A test vehicle prototype piece state monitoring system and method

Abstract

This invention discloses a system and method for monitoring the status of prototype vehicles and components. The system acquires initial data information of the prototype vehicles and components, including a unique identifier and multiple initial point cloud data sets. Based on the identified unique identifier, the system acquires entry and exit data information for each prototype vehicle and component during storage, including the unique identifier and multiple entry and exit point cloud data sets. The system determines whether the status of the prototype vehicle and component is abnormal based on the entry and exit point cloud data and the multiple initial point cloud data sets. This invention achieves comprehensive, real-time, and intelligent monitoring of the status of prototype vehicles and components through precise data initialization, efficient data entry and exit management, and accurate status judgment. This is of great significance for improving the R&D efficiency of prototype vehicles, reducing production costs, and ensuring product quality.

Description

Technical Field

[0001] This invention belongs to the field of warehouse management technology, specifically relating to a system and method for monitoring the status of prototype vehicles, prototypes, and prototype components. Background Technology

[0002] In the automotive product development process, complete vehicles produced through self-manufacturing, allocation, procurement, or donation are collectively referred to as prototype vehicles; engines and components used for engine installation are collectively referred to as prototypes and parts. Currently, the management process for the entry and exit of prototype vehicles, prototypes, and parts relies excessively on manual data entry. This practice not only easily leads to omissions, errors, and delays in data entry, but also directly results in low efficiency in quickly locating and obtaining the required prototype vehicles, prototypes, and parts, thus affecting the smooth progress of the test project and causing unnecessary economic losses. Furthermore, the status inspection of prototype vehicles, prototypes, and parts still mainly relies on manual inspection, which carries the risk of misjudgment and omissions, potentially leading to test failures and serious economic losses.

[0003] While image recognition technology theoretically offers a solution to these problems, its high algorithmic complexity and computational consumption limit its widespread application. Existing methods for managing prototype inventory still primarily rely on QR code technology, supplemented by manual online data entry, failing to achieve automated identification and management by machines or artificial intelligence. Consequently, there is still significant room for improvement in efficiency and accuracy. Summary of the Invention

[0004] To improve the efficiency and accuracy of the management of test vehicles, prototypes, and sample parts entering and leaving the warehouse, this invention proposes a test vehicle, prototype, and sample part status monitoring system and method.

[0005] A prototype vehicle / machine / sample status monitoring system, which achieves one of the objectives of this invention, includes:

[0006] Data initialization module: used to acquire initial data information of the test prototype vehicle / machine sample; the initial data information includes: a unique identifier feature code and multiple initial point cloud data; the unique identifier feature code is used to identify the test prototype vehicle / machine sample; the initial point cloud data represents the initial state of the test prototype vehicle / machine sample or the point cloud data when it was initially put into storage;

[0007] Data entry / exit module: used to obtain entry / exit data information of each test vehicle prototype and sample based on the identified unique identifier feature code; the entry / exit data information includes: unique identifier feature code, multiple entry / exit point cloud data; the entry / exit point cloud data represents the point cloud data of the test vehicle prototype and sample when entering / exiting the warehouse, including exit point cloud data and entry point cloud data;

[0008] Status monitoring module: It is used to compare the entry and exit point cloud data in the entry and exit data information of the test vehicle, prototype and sample with the multiple initial point cloud data, and determine whether the status of the test vehicle, prototype and sample is abnormal based on the comparison results.

[0009] In the above system, each prototype vehicle corresponds to multiple initial point cloud data; when the same camera (such as a 3D scanner) collects 3D point cloud data of the prototype vehicle, it needs to continuously scan and acquire multiple point cloud data.

[0010] The term "prototype vehicle," "prototype," and "prototype" is a collective term encompassing all of these; it can refer to one or more of them. For example, if experiments are conducted on a prototype vehicle, it refers to the prototype vehicle itself. A prototype vehicle typically refers to a vehicle manufactured to test, verify, or demonstrate a new technology, function, or design. These vehicles may not yet be in mass production, but they are mature enough for actual road or laboratory testing. A prototype is generally used to describe a prototype or model manufactured to test, verify, or demonstrate the performance of a device, machine, or system. In the automotive industry, a prototype typically refers to a prototype of a key component, such as a new engine, transmission, or other component.

