajectory analysis on the electric bed, generating displacement monitoring data and evaluating deviation nodes; synchronously collecting motor operation parameters, and combining displacement data to construct a multi-dimensional data item set. Using the FP-Growth association algorithm to mine the implicit association rules between displacement anomalies and motor parameters. When it is determined that there is an association between a specific displacement deviation and motor state parameters, generate an abnormal associated node and define an abnormal displacement-motor parameter group, and finally dynamically optimize the subsequent test plan based on this abnormal characteristic parameter group to form a closed-loop test process of "detection-diagnosis-adaptation". The present invention realizes the adaptive adjustment of the test plan, and significantly improves the intelligent level of the quality detection of the electric bed and the tracing efficiency of abnormal factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 Shows a flowchart of an intelligent test method for an electric bed based on visual analysis according to the present invention;

[0043] Figure 2 Shows a block diagram of an intelligent test system for an electric bed based on visual analysis according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0045] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0046] Figure 1 The flowchart of an intelligent test method for an electric bed based on visual analysis according to the present invention is shown.

[0047] As Figure 1 shown, in the first aspect of the present invention, an intelligent test method for an electric bed based on visual analysis is provided, including:

[0048] S1: In the first test cycle, set multiple test nodes, test the target electric bed based on a preset scheme, perform multi-site positioning and displacement analysis on the target electric bed based on a machine vision module, and obtain displacement monitoring data;

[0049] S2: Evaluate the displacement deviation according to the displacement monitoring data and set abnormal nodes;

[0050] S3: Obtain the motor monitoring data of the target electric bed through the motor module, set a data item according to each parameter, generate multiple data items according to the displacement monitoring data and the motor monitoring data, analyze the correlation between the data items through the FP-Growth association algorithm, and obtain associated data items;

[0051] S4: If the associated data items include displacement and motor parameters, and the corresponding test node is an abnormal node, mark the corresponding node as an abnormal associated node, and dynamically set an abnormal displacement-motor parameter group based on the abnormal associated node;

[0052] S5: Dynamically set the test scheme according to the abnormal displacement-motor parameter group, and generate a dynamic test scheme in combination with the abnormal associated node.

[0053] According to an embodiment of the present invention, the specific content of S1 is:

[0054] In the first test cycle, set multiple test nodes to ensure that the interval of each test node is consistent;

[0055] Test the target electric bed based on a preset scheme. During the test, obtain the video data of the target electric bed through the machine vision module;

[0056] Extract key frames from the video data, and perform preprocessing such as smoothing, noise reduction, and normalization on the key frame images;

[0057] The key frame images include multi-angle image frames of the target electric bed;

[0058] Based on the YOLOv7 model, perform feature extraction and target recognition on the key frame images, perform recognition and positioning of each part of the target electric bed and target movement monitoring, record the parameters of multiple test nodes based on the movement speed, movement amplitude, rotation angle, and movement trajectory of each part, and obtain displacement monitoring data.

[0059] It should be noted that the test node is a time node used to set multiple time points within the test cycle to analyze the displacement deviation of the electric bed and the abnormal changes in the electrical parameters of the motor. The machine vision module includes multiple camera devices that obtain video streams corresponding to different angles and perform corresponding displacement parameter analysis and calculation based on the image features extracted from different angles. The displacement parameters include moving speed, moving amplitude, rotation angle, and moving trajectory. Each part here can be set according to the moving structure of the bed body. For example, three parts can be set, corresponding to the head, waist, and legs in contact with the human body, and the corresponding bed body parts are moved to meet the user's control requirements. In the present invention, object detection is performed based on the YOLOv7 model to improve the detection efficiency. According to research requirements, other detection algorithms can be applied for object recognition and detection, such as image algorithm networks like R-CNN and Fast R-CNN. Before applying object detection, initial training can be performed based on the relevant preset image features of the target electric bed.

[0060] The preset scheme is a general test scheme, including moving and lifting tests, rotation tests, bed body pressure tests, load tests, etc. for multiple parts of the bed body.

[0061] According to an embodiment of the present invention, the specific content of S2 is as follows:

[0062] By comparing the displacement monitoring data with the expected displacement parameters of each part of the bed body, a preset weight value is set for the displacement parameters to calculate the displacement weighted deviation rate of multiple test nodes;

[0063] Judge whether the displacement weighted deviation rate is greater than the preset deviation rate. If so, mark the corresponding test node as an abnormal node.

