CN-121980709-A - Bearing capacity assessment method for manufacturing process of safety handrail based on industrial Internet of things

Abstract

The application provides a bearing capacity assessment method for a safety handrail manufacturing process based on an industrial Internet of things, which comprises the steps of reading the groove spacing of adjacent knurling grooves according to texture depth values, dividing the groove spacing by the texture depth values to obtain groove spacing depth ratios, identifying knurling sections with the groove spacing depth ratios lower than a safety threshold as stress superposition risk sections, extracting the maximum strain gradient in energy peaks of acoustic emission signals and pipe wall strain distribution data in the stress superposition risk sections, weighting and fusing to obtain groove root stress superposition strength, extracting position coordinates of first entering yield of each measuring point from the strain distribution data, identifying the conversion degree of yield starting positions from random distribution to linear arrangement along the knurling groove bottoms by adopting a support vector machine classification algorithm to obtain yield position concentration degrees, dividing damage grades corresponding to the texture depth values according to the yield position concentration degree and the groove root stress superposition strength, and marking the knurling sections with the damage grades exceeding preset warning grades as weak section primary positions.

Inventors

• ZHANG LICONG
• CHEN CHONGLIANG

Assignees

• 瑞沃科技(惠州)有限公司

Dates

Publication Date

20260505

Application Date

20260210

Claims (8)

