Building quality detection method based on multi-sensor fusion

Abstract

The invention relates to the technical field of quality detection, and particularly discloses a building quality detection method based on multi-sensor fusion, and the method comprises the steps: detecting a target building, and obtaining the detection data of the target building; calculating an abnormal coefficient of the target building based on the detection data; calculating an evaluation coefficient of the target building based on the detection data and the abnormal coefficient of the target building; based on the evaluation coefficient, evaluating the quality of the target building, judging whether the target building is qualified or not, and generating an evaluation signal; according to the method, the uniformity of abnormal distribution is evaluated through an intelligent algorithm, so that deep insight of the overall state of the building is realized; in addition, an abnormal adjustment value is introduced, the element abnormal ratio and the mutual influence relation of high abnormal elements are comprehensively considered in the calculation of the abnormal adjustment value, the single abnormal degree of the elements is reflected through weighted summation and the overall influence is quantified, the importance of key elements is highlighted, and therefore the accuracy of overall evaluation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of quality detection, and in particular to a construction quality detection method based on multi-sensor fusion. Background Art

[0002] Building quality refers to the ability of a building to meet relevant specifications, standards, design requirements and functional needs, including but not limited to structural stability, durability, safety, aesthetics, functionality and environmental protection. High-quality buildings can provide a comfortable, safe and healthy environment during use, while reducing subsequent maintenance costs and resource consumption.

[0003] However, existing technologies for building quality inspection and evaluation often ignore the differences in the importance of individual building components, and fail to comprehensively consider the component abnormality ratios of highly abnormal components and their mutual influence relationships. By weighted summing and quantifying the overall impact, the building quality assessment is inaccurate. Summary of the invention

[0004] The purpose of the present invention is to provide a building quality detection method based on multi-sensor fusion to solve the technical problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] In a first aspect, the present invention provides a construction quality detection method based on multi-sensor fusion, comprising the following steps:

[0007] Step 1: Detect the target building and obtain the detection data of the target building;

[0008] The detection data includes: abnormal degree characterization value and abnormal uniformity characterization value;

[0009] Step 2: Calculate the abnormal coefficient of the target building based on the detection data;

[0010] Step 3: Calculate the evaluation coefficient of the target building based on the detection data and abnormal coefficient of the target building;

[0011] Step 4: Based on the evaluation coefficient, the quality of the target building is evaluated to determine whether the target building is qualified and generate an evaluation signal.

[0012] As a further solution of the present invention: the process of detecting the target building and obtaining the detection data of the target building is as follows:

[0013] Obtaining component anomaly ratios of each building component in the target building;

[0014] Based on the element anomaly ratio of each building element, the abnormality degree characterization value and the abnormal uniformity characterization value of the target building are calculated respectively.

[0015] As a further solution of the present invention: the process of obtaining the component abnormality ratio is:

[0016] A plurality of sensors are arranged on the building elements, and abnormal values ​​of the elements detected by the sensors are obtained through the sensors;

[0017] The component abnormality value is ratio-calculated with the component preset value to obtain the component abnormality ratio.

[0018] As a further solution of the present invention: the process of obtaining the abnormality degree characterization value is:

[0019] comparing the component anomaly ratio of each building component with a component anomaly ratio threshold value;

[0020] If the component abnormality ratio is greater than the component abnormality ratio threshold, it means that the abnormality degree of the building element is high, that is, a high component abnormality degree signal is generated, and the building element is marked as a high abnormality element;

[0021] Extract the total number of highly abnormal components to obtain the number of highly abnormal components, calculate the ratio of the number of highly abnormal components to the total number of components, and obtain the abnormality degree coefficient;

[0022] The abnormal ratios of all components are averaged to obtain the abnormal mean, the abnormal mean is multiplied by the abnormal degree coefficient to obtain the abnormal degree adjustment value, and the abnormal degree adjustment value is summed with the abnormal mean to obtain the abnormal degree characterization value.