[0064] It should be noted that there are multiple displacement parameters. Among the preset weight values, the weight values of different displacement parameters are set based on the production requirements and control requirements of the bed body, which can regulate the deviation analysis direction of the system for the electric bed. The expected displacement parameters and other expected data are idealized expected parameter values set based on the test scheme and are used for comparative analysis of the control deviation degree.

[0065] It is worth mentioning here that the preset deviation rate can be set within a relatively low range to screen out nodes that may have deviation and abnormal risk situations, so that a relatively large number of abnormal nodes can be screened out. Based on the analysis requirements, the number of abnormal nodes obtained can be greater than 50% of all nodes. Further, associated abnormal evaluation is performed through subsequent associated analysis.

[0066] According to an embodiment of the present invention, the specific content of S3 is as follows:

[0067] Through the motor module, the motor parameters are monitored and recorded during the first test cycle to obtain the motor monitoring data;

[0068] The motor parameters include the effective value of current, current harmonic components, voltage, rotational speed, and vibration frequency;

[0069] In the motor monitoring data, each motor parameter is used as a data item, and in the displacement monitoring data, each movement parameter is used as a data item to generate a data item set;

[0070] Based on the FP-Growth association algorithm, scan each data item in the data item set and calculate its support degree, and filter out frequent items based on the minimum support degree;

[0071] Construct an initial FP tree structure, combine the frequent items of adjacent nodes to construct a transaction item set, sort the transaction item set in descending order based on the support degree, and insert it into the FP tree in sequence based on the sorted transaction items to complete the construction of the FP tree;

[0072] In a recursive form, perform frequent item set mining on the FP tree, and mark each screened frequent item set as an associated data item until all frequent item set mining is completed to obtain multiple associated data items.

[0073] It should be noted that one data item corresponds to a parameter information of a test node. The minimum support degree can be set to 0.3. The FP tree is a compressed data structure for efficiently mining frequent item sets, which can be constructed by scanning the data set twice. To mine frequent item sets from the FP tree, a conditional FP tree is generally constructed in a recursive form and the frequent item set generation method is applied to mine associated items. During the mining process, a frequent item in the FP tree is selected as a suffix to construct its conditional pattern base, and according to the conditional pattern base, the mining process is recursively executed on the conditional FP tree to generate all frequent item sets. The frequent item sets obtained by recursive mining are integrated to obtain the complete frequent item set data. In the present invention, the parameter information of relevant test nodes is used as data items, and the data items of adjacent nodes are used as transaction items. Adjacent nodes are the frequent items of adjacent test nodes. A frequent item is a special data item corresponding to a parameter. In the combination process, usually two or more data items are combined to form a transaction item. For example, transaction A [movement amplitude = 0.5, effective value of current = 10]. Further, based on the FP-Growth association algorithm, associated data items are mined from the frequent items, and the frequent item set is the associated data item.

[0074] Based on the test requirements, the motor parameters are analyzed by increasing or decreasing corresponding parameters.

[0075] According to the embodiment of the present invention, the specific content of S4 is as follows:

[0076] For an associated data item, if there are both displacement parameters and motor parameters at the same time, extract the corresponding multiple associated parameters, and mark the test nodes corresponding to the multiple associated parameters as associated nodes;

[0077] If the associated nodes are the same node or adjacent nodes, and the associated nodes are all abnormal nodes, the associated nodes are marked as abnormal associated nodes;

[0078] Taking the abnormal associated node as the reference point, based on the preset time span, the displacement parameters and motor parameters within the preset time range are obtained, and the parameters are associated and stored to obtain the abnormal displacement-motor parameter group.

[0079] It should be noted that there are multiple test nodes corresponding to an associated data item, and multiple associated nodes can be marked. The associated data item includes at least two data items, that is, corresponding to two parameters. The preset time span is set by the user, and the user obtains an associated parameter group within a certain time range. For example, two test nodes can be set as the preset time span, then an abnormal associated node is used as the reference point, and all displacements and motor parameters of the two test nodes forward and backward on the time axis are extracted to obtain an abnormal displacement-motor parameter group, in which the displacement and motor parameters under the same node are mapped, associated and stored in the parameter group, and the extraction process is obtained through the displacement monitoring data and motor monitoring data in the first test cycle.

