Personal protective equipment fit testing system

Abstract

A personal protective equipment (PPE) fit testing system is presented that includes a scanning device configured to capture a first scan data of a user wearing an article of PPE. The system also includes a fit test module configured to: detect, using a PPE detector, a model of the article of PPE, retrieve a second scan data of the user without the article of PPE, compare the first and second scan data, using a comparison module, and based on the comparison, generate a fit test result. The system also includes a communication component configured to communicate the generated fit test result to a device with a display.

Description

PERSONAL PROTECTIVE EQUIPMENT FIT TESTING SYSTEMBACKGROUND

[0001] In some environments, a worker may be required to wear one or more articles of personal protective equipment (PPE) while performing a certain job function, working in a specific work environment, or the like. For example, a worker may be required to wear at least one of respiratory- protection equipment, protective eyewear, protective headwear, hearing-protection devices, protective shoes, protective gloves, protective clothing, or any other article of PPE.SUMMARY

[0002] The disclosure describes devices, systems, and techniques relating to personal protective equipment (PPE) fit testing system.

[0003] A personal protective equipment (PPE) fit testing system is presented that includes a scanning device configured to capture a first scan data of a user wearing an article of PPE. The system also includes a fit test module configured to: detect, using a PPE detector, a model of the article of PPE, retrieve a second scan data of the user without the article of PPE, compare the first and second scan data, using a comparison module, and based on the comparison, generate a fit test result. The system also includes a communication component configured to communicate the generated fit test result to a device with a display.

[0004] Systems and methods herein provide improvements over the prior art fit testing systems and methods, by providing a system that increases training on proper use of PPE, simplifies the fit testing procedure, without the need for physical sensors. Systems and methods herein automatically capture data related to fit during the fit testing process and analyze the captured data to provide feedback to individuals, employers, manufacturers and / or other recipients.

[0005] The details of one or more examples of the disclosure are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the disclosure will be apparent from the description and drawings, and from the claims.BRIEF DESCRIPTION OF DRAWINGS

[0006] FIG. 1 is a block diagram illustrating an example system in which PPE may be used.

[0007] FIGS. 2A-2B illustrate individuals wearing PPE that may benefit from embodiments discussed herein.

[0008] FIG. 3 illustrates a method of conducting a PPE fit test in accordance with embodiments herein.

[0009] FIG. 4 illustrates a PPE fit testing system in accordance with embodiments herein.

[0010] FIG. 5 illustrates a PPE selection system in accordance with embodiments herein.

[0011] FIGS. 6A-6I illustrate example user interfaces that may be provided by a PPE fit testing system in accordance with embodiments herein.

[0012] FIGS. 7-8 illustrate methods of conducting a digital fit test in accordance with embodiments herein.

[0013] FIGS. 9A-9C illustrate example user interfaces in accordance with embodiments herein.

[0014] FIGS. 10A-10C are schematics illustrating hearing protection fit processes in accordance with embodiments herein.

[0015] FIG. 11 illustrates a block diagram of embodiments herein implemented on a cloud-based platform capable of supporting multiple, distinct access points for multiple users of systems herein.

[0016] FIG. 12 is a block diagram of a PPE fit test system architecture.

[0017] FIGS. 13-15 illustrate computing devices that may be used in accordance with embodiments herein.DETAILED DESCRIPTION

[0018] In general, a worker in a work environment may be exposed to various hazards or safety events (e.g., air contamination, heat, falls, etc.). Regulations, or company safety policies, may require the worker to wear one or more articles of personal protective equipment (PPE) to protect the worker from these hazards and safety events. It is important that PPE works correctly and fits correctly for a given worker.

[0019] A given worker may wear multiple types of PPE in a given worksite - e.g., a respirator because of particulates, hearing protection because of noise exposure, and safety glasses because of potential debris. It is important that each item of PPE fit correctly individually, and in combination.

[0020] It is therefore common for workers to be fit tested for a given make and model of PPE. OSHA Regulation 1910.134 Appendix A, for example, outlines specific requirements for both qualitative and quantitative respiratory fit tests. Work environments subject to such standards may also be subject to OSHA (or other regulatory agency) audit. Therefore, it is important for site managers to maintain records of fit test results for workers. OSHA is one of many global regulatory agencies that sets standards for fit testing of PPE and is used herein for example purposes only. Fit testing may, either additionally or alternatively, involve compliance with any of a number of global standards, depending on the location of a work environment. In some embodiments, fit testing refers to compliance with an ISO standard. In some embodiments, fit testing refers to compliance with an HSE standard. Other standards may be used in other embodiments.

[0021] However, respiratory fit testing is a complex process, involving many different steps, some thatmust be administered within a specified time limit, and many that require an individual with knowledge about how to conduct, and analyze each test result. It can be difficult to ensure that a fit tester is available and has enough time to fit test workers for a given environment, especially considering worker schedules and assignments.

[0022] A typical respirator fit test takes 15 to 20 minutes to complete for each worker, taking time away from productive work. As used herein, the terms “worker,” “test taker,” or “test subject” are used interchangeably to describe an individual taking a fit test for an article of PPE.

[0023] Fit testing requires a trained professional to conduct, which is a significant cost to the employer, and currently there is a shortage of trained respiratory fit technicians, which creates an undue burden on businesses and healthcare facilities. Additionally, testers need to provide fit testing certificates to the workers who successfully complete a fit test, which is often a manual and time-consuming process, further increasing time and expense required.

[0024] There is a need for a fit testing procedure that can be completed by a worker without the need for a fit testing professional . Embodiments herein provide a digital option that, based on a user’ s image and a given PPE article, provides an indication of how likely it is that the user would pass a fit test. A digital fit test, unlike a quantitative or qualitative fit test, can be done using a digital application (for example on a user’s device or at a worksite) without a worksite needing to schedule individual fit tests. Fit tests can be done by workers concurrently, or on an as-needed basis, reducing an amount of disrupted time that a worksite experiences. A digital fit test may also take less time than traditional qualitative or quantitative fit tests. Systems and methods herein may replace the traditional fit testing process, reducing disruptions at a worksite and reducing costs while keeping workers safe. Additionally, because a digital fit test is easier for a user and takes less time, a user may undergo fit testing for PPE more frequently, increasing fit testing compliance.

[0025] Digital fit tests, as described herein, may be provided in conjunction with a PPE model suggestion system such that, based on an image of a user’s face, a particular model of PPE is recommended and, based on an additional image of the user wearing the PPE article, an indication of fit is provided.

[0026] Embodiments herein require an image capturing device, or equivalent technology, to capture an image of a user’s face. No additional physical sensors are required. Additionally, no predetermined size reference (e.g., a coin, iris size, etc.) is required.

[0027] Systems and methods herein utilize machine learning algorithms, stored in a memory and executed using suitable processing circuitry, to analyze the face of a user with and without PPE and, based on said analysis, determine a likelihood of fit. For respirators, a likelihood of fit may be calculated based on determining facial dimensions, facial landmarks and distances / anglestherebetween, or otherwise comparing the captured image to a set of training images to determine a fit likelihood, described herein as a “fit factor.”

[0028] Systems and methods described herein provide an application (or other suitable) interface for a user to conduct a contact-free fit test using any device with a camera or other suitable sensor for capturing an indication of a user’s facial features.

[0029] FIG. 1 is a block diagram illustrating an example PPE fit testing system 100 that may, for example, facilitate fit testing for a worker 10, or other individual. PPE fit testing system 120 may be accessible, for example, using an application on a device with user interface 12. The device may also have a camera 22, for example for capturing images of a user before and while wearing a PPE product. In some embodiments, system 120 may also present worker 10A with images and / or augmented images to guide worker 10A through fit recommendations or alterations to increase a fit factor.

[0030] Using system 120, a worker can be fit tested quickly for one or more articles of PPE that he or she should be equipped with for environments 8 A, 8B, or for another worksite 110. In some examples, PPE fit testing system 120 may communicate with a PPE management system (PPEMS) 6 so as to maintain fit factor information for a number of workers, such as workers 10A-10N (collectively, “workers 10”). PPEMS 6 may store additional worker information, such as past PPE usage, trainings, etc., as well as environmental information, such as PPE requirements for workers 10 in different environments 8, 110.

[0031] In some examples, PPE fit testing system 120 may identify one or more articles of PPE that worker 10A needs testing for, for example by camera 22 scanning a barcode or by using an algorithm to identify a PPE and associated make or model from an image. In some embodiments, system 120 may also determine a PPE, or a subset of PPE, for fit-testing or training based on a work assignment for worker 10A in environment 8B and available PPE for environment 8B.

[0032] As shown in the example of FIG. 1, system 2 represents a computing environment in which a computing device 16, 18 (e.g., at access point 14A or 14B, and / or within or proximate to a plurality of environments 8), may electronically communicate with PPEMS 6 via one or more computer networks 4. Each environment 8 represents a physical environment, such as a work environment, in which one or more individuals, such as workers 10, utilize PPE while engaging in tasks or activities within the respective environment. As shown in FIG. 1, each of the environments 8 may have an access point 14 through which workers 10 and / or users 24 gain entrance into the environment 8. In some embodiments, systems and methods herein are coupled to, or interact with, access points 14A-14C, such that a worker 10 can be fit tested for PPE required beyond the access point 14A-C.

[0033] In the example of FIG. 1, environment 8 A is shown as generally having workers 10, while environment 8B is shown in expanded form to provide more detail. In the example of FIG. 1, a user10A is shown wearing an article of PPE 13 A, such as a respirator. A plurality of workers 1 OB- ION are shown within environment 8B wearing respective articles of PPE 13B-13N. Remote users 24, which may be examples of workers 10, access computing device(s) 18 within environment 8C. Worker 10C is shown wearing a respective article of PPE 13C at access point 14B outside of environment 8B. As shown, for example, in FIG. 1, each worker 10 may wear a respirator as an article of PPE 13A- 13N. In other examples, workers 10 may use one or more additional or alternative articles of PPE 13. In some cases, one or more articles of PPE 13 may be configured to transmit data from a sensor of the one or more articles of PPE 13 to network 4. For example, one or more articles of PPE 13 may be configured to transmit data relating to the usage, the useful life, the status, or the like of the one or more articles of PPE 13 to a device through network 4.

[0034] Each of environments 8 may include computing facilities (e.g., a local area network) by which one or more computing devices 16, 18 at access points 14 and / or within environments 8 are able to communicate with PPEMS 6 and / or PPE fit test system 120. For example, access points 14 and / or environments 8 may be configured with wireless technology, such as 802.11 wireless networks, 802.15 ZigBee networks, or the like. In the example of FIG. 1, access point 14B and environment 8B include a local network 7 that provides a packet-based transport medium for communicating with PPEMS 6 and / or PPE compliance system 120 via network 4. In addition, access point 14B and / or environment 8B may include a plurality of wireless access points 19A-19C geographically distributed throughout access point 14B and / or environment 8B to provide support for wireless communications both inside and outside of access point 14B and / or work environment 8B.

[0035] As shown in the example of FIG. 1, an environment, such as environment 8B, may also include one or more wireless-enabled beacons, such as beacons 17A-17C (collectively, “beacons 17”), that provide accurate location information within the work environment. For example, beacons 17 may be GPS-enabled such that a controller within the respective beacon may be able to precisely determine the position of the respective beacon. Information from beacons 17 may be helpful for confirming what PPE worker 10A may need, e.g., GPS information for a worker having a similar work assignment may indicate where worker 10A will need to go.