[0011] Finally, prototypes typically refer to individual parts or components used for testing, verification, or demonstration. They constitute the basic building blocks of a machine or equipment. These prototypes may represent a new design, material, or manufacturing process and require testing to verify their performance and quality. In the automotive industry, prototypes may include engine parts, drivetrain parts, suspension system parts, and so on.

[0012] The technical effects of the above technical solution are:

[0013] The data initialization module is responsible for acquiring initial data information for the prototype vehicle / machine sample, including a unique identifier and multiple initial point cloud datasets. The unique identifier ensures the uniqueness and traceability of each prototype vehicle / machine sample, facilitating accurate identification of specific samples in subsequent data processing. The initial point cloud data provides detailed 3D information about the sample in its initial state, which is crucial for subsequent state comparison. This precise and comprehensive data initialization lays a solid foundation for subsequent state monitoring.

[0014] The data entry and exit module can automatically obtain the point cloud data of each test vehicle prototype and sample part during entry and exit from the warehouse based on its unique identifier feature code. This automated data management method greatly improves the efficiency and accuracy of data processing and reduces the possibility of human error. At the same time, by recording the point cloud data during entry and exit from the warehouse, the system can track the status changes of the samples in real time.

[0015] The status monitoring module compares the incoming and outgoing point cloud data with the initial point cloud data to determine whether the prototype vehicle / machine part is in an abnormal state. Point cloud data, as a high-precision three-dimensional data representation, can capture minute changes on the surface of the part, thus enabling accurate judgment of the part's status. This point cloud data-based status judgment method is not only highly accurate but also able to promptly detect abnormal changes in the part's status, providing strong support for subsequent maintenance and management.

[0016] This system integrates multiple modules, including data initialization, data entry and exit management, and status assessment, to achieve comprehensive monitoring of the status of prototype vehicles and components. The collaborative work between these modules gives the entire system a high level of intelligence, enabling it to automatically complete data collection, processing, and analysis. This integrated and intelligent system design not only improves work efficiency but also reduces the cost and risk of manual intervention.

[0017] Furthermore, the initial data information and / or the entry / exit data information also include a camera number, which is used to represent the camera number that identifies the initial data information and / or entry / exit data information of the test vehicle prototype; the system also includes a position monitoring module, which is used to obtain the current location and / or historical movement path of the test vehicle prototype based on the camera number in the data information.

[0018] The technical effects of the above solution are as follows: By using camera identification numbers, the initial data and inventory data of prototype vehicles and components can be accurately identified and recorded, avoiding errors caused by information confusion or omissions and improving data accuracy; the introduction of camera identification numbers allows for quick location of relevant camera records when tracing the historical status of prototype vehicles and components, thereby obtaining accurate historical data. This helps resolve data disputes and improves the transparency of data management; automated identification and recording of camera identification numbers simplifies the status monitoring process for prototype vehicles and components, reducing manual intervention and errors; and with the system's real-time location and historical path tracking functions, managers can manage prototype vehicles and components more efficiently, optimize testing processes, and reduce management costs.

[0019] Furthermore, the data initialization module also includes a point cloud data processing module, used to process multiple initial point cloud data in the initial data information to obtain a safety threshold for the difference distance of the point cloud data of each test vehicle prototype; the data processing method includes: comparing the differences of the multiple initial point cloud data to obtain the maximum difference distance, which is used as the safety threshold for the difference distance of the initial point cloud data of each test vehicle prototype; the safety threshold for the difference distance is used to determine whether the state of the test vehicle prototype is abnormal.

[0020] Point cloud distance: This involves comparing the relative positional relationships between two or more point cloud datasets. By calculating the distance between the target to be identified and the known point cloud model, the differences between the target and the known point cloud model can be identified. The greater the point cloud distance, the greater the difference, and the greater the likelihood of the target being abnormal.

[0021] The technical effect of the above-mentioned point cloud data difference comparison is as follows: During the transportation of prototype vehicles, parts, and machines within the park, they are captured by multiple cameras or scanners. Each camera or scanner scans the prototype vehicle, part, or machine to obtain point cloud data. After the prototype vehicle, part, or machine is captured and scanned by scanner B to obtain point cloud data, it is compared with the point cloud data obtained by the previous scanner A. If an anomaly is found in the compared data, it can be determined that an anomaly occurred during the movement from the location of scanner A to scanner B.