[0080] According to an embodiment of the present invention, S5 specifically includes:

[0081] For an abnormal displacement-motor parameter group, dynamically set the test content, combine the proportion of abnormal related nodes in the test nodes, set the test time period, and generate a dynamic test plan;

[0082] Based on multiple abnormal displacement-motor parameter groups, multiple dynamic test scenarios are generated.

[0083] It should be noted that the higher the proportion of test nodes, the longer the test period, and the proportion calculation is based on the total number of abnormal associated nodes and the total number of test nodes. Each dynamic test scheme dynamically sets the associated parameters involved in each associated abnormal node. The setting of the dynamic test scheme can effectively explore the potential abnormal factors and related abnormal working conditions of the electric bed.

[0084] It is worth noting here that the traditional electric bed production and testing process often relies on manual operation and subjective judgment, and the testing scheme is single. Electric beds are prone to control deviation and inaccurate lifting and lowering in multiple scenarios and complex operating conditions. The traditional testing process is difficult to effectively evaluate abnormal conditions and regulate production, and there is a lack of correlation analysis between electric bed control deviations and motor operation processes, and a lack of dynamic testing and analysis processes, making it impossible to effectively explore potential abnormal control factors.

[0085] Based on this, the present invention conducts preliminary testing and monitoring on the target electric bed through a preset test scheme. Based on the machine vision module and the motor module, displacement monitoring data and motor monitoring data with multiple parameters are obtained. Through precise analysis of multiple test nodes, preliminary abnormal nodes are screened. The FP-Growth association algorithm is introduced to determine the nodes where there is an association between the motor and displacement parameters under multiple nodes, and the abnormal association nodes are screened out. The abnormal association nodes are time nodes with abnormal working conditions and potential control abnormalities in both parameters. After the nodes are mined, the preset time range is further dynamically expanded to extract and associatively map the relevant displacement and motor parameters to form a parameter group, and a dynamic test scheme is constructed for the parameter group and production regulation during the test process. Through the present invention, a test scheme applicable to the target electric bed can be dynamically set, potential abnormal control factors can be accurately mined, effective and complex test contents can be dynamically set, and collaborative analysis and fault prediction of multiple parameters of the electric bed can be realized.

[0086] Meanwhile, through the present invention, the efficiency of capturing abnormal working conditions can be improved, the operating state of the target electric bed can be accurately analyzed and predicted, the control abnormal deviation of the electric bed at different test time nodes can be effectively evaluated and tested, and efficient guidance for electric bed production and finished product screening can be achieved.

[0087] According to an embodiment of the present invention, it further includes:

[0088] Among the abnormal nodes, the associated abnormal nodes are marked as the first nodes, and the non-associated abnormal nodes are marked as the second nodes;

[0089] Based on multiple first nodes, the deviation rate of the corresponding motor parameters is calculated to obtain multiple first deviation rates, and linear fitting is performed based on the multiple first deviation rates to obtain the first curve;

[0090] Motor parameter fitting is performed based on multiple second nodes to obtain the second curve;

[0091] The first curve and the second curve are weighted and fused, specifically, the fitting coefficients of the first curve and the second curve are weighted and averaged, and a motor operation attenuation curve is generated;

[0092] During the test process of the target electric bed, abnormal working conditions are predicted according to the motor operation attenuation curve, and a test warning is set.

[0093] It should be noted that the deviation rate of the motor parameters can be used to compare one or more motor parameters with the expected parameter values to analyze the motor deviation rate at a certain node. The first curve is the motor operation attenuation curve obtained based on the analysis of the first node, which can reflect the trend of the probability of abnormal operation at the first node, while the second curve is based on the motor operation attenuation curve under the first node, and the fitting processes of the two are the same. In the weighted average of the fitting coefficients, the weights of the first and second curves are respectively the ratios of the first node to the abnormal node and the ratio of the second node to the abnormal node. The finally generated motor operation attenuation curve is a fitting curve for the overall evaluation based on abnormal working conditions. Through the fitting curve, the abnormal working condition trend of the motor operation can be effectively predicted, the state curve of normal operation can be evaluated, and intelligent test warning can be realized, improving the test safety and realizing the efficient production control of the electric bed.