[0036] In addition, an environment such as environment 8B, may also include one or more wireless- enabled sensing stations, such as sensing stations 21A and 21B (collectively, “sensing stations 21”). Each sensing station 21 includes one or more sensors and a controller configured to output data indicative of sensed environmental conditions. Moreover, sensing stations 21 may be positioned within respective geographic regions of environment 8B or may otherwise interact with beacons 17 to determine respective positions and may include such positional information when reporting environmental data to PPEMS 6. As such, PPEMS 6 may be configured to correlate the sensedenvironmental conditions with the particular regions. For example, PPEMS 6 may use the environmental data to aid when generating alerts or other instructions to workers 10 at access point 14B. For instance, PPEMS 6 may use such environmental data to inform workers 10 of environmental conditions he or she may experience upon entrance to work environment 8B, what PPE is required and what PPE items the worker needs fit testing for. Example environmental conditions that may be sensed by sensing stations 21 include but are not limited to temperature, humidity, presence or absence of a gas, pressure, visibility, wind, or the like. Information from sensing stations 21 may help indicate what PPE is appropriate for worker 10A. Fit testing information, such as what models of PPE the worker is fit test certified for, and when said certification expires, may be retrieved by PPEMS from a local memory, a cloud memory, and / or over a network from a device memory.

[0037] In general, physical access points 14 and / or environments 8 may include computing facilities that provide an operating environment for computing devices 16 to interact with PPEMS 6 and / or PPE fit testing system via network 4. Similarly, remote users 24 may use computing devices 18 to interact with PPEMS 6 and / or PPE fit testing system via network 4 from environment 8C. For example, access points 14 and / or environments 8 may include one or more safety managers responsible for overseeing safety compliance, such as PPE compliance of workers 10. In some such examples, remote users 24 may be able to access data acquired by PPEMS 6 and / or PPE fit testing system such as, for example, PPE compliance information, training information, avatars of workers 10, images of workers 10, or any other data available to PPEMS 6 and / or PPE Attesting system as described herein. In some examples, remote users 24 may include examples of workers 10 engaging in offsite PPE simulation training. Computing devices 16, 18 may include any suitable computing device, such as, for example, laptops, desktop computers, and / or mobile devices, such as tablets and / or smartphones, or the like. In some examples, access point 14B and / or environment 8B may also include one or more safety stations 15A, 15B (collectively, “safety stations 15”) for accessing one or more articles of PPE 13, such as the respirators shown in FIG. 1. Safety stations 15 may allow workers 10 to check out one or more articles of PPE 13, exchange a size of one or more articles of PPE 13, exchange data, or the like. In some examples, safety stations 15 may transmit alerts, rules, software updates, and / or firmware updates to one or more articles of PPE 13. Safety stations 15 may be able to access fit test records from fit testing system 120 to ensure that a worker has had training, and been fit tested, for a given PPE 13, or otherwise provide an indication of noncompliance or recommendation for a PPE 13 that would be sufficient for which worker 10 has passed a fit test.

[0038] For simplicity, much of the rest of this disclosure is described with respect to an example in which a PPE fit testing system is used to fit test worker 10A for a respiratory protection device (e.g., respirator 13 A), however, the techniques described herein may similarly be applicable to other articlesof PPE worn elsewhere on the body of worker 10A. For example, the techniques herein may be equally applicable to other PPE items such as a fall-protection device, a hearing protection device, an eye protection device, or a head protection device. In some embodiments herein, a PPE fit testing system also, based on information about a worker 10A, provides a list of one or more PPE likely to fit worker 10A.

[0039] When fit correctly, a respiratory protection device creates a seal around a seal perimeter on a user’s body, protecting a user from inhaling contaminated air. However, any gap along the seal perimeter can cause contaminated air to flow around the respiratory protection device instead of through a filter layer. Therefore, achieving a good seal around the perimeter of a respirator to the face of the wearer is critical for respiratory protection. Fit testing ensures that a good seal is achieved. Systems and methods herein calculate a fit factor, which may be an indication of how well an item of PPE fits a person. As used herein, a “fit factor” for a respiratory device is a ratio of a concentration of a contaminant (e.g., a test aerosol) in the air outside a respirator over a concentration inside the respirator. E.g., a respiratory device fit factor can be considered an inverse of leakage around the face seal. A fit factor of 100, for a respirator, correlates a 1% air leakage rate, which is considered a lower threshold for a suitable fit.

[0040] For respiratory protection devices, mandated respirator fit testing has been commonly practiced in the workplace and is required by the US Occupational Safety and Health Administration (OSHA) as part of the respiratory protection program in the United States. However, it is expressly contemplated that systems and methods herein may provide assistance in complying with other regulatory bodies, in the US or internationally.

[0041] FIG. 2A illustrates an example worker 200 wearing a respiratory protection device 210 and safety goggles 230. Respiratory protection device 210 has several features that must fit a wearer correctly. For example, a nose forming portion 218 must be formed around the specific geometry of the nose of worker 200. Additionally, an upper seal area 222 must be fit to the face of worker 200 with no gaps, such that air does not pass around seal area 222, and instead passes through a filter barrier 212. Similarly, respiratory device 210 also includes a lower seal 214 that must seal to a chin or neck of worker 200 with no gaps. The placement of straps 216 may be important as well and may affect the fit of respiratory protection device 210. Additionally, as illustrated in FIG. 2A, straps 216 may also interfere with, or change a position, of safety glasses 230. Similarly, safety glasses 230, may interfere with a fit of nose forming portion 218.

[0042] Worker 200 may, therefore, require Attesting for both safety glasses 230, respiratory protection device 210, and for the combination of PPE 210 and 230. Fit of each of devices 210 and 230 must both meet safety protection standards (e.g., sufficient eye protection and respiratory protection) but shouldalso be comfortable for worker 200.

[0043] FIG. 2B illustrates another fit testing scenario, where a worker 250 has three types of PPE donned: over-ear hearing protection 252, in-ear protection 256, and a helmet 254. PPE 252 - 256 must be comfortable to wear, provide sufficient hearing protection and head protection, without interfering with the functionality of each other. Systems and methods herein, in some embodiments, provide suggestions or recommendations regarding PPE that can be worn together without interference. Based on the worker’s PPE needs, a PPE wearer may need to undergo fit testing for one or more PPE articles they have not been fit tested for.

[0044] Currently, there are two types of fit testing for respiratory devices: qualitative fit test (QLFT) and quantitative fit test (QNFT). In QLFT, the olfactory, or taste response, of an individual to an aerosolized fit test solution is used to reach a dichotomous decision (“pass” or “fail”). In QNFT, the ratio of the concentration of the testing material outside a respiratory device compared to that inside the respiratory device is calculated to provide a fit factor, for example using an ambient aerosol condensation nuclei counter. However, both of these fit testing types require a trained fit tester to administer a test for each worker individually. Often, worksites have to hire a fit tester for one or more days to conduct fit tests. Generally, a trained fit tester is not available at all times on a worksite. This limits the ability for workers to get fit tested on multiple PPE models quickly and disrupts a worksite as each worker has to leave their assignment to undergo a 10-15 minute fit test before returning.

[0045] Systems and methods herein provide a new fit testing option that does not require a trained fit tester, takes less time, and can be completed by a worker anywhere with a device that can access a fit testing application - such as a mobile computing device of a worker, a PPE vending machine, at an access point to an environment, etc.

[0046] For regulatory compliance, a site manager or employer may need to have accessible copies of fit test certificates for workers for a given site. However, it is also common for workers to move between sites - e.g., from one production plant to another, from one building to another within a plant, or from one employer to another. It may also be helpful for the worker to have their own record of fit testing as well. It may also be beneficial for a PPE fit testing system to generate de-identified fit test information as well, for example for manufacturers to improve fit, improve PPE recommendations based on worker information, etc. Systems and methods herein may generate a digital fit test certificate that can be stored by an application (e.g., the fit testing application or another suitable application) on a device, or that can be communicated to another datastore over a wired, wireless, cloud or other suitable network.

[0047] Prior art efforts have been made to increase PPE fit and provide training to workers. For example, PCT publications W02019 / 224659 and W02021 / 229372 focus on the use of camera visionto ensure that a worker is wearing the same PPE in the manner that it was worn during the fit test. Additionally, medical companies have started providing computer guided instructions for donning and doffing PPE. Other fit testing programs, for example QNFT testing instruments by TSI provide some assistance with qualitative respirator fit testing but do not also provide fit training prior to a fit testing session. PCT Application PCT / CN2023 / 108870, filed July 24, 2023, describes a fit testing interface that may improve a qualitative or quantitative fit testing session as well as provide suggestions as to what PPE may be a good fit for a user.

[0048] Systems and methods herein provide improvements over the prior art fit testing systems and methods, by providing a fit testing system that removes the need for a fit tester, can administer a fit test on any device with a camera (or other suitable sensor), without the need for other physical sensors or a size reference fiducial. Systems and methods herein automatically, based on one or more photos of a user, calculate a likelihood of fit for a PPE model, herein referred to as a fit factor..

[0049] FIG. 3 illustrates a method of fit testing in accordance with embodiments herein. Method 300 may be implemented using a device with an image capturing device or other suitable sensor (e.g., laser scanning, etc.), a memory and suitable processing circuitry. Calculations and analysis may be completed locally or remotely.

[0050] In block 310, a user is scanned. Scanning a user may include capturing an image of a user relevant to a PPE article - e.g., a user’s face for a respiratory device, safety glasses, or helmet, or a user’s ear for a hearing protection article, a user’s body for fall protection or coveralls, etc. Scanning may be done using an image capturing device in some embodiments, such as a camera, video camera or other suitable device. However, scanning may be done using other suitable systems, such as a laserbased scanning system or another suitable scanning system. Any suitable system that obtains sufficient topographical information about a user may be utilized as a scanning system herein.

[0051] In block 320, landmarks are identified based on the scan. Landmarks may include, in the example of respirator fit testing, cheek bones, nose tip, chin, etc. The listed landmarks are provided for example only - it is expressly contemplated that many more suitable landmarks are possible. In some embodiments, the landmarks are identified using a machine learning algorithm trained on a set of images of users with known landmarks. It is noted that previous respirator recommendation systems based a recommendation on only a few measurements - such as a facial length, facial width, interpupillary distance, etc. Systems and methods herein may identify as many as 5-10 landmarks on a user’s face during a respirator fit test, in some embodiments. Systems and methods may even identify as many as 20 landmarks on a user’s face during a respirator fit test, or even as many as 25, or even more. Systems and methods may even identify as many as 50 landmarks on a user’s face during a respirator fit test, or even as many as 100, or even more.

[0052] In block 330, the identified landmarks are analyzed. Analyzing landmarks may include comparing landmarks to each other - e.g., determining a distance between landmark 1 and landmark 2, or an angle formed by landmarks 1, 2, and 3, etc. In some embodiments, over 50 datapoints are calculated based on the landmark analysis. In some embodiments over 100 datapoints are calculated based on the landmark analysis. In some embodiments, over 200 datapoints, or even over 300 datapoints, or even over 500 datapoints are calculated based on the landmark analysis. In some embodiments, some datapoints are weighted differently than others for analysis purposes.

[0053] In block 340, a PPE model selection is received. In some embodiments, systems and methods herein may provide one or more suggested PPE models for a user, based on the landmark analysis. A PPE model selection may be received by an I / O device, e.g., a touchscreen, a mouse, a keyboard, etc. based on a user’s input. A PPE model selection may also be made by scanning a barcode, recognizing the PPE model selection in a scan or image, etc.

[0054] In block 350, a scan is taken of a user wearing an article of PPE. The scan may be taken with any suitable scanning system. In some embodiments, the same system used in block 310 is used for the scan in block 350. In some embodiments, a different system may be used. For example, instead of actively scanning a user in block 310, a previous scan of a user could be retrieved.