[0022] The technical effect of the above solution is that by calculating the point cloud difference distance, it can more comprehensively reflect the changes in point cloud data of the test vehicle / prototype at different times or locations. This comprehensive difference comparison helps to more accurately determine whether the state of the prototype is abnormal, reducing misjudgments caused by fluctuations in a single data point.

[0023] Furthermore, the method for determining whether the status of the test vehicle / prototype is abnormal in the status monitoring module includes:

[0024] Continuously acquire multiple sets of inbound and outbound point cloud data of test prototype vehicles, prototypes, and prototype parts;

[0025] Each of the multiple inbound and outbound point cloud data is compared with the most recent inbound and outbound point cloud data scanned by the most recent scanner to obtain multiple data difference distances; when each data difference distance is greater than the difference distance safety threshold, the prototype vehicle is considered to be in an abnormal state.

[0026] The technical effect of the above solution is that by comparing each inbound / outbound point cloud data from the current scanner with the most recent data from the previous scanner, the system can more accurately capture the changing trends in the state of the prototype vehicle / machine sample. Compared to relying solely on a single data point or a simple threshold, this continuous comparison method better reflects subtle changes in the sample's state, thereby improving the accuracy of the judgment. Furthermore, by setting a safety threshold for the difference distance as the basis for judgment, the system can more scientifically assess the severity of state changes, avoiding false alarms or missed alarms.

[0027] Furthermore, it also includes an abnormal part identification module, which is used to identify the abnormal parts of the test vehicle prototype when the test vehicle prototype is in an abnormal state using 3D images, and record the images of the abnormal parts in the entry and exit data information of the test vehicle prototype.

[0028] The technical effect of the above solution is that by locating the specific location where the anomaly occurred, not only is the basic state information of the sample preserved, but also detailed image data of the abnormal part is added. This comprehensive data recording method helps to build a complete historical archive of the sample state, providing strong data support for subsequent analysis, research and improvement.

[0029] A method for monitoring the status of a prototype vehicle / machine part to achieve the second objective of this invention includes:

[0030] Acquire initial data information of the test prototype vehicle / machine sample; the initial data information includes: a unique identifier feature code and multiple initial point cloud data; the unique identifier feature code is used to identify the test prototype vehicle / machine sample; the initial point cloud data represents the initial state of the test prototype vehicle / machine sample or the point cloud data at the time of initial storage;

[0031] The entry and exit data information of each test vehicle, prototype, and sample is obtained based on the unique identifier feature code. The entry and exit data information includes: the unique identifier feature code and multiple entry and exit point cloud data. The entry and exit point cloud data represents the point cloud data of the test vehicle, prototype, and sample when entering and leaving the warehouse.

[0032] The entry and exit point cloud data in the entry and exit data information of the test vehicle, prototype and sample are compared with the multiple initial point cloud data, and the state of the test vehicle, prototype and sample is determined according to the comparison results.

[0033] Furthermore, the multiple initial point cloud data in the initial data information are processed to obtain the difference distance safety threshold of the point cloud data of each test vehicle prototype. The data processing method includes: comparing the differences of the multiple initial point cloud data to obtain the maximum difference distance, which is used as the difference distance safety threshold of the initial point cloud data of each test vehicle prototype.

[0034] Furthermore, methods for determining whether the condition of the test vehicle / prototype is abnormal include:

[0035] Continuously acquire multiple sets of inbound and outbound point cloud data of test prototype vehicles, prototypes, and prototype parts;

[0036] Each of the multiple inbound and outbound point cloud data is compared with the most recent inbound and outbound point cloud data scanned by the most recent scanner to obtain multiple data difference distances; when each data difference distance is greater than the difference distance safety threshold, the prototype vehicle is considered to be in an abnormal state.