[0094] According to an embodiment of the present invention, it further includes:

[0095] Set multiple consecutive test cycles based on multiple dynamic test schemes;

[0096] During multiple consecutive test cycles, test and monitor and analyze the electric bed, and perform motor operation parameter compensation control on the electric bed based on the abnormal displacement - motor parameter group;

[0097] Judge the growth of the number of abnormal nodes and the number of abnormally associated nodes in each test cycle, and evaluate the compensation control effect.

[0098] It should be noted that the motor operation parameter compensation includes voltage and current compensation. The dynamic test scheme can be applied in the second test cycle. The motor operation parameter compensation control is used to perform production control analysis on the electric bed during operation, and adjust the production processes of the motor and related mechanical structures to improve the yield rate.

[0099] During the process of testing and researching a single electric bed, a dynamic scheme can be generated based on the test process of the first test cycle, and the dynamic scheme can be applied to the next test cycle. Whether to perform intelligent evaluation and dynamic generation of the test scheme is determined based on the abnormal working conditions of the next test cycle.

[0100] Figure 2 Shows a block diagram of an intelligent test system for an electric bed based on visual analysis according to the present invention.

[0101] The second aspect of the present invention also provides an intelligent test system 2 for an electric bed based on visual analysis. The system includes: a memory 21 and a processor 22. The memory 21 includes an intelligent test program for an electric bed based on visual analysis. When the intelligent test program for an electric bed based on visual analysis is executed by the processor 22, the following steps are implemented:

[0102] S1: In the first test cycle, set multiple test nodes, test the target electric bed based on a preset scheme, perform multi-site positioning and displacement analysis on the target electric bed based on the machine vision module, and obtain displacement monitoring data;

[0103] S2: Evaluate the displacement deviation according to the displacement monitoring data and set abnormal nodes;

[0104] S3: Through the motor module, obtain the motor monitoring data of the target electric bed, set a data item for each parameter, generate multiple data items based on the displacement monitoring data and the motor monitoring data, analyze the correlation between the data items through the FP-Growth association algorithm, and obtain associated data items;

[0105] S4: If the associated data items include displacement and motor parameters, and the corresponding test node is an abnormal node, then mark the corresponding node as an abnormal associated node, and dynamically set an abnormal displacement-motor parameter group based on the abnormal associated node;

[0106] S5: Dynamically set the test scheme according to the abnormal displacement-motor parameter group, and combine the abnormal associated nodes to generate a dynamic test scheme.

[0107] According to the embodiment of the present invention, the specific content of S1 is as follows:

[0108] In the first test cycle, set multiple test nodes to ensure that the interval of each test node is consistent;

[0109] Test the target electric bed based on a preset scheme. During the test, obtain the video data of the target electric bed through the machine vision module;

[0110] Extract key frames from the video data, and perform preprocessing of smoothing, noise reduction and standardization on the key frame images;

[0111] The key frame images include multi-angle image frames of the target electric bed;

[0112] Based on the YOLOv7 model, perform feature extraction and target recognition on the key frame images, perform recognition and positioning of each part of the target electric bed and target movement monitoring, record the parameters of multiple test nodes based on the movement speed, movement amplitude, rotation angle and movement trajectory of each part, and obtain displacement monitoring data.

[0113] It should be noted that the test node is a time node used to set multiple time points within the test cycle to analyze the displacement deviation of the electric bed and the abnormal changes in the electrical parameters of the motor. The machine vision module includes multiple camera devices that acquire video streams from different angles and perform corresponding displacement parameter analysis and calculation based on the image features extracted from different angles. The displacement parameters include moving speed, moving amplitude, rotation angle, and moving trajectory. Each part here can be set according to the moving structure of the bed body. For example, three parts can be set, corresponding to the head, waist, and legs in contact with the human body, and the corresponding bed body parts are moved to meet the user control requirements. In the present invention, object detection is performed based on the YOLOv7 model to improve the detection efficiency. According to research requirements, other detection algorithms can be applied for object recognition and detection, such as image algorithm networks like R-CNN and Fast R-CNN. Before applying object detection, initial training can be performed based on the relevant preset image features of the target electric bed.