[0055] In block 360, the scans of the user before and after donning the article of PPE are compared to determine potential fit inconsistencies. The comparison may be done using a machine learning algorithm. For respirator fit testing, fit inconsistencies may be gaps where environmental air may leak into the breathing zone within the respirator cavity. In some embodiments, a comparison includes comparing the way a PPE lays on the body part in a current scan with the way the PPE laid on the same body part in a scan captured after a successful fit test and determining a difference. In some embodiments, comparing includes mapping landmarks and determining which landmarks should be obscured by the PPE, and by how much.

[0056] In block 370, the identified inconsistencies are evaluated. The evaluation may be done, for example, by a machine learning algorithm, look-up tables, or another suitable method to determine if the identified gaps are significant enough to cause failure of a fit test.

[0057] In block 380, a fit test result is generated. For example, if identified inconsistencies are insignificant, a “fit test pass” indication may be provided. If the identified inconsistencies are significant enough to cause failure of a fit test, a “fit test failed” may be provided. In some embodiments, generating a fit test result includes generating a fit factor. The fit factor may be provided in addition to, or instead of, a fit test pass or fail indication.

[0058] A generated fit test result may be provided as a fit test certificate to the user, to a worksite management system (e.g., PPEMS 6 in FIG. 1), to a site supervisor, etc. In some embodiments, fittestresults are stored for later retrieval. E.g., a “fit test pass” at a first access point (e.g. access points 14 in FIG. 1), may be retrieved when a user attempts to pass a second access point, such that the user is automatically allowed entry based on a previous fit test indication.

[0059] Method 300, if fit inconsistencies would cause a failure of a fit test, may return back to block 340, as indicated by arrow 390. Because a worker can conduct their own fit test, it is more convenient to conduct multiple digital fit tests until a PPE model is found that can result in a passing fit test.

[0060] It is noted that, in some embodiments, a number of landmarks to be detected and / or datapoints to calculate may be specified for a landmark detector and / or analyzer. However, it is expressly contemplated that a machine learning algorithm may find correlations based on training data without correlation.

[0061] Systems herein generate a fit test result automatically based on a comparison between a pre and post scan of a user donning a PPE article. The fit test result may be physically generated, for example sent to a printer for printing on paper, or another suitable medium. Generating a fit test result may also include generating the result in a manner that makes regulatory compliance, or audit compliance, more convenient. Generating the result may also include generating a physical or digital copy that is provided to an employer, for employer records. Generating the result may also include generating a digital or physical copy for the worker. For example, the worker may have an account, or otherwise have access to at least some of information accessible using systems herein.

[0062] Systems and methods herein also automatically generate a digital fit test record for a fit test. This contrasts with traditional fit testing which requires recording all test results, for example in a spreadsheet, capturing the test result record, and then compiling and emailing the records to a site safety manager.

[0063] Information about fit tests, fit test results available and completed training modules, comfort scores or other information regarding PPE may be provided to the worker such that it can be accessed later. For example, if the worker later leaves a current employer to work for a new employer, the worker may be able to retrieve, or access, past fit test results to provide to the new employer. The results provided to the worker may be provided in a digitally secure format, using encryptions, a blockchain or other secure ledger, or other suitable mechanisms to ensure that the data is uncompromised. In some embodiments, the fit test information may be provided to a third-party provider (e.g., a ‘digital wallet’ application) for validation. For example, a worker may move from a first site, where a fit test was taken, to a second site, where they need to provide proof of passing a fit test on a specific model of PPE.

[0064] Systems herein may also provide aggregated fit test results to an employer, a manufacturer, a distributor, a regulatory agency, or another interested party. For example, a manufacturer may want toknow what the most frequently used PPE is at a given site, for supply ordering purposes. Alternatively, a manufacturer may want information about what PPE needs to be stocked at a given location. For example, if 10 models of a PPE type are currently offered, but all employees pass a fit test on 8 of those models of PPE, the employer may be able to save money by not ordering the two other PPE models. Employers may also want fit test information provided in a manner that makes audit compliance convenient, for example in a manner that is easily providable to, or readable by, a regulatory agency - this may include identifiable, or deidentified, fit information. Deidentified information may include, for example, analytics surrounding respirator usage, work assignment, fit test results, or other useful information.

[0065] Similarly, a manufacturer or distributor may want to improve a product offering for sites they supply. A manufacturer may want to improve fit for a given PPE model for more individuals. Additionally, a distributor may want to analyze fit test results to recommend PPE models for purchase for a given site, or generally.

[0066] Results generated, and information obtained using systems and methods herein, may be stored in any suitable manner. For example, it may be possible to retrieve training information and model specific fit testing parameters using a cloud-based or other wireless network protocol, for example 802.11 a / b / g / n, Bluetooth®, Zigbee, etc. However, where personal identifying information is concerned, it may be preferable for at least some information generated or retrieved by systems herein to be accessible through a local area network (LAN), or by using a wired network.

[0067] Additionally, systems and methods herein may increase PPE compliance, and therefore safety for individuals that undergo fit testing using systems and methods herein. In some embodiments, systems herein may allow users to, in addition to conduct a fit test, receive specific guidance on how to properly don and doff PPE in a manner consistent with current best practices. Additional training models may also be available. In some embodiments, individuals may have personalized access to a fit testing system such as those described in embodiments herein and may be able to access additional training information for a given PPE model, training modules to refamiliarize themselves with proper procedure, or undergo fit testing for additional PPE models.

[0068] Systems and methods herein may also allow for data synchronization across workplaces. An employer may have fit test records accessible across multiple site locations, such that a worker can travel between locations and have fit test certification easily verified. In some embodiments, data synchronization occurs using a wireless network, such as a cloud-based network.

[0069] FIG. 4 illustrates a PPE fit testing system in accordance with some embodiments herein. While systems and methods herein provide digital fit testing functionality, they also provide an intuitive interface for generation and collection of fit test records, access to past fit test records as well astraining, recommendation of, and information specific to, PPE of interest to a given individual.

[0070] FIG. 4 illustrates a block diagram of one embodiment of a PPE fit testing system 400. System 400 includes a scanning module 410 configured to capture a scan of a user. For example, a user’s face may be scanned for fitting a respirator, a user’s ear may be scanned for fitting a hearing protection article, a user’s entire body may be scanned for fitting a fall protection harness or coveralls, etc.

[0071] PPE fit testing system 400 may retrieve information from a worker datastore 472. Worker information datastore 472 may include information about a worker relevant to a fit testing experience. For example, work assignments for a given worker, PPE needed for the worker for said working assignments, past fit result data (including PPE fit tested, pass / fail information as well as comfort information) may also be retrieved, which may inform what PPE a user needs to be fit tested for, and whether fit testing was done previously, and recently enough to be relied upon (e.g. fit re-certification is required annually in many jurisdictions). Additionally, information about a worker that is relevant to fit testing, training, etc. may also be retrieved. For example, a worker language preference may be retrieved.

[0072] Worker information in datastore 472 may come from any number of suitable sources. For example, an employer may maintain information about workers past fit test results, PPE used, work assignments, etc. A worker may have direct access to, and store information within a data repository of PPE fit testing system 400 and may provide data for storage in datastore 472. For example, a worker may want access to their own fit testing records, and may authorize retrieval of said records, or other information, for the purposes of conducting a fit test.

[0073] A user of system 400 (e.g., a worker within a site) may be scanned using a scanning device 412, which may be any suitable device that captures PPE fitting data. For example, a laser scanning system such as LIDAR may be used to obtain topographical information about a user. Other suitable scanning technology is expressly contemplated such as 3D time of flight, e.g. scanner-less LIDAR, stereo cameras, ultrasonic sensors, or using structured light. A camera may be used to capture an image of a user. Other suitable scanning technology is expressly contemplated such as 3D time of flight, e.g., scanner-less LIDAR, or using structured light. Scanning module 410 may include a scan actuator 414 configured to trigger scanning device 412 to obtain scanning data. For example, scan actuator 414 may trigger a scan, for example, based on a user input - e.g., a user providing an indication that they are ready for a scan to take place.

[0074] Scan actuator 414 may also trigger a scan, in some embodiments, automatically. For example, scan actuator 414 may detect that a relevant part of a user is positioned within a scanning frame (e.g., in front of a laser detector, within a frame of a camera, etc.) and start a scan without receiving a user indication. Scan actuator 414 may also, in some examples, start a scan on a delay - e.g., a warningmay be given to a user to “stand still,” and a scan may start within a few seconds of the warning.

[0075] Scanning module 410 may include a light source 416. For example, if a user is in a dark environment, light may be needed in order to illuminate features important to detecting a fit. For example, fitting a respirator may require an image with facial features (nose, chin, eyes) clearly detectable. Scan actuator 414 may actuate light source 416 based on an indication that ambient light is not sufficient. For example, light source 416 may be turned on if a camera detects ambient light below a light threshold.

[0076] Scanning module 410 may have other functionality 418 as well . For example, scanning module 410 may provide a scan result (image, topography information, etc.) to a user. Scanning module 410 may provide, for example, a captured image for a user to approve prior to providing the image to fit test module 420. Other functionality is expressly contemplated.

[0077] Scanning module 400 also includes a fit testing module 420. A scan retriever 422 may retrieve scan data from scanning module 410. Scan data may be retrieved from scanning module 410 as soon as it is captured or may be retrieved at a later date. For example, if an image of a user was recently captured, a new scan may not be required. E.g., if a user had their face scanned as part of a recent fit test, the scan from that previous fit test may be used. Scan data, in some embodiments, is sufficiently recent if it was captured earlier in a given day. Scan data, in some embodiments, is sufficiently recent if it was captured earlier in a given week, or earlier in a given month. It may be necessary to obtain new scan data periodically as human faces change as an individual ages.

[0078] A landmark detector 424 may, based on received scan data, detect one or more landmarks of interest. Landmarks may include user specifications such as top of head, eyebrow ridge, a position of a cheek bone, a chin location, etc. Other landmark options are expressly contemplated. Landmark detector 424 may detect a first set of landmarks for fit testing a first type of PPE (e.g., facial landmarks for a respirator) and a second set of landmarks for fit testing a second type of PPE (e.g. body landmarks for a fall protection harness). Landmark detector 424 may detect landmarks based on a known PPE being fit tested - for example a user may designate that a fit test for a respirator is needed, or fit testing system 400 may designate that a respirator fit test is needed based on a known work assignment for the user, or a PPE requirement for an access point near the user.

[0079] Landmark data generator 426, based on the detected landmarks, generates landmark data for the user. For example, a distance between two landmarks (e.g., a distance from a detected ground point to a top of head gives a user’s height, or a distance between two detected pupils gives an IPD), or an angle formed by three landmarks may be generated. Other data may be generated.

[0080] Landmark detector 424 and / or landmark data generator 426 may include machine learning algorithms trained based on relevant training datasets. While it is discussed herein that machinelearning algorithms may first detect a series of landmarks and may then generate landmark data based on the detected landmarks, it is expressly contemplated that a machine learning algorithm may, based on the training data, conduct an image comparison between a first scan and a second scan using other methods.

[0081] A PPE detector 432 may be configured to detect a PPE article that a user wants to be fit tested for. For example, system 400 may detect a PPE article from an image (e.g., a user holding the PPE, pointing to the PPE, etc.), from a barcode scan, from an RFID or NFC chip associated with the PPE article, from a user input, or another suitable source.