1. 1. The utility model provides a bearing capacity evaluation method of safety handrail manufacturing process based on industry thing networking which is characterized in that the method includes: The acoustic emission sensing units deployed in the safety handrail manufacturing production line collect acoustic signals during knurling, strain distribution data of all measuring points of the pipe wall are synchronously read by the strain collecting module, texture depth values are extracted from the acoustic signals, and the reduction rate of the effective bearing sectional area of the pipe wall is identified from the strain distribution data; Reading the groove spacing of adjacent knurling grooves according to the texture depth value, dividing the groove spacing by the texture depth value to obtain a groove spacing depth ratio, and identifying a knurling section with the groove spacing depth ratio lower than a safety threshold as a stress superposition risk section; Extracting the energy peak value of the acoustic emission signal in the stress superposition risk section and the maximum strain gradient in the pipe wall strain distribution data, and obtaining the stress superposition strength of the groove root by weighting and fusing; Extracting position coordinates of each measuring point entering yield for the first time from the strain distribution data, and identifying the conversion degree of the yield starting position from random distribution to linear arrangement along the knurl groove bottom by adopting a support vector machine classification algorithm to obtain yield position concentration; dividing the damage level corresponding to the texture depth value according to the yield position concentration degree and the groove root stress superposition intensity, and marking the knurled section with the damage level exceeding a preset warning level as a weak section preliminary position; Extracting the ratio of the reduction rate of the bearing cross section of the primary position of the weak section to the space-between-grooves depth, analyzing the condition that the reduction rate of the bearing cross section exceeds a critical bearing threshold value and the space-between-grooves depth ratio is lower than a safety threshold value, and confirming that the primary position of the weak section is the target weak section position; Extracting the residual wall thickness of the pipe body and the stress superposition intensity of the groove root at the position of the target weak section, carrying out polymerization optimization on the residual wall thickness and the stress superposition intensity of the groove root, constructing a bearing capacity assessment model, and outputting the residual bearing capacity grade of the pipe body.
2. 2. The method for evaluating the bearing capacity of the safety handrail manufacturing process based on the industrial internet of things according to claim 1, wherein the acoustic emission sensing unit deployed in the safety handrail manufacturing line collects acoustic signals during knurling, the strain distribution data of each measuring point of the pipe wall is synchronously read by the strain collection module, the texture depth value is extracted from the acoustic signals, and the effective bearing sectional area reduction rate of the pipe wall is identified from the strain distribution data, and the method comprises the following steps: Continuously acquiring sound wave signals in the processing stage of cutting a knurling cutter into a pipe wall through an acoustic emission sensing unit arranged in a safety handrail manufacturing line, dividing the sound wave signals into frequency bands according to frequency ranges, identifying pulse vibration amplitude values generated by periodic contact of knurling cutter teeth and the pipe wall from high frequency bands, and converting texture depth values of the knurling grooves according to peak-to-valley intervals of the pulse vibration amplitude values; Determining the arrangement interval of measuring points of the strain acquisition module according to the texture depth value, arranging a plurality of groups of strain gauges along the circumferential direction and the axial direction of the pipe wall, acquiring the strain value generated by each measuring point in the knurling process, calculating the strain value difference between adjacent measuring points, and identifying the area where the strain value difference exceeds a preset difference threshold as a wall thickness reduction concentration area; And reading the current wall thickness measured value corresponding to each measuring point in the wall thickness reduction concentration area, subtracting the current wall thickness measured value from the original wall thickness of the pipe body to obtain the wall thickness reduction amount, dividing the wall thickness reduction amount by the original wall thickness to obtain the wall thickness reduction ratio, and multiplying the wall thickness reduction ratio by the original sectional area of the pipe body to obtain the effective bearing sectional area reduction rate of the pipe wall.
3. 3. The method for evaluating the bearing capacity of the manufacturing process of the safety handrail based on the industrial internet of things according to claim 1, wherein the step of reading the groove spacing of the adjacent knurled grooves according to the texture depth value, dividing the groove spacing by the texture depth value to obtain a groove spacing depth ratio, and identifying the knurled section with the groove spacing depth ratio lower than a safety threshold as a stress superposition risk section comprises: Extracting the groove spacing between two adjacent knurl grooves from the pulse period of the acoustic wave signal according to the knurl groove positions corresponding to the texture depth values, dividing the groove spacing by the texture depth values to obtain groove spacing depth ratio values, and recording the groove spacing depth ratio values corresponding to all knurl sections section by section along the axial direction of the pipe body; and judging that the groove spacing depth ratio is lower than a preset safety threshold value according to the groove spacing depth ratio value of each knurl section, and marking the knurl section as a stress superposition risk section.
4. 4. The method for evaluating the bearing capacity of the safety handrail manufacturing process based on the industrial internet of things according to claim 1, wherein the extracting the energy peak value of the acoustic emission signal in the stress superposition risk section and the maximum strain gradient in the pipe wall strain distribution data, and the weighting and fusing to obtain the root stress superposition strength comprises the following steps: For the stress superposition risk section, extracting an energy peak value from the acoustic emission signals in a time window corresponding to the section, squaring the amplitude of the acoustic wave signals and accumulating the squared amplitude of the acoustic wave signals, and recording the corresponding energy peak value when the acoustic wave energy in the section reaches the maximum; Reading the strain value difference between adjacent measuring points from the pipe wall strain distribution data in the stress superposition risk section, dividing the strain value difference by the distance between the measuring points to obtain a strain gradient, and identifying the maximum value of the strain gradient in the relevant section as the maximum strain gradient; And dividing the energy peak value and the maximum strain gradient by the upper limits of the respective measuring ranges respectively to obtain normalized values, and carrying out weighted summation on the normalized values according to preset energy weight coefficients and strain weight coefficients to obtain the root stress superposition intensity of the stress superposition risk section.