[0114] The preset scheme is a general test scheme, including moving and lifting tests, rotation tests, bed body pressure tests, load tests, etc. for multiple parts of the bed body.

[0115] According to an embodiment of the present invention, the specific content of S2 is as follows:

[0116] By comparing the displacement monitoring data with the expected displacement parameters of each part of the bed body, a preset weight value is set for the displacement parameters to calculate the displacement weighted deviation rate of multiple test nodes;

[0117] Judge whether the displacement weighted deviation rate is greater than the preset deviation rate. If so, mark the corresponding test node as an abnormal node.

[0118] It should be noted that there are multiple displacement parameters. In the preset weight value, the weight values of different displacement parameters are set based on the production requirements and control requirements of the bed body, which can regulate the deviation analysis direction of the system for the electric bed. The expected displacement parameters and other expected data are idealized expected parameter values set based on the test scheme and are used for comparative analysis of the control deviation degree.

[0119] It is worth mentioning here that the preset deviation rate can be set within a relatively low range to screen out nodes that may have deviation and abnormal risk situations, so that a relatively large number of abnormal nodes can be screened out. Based on the analysis requirements, the number of abnormal nodes obtained can be greater than 50% of all nodes. Further, associated abnormal evaluation is performed through subsequent associated analysis.

[0120] According to an embodiment of the present invention, the specific content of S3 is as follows:

[0121] Through the motor module, the motor parameters are monitored and recorded in the first test cycle to obtain the motor monitoring data;

[0122] The motor parameters include the effective value of current, current harmonic components, voltage, rotational speed, and vibration frequency;

[0123] In the motor monitoring data, each motor parameter is used as a data item, and in the displacement monitoring data, each movement parameter is used as a data item to generate a data item set;

[0124] Based on the FP-Growth association algorithm, each data item in the data item set is scanned and its support degree is calculated, and frequent items are screened out based on the minimum support degree;

[0125] An initial FP tree structure is constructed, the frequent items of adjacent nodes are combined to construct a transaction item set, the transaction item set is sorted in descending order based on the support degree, and the sorted transaction items are inserted into the FP tree in turn to complete the construction of the FP tree;

[0126] In a recursive form, frequent item set mining is performed on the FP tree, and each screened frequent item set is marked as an associated data item until all frequent item set mining is completed to obtain multiple associated data items.

[0127] It should be noted that a data item corresponds to a parameter information of a test node. The minimum support degree can be set to 0.3. The FP tree is a compressed data structure for efficiently mining frequent item sets, which can be constructed by scanning the data set twice. To mine frequent item sets from the FP tree, a conditional FP tree is generally constructed in a recursive form and the frequent item set generation method is applied to mine associated items. During the mining process, a frequent item in the FP tree is selected as a suffix, its conditional pattern base is constructed, and according to the conditional pattern base, the mining process is recursively executed on the conditional FP tree to generate all frequent item sets. The frequent item sets obtained by recursive mining are integrated to obtain the complete frequent item set data. In the present invention, the parameter information of relevant test nodes is used as data items, and the data items of adjacent nodes are used as transaction items. Adjacent nodes are the frequent items of adjacent test nodes. A frequent item is a special data item corresponding to a parameter. During the combination process, usually two or more data items are combined to form a transaction item. For example, transaction A [movement amplitude = 0.5, effective value of current = 10]. Further, based on the FP-Growth association algorithm, associated data items are mined from the frequent items, and the frequent item set is the associated data item.

[0128] Based on the test requirements, the corresponding parameters of the motor parameters are increased or decreased for analysis.

[0129] According to an embodiment of the present invention, the specific content of S4 is:

[0130] For an associated data item, if there are both displacement parameters and motor parameters at the same time, the corresponding multiple associated parameters are extracted, and the test nodes corresponding to the multiple associated parameters are marked as associated nodes;

[0131] If the associated nodes are the same node or adjacent nodes, and all the associated nodes belong to abnormal nodes, then mark the associated nodes as abnormal associated nodes;

[0132] Taking the abnormal associated nodes as reference points, based on a preset time span, obtain the displacement parameters and motor parameters within a preset time range, and store the parameters in an associated manner to obtain an abnormal displacement - motor parameter group.