[0082] PPE fit testing system 400 may include a PPE selection system 428, which may provide a user with one or more PPE options that may result in a passing fit test score. PPE selection system 428 may provide recommendations using a machine learning algorithm, as described in PCT with Application No. PCT / CN2023 / 108870, filed July 24, 2023), or using another suitable method. For example, look-up tables may be used based on identified body dimensions. PPE selection system 428, in some embodiments, encompasses functionality similar to that illustrated in FIG. 5.

[0083] Fit test module 420 may compare scan data from a user wearing the PPE article to scan data of a user not wearing the PPE article to determine a fit likelihood, using scan comparison module 434, for example. Scan retriever 422 may retrieve scan data of a user wearing a selected PPE article, in some embodiments, from scanning module 410. PPE fit testing system 400 may have multiple scanning modules such that a first scanning module 410 obtains a scan of a user without an article of PPE for fit testing, and a second scanning module 410 obtains a scan of the user wearing the article of PPE.

[0084] Scan comparison module 434 may compare the pre-and post PPE donning scan for fit inconsistencies. For example, a respirator fit is dependent on a good seal between the respirator and a user’s face. Fit inconsistencies for a respirator, therefore, may include indications that the seal may leak. In addition to PPE functionality, PPE comfort may also be considered by scan module 434. For example, if anticipated respirator-skin contact area is too high, or not enough space is anticipated between the inner surface of the respirator and a user’s nose, the respirator may be uncomfortable. In some embodiments, in addition to providing a fit factor or fit test result, a comfort indication may also be provided.

[0085] Fit test module 420 may receive PPE specification information using a PPE specification retriever 436. PPE specification information may include identifying information for a number of PPE models, for example from PPE datastore 474. PPE datastore 474 may include sufficient information for PPE detector 432 to identify an article of PPE.

[0086] A make and / or model of the detected PPE may then be identified using PPE detector 432.PPE detector 432 may analyze images, or other sensor signals that could be used to identify a given article of PPE. However, it is expressly contemplated that PPE specification retriever 436 may retrieve information about an article of PPE outside the fit testing context. For example, an individual may wish to obtain information about properly donning or doffing a specific item of PPE, proper use of said PPE, maintenance of said PPE, etc. PPE specification retriever 436 may interact with any number of suitable databases to obtain relevant information. For example, PPE fit testing system 400 may be associated with a PPE information data store 474, that includes information on PPE, for example gathered through historic fit testing, provided by manufacturers, provided by site managers, etc.

[0087] Fit testing module 420 may use one or more machine learning algorithms trained by model specific fit test datastore 476, which includes training data related to a number of different PPE models, images of users with and without PPE, and fit test result information.

[0088] Fit testing module 420 may include a fit factor generator 438. Fit factor generator 438 calculates a fit factor for a user for a given PPE article. The fit factor may be based on an image comparison before and after the user dons the PPE article. Fit factor generator 438 may include a machine learning algorithm. A fit factor is an alphanumeric indicator of how well, or how poorly, an article of PPE will fit a user. In some embodiments, a fit factor is based on a threshold fit. For respirators, a fit factor of 100 indicates that 1% contaminated air penetration occurred through the respirator body. A fit factor of 1000 indicates 0. 1% contaminated air penetration occurred through the respirator body. In some embodiments, a fit factor represents a different measurement of fit likelihood, such as a percentage of an ideal fit, etc.

[0089] Fit testing module 420 may include a fit test certificate generator that generates a fit test result - pass while wearing a specific model / size of a respirator or fail, for example - which may be provided to a device 460, using user interface generator 402, for example.

[0090] Fit testing module 420 is illustrated and described as having multiple functional components - landmark detector 424, landmark data generator 426, PPE detector 432, scan comparison module 434, and fit factor generator 438, for example. It is expressly contemplated that these functionalities may be completed by one or more algorithms and are described herein separately for ease of understanding. Additionally, while functionalities 422-440 are illustrated as part of a single fit test module 420, it is expressly contemplated that some of functionalities 422-440 are provided by multiple devices. For example, fit test module 420 may be part of the same device as scanning module 410 or may be part of separate devices. PPE fit testing system 400 may be an application implemented on device 460 by processing circuitry 466, for example. It is also contemplated that not all illustrated functionality is needed in all embodiments. In embodiments where scanning module 410 and fit test module 420 are incorporated into the same device, a scan retriever may not be needed, as scan data may be passeddirectly from scanning module 410 to fit test module 420. Additionally, some functionalities may be combined, such as landmark detector 424 and landmark data generator 426 - in some embodiments a single scan analyzing algorithm is used. Analysis of a scan of a user without PPE is used to provide recommendations of suitable PPE, while analysis of a scan of a user with and without PPE is used to provide a fit likelihood indication.

[0091] PPE fit testing system 400 is illustrated in FIG. 4 as having a training module 450. Training module 450 may provide a user of system 400 with information and / or tutorials on PPE models, fit testing, proper donning and doffing procedures, etc. Training module 450 may be used by an individual before or after a fit test. For example, a comfort assessment may be done by an individual minutes before, hours before, or even days before an actual fit test takes place. Training module 450 may provide a comfort assessment tutorial for a user.

[0092] A tutorial selector 452 may indicate relevant tutorials for a user or may receive an indication of a desired tutorial from a user. A training retriever 454 may retrieve a tutorial from tutorial datastore 480. Training module 450 may have other functionality 456, such as a language selection feature, etc.

[0093] PPE fit testing system 400 may retrieve information from other datastores 482.

[0094] A device 460 may be used by a user to access PPE fit testing system 400. Device 460 may be a stationary computing device or a mobile computing device such as a tablet, cell phone, smart device, etc. Device 460 may be incorporated into an access point, a PPE vending machine, or another suitable device in a work environment. Device 460 may include an input / output (I / O) mechanism 462 capable of receiving user input, such as a touchscreen, keyboard, mouse, etc. Device 460 may have a memory 464 and processing circuitry 466 configured to store and support a fit testing application that includes some or all of system 400 functionality. Device 460 includes a display component 468 which may receive and present a user interface, generated by user interface generator 402 for example, to a user. Device 460 may have other functionality 470.

[0095] PPE fit testing system 400 is illustrated as separate from a device 460. However, it is expressly contemplated that system 400 may be an application program stored in memory 464. In some embodiments, some or all of PPE fit testing functionality is accessed by device 460 using a wired, wireless or cloud-based network.

[0096] PPE fit testing system 400 may also include an augmented reality generator 406, that may be interactive with a worker, for example as described in related PCT Publication WO 2021 / 229372, published on November 18, 2021, paragraphs [0020-0025] all of which are incorporated herein by reference. A worker may interact with AR generator 406, for example to view how a given PPE article may look when worn, or to adjust a PPE article from a current configuration to a preferred configuration. For example, a respirator includes one or more straps that, if placed incorrectly, makeleaks more likely. AR generator 406 may assist a worker in changing a strap placement position. Similarly, a nose portion of a disposable respirator often requires manipulation to accommodate a user’s nose bridge geometry. AR generator 406 may provide instructions or an overlay illustrating how and where a user should deform a nose portion of a respirator to increase fit. AR generator 406 may also be useful for providing training through training module 450.

[0097] PPE fit testing system 400 may also include other functionality 408 as appropriate. For example, another information retriever may access information from data store 482.

[0098] PPE fit testing system 400 also includes a communication component 404, that communicates information collected or generated by PPE fit testing system 400 to another source. Communication component 404 may communicate information to: a worker, a site manager or employer, a PPE manufacturer, a regulatory agency, etc. Fit test certificate generator 440 may generate a fit test result based on recorded results from the fit test. The fit test certificate may be communicated directly to a worker datastore 472 associated with a worker 21, for example, for later access at a different location, a different site, or with a different employer.

[0099] Additionally, fit information may also be communicated to a site compliance data store 495. The data may be communicated to site compliance datastore 495 such that it is easily retrievable if an audit is requested by a regulatory agency. Historically, site managers are responsible for keeping individual fit test certificates, or copies thereof, in a manner that can be reviewed by a regulatory agent during an audit. Digital aggregation and storage reduce the burden on a site manager for regulatory compliance, increases transparency, and may make regulatory audits take less time and cause less disruption.

[0100] Communication component 404 may communicate fit test results, or training information from training module 450, to another device 460. For example, second device 460 may be a device that a worker uses to access a training module at a later time.

[0101] Anonymized, or de-identified fit test results may also be communicated to a data store 490, for access by site managers for analytics purposes, distributors and / or manufacturers for improved product experience, etc.

[0102] FIG. 5 illustrates a PPE selection system 500. PPE selection system may include, as one example of PPE, a respirator selection system 510. However, while respirators are discussed in detail herein, it is expressly contemplated that PPE selection system may also provide PPE selection options for different types of PPE including, but not limiting to, hearing protection articles, eyewear, helmets, safety harnesses, coveralls, etc. Respirator selection system 510 may include, or have access to, a respirator database 512, which may store information on a number of respirator makes and models.

[0103] PPE selecting system 500 includes a respirator selection system 510. Respirator selection system 510 is illustrated in FIG. 5 as containing a respirator database 512, however it is expressly contemplated that respirator database 512 may be remotely accessed, for example over a wireless or cloud network. Respirator database 512 includes information on a number of models of respirators that may be useful for different environments. Respirator database 512 may also, or alternatively, include training data for a machine learning model such as images of individuals with known facial dimensions and fit test results and / or comfort scores.

[0104] Respirator selection system 500 receives information about a worker (or user of system 500) from worker information retriever 520. For example, an image receiver 522 may receive an image of a user’s face from a camera or other image source. Other information may be retrieved from another receiver 524, which may receive sensor information, stored data, or other relevant information. For example, an inter-pupillary distance for a user may already be known and retrievable. This may be helpful for testing whether a received image is a suitable representation, or whether a mesh has been correctly applied to a detected face.

[0105] Image information may be used by a fit estimator 514 to generate a likelihood of fit. Fit estimator 514 may be any suitable machine-learning or artificial-intelligence based model. Fit estimator 514 may use processed image analysis from a landmark analyzer 530. However, it is expressly contemplated that fit estimator 514, like other machine learning algorithms herein may, with sufficient training data, generate recommendations based on other image analysis techniques.

[0106] A landmark analyzer 530 may quantify a user’s relevant dimensions so that a fit can be estimated by fit estimator 514 and / or so that a comfort estimate can be generated by comfort estimator 515. For a respirator, fit and comfort of wear are dependent on a user’s facial geometry. A mesh applicator 532 may apply a mesh to a detected face in a received image or to a set of facial scan data. The face may be detected using any suitable image analysis technique.

[0107] Landmark measurement generator 534 may generate data regarding distances between landmarks detected from the applied mesh. Landmark angle generator 536 may generate data regarding how the detected landmarks relate to each other. Landmark analyzer may use other techniques 538 to obtain information relevant to recommending a respirator.

[0108] PPE selecting system may also include a communication component 516 which may communicate a generated selection of one or more PPE models, to another device or to a user interface generator. Communication component 516 may also communicate information from a respirator database 512 which may include relevant donning and doffing instructions and other relevant information for a user 518.

[0109] PPE selection system 500 may recommend PPE for use by an individual worker or recommendPPE for a site to keep on hand. Selections of possible PPE may be based on historic PPE used by an individual, or at a worksite. Selections may include a particular article of PPE for a given worker, or articles of PPE for a worksite to have on site. For example, PPE selection system 500, based on fit tests that have been completed on a site after a set amount of time, may determine that all individuals fit tested can use two of five disposable respirator models, and therefore, three other models that a worksite had available, could be discontinued.

[0110] FIGS. 6A-6I illustrate example user interfaces which show some functionality of embodiments of the present invention. It is expressly contemplated that objects or features illustrated in FIGS. 6A- 61 may be presented differently or in a different combination in embodiments of the invention. Additionally, some embodiments have more, or less, functionality. User interfaces 600A-600I are intended to be illustrative of some functionality, and not intended to limit functionality of any embodiments herein.