[0037] The beneficial effects of this invention include:

[0038] This invention achieves comprehensive, real-time, and intelligent monitoring of the status of prototype vehicles and components through precise data initialization, efficient data inbound and outbound management, and accurate status judgment. This is of great significance for improving the R&D efficiency of prototype vehicles, reducing production costs, and ensuring product quality. Through the point cloud data comparison processing described in this invention, the image recognition server only needs to identify the abnormal parts of the prototype vehicles and components with abnormal status, which can greatly reduce the number of calculations required for image recognition services and alleviate server pressure. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the data processing logic of the method described in this invention;

[0040] Figure 2 It is a system architecture diagram;

[0041] Figure 3 This is a diagram illustrating the data import process;

[0042] Figure 4 It is a schematic diagram of the control chart boundaries;

[0043] Figure 5 This is a schematic diagram showing the path of the prototype vehicle being moved from warehouse A to warehouse B;

[0044] Figure 6 It is a schematic control of point cloud data differences. Figure 1 ;

[0045] Figure 7 It is a schematic control of point cloud data differences. Figure 2 ;

[0046] Figure 8 This is a diagram of the identified abnormal parts. Detailed Implementation

[0047] The following detailed embodiments are provided to explain the technical solutions of the claims of this invention, so that those skilled in the art can understand the claims. The scope of protection of this invention is not limited to the following specific embodiments. Any modifications made by those skilled in the art that incorporate the technical solutions of the claims but differ from the following detailed embodiments are also within the scope of protection of this invention.

[0048] like Figure 2The system architecture diagram shown illustrates the following: the warehouse image recognition system is deployed within the warehouse to identify prototype vehicles, models, and components entering the warehouse; the road image recognition system is deployed on the main roads of the park to identify prototype vehicles, models, and components outside the warehouse; Kafka is a message queue used to store prototype vehicle, model, and component information pushed by the warehouse and road image recognition systems; the data acquisition server receives prototype vehicle, model, and component information from Kafka, persists the data, and builds a presentation layer view for viewing on PCs and mobile devices; the database persistently stores prototype vehicle, model, and component information; and the display client displays the prototype vehicle, model, and component information view built by the data acquisition server.

[0049] Example 1

[0050] A method for monitoring the status of prototype vehicles and components

[0051] S1. Obtain initial data information of the test prototype vehicle / machine sample; the initial data information includes: a unique identifier feature code and multiple initial point cloud data; the unique identifier feature code is used to identify the test prototype vehicle / machine sample; the initial point cloud data represents the initial state of the test prototype vehicle / machine sample or the point cloud data when it was initially put into storage;

[0052] In some embodiments, the initial data information of the prototype vehicle / sample is shown in Table 1 below. The method for obtaining the initialization information of the prototype vehicle / sample and incorporating it into the database is as follows. Figure 3 As shown, when the prototype vehicle, prototype, or prototype data is initially archived or initially entered into the warehouse, the classification and the unique identifier code of that classification need to be manually determined.

[0053] In some embodiments, data differences are compared among multiple initial point cloud data sets in the initial data information to obtain a safe threshold for the difference distance of the point cloud data for each test vehicle / prototype. The data difference comparison method includes: comparing the multiple initial point cloud data sets to obtain the maximum difference distance, which is used as the safe threshold for the difference distance of the initial point cloud data for each test vehicle / prototype. For example, when the initial data information for the test vehicle / prototype is stored in the warehouse, a first 3D scanner A is used to perform a 3D scan on the test vehicle / prototype to generate point cloud data. This scan is repeated multiple times to generate multiple point cloud data sets A1 to A2. N For example, seven PCD values ​​are obtained as initial point cloud data; each PCD value is compared pairwise to obtain multiple differences, and the maximum value 'a' is taken as the difference distance safety threshold for the prototype vehicle / sample. This maximum value 'a' is used as the boundary of the control chart, such as... Figure 4As shown in Table 2 below, the control chart is a chart with control limits used to analyze and judge whether the process is in a stable state. It is a functional chart that can distinguish between normal fluctuations and abnormal fluctuations, and is an important statistical tool in on-site quality management.

[0054] Table 1

[0055]

[0056] Each field of the data structure is described below:

[0057] Unique Identifier Code: A unique code generated from the unique and immutable feature points of the prototype vehicle / machine / sample used to identify the prototype vehicle / machine / sample.

[0058] Point cloud PCD value: Used to record 3D point cloud data, where PCD (Point Cloud Data) is a storage format for point cloud data;

[0059] Difference Distance Safety Threshold: Used to record the safe floating range of the PCD difference distance for this item.

[0060] Point cloud comparison difference distance for prototype vehicles, prototypes, and prototypes: The point cloud difference value is formed by comparing the current point cloud PCD with the most recent inbound / outbound point cloud data PCD from the previous 3D scanner, and is used for statistical analysis.