[0023] As a further solution of the present invention: the process of obtaining the abnormal uniformity characterization value is:

[0024] Calculate the difference between the component anomaly ratio and the anomaly mean of each building component respectively, and take the absolute value to obtain the component anomaly offset value of each building component, calculate the mean of the component anomaly offset values ​​of all building components, and obtain the component anomaly offset mean;

[0025] Extract the maximum and minimum values ​​of the component anomaly ratios of all building components to obtain the maximum component anomaly ratio and the minimum component anomaly ratio, perform difference calculation on the maximum component anomaly ratio and the minimum component anomaly ratio to obtain the maximum component anomaly offset value, perform ratio calculation on the maximum component anomaly offset value and the mean component anomaly offset value to obtain the anomaly offset coefficient;

[0026] The abnormal offset coefficient is multiplied by the average abnormal offset of the abnormal component to obtain the abnormal offset adjustment value, and the abnormal offset adjustment value is summed with the average abnormal offset of the component to obtain the abnormal uniform characterization value.

[0027] As a further solution of the present invention: Based on the detection data, the process of calculating the abnormality coefficient of the target building is:

[0028] The abnormal coefficient YC is calculated.

[0029] As a further solution of the present invention: the process of calculating the evaluation coefficient of the target building is:

[0030] Based on the detection data of the target building, the abnormal adjustment value is calculated;

[0031] The abnormal adjustment value is multiplied by the abnormal coefficient to obtain the evaluation coefficient.

[0032] As a further solution of the present invention: the process of obtaining the abnormal adjustment value is:

[0033] Obtain the location information of each high abnormal component respectively, and evaluate the influence relationship between each high abnormal component;

[0034] According to the influence relationship between each high abnormal component in the target building, the component abnormality ratio of each high abnormal component is weighted and summed to obtain the high abnormality weighted total value ratio;

[0035] The anomaly adjustment value is obtained by calculating the ratio of the target building's high anomaly weighted total value to the high anomaly total value.

[0036] As a further solution of the present invention: a qualified quality signal and a failed quality signal;

[0037] The process of generating the evaluation signal is:

[0038] Preset an evaluation coefficient threshold, and compare and analyze the evaluation coefficient with the evaluation coefficient threshold;

[0039] If the evaluation coefficient is less than the evaluation coefficient threshold, a quality qualified signal is generated;

[0040] If the evaluation coefficient is greater than or equal to the evaluation coefficient threshold, a quality failure signal is generated.

[0041] In a second aspect, the present invention provides a building quality detection system based on multi-sensor fusion, the system comprising:

[0042] Data acquisition module: detect the target building and obtain the detection data of the target building;

[0043] The detection data includes: abnormal degree characterization value and abnormal uniformity characterization value;

[0044] Data processing module: calculate the abnormal coefficient of the target building based on the detection data;

[0045] Data adjustment module: Calculate the evaluation coefficient of the target building based on the detection data and abnormal coefficient of the target building;

[0046] Quality assessment module: Based on the assessment coefficient, the quality of the target building is assessed, whether the target building is qualified is determined, and an assessment signal is generated.

[0047] Beneficial effects of the present invention:

[0048] The present invention collects real-time data through multiple sensors installed on building elements, calculates the abnormality degree of each building element (i.e., the ratio of abnormal value to preset value); then, integrates the abnormal information of all building elements, and calculates two key indicators: abnormality degree characterization value, which reflects the overall abnormality level; abnormal uniformity characterization value, which measures the balance of abnormal distribution; then, uses a preset formula, combines these two characterization values ​​and weight factors, and calculates the abnormality coefficient of the target building; this coefficient combines the abnormality degree and uniformity of the building, and provides a basis for subsequent evaluation; further, according to the mutual influence relationship between high abnormal elements, the abnormal ratio is weighted and summed to obtain Abnormal adjustment value; this value takes into account the abnormal degree of important components and their impact on the entire building; finally, the abnormal adjustment value is multiplied by the abnormal coefficient to obtain the evaluation coefficient; the present invention not only comprehensively considers the abnormal conditions of various components in the building, but also evaluates the uniformity of abnormal distribution through intelligent algorithms, thereby achieving a deep insight into the overall state of the building; in addition, the present invention also introduces an abnormal adjustment value, and the calculation of the abnormal adjustment value comprehensively considers the component abnormality ratio of high-abnormal components and their mutual influence relationship, and through weighted summation and quantification of the overall impact, it not only reflects the single abnormal degree of the component, but also highlights the importance of key components, thereby improving the accuracy of the overall evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further described below in conjunction with the accompanying drawings.

[0050] Figure 1 is a flowchart of Embodiment 1 of the present invention;

[0051] Figure 2 It is a system block diagram of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] Embodiment 1:

[0054] See also Figure 1 As shown, a building quality detection method based on multi-sensor fusion according to an embodiment of the present invention comprises the following steps:

[0055] Step 1: Detect the target building and obtain the detection data of the target building;

[0056] The detection data includes: abnormal degree characterization value and abnormal uniformity characterization value;

[0057] In some embodiments, obtaining an element anomaly ratio of each building element in the target building;

[0058] Based on the component anomaly ratio of each building component, the abnormal degree representation value and the abnormal uniformity representation value of the target building are calculated respectively;

[0059] In a first exemplary embodiment, the process of obtaining the component abnormality ratio is as follows:

[0060] A plurality of sensors (sensors include but are not limited to: displacement sensors, infrared imaging sensors) are arranged on the building elements, and through each sensor, an abnormal value of the element detected by each sensor is obtained (the abnormal value of the element is the detection value of the building element by the sensor, and different types of sensors obtain different abnormal values ​​of the element. For example, the abnormal value of the element obtained by the displacement sensor is the value of the position change of the building element, which reflects the difference between the position of the building element and the preset position, that is, the difference between the detection position obtained by the displacement sensor and the preset position; wherein the preset position is the position of the building element set in advance by a person skilled in the art during the construction process);

[0061] Calculate the ratio of the component abnormal value to the component preset value to obtain the component abnormal ratio;

[0062] In a second exemplary embodiment, the process of obtaining the abnormality degree characterization value is as follows:

[0063] comparing the component anomaly ratio of each building component with a component anomaly ratio threshold value;

[0064] If the component abnormality ratio is greater than the component abnormality ratio threshold, it means that the abnormality degree of the building element is high, that is, a high component abnormality degree signal is generated, and the building element is marked as a high abnormality element;

[0065] If the component abnormality ratio is less than or equal to the component abnormality ratio threshold, it means that the abnormality degree of the building component is low, that is, a component abnormality low signal is generated;

[0066] The total number of highly abnormal components is extracted to obtain the number of highly abnormal components, and the ratio of the number of highly abnormal components to the total number of components (the total number of components is the total number of all building components of the target building) is calculated to obtain the abnormality degree coefficient;

[0067] Calculate the mean of all component abnormality ratios to obtain an abnormal mean, calculate the product of the abnormal mean and the abnormality degree coefficient to obtain an abnormality degree adjustment value, and calculate the sum of the abnormality degree adjustment value and the abnormal mean to obtain an abnormality degree representation value;

[0068] In a third exemplary embodiment, the process of obtaining the abnormal uniformity characterization value is as follows:

[0069] Calculate the difference between the component anomaly ratio and the anomaly mean of each building component respectively, and take the absolute value to obtain the component anomaly offset value of each building component, calculate the mean of the component anomaly offset values ​​of all building components, and obtain the component anomaly offset mean;