[0111] FIG. 6A illustrates an example landing page 600A that may be presented to the user of a PPE fit testing system. A number of different user types may benefit from a PPE fit testing system. For example, a site manager may manage one or more worksites, and may view information about or manage a worksite. Different organizations, sites, or other subgroups of individuals (e.g., all of the workers in a particular building, on a particular floor, or a particular line) may be designated using manage worksite feature 602. Similarly different PPE users or PPE models may be added using feature 604. It may be possible, using feature 604, to designate PPE used or needed for an individual. A user may enter a fit testing mode using feature 606. Feature 608 may also allow a worker to view their own fit test history or may allow a site manager to review fit test history for workers.

[0112] FIG. 6B illustrates an example user interface 612 on a device 610 that may be presented to a user. A user may encounter user interface based on an interaction with feature 606. However, it is also contemplated that a user interface 612 may be presented on a device 610 in a worksite to ensure that workers are in compliance with fit testing requirements. Device 610 may be built into a worksite entry point, into access points within a worksite, into a PPE dispensing machine, into a safety station, or in another suitable location. Device 610 may also be a mobile computing device associated with a worker. Device 610 may prompt the worker to conduct fit testing periodically, e.g., at the start of a shift, or may allow a manager or safety officer to prompt the worker to conduct a fit test.

[0113] FIG. 6C illustrates a user interface 616 on a device 610 prompting a user to capture an image without PPE. FIGS. 6B-6I illustrate an example where the PPE being fit tested is a respirator, however it is expressly contemplated that systems and methods herein would work similarly for other PPE. Additionally, while FIGS. 6B-6I illustrate an embodiment where a camera is used to capture an image of a user for landmark detection and analysis, it is expressly contemplated that other data capturemechanisms, such as laser scanning, may be used in other embodiments.

[0114] FIG. 6D illustrates a user interface 620 on a device 610 with a captured image 622 presented to a user. A user may have the option to re-take a picture if needed.

[0115] FIG. 6E illustrates a user interface 626 on a device 610 that illustrates a number of PPE options 624 for a user. A user may select one or more PPE items from list 624 to fit test. However, while it is illustrated that a list of PPE models may be presented to a user on a screen, it is also expressly contemplated that a PPE article for fit testing may also be identified by a user scanning a barcode, entering a model number, searching for a specific model within a database, etc. Additionally, in some embodiments an image is captured of the respiratory protection device, its packaging, etc., from which a particular model can be identified. In some embodiments, the PPE model is identified when an image is captured of the user wearing it. In embodiments, such as that of FIG. 6E, where a number of PPE options are provided, it is expressly contemplated that the PPE models 624 may be ordered based on a predicted likelihood of fit, based on a comfort score, or a combination of both, as described in PCT Application PCT / CN2023 / 108870, filed on July 24, 2023.

[0116] Generating a list of PPE models 624 may include ranking the results for a subject - e.g., in order of most likely fit, in order of comfort, etc. In some embodiments, a mixed ranking order may be applied to the selection results - e.g., limited to only PPE currently stocked, and then ranked based on estimated comfort for all PPE above a minimum fit score.

[0117] Donning and / or doffing instructions may be displayed as well, or in conjunction with selection results. Selection results may also be communicated in addition, or alternatively, to a third-party device. For example, an EHS supervisor may receive deidentified results to provide enough respirator models for all workers, and potentially reduce a number of respirators previously provided to just enough models for all workers. Deidentified results may also be communicated to a PPE manufacturer, in some embodiments, such that improved PPE products can be designed. Deidentified results may also be provided to a distributor or purchasing agent, which can then facilitate needed purchases.

[0118] FIG. 6F illustrates a user interface 628 presented on a device 610 that prompts a user to capture an image of themselves wearing the selected respiratory device. As noted previously, it is expressly contemplated that a model of the respiratory device may be identified from such an image.

[0119] FIG. 6G illustrates a user interface 630 presented on a device 610 that illustrates an image of a user wearing a respiratory protection device 632. A user may be prompted to accept the image or may have an option to re -take the image.

[0120] FIG. 6H illustrates a user interface 640 presenting a detected fit inconsistency 642. Fit inconsistency 642 is illustrated as an area of the respirator where a leak is expected. It is noted that an imaging device may include a filter or may otherwise have the capability to capture images in thenonvisible range, as described in PCT Application PCT / IB / 2022 / 056222, filed July 4, 2022. Carbon dioxide flow (indicative of a leak during a user’s exhalation) may be visible using an infrared filter, for example. Based on a detected fit inconsistency, in some embodiments, a tutorial or training prompt may be provided for a user. For example, as illustrated in FIG. 6H, the potential leak area may be caused by improper forming of the nose portion of the respirator. A tutorial may help the user correctly form the nose portion to reduce or remove the detected fit inconsistency.

[0121] FIG. 61 illustrates a fit test result user interface 652 which may be presented on a device 610. One or more fit result indications may be provided. For example, a pass / fail indication 654 may be provided. Additionally, or alternatively, a calculated fit factor 656 may also be presented.

[0122] It is expressly contemplated that user interfaces and features presented herein are customizable. For example, a fit test passed indication 654 may be customized to include a corporate logo, a manufacturer’s logo, of a worker’s picture, etc. Additionally, guidance may be customized and included on user interface 652 such as restrictions that may apply to a fit test (e.g., that a traditional fit test is also required, how long the fit test result is good for, etc.).

[0123] System and methods herein may also assist a user in determining which respirator(s) are most likely to fit a given user. Fit of a particular respirator for a specific individual is dependent on the facial geometry of the individual. For example, a cup-shaped respirator will not work on an individual if their facial length is too long for the respirator to cover both nose and chin.

[0124] Currently, individuals pick a respirator (or other PPE) for fit testing with little to no guidance. It is often not feasible to switch during a fit test, and it may not be possible to switch models and retake a traditional fit test. Systems and methods herein allow for a user to quickly take a digital fit test with a first model and, if the first model does not pass, quickly take a second digital fit test with a second model.

[0125] PPE fit testing systems and methods herein may also help a worksite select PPE to have available for workers. For example, it may be possible to do an assessment of workers using a respirator selection system to quickly identify a subset of respirators that can fit the most workers. For example, a majority of users may have sufficient fit using a 9205+ respirator, so only a few other models may need to be stocked, and they may not need to be restocked as often.

[0126] It may also be possible, using systems herein, for a selecting system to consider an expected comfort level of a wearer of an item of PPE and provide a recommendation based on both fit and expected comfort. Often, for an annual fit test, workers will continue to use a PPE model that they previously passed a fit test with. However, while their selected PPE model may be sufficient to pass a fit test, there may be a different PPE model that can pass and provide better comfort. Additionally,while systems herein may provide fit testing for one or more potential PPE for a user, it is expressly contemplated that the tool may be used in conjunction with regulatory requirements for respiratory fit.

[0127] In some embodiments, a fit test system may be accessed by using a physical kiosk, for example located within a worksite or within a retailer where different respirator models are available. A user may interact with the kiosk to get a PPE selection, receive a selected PPE model, and take a fit test for the selected PPE model. The user may also be presented with donning / doffing instructions, fit improvement options, etc. The kiosk may be built into a vending machine stocked with different PPE models, for example. PPE vending machines are commonplace in buildings where workers may occasionally need more or new personal protective equipment, such as safety glasses, ear plugs, gloves, or respirators. These PPE vending machines are now also in airports, where the machine contains PPE that many people use since the COVID-19 pandemic, such as gloves, respirators, and sanitization wipes.

[0128] PPE selection system may be built into a PPE dispensing system in a worksite such that workers are prompted to wear the right PPE for that worksite. A proximity sensor, or camera, may detect a worker approaching a work zone and generate an alert for the worker. The alert may be a visual alert (a blinking or color changing light, for example) or an audio alert (e.g., an alarm, a verbal prompt, etc.).

[0129] Such systems, located on a worksite, may both increase the use of correct PPE, and reduce waste as workers will be less likely to choose a PPE model that does not fit and must be discarded.

[0130] Systems and methods for selecting one or more respirators for a user may provide images of a user to a trained machine learning algorithm to determine what respirator(s) may provide a good fit. The trained machine learning algorithm may have been trained using many different faces and fit information for a number of different types of PPE and models for each type of PPE.

[0131] FIG. 7 illustrates a method for fit testing a respirator for a user in accordance with embodiments herein. Method 700 may be completed using a module of a PPE fit testing system, using a standalone respirator selection system, using a website to access a cloud-based system, or in another suitable manner.

[0132] In block 710, a scan of a subject is captured. As described with respect to method 700, a scan may include an image of the subject. However, it is expressly contemplated that relevant user geometry information can be obtained using other suitable methods. The image is captured of the subject prior to donning an article of PPE. In some embodiments, a single image is sufficient. However, it is expressly contemplated that multiple images may be captured, or a video of the subject may be captured.

[0133] In block 720, landmarks are identified from the image data. In some embodiments, landmarks are identified based on a generated facial map for a face detected in an image. The facial map may allow for facial landmarks to be detected and may facilitate estimates of distance, angles and curvature between facial landmarks. In some embodiments the facial map is a mesh generator, for example like that generated using the MediaPipe Face Landmarker task, available from MediaPipe Solutions, accessible on Github.com, which combines both a facial detectorthat computes face locations as well as a face landmark model which approximates the 3D facial surface using regression.

[0134] However, it is expressly contemplated that other mapping techniques may be used, such as a 3D point cloud. Similarly, in some applications, only coordinates related to points on a mesh are generated. The facial map may be presented to a user in some embodiments, e.g., as an overlay on the detected face. However, in some embodiments the facial map is generated, but not displayed. Additionally, in some embodiments, augmented reality techniques may be used to provide a demonstration of what a selected respirator may look like on the user’s facial topography.

[0135] In some embodiments, measurements are calculated based on detected landmarks. For example, an interpupillary distance can be measured by identifying each pupil as a landmark and measuring a distance between them. Similarly, a relevant facial length may be measured (e.g., from an eye-level to a chin level for respirators). A facial width may also be measured, e.g., a width at the widest part of the face - from cheekbone to cheekbone. Other measurements may also be calculated, such as angles formed by different landmarks, ratios of distances between landmarks, etc. For example, other measurements may be needed for fitting safety eyewear, hearing protection, helmets, etc.

[0136] In block 730, the user’s face is classified by shape. Classification may be done by comparing landmark-based ratios. For example, a ratio of a face length to width may indicate a roundness of a face. A face may be classified by shape (e.g., long and thin, short and wide, round), by head size (e.g. small, medium, large), or by other classification metrics.

[0137] While not illustrated in FIG. 7, it is expressly contemplated that, based on a facial classification, a fit testing system may provide recommendations regarding respirators that may be likely to fit, likely to be comfortable, etc. A user may select a PPE model for fit testing based on a provided recommendation, or may indicate a PPE model selected using another method - e.g., barcode scanner, RFID or NFC tag, or I / O mechanism, etc.

[0138] In block 740, a scan of the user’s face while wearing the respirator is obtained. The scan of block 710 and the scan of block 740 may be obtained using the same scanning device - e.g., a camera on a PPE vending machine may capture the scan 710 when a user first approaches, and capture scan740 after dispensing a selected PPE. However, it is expressly contemplated that the scan of block 710 may be obtained from a first device and the scan of block 740 may be obtained from a second device.

[0139] In block 750, potential leak areas are identified. Based on the scan data of a user before and after donning a PPE article, potential leak areas may be identified. A potential leak area may include a gap in a seal between a user’ s face and a respirator where contaminated air may leak into the breathing zone.