[0061] Location ID: Stores the current location of the prototype vehicle / model / sample, including: warehouse number / road number;

[0062] Time: Record time;

[0063] Status: Is there any malfunction in the equipment?

[0064] S2. Obtain the entry and exit data information of each test vehicle, prototype, and sample when entering and leaving the warehouse based on the unique identifier feature code; the entry and exit data information includes: unique identifier feature code, multiple entry and exit point cloud data; the entry and exit point cloud data represents the point cloud data of the test vehicle, prototype, and sample when entering and leaving the warehouse.

[0065] The following is an example Figure 5 Taking the example of moving the prototype vehicle / sample from warehouse A to warehouse B:

[0066] S2.1, Data entry for prototype vehicles, prototypes, and prototype parts (hereinafter referred to as "items"): Each item must be manually categorized and assigned a unique identifier code upon entry into the warehouse. The process is as follows: Figure 4 As shown;

[0067] S2.2, Outbound: The roadside camera or scanner A captures the item, and a convolutional neural network image recognition algorithm determines the item category, whether it is a prototype vehicle, engine, sample, or others. A unique identifier Tzm000001 is generated based on the item's feature points; the 3D point cloud data of the item is then identified.

[0068] S3. Compare the entry and exit point cloud data in the entry and exit data information of the test vehicle, prototype and sample with the multiple initial point cloud data, and determine whether the state of the test vehicle, prototype and sample is abnormal based on the comparison results.

[0069] In some embodiments, the method for determining whether the condition of the test vehicle prototype is abnormal includes:

[0070] Multiple entry and exit point cloud data of the test vehicle prototype sample scanned by the current scanner are continuously acquired; each entry and exit point cloud data of the current scanner is compared with the most recent entry and exit point cloud data of the previous scanner to obtain multiple data difference distances; when each data difference distance is greater than the maximum difference distance, i.e. the difference distance safety threshold, the test vehicle prototype sample is considered to be in an abnormal state.

[0071] For example, during the outbound journey, the data is captured by a second 3D scanner B deployed along the road, generating multiple 3D point cloud data sets B1 to B2. N Point cloud data B1 is compared with multiple point cloud data A1~A generated by 3D scanner A in the warehouse before the data is moved out of the warehouse. N The last point cloud data A in N By comparison, the second point cloud data B2, located at a distance of b1 meters, is obtained, along with the last point cloud A generated by the 3D scanner A inside the warehouse before the item was moved out of the warehouse. N By comparison, we obtain the distance b2 meters, ..., the Nth point cloud data B N Compared with the last point cloud A generated by 3D scanner A in the warehouse before the goods are moved out of the warehouse. N By comparison, the distance b is obtained. N Rice, if b1~b N If the difference distance is greater than the safety threshold 'a' for the test vehicle prototype, it indicates that the test vehicle prototype is malfunctioning during the journey from the location of scanner A to the location of scanner B; otherwise, the test vehicle prototype is considered to be in a normal state.

[0072] During the journey from warehouse A to warehouse B, a third 3D scanner C captures the prototype vehicle sample, generating point cloud data C1 to C2. N C1~C N The last point cloud data B from the previous second 3D scanner B N By comparison, we obtain the distances: c1 to cN If c1~c N If the difference distance is greater than the safety threshold 'a' for the test vehicle prototype, it indicates that the test vehicle prototype is malfunctioning during its movement from the location of the second 3D scanner B to the location of the third 3D scanner C; otherwise, the test vehicle prototype is considered to be in a normal state.

[0073] Specifically, in one embodiment, seven sets of 3D point cloud data are obtained, and the distance between each set and the most recent set of point cloud data from the previous 3D scanner is calculated, such as... Figure 6 As shown in Table 2, if there are no seven consecutive points outside the PCD difference distance safety threshold, the status is considered normal.