[0070] Extract the maximum and minimum values ​​of the component anomaly ratios of all building components to obtain the maximum component anomaly ratio and the minimum component anomaly ratio, perform difference calculation on the maximum component anomaly ratio and the minimum component anomaly ratio to obtain the maximum component anomaly offset value, perform ratio calculation on the maximum component anomaly offset value and the mean component anomaly offset value to obtain the anomaly offset coefficient;

[0071] The abnormal offset coefficient is multiplied by the abnormal offset mean of the abnormal component to obtain the abnormal offset adjustment value, and the abnormal offset adjustment value is summed with the abnormal offset mean of the component to obtain the abnormal uniform characterization value;

[0072] Step 2: Calculate the abnormal coefficient of the target building based on the detection data;

[0073] In some embodiments, by the formula: The abnormal coefficient YC is calculated, where a1 and a2 are preset proportional factors and are both greater than 0, CD is the abnormal degree characterization value, and JY is the abnormal uniformity characterization value;

[0074] Step 3: Calculate the evaluation coefficient of the target building based on the detection data and abnormal coefficient of the target building;

[0075] In some embodiments, an abnormal adjustment value is calculated based on the detection data of the target building;

[0076] The abnormal adjustment value is multiplied by the abnormal coefficient to obtain the evaluation coefficient;

[0077] Exemplarily, the process of obtaining the abnormal adjustment value is as follows:

[0078] Obtain the location information of each high abnormal component respectively, and evaluate the influence relationship between each high abnormal component;

[0079] According to the influence relationship between each high abnormal component in the target building, the component abnormality ratio of each high abnormal component is weighted and summed to obtain the high abnormality weighted total value ratio;

[0080] It should be explained that: the weighted summation of the component abnormality ratios of each high abnormal component is weighted according to the magnitude of the influence relationship between each high abnormal component. The greater the influence of a high abnormal component on other high abnormal components, the higher the weight of the high abnormal component; and the sum of the weights of all high abnormal components is 1;

[0081] Calculate the ratio of the high anomaly weighted total value ratio of the target building to the high anomaly total value (the high anomaly total value is the sum of the component anomaly ratios of all high anomaly components in the target building) to obtain the anomaly adjustment value (the anomaly adjustment value is calculated from the high anomaly weighted total value ratio and the high anomaly total value ratio; when the high anomaly weighted total value ratio is greater than the high anomaly total value ratio, it means that there are building components with a large influence relationship and a large component anomaly ratio in the high anomaly components, and at this time the anomaly adjustment value is greater than 1, thereby increasing the value of the target building anomaly coefficient);

[0082] Step 4: Based on the evaluation coefficient, the quality of the target building is evaluated to determine whether the target building is qualified and generate an evaluation signal;

[0083] The evaluation signals include: qualified quality signals and unqualified quality signals;

[0084] In some embodiments, an evaluation coefficient threshold is preset, and the evaluation coefficient is compared and analyzed with the evaluation coefficient threshold;

[0085] If the evaluation coefficient is less than the evaluation coefficient threshold, it means that the abnormality of each building element in the target building is low, and the quality of the target building is determined to be qualified, that is, a quality qualified signal is generated;

[0086] If the evaluation coefficient is greater than or equal to the evaluation coefficient threshold, it means that the abnormality of each building element in the target building is high, or the abnormality of an important building element (an important building element is a building element with a high influence relationship) is high, and the quality of the target building is judged to be unqualified, that is, a quality unqualified signal is generated;