[0140] In block 760, a potential leak is evaluated. Using machine learning models or other suitable methods (lookup tables, e.g.), a severity of the potential leak is identified.

[0141] In block 770, if a gap is determined to be significant enough to cause a fit test failure, a fit test result of failure is returned.

[0142] If a fit test failure occurs, the user may be prompted to select a different PPE model, as indicated in block 780, and have their face scanned again wearing a second PPE model.

[0143] In block 790, if no gaps are detected, or the gaps detected are not significant enough to cause a fit test failure, a fit test passed indication is provided.

[0144] In block 770 and 790, the pass / fail indication may be communicated as a message, e.g., “Fit test passed” delivered visually or audibly. In some embodiments, a calculated fit factor is provided in addition to the pass / fail indication.

[0145] FIG. 8 illustrates a method of digitally fit testing in accordance with embodiments here.

[0146] Described herein thus far are systems and methods that provide a digital fit testing alternative based on identifying landmarks on a user and based on that, generating datapoints regarding the user’s geometry. However, it is expressly contemplated that machine learning algorithms may conduct image comparison without identifying facial landmarks. Method 800 concerns predicting a fit factor using a machine learning algorithm to compare user data to a datastore of fit test results associated with images of other individuals.

[0147] In block 810, a facial scan of a user is obtained. The facial scan may be captured using any suitable scanning technology.

[0148] In block 820, the facial scan is compared to a datastore . The datastore includes a larger number of fit test results that include facial scan files for individuals pre and post donning of a PPE article, descriptions of PPE models, traditional fit testing data, and fit factors. If insufficient data is present in the database for a reliable fit test result, then, as indicated by block 822, a user is instructed to proceed to a traditional fit testing process (e.g. qualitative or quantitative) in block 830.

[0149] If sufficient data is present in the datastore for confidence in a fit test result, as indicated in block 824, then fit test data for an indicated respirator 840 is retrieved. In some embodiments, the comparison returns a respirator model associated with the closest match of the user’s face. E.g., if theclosest facial match to the face scan captured in block 810 corresponds to a fit test for “Sally” wearing a “8210” respirator that resulted in a passed fit test in a qualitative fit test, then an 8210 respirator may be recommended.

[0150] In block 850, a scan is captured of a user wearing the indicated respirator.

[0151] In block 860, the scan of the user wearing the indicated respirator is compared to the scan of the closest-match fit test. E.g., the scan of the user is compared to the scan of Sally while Sally is wearing the 8210 respirators.

[0152] In some embodiments, a scan of a user wearing PPE is captured and reference fit factors are retrieved from a database. The best fit respirator is retrieved. For example, if the PPE is a full-face respirator, the system predicts a fit for a number of full face facepiece respirators.

[0153] In some embodiments, scanning a user wearing PPE includes detecting how the PPE itself is warped by being pressed to the body part. Based on the definition, similar looking deformations are retrieved from the database. E.g., the comparison is done based on the PPE and not solely the user’s face.

[0154] In block 870, fit test results are provided to the user. If the comparison between the user’s scan data and, for example, Sally’s scan data is within an acceptable threshold, then a pass result is provided. The fit factor calculated for Sally’s fit test may also be provided along with the pass result. If the comparison is outside of an acceptable threshold, a fail result may be provided, and the user may try a different PPE model if a fit test result in the database is available, or the user may be instructed to undergo traditional fit testing.

[0155] Machine learning models described herein can rely on any suitable algorithm, such as a nearest neighbor or other suitable options for generating a selection. It is noted that, without good information about a specific face, it is difficult to determine a fit or comfort metric. A trained machine learning model can learn different relationships between facial measurements and topography that are not as simple as length and width.

[0156] By analyzing both a fit and a comfort metric for a number of PPE models for a user, it is possible to find respirators that satisfy both. For example, a user may have a high score with two different models, or model sizes. While a user may fit into a ‘small,’ for example, they may be more comfortable wearing a ‘large.’

[0157] In addition to information about a PPE user, systems and methods herein may also retrieve other relevant information. For example, environmental condition information may help inform what type of PPE is needed, or where the nearest retail location having a PPE model in stock is.

[0158] In some embodiments, using a camera feature on a device, it may be possible to use augmented reality techniques in combination with machine learning techniques herein to present a representationof a given PPE model on a user (e.g., a respirator on the user’s face). This may assist in providing donning / doffing / fitting / maintenance instructions.

[0159] As used herein, the term “comfort” or “comfort score” can include a number of different factors including breathability, heat and moisture inside the respirator, pressure points on the skin, headband pressure, skin irritation, etc.

[0160] In some embodiments, systems and methods herein also include a gamification aspect to encourage correct user behavior. For example, points may be awarded when a fit test is complete, when a guidance module is completed, when donning / doffing guidance is followed. Points may be redeemed for any suitable reward - e.g., monetary, prize, donation to charity, etc.

[0161] Other customizations are also expressly envisioned for embodiments herein. For example, different customizations may be present for different countries - e.g., whether imperial or metric units are illustrated, what language is used to present information, or what PPE models are available for purchase in a given country. Similarly, systems and methods herein can be used by a site to recommend only what PPE is currently available, or by a distributor to limit to what products it carries.

[0162] Systems and methods herein may also have purchasing capability - e.g., may interface directly with a distributor (e.g. through an online store, or placing an order directly with a retailer) so that a user can order the PPE model through user interfaces generated by systems and methods herein.

[0163] Additionally, based on detected facial landmarks, tailored donning / doffing information may be retrieved. For example, many respirators need to have a “nose portion” formed to a user’s face. Based on a detected nose shape, tailored instructions may be provided.

[0164] Some embodiments herein may also utilize information about what other PPE a user wears. For example, if a user has already been fit tested for a hearing protection device, their respiratory protection options, or eyewear options, may be limited as not all models of PPE are compatible. In some embodiments, PPE selections systems also retrieve information about other PPE selected or required. For example, if a hard hat is required, in-ear hearing protection may be recommended if a preferred over-ear hearing protection unit is incompatible with available hard hats. In some embodiments, a PPE selection system may provide a selected PPE configuration - e.g., hearing protection device A, respirator G, and eye protection X.

[0165] FIGS. 9A-9C illustrate example user interfaces in accordance with embodiments herein. As noted previously, it is expressly contemplated that a PPE fit testing system may be useful for any PPE article where fit is important and / or regulated. While systems and methods herein have thus far been primarily discussed with respect to respiratory protection articles, it is expressly contemplated that other PPE, as well as combinations of PPE have important fit considerations.

[0166] While respirators are discussed in depth as an example, systems and methods herein may similarly be applied to other PPE articles such as, but not limited to: protective eyewear, headgear, hearing protection devices, fall protection, coveralls, or any other personal protective equipment that requires fit or comfort testing. Fall protection, for example, includes harnesses with overlapping ranges of acceptable user height / weight. However, with a better understanding of a user’s dimensions, systems and methods herein may allow a user to find PPE that both fits and is comfortable to wear.

[0167] FIGS. 9A-9B illustrate user interfaces where an individual may select different types of PPE needing individual fit testing, or fit testing as a combination of PPE. FIG. 9A illustrates a scenario where a user has selected head protection (a helmet), in-ear protection, and a safety suit. FIG. 9B, in contrast, illustrates a scenario where a user has selected a fall harness and over-the-ear hearing protection.

[0168] While generic PPE models are illustrated in FIGS. 9A-9B, it is expressly contemplated that, once PPE types are selected, as described herein, specific make and models of PPE may be specified, selected or detected. Based on PPE identification, customized fit training, testing and proper PPE usage may be provided.

[0169] Another example of PPE training and fit testing that may be provided by systems and methods herein is illustrated in FIG. 9C, which illustrates functionality that may be useful for providing, fitting, and properly using eye ware.

[0170] FIGS. 10A-10C illustrates embodiments in which systems herein may be used for hearing protection articles. FIG. 10A illustrates an image 2000 of a user’s ear, illustrating an exterior of an ear canal 2002. Different individuals have different ear geometries, which contributes to the need for proper fit of hearing protection devices.

[0171] FIG. 10B illustrates a schematic perspective view of an earplug 2010 inserted into an ear canal 2002 of an individual. Ear canal 2002 is illustrated as having a canal depth 2005. The canal depth 2005 may refer to a length of the ear canal 2002 up to which the earplug 2010 may need to be inserted in order to provide the good fit.

[0172] Using systems herein, the canal depth 2005 may be estimated based on one or more images taken of the ear canal 2002, e.g., such as image 2000. In some embodiments, an ear canal depth 2005 may further be estimated by imaging an indicator 2012 present on earplug 2010. An indicator 2012 may facilitate systems herein in determining and estimating an insertion depth 2014 of the earplug 2010 into the ear canal 2002. An indicator 2012 may include any alphanumeric or geometric indication - e.g., a numeric depth, a solid or dashed line, etc. Indicator 2012 may also or alternatively include a color change, a change in material, or any other suitable indication detectable by sensors describedherein.

[0173] Systems here may be configured to determine the fit quality of the earplug 2010 on an individual user based on the one or more first indicators 2012. Using a suitable fit testing procedure, a fit indication (e.g., a pass / fail, score, etc.) can be associated with a captured image. For example, in the schematic of FIG. 10B, it may be determined that insertion depth 2014 relative to ear canal depth 2005 provides a suitable fit for a user. An image, or other sensed indication, can be captured that provides an example of suitable fit. The image may be associated with an identification of the user for later retrieval.

[0174] Some examples of suitable fit testing systems and methods are described in, for example, U.S. Pat. 6687377 to Voix et al., U.S. Pat. 8254586 to Voix et al., U.S. Pat. RE47,938 to Voix et al., U.S. PAP 2022 / 0053280 to Voix et al., U.S. PAP 2020 / 0214601 to Brown et al., U.S. Pat. 10,617,333 to Brown et al., and US PAP 2021 / 0236339 to Bonnet et al. However, it is expressly contemplated that other fit testing systems and methods may be used.

[0175] Additionally, based on an ear canal depth 2005, systems herein may provide suggestions of which hearing protection device may be most likely to fit.

[0176] When the user has donned and is currently wearing a hearing protection device, images can be captured using systems herein. The captured images may be compared to the suitable fit image and, based on the comparison, systems and methods herein may provide an indication of a likely fit detected or likely fit not detected.

[0177] Specifically, in some embodiments, systems herein may determine and provide a fit quality of earplug 2010 within an ear based on the canal depth 2005 of the ear canal 2002 and the insertion depth 2014 within ear canal 2002. A fit quality indication may be provided on a user interface of a device, or using another suitable display, speaker or haptic feedback process.

[0178] FIG. 10C illustrates a schematic top perspective view of earplug 2010 inserted into the ear canal 2002 of the individual user. As discussed, systems and methods described herein may provide a fit indication for a user wearing an article of PPE. FIG. 10C illustrates one example of an image that may be provided to a system herein for fit determination.

[0179] Specifically, in some embodiments, systems herein may be configured to fit an ellipse 2020 to one or more second indicators 2022. In some embodiments, systems herein are configured to generate a two-dimensional probabilistic map based on the ellipse 2020. In some embodiments, systems herein are configured to determine the fit quality of the earplug 2010 on the individual user based on the two- dimensional probabilistic map. The insertion depth 2005 may also be estimated based on the ellipse 2020. An accuracy of estimation of the insertion depth 2005 may decrease as the ellipse 2020 gets more circular.