[0133] It should be noted that the test nodes corresponding to an associated data item include multiple ones, and multiple associated nodes can be marked. The associated data item includes at least two data items, that is, corresponding to two types of parameters. The preset time span is set by the user. The user obtains an associated parameter group within a certain time range. For example, two test nodes can be set as the preset time span. Then, taking an abnormal associated node as a reference point, all the displacements and motor parameters of the two test nodes before and after on the time axis are extracted to obtain an abnormal displacement - motor parameter group. In the parameter group, the displacements and motor parameters under the same node are mapped and associated for storage. The extraction process is obtained through the displacement monitoring data and motor monitoring data in the first test cycle.

[0134] According to an embodiment of the present invention, the S5 is specifically:

[0135] For an abnormal displacement - motor parameter group, dynamically set the test content, combine the proportion of the abnormal associated nodes in the test nodes, and set the test time period to generate a dynamic test plan;

[0136] Based on multiple abnormal displacement - motor parameter groups, generate multiple dynamic test plans.

[0137] It should be noted that the higher the proportion of the test nodes occupied, the longer the test time period. The proportion is calculated based on the total number of abnormal associated nodes and the total number of test nodes. Each dynamic test plan is dynamically set for the associated parameters involved in each associated abnormal node. The setting of the dynamic test plan can effectively discover potential abnormal factors and related abnormal working conditions of the electric bed.

[0138] The third aspect of the present invention also provides a computer - readable storage medium. The computer - readable storage medium includes an intelligent test program for an electric bed based on visual analysis. When the intelligent test program for an electric bed based on visual analysis is executed by a processor, the steps of the intelligent test method for an electric bed based on visual analysis as described in any one of the above are implemented.

[0139] The present invention discloses an intelligent testing method and system for an electric bed based on visual analysis, including in the first test cycle, using a machine vision module to perform multi-site spatial positioning and displacement trajectory analysis on the electric bed, generating displacement monitoring data and evaluating deviation nodes; synchronously collecting motor operation parameters, and constructing a multi-dimensional data item set in combination with the displacement data. The FP-Growth association algorithm is used to mine the implicit association rules between displacement anomalies and motor parameters. When it is determined that there is a correlation between a specific displacement deviation and motor state parameters, an abnormal association node is generated and an abnormal displacement-motor parameter group is defined. Finally, based on this abnormal characteristic parameter group, the subsequent test scheme is dynamically optimized to form a closed-loop test process of "detection-diagnosis-adaptation". The present invention realizes the adaptive adjustment of the test scheme, significantly improving the intelligent level of electric bed quality detection and the tracing efficiency of abnormal factors.

[0140] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0141] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0142] In addition, in each embodiment of the present invention, the various functional units can all be integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in a unit; the above-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0143] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments. The foregoing storage medium includes: various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0144] Alternatively, if the above integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0145] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention.

Claims

1. An intelligent test method for an electric bed based on visual analysis, characterized in that, Including: S1: In the first test cycle, set multiple test nodes, test the target electric bed based on a preset scheme, perform multi-site positioning and displacement analysis on the target electric bed based on the machine vision module, and obtain displacement monitoring data; S2: Evaluate the displacement deviation according to the displacement monitoring data and set abnormal nodes; S3: Through the motor module, obtain the motor monitoring data of the target electric bed, set a data item for each parameter, generate multiple data items according to the displacement monitoring data and the motor monitoring data, analyze the correlation between the data items through the FP-Growth association algorithm, and obtain associated data items; S4: If the associated data items include displacement and motor parameters, and the corresponding test node is an abnormal node, mark the corresponding node as an abnormal associated node, and dynamically set an abnormal displacement-motor parameter group based on the abnormal associated node; S5: Dynamically set the test scheme according to the abnormal displacement-motor parameter group, and combine the abnormal associated nodes to generate a dynamic test scheme.