[0074] Table 2

[0075]

[0076] If 7 consecutive points are outside the PCD difference distance safety threshold 'a', such as Figure 7 If the condition is as shown, it is determined to be an abnormal state, an abnormal alarm is generated, and the recorded data is shown in Table 3 below;

[0077] Table 3

[0078]

[0079]

[0080] In some embodiments, the convolutional neural network image recognition algorithm is used to locate abnormal areas, and the generated data is shown in Table 4 below;

[0081] Table 4

[0082]

[0083] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0084] Example 2

[0085] A prototype vehicle / machine / sample status monitoring system includes:

[0086] Data initialization module: used to acquire initial data information of the test vehicle prototype; the initial data information includes: a unique identifier feature code and multiple initial point cloud data; the unique identifier feature code is used to identify the test vehicle prototype; the initial point cloud data represents the point cloud data of the test vehicle prototype at the initial stage;

[0087] Data entry / exit module: used to obtain entry / exit data information of each test vehicle prototype and sample based on the identified unique identifier feature code; the entry / exit data information includes: unique identifier feature code, multiple entry / exit point cloud data; the entry / exit point cloud data represents the point cloud data of the test vehicle prototype and sample when entering / exiting the warehouse;

[0088] Status monitoring module: It is used to compare the entry and exit point cloud data in the entry and exit data information of the test vehicle, prototype and sample with the multiple initial point cloud data, and determine whether the status of the test vehicle, prototype and sample is abnormal based on the comparison results.

[0089] In some embodiments, the initial data information and / or the entry / exit data information further includes a camera number, used to represent the camera number that identifies the initial data information and / or entry / exit data of the test vehicle prototype; the system further includes a location monitoring module, used to obtain the current location and / or historical movement path of the test vehicle prototype based on the camera number in the data information.

[0090] In some embodiments, the data initialization module further includes a point cloud data processing module, which is used to process multiple initial point cloud data in the initial data information to obtain a safety threshold for the difference distance of the point cloud data of each test vehicle prototype. The data processing method includes: comparing the differences of the multiple initial point cloud data to obtain the maximum difference distance, which is used as the safety threshold for the difference distance of the initial point cloud data of each test vehicle prototype.

[0091] In some embodiments, the method for determining whether the state of the test vehicle / prototype is abnormal in the status monitoring module includes:

[0092] Continuously acquire multiple sets of inbound and outbound point cloud data of test prototype vehicles, prototypes, and prototype parts;

[0093] Each of the multiple inbound and outbound point cloud data is compared with the most recent inbound and outbound point cloud data from the previous scanner to obtain multiple data difference distances; when each data difference distance is greater than the maximum difference distance, i.e. the difference distance safety threshold, the test vehicle prototype is considered to be in an abnormal state.

[0094] In some embodiments, an abnormal part identification module is also included, which is used to identify the abnormal part of the test vehicle prototype when the test vehicle prototype is in an abnormal state, and record the image of the abnormal part in the inbound and outbound data information.

[0095] Example 3

[0096] This invention also provides a computer-readable storage medium storing a computer program, which includes program instructions that, when executed by a processor, implement the various steps of the method described in this invention, which will not be elaborated further here.

[0097] The computer-readable storage medium can be the data transmission apparatus or the internal storage unit of a computer device provided in any of the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., provided on the computer device.

[0098] Furthermore, the computer-readable storage medium may include both internal storage units and external storage devices of the computer device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium may also be used to temporarily store data that is to be output or has already been output.

[0099] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0101] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0102] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0103] Example 4

[0104] A computer program product includes a computer program / instructions that, when executed by a processor, implement any step of the test vehicle / prototype status monitoring method.

[0105] The contents not described in detail in this specification are existing technologies known to those skilled in the art.