[0087] The technical solution of the embodiment of the present invention is mainly as follows: by collecting real-time data through a variety of sensors installed on building elements, the degree of abnormality of each building element (i.e., the ratio of abnormal value to preset value) is calculated; then, the abnormal information of all building elements is integrated to calculate two key indicators: the abnormal degree characterization value, which reflects the overall abnormal level; the abnormal uniformity characterization value, which measures the balance of abnormal distribution; then, the abnormal coefficient of the target building is calculated by combining the two characterization values ​​and the weight factor using a preset formula; this coefficient combines the abnormal degree and uniformity of the building, and provides a basis for subsequent evaluation; further, according to the mutual influence relationship between high abnormal elements, the abnormal ratio is weighted. The weighted sum is used to obtain the abnormality adjustment value; this value takes into account the abnormality degree of important components and their impact on the entire building; finally, the abnormality adjustment value is multiplied by the abnormality coefficient to obtain the evaluation coefficient; the present invention not only comprehensively considers the abnormal conditions of various components in the building, but also evaluates the uniformity of abnormal distribution through an intelligent algorithm, thereby achieving a deep insight into the overall state of the building; in addition, the present invention also introduces an abnormality adjustment value, and the calculation of the abnormality adjustment value comprehensively considers the component abnormality ratio of high-abnormal components and their mutual influence relationship. By weighted summation and quantifying the overall impact, it not only reflects the single abnormality degree of the component, but also highlights the importance of key components, thereby improving the accuracy of the overall evaluation.

[0088] Embodiment 2:

[0089] Based on Example 1, please refer to Figure 2 As shown, a building quality detection system based on multi-sensor fusion according to an embodiment of the present invention includes:

[0090] Data acquisition module: detect the target building and obtain the detection data of the target building;

[0091] The detection data includes: abnormal degree characterization value and abnormal uniformity characterization value;

[0092] Data processing module: calculate the abnormal coefficient of the target building based on the detection data;

[0093] Data adjustment module: Calculate the evaluation coefficient of the target building based on the detection data and abnormal coefficient of the target building;

[0094] Quality assessment module: Based on the assessment coefficient, the quality of the target building is assessed, whether the target building is qualified is determined, and an assessment signal is generated.

[0095] The above thresholds are set for the convenience of comparison. The thresholds depend on the amount of sample data and the number of bases set by technicians in this field for each set of sample data.

[0096] The above formulas are obtained by collecting a large amount of data and performing software simulation to select a formula close to the actual value. The factors in the formula are set by technicians in this field according to actual conditions; for example: Formula A technician in this field collects multiple groups of test data and sets a corresponding abnormal coefficient for each group of test data; substitutes the set abnormal coefficient and the collected test data into the formula, and any three formulas constitute a three-variable linear equation system. The calculated factors are screened and averaged, and the values ​​of a1 and a2 are obtained to be 2.46 and 2.31 respectively;

[0097] The size of the factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the factor depends on the amount of test data and the technical personnel in this field preliminarily setting the corresponding abnormal coefficient for each set of test data; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the abnormal coefficient is proportional to the value representing the degree of abnormality.

[0098] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A building quality detection method based on multi-sensor fusion, characterized in that: The following steps are involved: Step 1: Detect the target building and obtain the detection data of the target building; The detection data includes: abnormal degree characterization value and abnormal uniformity characterization value; Step 2: Calculate the abnormal coefficient of the target building based on the detection data; Step 3: Calculate the evaluation coefficient of the target building based on the detection data and abnormal coefficient of the target building; Step 4: Based on the evaluation coefficient, the quality of the target building is evaluated to determine whether the target building is qualified and generate an evaluation signal.

2. The building quality detection method based on multi-sensor fusion according to claim 1 is characterized in that: The process of detecting the target building and obtaining the detection data of the target building is as follows: Obtaining component anomaly ratios of various building components in the target building; Based on the element anomaly ratio of each building element, the abnormality degree characterization value and the abnormal uniformity characterization value of the target building are calculated respectively.

3. The building quality detection method based on multi-sensor fusion according to claim 2 is characterized in that: The process of obtaining the component abnormality ratio is as follows: A plurality of sensors are arranged on the building elements, and abnormal values ​​of the elements detected by the sensors are obtained through the sensors; The component abnormality value is ratio-calculated with the component preset value to obtain the component abnormality ratio.