5. 5. The method for evaluating the bearing capacity of the safety handrail manufacturing process based on the industrial internet of things according to claim 1, wherein the step of extracting the position coordinates of each measuring point entering yield for the first time from the strain distribution data, and identifying the transition degree of the yield starting position from random distribution to linear arrangement along the bottom of the knurling groove by adopting a support vector machine classification algorithm to obtain the yield position concentration degree comprises the following steps: Reading the strain value of each measuring point by point from the strain distribution data, comparing the strain value with the yield strain threshold value of the material corresponding to the measuring point, and recording the position coordinate of the measuring point on the pipe wall to obtain a yield initial position coordinate sequence if the strain value of the measuring point reaches or exceeds the yield strain threshold value for the first time; For the coordinate sequence of the yield starting position, reading the transverse offset distance of each coordinate point relative to the central line of the bottom of the knurling groove along the axial direction of the pipe body, and combining the transverse offset distances to form a distribution feature vector of each yield starting position; calculating the spatial dispersion between the yield starting positions according to the distribution feature vector, wherein the spatial dispersion is obtained by counting the distance variance from each coordinate point to the center line of the knurling groove bottom, and the spatial dispersion is used as a quantization index for representing the distribution form of the yield starting positions; And a support vector machine classification algorithm is adopted, the distribution feature vector and the spatial dispersion are used as input features, a pre-marked random distribution sample and a pre-marked linear arrangement sample are used as training data, a classification boundary for distinguishing the random distribution from the linear arrangement is obtained, the confidence that the current yield starting position sequence belongs to the linear arrangement is output according to the classification boundary, and the confidence is used as yield position concentration.
6. 6. The method for evaluating the bearing capacity of the safety handrail manufacturing process based on the industrial internet of things according to claim 1, wherein the classifying the damage level corresponding to the texture depth value according to the yield position concentration and the groove root stress superposition intensity, marking the knurled section with the damage level exceeding a preset warning level as a weak section preliminary position, comprises: Establishing a two-dimensional damage evaluation coordinate according to the yield position concentration degree and the groove root stress superposition strength, taking the yield position concentration degree as a horizontal axis value, taking the groove root stress superposition strength as a vertical axis value, and marking the position points of all knurled sections in the two-dimensional damage evaluation coordinate; A plurality of damage level areas are defined in the two-dimensional damage evaluation coordinates in advance, and the damage level of each knurl section under the current texture depth value is determined according to the damage level areas in which the position points of the knurl section fall; and judging that the damage level exceeds a preset warning level aiming at the damage level of each knurled section, and marking the knurled section as a primary position of the weak section.
7. 7. The method for evaluating the bearing capacity of a safety handrail manufacturing process based on the industrial internet of things according to claim 1, wherein the extracting the ratio of the reduction rate of the bearing cross-sectional area of the preliminary position of the weak section to the groove pitch depth, analyzing the case that the reduction rate of the bearing cross-sectional area exceeds a critical bearing threshold value and the groove pitch depth ratio is lower than a safety threshold value, and confirming the preliminary position of the weak section as the target weak section position, comprises: extracting the ratio of the reduction rate of the bearing sectional area to the depth of the groove spacing corresponding to the weak section aiming at the preliminary position of the weak section, judging that the reduction rate of the bearing sectional area exceeds a preset critical bearing threshold value, and simultaneously judging that the depth ratio of the groove spacing is lower than a preset safety threshold value; and if the bearing sectional area reduction rate exceeds a critical bearing threshold value and the groove spacing depth ratio is lower than a safety threshold value, confirming the primary position of the weak section as a target weak section position.
8. 8. The method for evaluating the bearing capacity of the safety handrail manufacturing process based on the industrial internet of things according to claim 1, wherein the extracting the residual wall thickness of the pipe body and the superposition strength of the groove root stress at the position of the target weak section, performing polymerization optimization on the residual wall thickness and the superposition strength of the groove root stress, constructing a bearing capacity evaluation model, outputting the residual bearing capacity grade of the pipe body, comprises: Extracting the residual wall thickness of the target weak section from the pipe wall strain distribution data, wherein the residual wall thickness is obtained by subtracting the reduced wall thickness from the original wall thickness of the pipe body, and simultaneously reading the corresponding root stress superposition strength of the section; Performing polymerization optimization treatment on the residual wall thickness and the groove root stress superposition intensity, dividing the residual wall thickness by the original wall thickness of the pipe body to obtain a wall thickness retention ratio, multiplying the wall thickness retention ratio by a normalized complement value of the groove root stress superposition intensity to obtain a comprehensive load-bearing index, wherein the normalized complement value is a normalized value obtained by subtracting the groove root stress superposition intensity; Reading texture depth values, groove spacing depth ratios and yield position concentration degrees corresponding to the positions of the target weak sections, and combining the texture depth values, the groove spacing depth ratios, the yield position concentration degrees and the comprehensive bearing indexes to form bearing capacity evaluation input vectors; And training by taking the bearing capacity evaluation input vector as an input characteristic and taking pre-labeled pipe body bearing capacity test data as a training label, outputting a continuous bearing capacity prediction value, and mapping the bearing capacity prediction value into the residual bearing capacity grade of the pipe body according to a preset bearing capacity grade division interval.