Claims

1. A test vehicle / prototype component status monitoring system, characterized in that, include: Data initialization module: used to acquire initial data information of the test prototype vehicle / machine sample; The initial data information includes: a unique identifier code and multiple initial point cloud data sets; the unique identifier code is used to identify the test prototype vehicle / machine / sample. Data entry / exit module: used to obtain entry / exit data information of each test vehicle prototype and sample based on the identified unique identifier feature code; the entry / exit data information includes: unique identifier feature code, multiple entry / exit point cloud data; the entry / exit point cloud data represents the point cloud data of the test vehicle prototype and sample when entering / exiting the warehouse; Status monitoring module: It is used to compare the entry and exit point cloud data in the entry and exit data information of the test vehicle, prototype and sample with the multiple initial point cloud data, and determine whether the status of the test vehicle, prototype and sample is abnormal based on the comparison results. The data initialization module further includes a point cloud data processing module, used to process the multiple initial point cloud data of each test vehicle prototype to obtain a safety threshold for the difference distance of the point cloud data of each test vehicle prototype. The data processing method includes: comparing the differences of the multiple initial point cloud data to obtain the maximum difference distance, which is used as the safety threshold for the difference distance of the initial point cloud data of each test vehicle prototype; the safety threshold for the difference distance is used to determine whether the state of the test vehicle prototype is abnormal. Methods for determining whether the condition of a test vehicle, prototype, or sample is abnormal include: Continuously acquire multiple sets of inbound and outbound point cloud data of test prototype vehicles, prototypes, and prototype parts; Each of the multiple inbound and outbound point cloud data is compared with the most recent inbound and outbound point cloud data scanned by the most recent scanner to obtain multiple data difference distances; when each data difference distance is greater than the difference distance safety threshold, the prototype vehicle / machine sample is considered to be in an abnormal state. It also includes: a warehouse image recognition system deployed in the warehouse to identify prototype vehicles, prototypes, and prototypes entering the warehouse; a road image recognition system deployed on the main roads of the park to identify prototype vehicles, prototypes, and prototypes outside the warehouse; prototype vehicle, prototype, and prototype information pushed by the warehouse image recognition system and the road image recognition system is stored in a message queue; a data acquisition server is used to receive prototype vehicle, prototype, and prototype information in the message queue, persist the data, and build a display layer view for PC and mobile devices to view; a database is used to persistently store prototype vehicle, prototype, and prototype information; and a display terminal is used to display the prototype vehicle, prototype, and prototype information view built by the data acquisition server.

2. The prototype vehicle / machine / sample status monitoring system as described in claim 1, characterized in that, The initial data information and / or inbound / outbound data information also include camera numbers, which are used to identify the camera numbers of the initial data information and / or inbound / outbound data information of the test vehicle prototype; the system also includes a position monitoring module, which is used to obtain the current location and / or historical movement path of the test vehicle prototype based on the camera numbers.

3. The test vehicle / prototype / sample status monitoring system as described in claim 1, characterized in that, It also includes an abnormal part identification module, which is used to identify the abnormal parts of the test vehicle prototype when the test vehicle prototype is in an abnormal state using 3D images, and record the images of the abnormal parts in the entry and exit data information of the test vehicle prototype.

4. A method for monitoring the status of a prototype vehicle / machine / sample component of the system as described in claim 1, characterized in that, include: Obtain initial data information for the test prototype vehicle / machine sample; The initial data information includes: a unique identifier code and multiple initial point cloud data sets; the unique identifier code is used to identify the test prototype vehicle / machine / sample. The entry and exit data information of each test vehicle, prototype, and sample is obtained based on the unique identifier feature code. The entry and exit data information includes: the unique identifier feature code and multiple entry and exit point cloud data. The entry and exit point cloud data represents the point cloud data of the test vehicle, prototype, and sample when entering and leaving the warehouse. The entry and exit point cloud data in the entry and exit data information of the test vehicle, prototype and sample are compared with the multiple initial point cloud data, and the state of the test vehicle, prototype and sample is determined according to the comparison results.

5. The method for monitoring the status of test vehicle / prototype components as described in claim 4, characterized in that, Also includes: Data processing is performed on the multiple initial point cloud data sets of each test vehicle prototype to obtain a safety threshold for the difference distance of the point cloud data of each test vehicle prototype. The data processing method includes: comparing the differences of the multiple initial point cloud data sets to obtain the maximum difference distance, which is used as the safety threshold for the difference distance of the initial point cloud data of each test vehicle prototype. The safety threshold for the difference distance is used to determine whether the state of the test vehicle prototype is abnormal.

6. The method for monitoring the status of test vehicle / prototype components as described in claim 5, characterized in that, Methods for determining whether the condition of a test vehicle, prototype, or sample is abnormal include: Continuously acquire multiple sets of inbound and outbound point cloud data of test prototype vehicles, prototypes, and prototype parts; Each of the multiple inbound and outbound point cloud data is compared with the most recent inbound and outbound point cloud data scanned by the most recent scanner to obtain multiple data difference distances; when each data difference distance is greater than the difference distance safety threshold, the prototype vehicle / machine sample is considered to be in an abnormal state.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the test vehicle / prototype status monitoring method as described in any one of claims 4 to 6.

8. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements any step of the test vehicle / prototype status monitoring method described in claims 4 to 6.

Images