[0180] FIG. 11 is a block diagram providing an operating perspective of a PPE fit testing system 1106 (PPEFTS) when hosted as a cloud-based platform. As described herein, PPE fit testing system 1106, in some embodiments, is capable of supporting multiple, distinct access points 1115 and / or work environments having an overall population of workers, as described with respect to FIG. 1, for example . In the example of FIG. 11 , the components of a PPE fit testing system are arranged according to multiple logical layers that implement the techniques of the disclosure. Each layer may be implemented by one or more modules and may include hardware, software, or a combination of hardware and software.

[0181] In some example approaches, computing devices 1132, display 1112, input devices 1134, and / or safety stations 1115 operate as clients 1130 that communicate with PPE fit testing system 1106 via interface layer 1136. Computing devices 1132 typically execute client software applications, such as desktop applications, mobile applications, and / or web applications. Computing devices 1132 may represent any of computing devices 16, 18 of FIG. 1. Examples of computing devices 1132 may include, but are not limited to, a portable or mobile computing device (e.g., smartphone, wearable computing device, tablet), laptop computers, desktop computers, smart television platforms, and / or servers.

[0182] In some example approaches, computing devices 1132, display 1112, sensors (e.g., cameras, scanners, barcode or other) 1122, input devices 1134 and / or safety stations 1115 may communicate with PPEFTS 1106 to send and receive information related to PPE fit testing, PPE fit verification, fit test results alert generation, or the like. Client applications executing on computing devices 1132 may communicate with system 1106 to send and receive information that is retrieved, stored, generated, and / or otherwise processed by functionalities 1140. In some examples, client applications may request and display information received or generated by system 1106, such as steps of a compiled fit test, model-specific tutorials, fit test results, and the like. In addition, the client applications may interact with system 1106 to query for analytics information about PPE usage, site-wide fit test results, individual test results, worker tutorial completion, or the like. The client applications may output for display information received from system 1106 to visualize such information for users of clients 1130. Additionally, as described herein, system 1106 may provide an interactive experience for users using client applications.

[0183] Client applications executing on computing devices 1132 may be implemented for different platforms but include similar or the same functionality. For instance, a client application may be a desktop application compiled to run on a desktop operating system, such as MicrosoftWindows, Apple OS X, or Linux, to name only a few examples. As another example, a client application may be a mobile application compiled to run on a mobile operating system, such as Google Android, Apple iOS,Microsoft Windows Mobile, or BlackBerry OS to name only a few examples. As another example, a client application may be a web application such as a web browser that displays web pages received from system 1106. In the example of a web application, system 1106 may receive requests from the web application (e.g., the web browser), process the requests, and send one or more responses back to the web application. In this way, the collection of web pages, the client-side processing web application, and the server-side processing performed by 1106 collectively provides the functionality described herein.

[0184] In some examples, interface layer 1136 may provide Representational State Transfer (RESTful) interfaces that use HTTP methods to interact with services and manipulate resources of systems 1106. In such examples, functionalities 1140 may generate JavaScript Object Notation (JSON) messages that interface layer 1136 sends back to the client application that submitted the initial request. In some examples, interface layer 1136 provides web services using Simple Object Access Protocol (SOAP) to process requests from client applications. In still other examples, interface layer 1136 may use Remote Procedure Calls (RPC) to process requests from clients 1130. Upon receiving a request from a client application to use one or more functionalities 1140, interface layer 736 sends the information to application layer 1138, which includes functionality 1140.

[0185] As shown in FIG. 11, system 1106 also includes an application layer 1138 that represents a collection of services for implementing much of the underlying operations of system 1106. Application layer 1138 receives information included in requests received from client applications that are forwarded by interface layer 1136 and processes the information received according to one or more of services 1140 invoked by the requests. Application layer 1138 may be implemented as one or more discrete software services executing on one or more application servers, e.g., physical or virtual machines. That is, the application servers provide runtime environments for execution of services 1140. In some examples, the functionality of interface layer 1136 as described above and the functionality of application layer 1138 may be implemented at the same server.

[0186] Application layer 1138 may include one or more separate software functionalities 1140 (e.g., processes) that may communicate via, for example, a logical service bus 1144. Service bus 1144 generally represents a logical interconnection or set of interfaces that allows different services to send messages to other services, such as by a publish / subscription communication model. For example, each of services 1140 may subscribe to specific types of messages based on criteria set for the respective service. When a service publishes a message of a particular type on service bus 1144, other services that subscribe to messages of that type will receive the message. In this way, each of services 1140 may communicate information to one another. As another example, services 1140 maycommunicate in point-to-point fashion using sockets or other communication mechanism. Before describing the functionality of each of services 1140, the layers are briefly described herein.

[0187] Data layer 1146 of system 1106 includes one or more datastores 1148. A datastore, generally, may be any data structure or software that stores and / or manages data; a datastore may store data in structured or unstructured form. For example, a datastore may be a remote datastore hosted by one or more remote compute servers coupled to the controller by a packet-switched network. As another example, the datastore may be locally cached within a computer-readable medium of the computing device. Example datastores include but are not limited to one or more of database management systems, online analytical processing database, map, table, hash tables, or any other suitable structure for storing data. In one example approach, data layer 1146 of system 1106 includes datastores 1148 used to provide persistence for information in system 1106. Data layer 1146 may be implemented, for instance, using Relational Database Management System (RDBMS) software to manage information in datastores 1148. The RDBMS software may manage one or more datastores 1148, which may be accessed using Structured Query Language (SQL). Information in the one or more databases may be stored, retrieved, and modified using the RDBMS software. In some examples, data layer 1146 may be implemented using an Object Database Management System (ODBMS), Online Analytical Processing (OLAP) database, or any other suitable data management system.

[0188] In the example of FIG. 11, each of services 1140A-11401 is implemented in a modular form within system 1106. Although shown as separate modules for each service, in some examples the functionality of two or more services may be combined into a single module or component. Each of functionalities 1140 may be implemented in software, hardware, or a combination of hardware and software. Moreover, functionalities 1140 may be implemented as standalone devices, separate virtual machines or containers, processes, threads, or software instructions generally for execution on one or more computer processors or processing circuitry.

[0189] Although generally described herein as user data, PPE data, fit test and tutorial related data, or any other stored information described herein being stored in datastores 1148, in some examples, datastores 1148 may additionally or alternatively include data representing said data or any other stored information described herein. As one example, encoded lists, vectors, or the like representing a previously stored image may be stored in addition to, or as an alternative, the previously stored image itself. In some examples, such data representing user data, PPE data, fit data, fit test data, fit tutorials or any other stored information described herein may be simpler to store, evaluate, organize, categorize, or the like in comparison to storage of the actual user data, PPE data, model data, image data, fit data, or the like.

[0190] FIG. 12 is a block diagram of a PPE fit test system architecture. The remote server architecture 1200 illustrates one embodiment of an implementation of a PPE fit test system 1210. As an example, remote server architecture 1200 can provide computation, software, data access, and storage services that do not require end-user knowledge of the physical location or configuration of the system that delivers the services. In various embodiments, remote servers can deliver the services over a wide area network, such as the internet, using appropriate protocols. For instance, remote servers can deliver applications over a wide area network, and they can be accessed through a web browser or any other computing component. Software or components shown or described in FIGS. 1-11 as well as the corresponding data, can be stored on servers at a remote location. The computing resources in a remote server environment can be consolidated at a remote data center location or they can be dispersed. Remote server infrastructures can deliver services through shared data centers, even though they appear as a single point of access for the user. Thus, the components and functions described herein can be provided from a remote server at a remote location using a remote server architecture. Alternatively, they can be provided by a conventional server, installed on client devices directly, or in other ways.

[0191] In the example shown in FIG. 12, some items are similar to those shown in earlier figures. FIG. 12 specifically shows that system 1210 can be located at a remote server location 1202. Therefore, computing device 1220 accesses those systems through remote server location 1202. Operator 1250 can use computing device 1220 to access user interfaces 1222 as well. While a single operator 1250 is illustrated as connecting to system 1210, it is expressly contemplated that multiple operators may access system 1210, using either device 1220 or another suitable device.

[0192] FIG. 12 also depicts another example of a remote server architecture. FIG. 12 shows that it is also contemplated that some elements of systems described herein are disposed at remote server location 1202 while others are not. By way of example, storage 1230, 1240 or 1260 or module selector 1270 can be disposed at a location separate from location 1202 and accessed through the remote server at location 1202. Regardless of where they are located, they can be accessed directly by computing device 1220, through a network (either a wide area network or a local area network), hosted at a remote site by a service, provided as a service, or accessed by a connection service that resides in a remote location. Also, the data can be stored in substantially any location and intermittently accessed by, or forwarded to, interested parties. For instance, physical carriers can be used instead of, or in addition to, electromagnetic wave carriers.

[0193] It will also be noted that the elements of systems described herein, or portions of them, can be disposed on a wide variety of different devices. Some of those devices include servers, desktop computers, laptop computers, imbedded computer, industrial controllers, tablet computers, or othermobile devices, such as palm top computers, cell phones, smart phones, multimedia players, personal digital assistants, etc.

[0194] FIGS. 13-14 show examples of mobile devices that can be used in the embodiments shown in previous Figures.

[0195] FIG. 13 is a simplified block diagram of one illustrative example of a handheld or mobile computing device that can be used as a user's or client's handheld device 1316 (e.g., as computing device 1320 in FIG. 13), in which the present system (or parts of it) can be deployed. For instance, a mobile device can be deployed in the operator compartment of computing device 1320 for use in generating, processing, or displaying the data. FIG. 14 is another example of a handheld or mobile device.

[0196] FIG. 13 provides a general block diagram of the components of a client device 1316 that can run some components shown and described herein. Client device 1316 interacts with them or runs some and interacts with some. In the device 1316, a communications link 1313 is provided that allows the handheld device to communicate with other computing devices and under some embodiments provides a channel for receiving information automatically, such as by scanning. Examples of communications link 1313 include allowing communication though one or more communication protocols, such as wireless services used to provide cellular access to a network, as well as protocols that provide local wireless connections to networks.

[0197] In other examples, applications can be received on a removable Secure Digital (SD) card that is connected to an interface 1315. Interface 1315 and communication links 1313 communicate with a processor 1317 (which can also embody a processor) along a bus 1319 that is also connected to memory 1321 and input / output (I / O) components 1323, as well as clock 1325 and location system 1327.

[0198] I / O components 1323, in one embodiment, are provided to facilitate input and output operations and the device 1316 can include input components such as buttons, touch sensors, optical sensors, microphones, touch screens, proximity sensors, accelerometers, orientation sensors and output components such as a display device, a speaker, and or a printer port. Other I / O components 1323 can be used as well.

[0199] Clock 1325 illustratively comprises a real time clock component that outputs a time and date. It can also provide timing functions for processor 1317.

[0200] Illustratively, location system 1327 includes a component that outputs a current geographical location of device 1316. This can include, for instance, a global positioning system (GPS) receiver, a LORAN system, a dead reckoning system, a cellular triangulation system, or other positioning system.It can also include, for example, mapping software or navigation software that generates desired maps, navigation routes and other geographic functions.

[0201] Memory 1321 stores operating system 1329, network settings 1331, applications 1333, application configuration settings 1335, data store 1337, communication drivers 1339, and communication configuration settings 1341. Memory 1321 can include all types of tangible volatile and non-volatile computer-readable memory devices. It can also include computer storage media (described below). Memory 1321 stores computer readable instructions that, when executed by processor 1317, cause the processor to perform computer-implemented steps or functions according to the instructions. Processor 1317 can be activated by other components to facilitate their functionality as well.