Description

Bearing capacity assessment method for manufacturing process of safety handrail based on industrial Internet of things Technical Field The invention relates to the technical field of information, in particular to a bearing capacity evaluation method for a safety handrail manufacturing process based on industrial Internet of things. Background Industrial internet of things technology is increasingly widely applied in manufacturing industry, and particularly in the production process of metal-like bearing pipes such as safety armrests, the quality of the metal-like bearing pipes is directly related to life safety and use reliability of personnel in public places. The safety handrail is used as a daily protection member, and has enough structural strength and surface anti-skid performance to cope with the load requirements under various complex use environments, so that the fine control of the manufacturing process becomes a key link for guaranteeing the safety of products. Most of current manufacturing enterprises adopt the traditional knurling process to lift the friction coefficient of the surface of the pipe body so as to prevent accidental hand slipping caused by hand wet sliding. However, this seemingly reasonable process option introduces implicit structural damage. The grooves formed during the knurling process, while increasing the gripping force, simultaneously allow localized material removal from the tube wall and a reduction in the effective bearing area of the cross section. More importantly, when the depth of the knurled texture is increased continuously, the ratio of the distance between adjacent grooves to the depth is changed, and the stress concentration at the groove bottom area is not isolated any more, but obvious mutual influence and superposition effects occur. The superposition of the stress fields enables the originally randomly distributed tiny yield points to gradually concentrate towards the bottom of the knurling groove and be connected into a line when the pipe body bears external force, so that the integral resistance of the pipe is obviously reduced. For example, in the production of a batch of safety rails of the same specification, if the knurling depth is increased from 0.3 mm to 0.6 mm in order to pursue a higher level of anti-slip, the surface friction performance is indeed improved, but in standard load tests, a part of the pipe body is subjected to macroscopic plastic deformation in advance, and even partial collapse occurs well below the design load bearing capacity. The reason is that, because the grain depth is increased, the ratio of the groove spacing to the depth deviates from a reasonable range, so that the stress peaks of the root parts of the adjacent grooves are close to each other and are strengthened, the damage evolution path of the weak area of the pipe wall is changed from dispersion into linear arrangement which is highly concentrated along the groove bottom, and the bearing capacity is greatly weakened. The inherent contradiction between strength and anti-skid performance caused by the adjustment of the technological parameters makes it difficult for manufacturing enterprises to accurately predict and control the actual residual bearing capacity of the pipe body while pursuing a higher anti-skid grade. Therefore, how to effectively identify and quantify the weakening degree of the bearing capacity of the pipe body due to the stress superposition caused by the change of the space between grooves and the depth ratio while the increase of the depth of the knurled textures brings better gripping anti-skid effect, and capture the transition characteristic of the pipe wall damage from random distribution to linear concentration of the groove bottom in real time in the production process, thereby becoming a key problem for ensuring the reliable assessment of the bearing capacity in the manufacturing process of the safety handrail. Disclosure of Invention The invention provides a bearing capacity evaluation method for a safety handrail manufacturing process based on industrial Internet of things, which comprises the following steps: The acoustic emission sensing units deployed in the safety handrail manufacturing production line collect acoustic signals during knurling, strain distribution data of all measuring points of the pipe wall are synchronously read by the strain collecting module, texture depth values are extracted from the acoustic signals, and the reduction rate of the effective bearing sectional area of the pipe wall is identified from the strain distribution data; Reading the groove spacing of adjacent knurling grooves according to the texture depth value, dividing the groove spacing by the texture depth value to obtain a groove spacing depth ratio, and identifying a knurling section with the groove spacing depth ratio lower than a safety threshold as a stress superposition risk section; Extracting the energy peak value of the acoustic emission sign