4. The building quality detection method based on multi-sensor fusion according to claim 3 is characterized in that: The process of obtaining the abnormality degree characterization value is as follows: comparing the component anomaly ratio of each building component with a component anomaly ratio threshold value; If the component abnormality ratio is greater than the component abnormality ratio threshold, it means that the abnormality degree of the building element is high, that is, a high component abnormality degree signal is generated, and the building element is marked as a high abnormality element; Extract the total number of highly abnormal components to obtain the number of highly abnormal components, calculate the ratio of the number of highly abnormal components to the total number of components, and obtain the abnormality degree coefficient; The abnormal ratios of all components are averaged to obtain the abnormal mean, the abnormal mean is multiplied by the abnormal degree coefficient to obtain the abnormal degree adjustment value, and the abnormal degree adjustment value is summed with the abnormal mean to obtain the abnormal degree characterization value.

5. The building quality detection method based on multi-sensor fusion according to claim 3 is characterized in that: The process of obtaining the abnormal uniform characterization value is as follows: Calculate the difference between the component anomaly ratio and the anomaly mean of each building component respectively, and take the absolute value to obtain the component anomaly offset value of each building component, calculate the mean of the component anomaly offset values ​​of all building components, and obtain the component anomaly offset mean; Extract the maximum and minimum values ​​of the component anomaly ratios of all building components to obtain the maximum component anomaly ratio and the minimum component anomaly ratio, perform difference calculation on the maximum component anomaly ratio and the minimum component anomaly ratio to obtain the maximum component anomaly offset value, perform ratio calculation on the maximum component anomaly offset value and the mean component anomaly offset value to obtain the anomaly offset coefficient; The abnormal offset coefficient is multiplied by the average abnormal offset of the abnormal component to obtain the abnormal offset adjustment value, and the abnormal offset adjustment value is summed with the average abnormal offset of the component to obtain the abnormal uniform characterization value.

6. The building quality detection method based on multi-sensor fusion according to claim 1 is characterized in that: Based on the detection data, the process of calculating the abnormal coefficient of the target building is: The abnormal coefficient YC is calculated.

7. The building quality detection method based on multi-sensor fusion according to claim 1 is characterized in that: The process of calculating the evaluation coefficient of the target building is: Based on the detection data of the target building, the abnormal adjustment value is calculated; The abnormal adjustment value is multiplied by the abnormal coefficient to obtain the evaluation coefficient.

8. The building quality detection method based on multi-sensor fusion according to claim 7 is characterized in that: The process of obtaining the abnormal adjustment value is as follows: Obtain the location information of each high abnormal component respectively, and evaluate the influence relationship between each high abnormal component; According to the influence relationship between each high abnormal component in the target building, the component abnormality ratio of each high abnormal component is weighted and summed to obtain the high abnormality weighted total value ratio; The anomaly adjustment value is obtained by calculating the ratio of the target building's high anomaly weighted total value to the high anomaly total value.

9. The building quality detection method based on multi-sensor fusion according to claim 1 is characterized in that: Evaluation signals include: qualified quality signals and unqualified quality signals; The process of generating the evaluation signal is: Preset an evaluation coefficient threshold, and compare and analyze the evaluation coefficient with the evaluation coefficient threshold; If the evaluation coefficient is less than the evaluation coefficient threshold, a quality qualified signal is generated; If the evaluation coefficient is greater than or equal to the evaluation coefficient threshold, a quality failure signal is generated.

10. A building quality detection system based on multi-sensor fusion, characterized in that: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Data acquisition module: detect the target building and obtain the detection data of the target building; The detection data includes: abnormal degree characterization value and abnormal uniformity characterization value; Data processing module: calculate the abnormal coefficient of the target building based on the detection data; Data adjustment module: Calculate the evaluation coefficient of the target building based on the detection data and abnormal coefficient of the target building; Quality assessment module: Based on the assessment coefficient, the quality of the target building is assessed, whether the target building is qualified is determined, and an assessment signal is generated.

Images