2. The intelligent test method for an electric bed based on visual analysis according to claim 1, wherein The specific content of S1 is: In the first test cycle, set multiple test nodes to ensure that the interval of each test node is consistent; Test the target electric bed based on a preset scheme. During the test, obtain the video data of the target electric bed through the machine vision module; Extract key frames from the video data, and perform preprocessing such as smoothing, noise reduction, and normalization on the key frame images; The key frame images include multi-angle image frames of the target electric bed; Based on the YOLOv7 model, perform feature extraction and target recognition on the key frame images, perform recognition and positioning of each part of the target electric bed and target movement monitoring, record the parameters of multiple test nodes based on the movement speed, movement amplitude, rotation angle, and movement trajectory of each part, and obtain displacement monitoring data.

3. The intelligent test method for an electric bed based on visual analysis according to claim 1, wherein The specific content of S2 is: Compare the displacement monitoring data with the expected displacement parameters of each part of the bed body, set a preset weight for the displacement parameters, and calculate the displacement weighted deviation rate of multiple test nodes; Judge whether the displacement weighted deviation rate is greater than the preset deviation rate. If so, mark the corresponding test node as an abnormal node.

4. The intelligent test method for an electric bed based on visual analysis according to claim 1, characterized in that, The specific content of S3 is: Through the motor module, monitor and record the motor parameters in the first test cycle to obtain motor monitoring data; The motor parameters include the effective value of current, current harmonic component, voltage, rotational speed, and vibration frequency; In the motor monitoring data, use each motor parameter as a data item, and in the displacement monitoring data, use each movement parameter as a data item to generate a data item set; Based on the FP-Growth association algorithm, scan each data item in the data item set and calculate its support degree, and screen out frequent items based on the minimum support degree; Construct an initial FP tree structure, combine the frequent items of adjacent nodes to construct a transaction item set, sort the transaction item set in descending order based on the support degree, and insert the sorted transaction items into the FP tree in turn to complete the construction of the FP tree; In a recursive form, perform frequent item set mining on the FP tree, and mark each frequent item set obtained by each screening as an associated data item until all frequent item set mining is completed to obtain multiple associated data items.

5. The intelligent test method for an electric bed based on visual analysis according to claim 1, wherein The specific content of S4 is: For an associated data item, if there are both displacement parameters and motor parameters, extract multiple corresponding associated parameters, and mark the test nodes corresponding to the multiple associated parameters as associated nodes; If the associated nodes are the same nodes or adjacent nodes, and all the associated nodes belong to abnormal nodes, mark the associated nodes as abnormal associated nodes; Taking the abnormal associated nodes as reference points, based on a preset time span, obtain the displacement parameters and motor parameters within a preset time range, and store the parameters in an associated manner to obtain an abnormal displacement-motor parameter group.

6. The intelligent test method for an electric bed based on visual analysis according to claim 1, wherein, Specifically, S5 is as follows: For an abnormal displacement-motor parameter group, dynamically set the test content, combine the proportion of abnormal associated nodes in the test nodes, and set the test time period to generate a dynamic test plan; Based on multiple abnormal displacement-motor parameter groups, generate multiple dynamic test plans.

7. An intelligent test system for an electric bed based on visual analysis, characterized in that, The system includes: a memory and a processor. The memory includes an intelligent test program for an electric bed based on visual analysis. When the intelligent test program for the electric bed based on visual analysis is executed by the processor, the following steps are implemented: S1: In the first test cycle, set multiple test nodes, test the target electric bed based on a preset plan, perform multi-site positioning and displacement analysis on the target electric bed based on the machine vision module, and obtain displacement monitoring data; S2: Evaluate the displacement deviation according to the displacement monitoring data and set abnormal nodes; S3: Through the motor module, obtain the motor monitoring data of the target electric bed. Set a data item according to each parameter. Generate multiple data items according to the displacement monitoring data and the motor monitoring data. Analyze the correlation between the data items through the FP-Growth association algorithm and obtain associated data items; S4: If the associated data items include displacement and motor parameters, and the corresponding test nodes are abnormal nodes, mark the corresponding nodes as abnormal associated nodes, and dynamically set an abnormal displacement-motor parameter group based on the abnormal associated nodes; S5: Dynamically set the test plan according to the abnormal displacement-motor parameter group, and combine the abnormal associated nodes to generate a dynamic test plan.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes an intelligent test program for an electric bed based on visual analysis. When the intelligent test program for the electric bed based on visual analysis is executed by a processor, the steps of the intelligent test method for an electric bed based on visual analysis as described in any one of claims 1 to 6 are implemented.

Images