[0202] FIG. 14 shows that the device can be a smart phone 1471. Smart phone 1471 has a touch sensitive display 1473 that displays icons or tiles or other user input mechanisms 1475. Mechanisms 1475 can be used by a user to run applications, make calls, perform data transfer operations, etc. In general, smart phone 1471 is built on a mobile operating system and offers more advanced computing capability and connectivity than a feature phone.

[0203] Note that other forms of the devices 1471 are possible.

[0204] FIG. 15 is a block diagram of a computing environment that can be used in embodiments shown in previous Figures.

[0205] FIG. 15 is one example of a computing environment in which elements of systems and methods described herein, or parts of them (for example), can be deployed. With reference to FIG. 15, an example system for implementing some embodiments includes a general-purpose computing device in the form of a computer 1510. Components of computer 1510 may include, but are not limited to, a processing unit 1520 (which can comprise aprocessor), a system memory 1530, and a system bus 1521 that couples various system components including the system memory to the processing unit 1520. The system bus 1521 may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. Memory and programs described with respect to systems and methods described herein can be deployed in corresponding portions of FIG. 15.

[0206] Computer 1510 typically includes a variety of computer readable media. Computer readable media can be any available media that can be accessed by computer 1510 and includes both volatile / nonvolatile media and removable / non-removable media. By way of example, and not limitation, computer readable media may comprise computer storage media and communication media. Computer storage media is different from, and does not include, a modulated data signal or carrier wave. It includes hardware storage media including both volatile / nonvolatile andremovable / non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information, and which can be accessed by computer 1510. Communication media may embody computer readable instructions, data structures, program modules or other data in a transport mechanism and includes any information delivery media. The term “modulated data signal” means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.

[0207] The system memory 1530 includes computer storage media in the form of volatile and / or nonvolatile memory such as read only memory (ROM) 1531 and random -access memory (RAM) 1532. A basic input / output system 1533 (BIOS) containing the basic routines that help to transfer information between elements within computer 1510, such as during start-up, is typically stored in ROM 1531. RAM 1532 typically contains data and / or program modules that are immediately accessible to and / or presently being operated on by processing unit 1520. By way of example, and not limitation, FIG. 15 illustrates operating system 1534, application programs 1535, other program modules 1536, and program data 1537.

[0208] The computer 1510 may also include other removable / non-removable and volatile / nonvolatile computer storage media. By way of example only, FIG. 15 illustrates a hard disk drive 1541 that reads from or writes to non-removable, nonvolatile magnetic media, nonvolatile magnetic disk 1552, an optical disk drive 1555, and nonvolatile optical disk 1556. The hard disk drive 1541 is typically connected to the system bus 1521 through a non-removable memory interface such as interface 1540, and optical disk drive 1555 are typically connected to the system bus 1521 by a removable memory interface, such as interface 1550.

[0209] Alternatively, or in addition, the functionality described herein can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (e.g., ASICs), Application-specific Standard Products (e.g., ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0210] The drives and their associated computer storage media discussed above and illustrated in FIG. 15, provide storage of computer readable instructions, data structures, program modules and other data forthe computer 1510. In FIG. 15, for example, hard disk drive 1541 is illustrated as storing operatingsystem 1544, application programs 1545, other program modules 1546, and program data 1547. Note that these components can either be the same as or different from operating system 1534, application programs 1535, other program modules 1536, and program data 1537.

[0211] A user may enter commands and information into the computer 1510 through input devices such as a keyboard 1562, a microphone 1563, and a pointing device 1561, such as a mouse, trackball or touch pad. Other input devices (not shown) may include a joystick, game pad, satellite receiver, scanner, or the like. These and other input devices are often connected to the processing unit 1520 through a user input interface 1560 that is coupled to the system bus but may be connected by other interface and bus structures. A visual display 1591 or other type of display device is also connected to the system bus 1521 via an interface, such as a video interface 1590. In addition to the monitor, computers may also include other peripheral output devices such as speakers 1597 and printer 1596, which may be connected through an output peripheral interface 1595.

[0212] The computer 1510 is operated in a networked environment using logical connections, such as a Local Area Network (LAN) or Wide Area Network (WAN) to one or more remote computers, such as a remote computer 1580.

[0213] When used in a LAN networking environment, the computer 1510 is connected to the LAN 1571 through a network interface or adapter 1570. When used in a WAN networking environment, the computer 1510 typically includes a modem 1572 or other means for establishing communications over the WAN 1573, such as the Internet. In a networked environment, program modules may be stored in a remote memory storage device. FIG. 15 illustrates, for example, that remote application programs 1585 can reside on remote computer 1580.

Claims

WHAT IS CLAIMED IS:

1. A personal protective equipment (PPE) fit testing system comprising: a scanning device configured to capture a first scan data of a user wearing an article of PPE; a fit test module configured to: detect, using a PPE detector, a model of the article of PPE; retrieve a second scan data of the user without the article of PPE; compare the first and second scan data, using a comparison module; and based on the comparison, generate a fit test result; and a communication component configured to communicate the generated fit test result to a device with a display.

2. The system of claim 1, wherein the scanning device comprises a camera.

3. The system of claim 1 or 2, wherein the camera captures images in the infrared spectrum range.

4. The system of claim 3, wherein the camera is a first camera, and wherein a second camera captures the second scan data.

5. The system of any of claims 1-4, and further comprising: a facial classifier configured to classify the user based on the second scan data.

6. The system of claim 5, and further comprising a PPE selection system configured to: identify, within a database of fit test data, a closest fit to the second scan data, wherein the closest fit data comprises: a retrieved first scan data; a retrieved second scan data; a retrieved PPE model; a retrieved fit test result. assign the retrieved PPE model as the PPE model; compare the second scan data to the retrieved second scan data; and provide the retrieved fit test result based on the comparison.

7. The system of any of claims 1-6, wherein the comparison module is configured to: detect, in the second scan data, a plurality of landmarks; generate a plurality of landmark measurements based on the plurality of landmarks; retrieve a PPE specification associated with the model of the article of PPE; identify, based on the first scan data, the second scan data, and the PPE specification, a fit inconsistency; evaluate the fit inconsistency; and wherein the fit test result is generated based on the evaluated fit inconsistency.

8. The system of any of claims 1-7, wherein the device comprises the system, and wherein the communication component comprises a user interface generator that generates a user interface for presentation on the display.

9. The system of claim 8, wherein the device is a mobile computing device.

10. The system of claim 8, wherein the device comprises a PPE vending system.

11. The system of any of claims 1-10, wherein the fit test result comprises a fit factor.

12. The system of claim 11, wherein the article of PPE comprises a respirator, and wherein the fit factor comprises a reciprocal of a percentage of contaminated air leakage into a breathing space from an ambient space.

13. The system of any of claims 1-12, wherein the PPE detector detects the model by receiving an input indicative of the model.

14. The system of claim 13, wherein the input comprises an image including the article of PPE, and wherein the PPE detector identifies the model from the image.

15. The system of any of claims 1-14, and further comprising: a PPE selection system comprising: a user indicia receiver that receives an indication of the user; a fit estimator that, based on the received indication, estimates a fit for each of a plurality of PPE models; anda communication component that communicates a list of the plurality of PPE models, the list comprising the estimated fit for each of the plurality of PPE models; and wherein the PPE detector detects a user selection of the model of the article of PPE from the communicated list.

16. The system of claim 15, wherein the user indication comprises the second scan data.

17. The system of claim 15, wherein the user indication comprises a PPE model associated with a past fit test result.

18. The system of claim 15, wherein the user indication comprises a work assignment for the user.

19. The system of claim 15, wherein the user indication comprises a work environment indication.

20. The system of claim 15, wherein the PPE selection system further comprises a comfort estimator configured to estimate a comfort for each of the plurality of PPE models, and wherein the list of the plurality of PPE models comprises the comfort estimate.

21. The system of any of claims 1 -20, wherein the article of PPE comprises a respirator and wherein the respirator comprises a disposable respirator, a reusable respirator, or a powered air purifying respirator.

22. The system of any of claims 1-21, wherein the article of PPE comprises a harness , a hearing protection device, an eyewear protection device, or coveralls.

23. A method of generating a fit test result for an article of personal protective equipment (PPE), the method comprising: receiving a first scan of a user from a first scanning device, the first scan comprising the user without the article of PPE; identifying a plurality of landmarks on the user based on the first scan; calculating a plurality of landmark measurements for the user based on the scan;receiving a second scan of the user from a second scanning device, the second scan comprising the user wearing the article of PPE; identifying a fit inconsistency for the user; evaluating a severity of the fit inconsistency; and generating, using a fit test results generator, a fit test result for the user.

24. The method of claim 23, wherein the first scanning device is a camera.

25. The method of claim 23 or 24, wherein the first scanning device is the second scanning device.

26. The method of any of claims 23-25, wherein the first scanning device is at a first location in a worksite, the second scanning device is at a second location, and the first and second locations are different.

27. The method of any of claims 23-26, and further comprising: receiving a user input selecting the article of PPE for fit testing.

28. The method of any of claims 23-27, and further comprising: detecting a model of the article of PPE.

29. The method of claim 28, and further comprising: retrieving a specification for the model of the article of PPE.

30. The method of any of claims 23-29, and further comprising: communicating the generated fit test result to a device.

31. The method of claim 30, wherein the device is a mobile computing device comprising a display.

32. The method of any of claims 23-31, wherein the fit test results comprise a calculated fit factor.

33. The method of claim 32, wherein the fit factor comprises an alphanumeric representation of how well the article of PPE fits the user.

34. The method of any of claims 23-33, wherein the article of PPE is a respirator, and further comprising: identifying a face of the user in the first scan; and wherein the landmarks comprise facial landmarks.

35. The method of any of claims 23-34, wherein the article of PPE comprises a respirator, a fall protection harness, a hearing protection device, or an eyewear protection device.

36. A method of fit testing an individual for a respirator, the method comprising: receiving a first facial scan from a first scanning device, the first facial scan comprising a user without the respirator; receiving a second facial scan from a second scanning device, the second facial scan comprising a user wearing the respirator; identifying, using an image analyzer, a fit inconsistency for the respirator based on the second image; determining a potential leak severity of the fit inconsistency; and based on the potential leak severity, automatically generating a fit test result, the fit test result being specific to the user for the respirator.

37. A PPE dispensing system comprising: a vending machine comprising a plurality of product dispensing devices, wherein each of the product dispensing devices comprises a dispensing location, which holds a next product to be dispensed, and a storage location, which holds products to be sequentially moved to the dispensing location after the next product to be dispensed is moved from the product dispensing location; a sensor configured to sense a physical indication of a user of the vending machine, wherein each of the product dispensing devices is configured to store and dispense a PPE model; a user input receiver configured to receive a selection of one of the dispensing locations; a vending actuator that actuates the product dispensing device associated with the selected dispensing location; and a fit test module comprising:a scan retriever configured to retrieve a first scan of the user without the dispensed PPE model, the first scan being captured by a first scanning device; a second scanning device configured to capture a scan of the user wearing the dispensed PPE model; a scan comparison module configured to compare the first and second scans and, based on the comparison, generate a fit test result.

38. The system of claim 37, and further comprising: a PPE selection system comprising: a sensor signal receiver that receives the sensed physical indication; a fit estimator that, based on the sensed physical indication, generates a fit estimate for the user for each of the PPE models; and a selection generator that generates a PPE selection for the user based on the generated fit estimates.

39. The system of claim 38, wherein the worksite hazard comprises: potential falling objects, potentially loud ambient noise, potential airborne particulates, potential airborne biological material; or potential organic vapors.

40. The system of claim 39, wherein the worksite hazard comprises a potential ledge, potential drop-off, potential cliff, a potential worksite at height, a potential floor gap or a potential chasm.

Images